Journal Cover
Information Sciences
Journal Prestige (SJR): 1.635
Citation Impact (citeScore): 5
Number of Followers: 587  
 
  Hybrid Journal Hybrid journal (It can contain Open Access articles)
ISSN (Print) 0020-0255
Published by Elsevier Homepage  [3184 journals]
  • Seeking affinity structure: Strategies for improving m-best graph matching
    • Abstract: Publication date: January 2020Source: Information Sciences, Volume 509Author(s): Manuel Curado, Francisco Escolano, Miguel A. Lozano, Edwin R. Hancock State-of-the-art methods for finding the m-best solutions to graph matching (QAP) rely on exclusion strategies. The k-th best solution is found by excluding all better ones from the search space. This provides diversity, a natural requirement for transforming a MAP problem into a m-best one. Since diversity enforces mode hopping, it is usually combined with a mode-approximation strategy such as marginalisation. However, these methods are generic insofar they do not incorporate the detailed structure of the problem at hand, i.e. the properties of the global affinity matrix which characterise the search space. Without this knowledge, it is thus hard to devise a practical criterion for choosing the next variable to clamp. In this paper, we propose several strategies to select the next variable to clamp, spanning the whole range between depth-first and breadth-first search, and we contribute with a unifying view for characterising the search space on the fly. Our strategies are: a) Number of factors in which the variables participate, b) centrality measures associated with the affinity matrix, and c) discrete pooling. Our experiments show that max number of factors and centrality provide a trade-off between efficiency and accuracy, whereas discrete pooling leads to an improvement of the state-of-the-art
       
  • Synergy of Granular Computing, Shadowed Sets, and Three-way Decisions
    • Abstract: Publication date: January 2020Source: Information Sciences, Volume 508Author(s): Davide Ciucci, Yiyu Yao
       
  • Semantic relation extraction using sequential and tree-structured LSTM
           with attention
    • Abstract: Publication date: January 2020Source: Information Sciences, Volume 509Author(s): ZhiQiang Geng, GuoFei Chen, YongMing Han, Gang Lu, Fang Li Semantic relation extraction is crucial to automatically constructing a knowledge graph (KG), and it supports a variety of downstream natural language processing (NLP) tasks such as query answering (QA), semantic search and textual entailment. In addition, the semantic relation extraction task is mainly responsible for identifying entity pairs from raw texts and extracting the semantic relations between the extracted entity pairs. Existing methods consider only lexical-level features and often ignore syntactic features, resulting in poor relation extraction performance. By analyzing the necessity of the syntactic dependency and the contributions of words in a sentence to relation extraction, this paper proposes an end-to-end method that uses bidirectional tree-structured long short-term memory (LSTM) to extract structural features based on the dependency tree of a sentence. To enhance the performance of the relation extraction, the bidirectional sequential LSTM with attention is used to identify word-based features including the positional information of entity pairs and the contribution of words. Then, structural features and word-based features are concatenated to optimize the relation extraction performance. Finally, the proposed method is used on the SemEval 2010 task 8 and the CoNLL04 datasets to validate its performance. The experimental results show that the proposed method achieves state-of-the-art results on the SemEval 2010 task 8 and the CoNLL04 datasets.
       
  • A knee-guided prediction approach for dynamic multi-objective optimization
    • Abstract: Publication date: January 2020Source: Information Sciences, Volume 509Author(s): Fei Zou, Gary G. Yen, Lixin Tang Although dynamic multi-objective optimization problems dictate the evolutionary algorithms to quickly track the varying Pareto front when the environmental change occurs, the decision maker in the loop still needs to select a final optimal solution among a large number of candidate solutions before and after the environmental change. Most designs focus on searching for a well-distributed Pareto front which inadvertently demand excessive computational burden during the evolutionary process. In this paper, we propose a novel knee-guided prediction evolutionary algorithm (KPEA) which maintains non-dominated solutions near knee and boundary regions, in order to reduce the burden of maintaining a large and diversified population throughout the evolution process. When a change is detected, this design relocates the knee and boundary solutions based on the movement of the global knee solution in the new environment. In this way, this algorithm incurs a lower computational cost, allowing the evolutionary algorithm to converge quickly. In order to test the performance of the proposed algorithm, five popular dynamic multi-objective evolutionary algorithms (DMOEAs) are compared with KPEA based on two newly proposed metrics. The experimental results validate that the proposed algorithm effectively and efficiently converges to the global knee solution under the changing environments.
       
  • Adaptive robust control of oxygen excess ratio for PEMFC system based on
           type-2 fuzzy logic system
    • Abstract: Publication date: Available online 12 September 2019Source: Information SciencesAuthor(s): H.K. Zhang, Y.F. Wang, D.H. Wang, Y.L. Wang The Proton Exchange Membrane Fuel Cell (PEMFC) air supply system takes on the characteristics of external disturbances and uncertain parameters, which is difficult to achieve accurate modeling and stability control. In this paper, an adaptive robust controller based on type-2 fuzzy logic systems (T2-FLS) is proposed to control the oxygen excess ratio (OER) of PEMFC air supply system. The controller does not need the unmodeled dynamics, which can be approximated by adaptive T2-FLS whose adaptive parameters are derived based on Lyapunov theory. The stability analysis shows that the system tracking error is uniform ultimate bounded. Finally, the practicability and feasibility of controller are validated by numerical simulation and Hardware-In-Loop (HIL) experiment.
       
  • YAKE! Keyword Extraction from Single Documents using Multiple Local
           Features
    • Abstract: Publication date: Available online 11 September 2019Source: Information SciencesAuthor(s): Ricardo Campos, Vítor Mangaravite, Arian Pasquali, Alípio Jorge, Célia Nunes, Adam JatowtABSTRACTAs the amount of generated information grows, reading and summarizing texts of large collections turns into a challenging task. Many documents do not come with descriptive terms, thus requiring humans to generate keywords on-the-fly. The need to automate this kind of task demands the development of keyword extraction systems with the ability to automatically identify keywords within the text. One approach is to resort to machine-learning algorithms. These, however, depend on large annotated text corpora, which are not always available. An alternative solution is to consider an unsupervised approach. In this article, we describe YAKE!, a light-weight unsupervised automatic keyword extraction method which rests on statistical text features extracted from single documents to select the most relevant keywords of a text. Our system does not need to be trained on a particular set of documents, nor does it depend on dictionaries, external corpora, text size, language, or domain. To demonstrate the merits and significance of YAKE!, we compare it against ten state-of-the-art unsupervised approaches and one supervised method. Experimental results carried out on top of twenty datasets show that YAKE! significantly outperforms other unsupervised methods on texts of different sizes, languages, and domains.
       
  • Robust Deadlock Control for Automated Manufacturing Systems Based on
           Elementary Siphons Theory
    • Abstract: Publication date: Available online 11 September 2019Source: Information SciencesAuthor(s): GaiYun Liu, LingChun Zhang, Liang Chang, Abdulraham Al-Ahmari, NaiQi Wu Resource failures may happen from time to time in an automated manufacturing system (AMS) in production practice, leading to that most of deadlock control methods in the literature are not applicable. For a generalized system of simple sequential process with resources (GS3PR), this paper develops a robust deadlock control strategy when there exists a type of unreliable resources. To do so, after computing the system’s elementary and dependent strict minimal siphons (SMSs), by using the concept of max′-controllability of siphons, we then check whether an elementary SMS is self-max′-controlled or not, and whether it contains unreliable resources. Afterwards, a constraint set for a siphon is introduced and a monitor is designed for each non-max′-controlled elementary SMS and self-max′-controlled elementary one that contains unreliable resources. Then, if a dependent SMS is max′-controlled with respect to the control depth variables of its elementary siphons, it needs no monitor, otherwise, we add a monitor for such a dependent SMS. Finally, a robust deadlock control algorithm is developed to keep each SMS to be max′-controlled, even if there exists a type of unreliable resources. The proposed method is demonstrated by using examples.
       
  • Toward Conditionally Anonymous Bitcoin Transactions: A Lightweight-Script
           Approach
    • Abstract: Publication date: Available online 11 September 2019Source: Information SciencesAuthor(s): Li Lun, Jiqiang Liu, Xiaolin Chang, Tianhao Liu, Jingxian Liu Bitcoin is being explored for applications in various Internet of Things (IoT) scenarios as a peer-to-peer payment platform. However, security and anonymity problems exist with Bitcoin, which threaten vulnerable IoT facilities. This paper aims to achieve conditional anonymity inside Bitcoin transactions. We first propose an identity-based conditionally anonymous signature (ICAS) algorithm and then design a lightweight Bitcoin script scheme (named pay-to-public-key-hash-with-conditional-anonymity or P2PKHCA), which applies the ICAS algorithm to make conditionally anonymous Bitcoin transactions. P2PKHCA allows the identity manager to trace the real identity of users while preserving users’ anonymity. Furthermore, P2PKHCA is backward compatible in terms of being able to work seamlessly with the existing Bitcoin script scheme pay-to-public-key-hash (P2PKH) in the Bitcoin network. We conduct a security analysis to verify the security features of P2PKHCA and employ a performance evaluation in terms of the cryptographic time and space costs by comparison with P2PKH. The simulation results demonstrate the effectiveness of P2PKHCA in reducing both time cost and data size.
       
  • Robust Visual Tracking based on Variational Auto-encoding Markov Chain
           Monte Carlo
    • Abstract: Publication date: Available online 10 September 2019Source: Information SciencesAuthor(s): Junseok Kwon In this study, we present a novel visual tracker based on the variational auto-encoding Markov chain Monte Carlo (VAE-MCMC) method. A target is tracked over time with the help of multiple geometrically related supporters whose motions correlate with those of the target. Good supporters are obtained using variational auto-encoding techniques that measure the confidence of supporters in terms of marginal probabilities. These probabilities are then used in the MCMC method to search for the best state of the target. We extend the VAE-MCMC method to a variational mixture of posteriors (VampPrior)-MCMC and hierarchical VampPrior-MCMC methods. Experimental results demonstrate that the supporters are useful for robust visual tracking and that the variational auto-encoding can accurately estimate the distribution of supporters’ states. Moreover, our proposed VAE-MCMC method quantitatively and qualitatively outperforms recent state-of-the-art tracking methods.
       
  • Towards Efficient and Effective Discovery of Markov Blankets for Feature
           Selection
    • Abstract: Publication date: Available online 10 September 2019Source: Information SciencesAuthor(s): Hao Wang, Zhaolong Ling, Kui Yu, Xindong Wu The Markov blanket (MB), a key concept in a Bayesian network (BN), is essential for large-scale BN structure learning and optimal feature selection. Many MB discovery algorithms that are either efficient or effective have been proposed for addressing high-dimensional data. In this paper, we propose a new algorithm for Efficient and Effective MB discovery, called EEMB. Specifically, given a target feature, the EEMB algorithm discovers the PC (i.e., parents and children) and spouses of the target simultaneously and can distinguish PC from spouses during MB discovery. We compare EEMB with the state-of-the-art MB discovery algorithms using a series of benchmark BNs and real-world datasets. The experiments demonstrate that EEMB is competitive with the fastest MB discovery algorithm in terms of computational efficiency and achieves almost the same MB discovery accuracy as the most accurate of the compared algorithms.
       
  • H +Fuzzy+Filtering+for+Nonlinear+Parabolic+PDE+Systems+with+Markovian+Jumping+Sensor+Faults&rft.title=Information+Sciences&rft.issn=0020-0255&rft.date=&rft.volume=">Event-Triggered Reliable H ∞ Fuzzy Filtering for Nonlinear Parabolic PDE
           Systems with Markovian Jumping Sensor Faults
    • Abstract: Publication date: Available online 10 September 2019Source: Information SciencesAuthor(s): Xiaona Song, Mi Wang, Baoyong Zhang, Shuai Song This paper is devoted to event-triggered reliable H∞ filter design for a class of nonlinear partial differential equation (PDE) systems with Markovian jumping sensor faults. Initially, a Takagi-Sugeno (T-S) fuzzy model is adopted to reconstruct the nonlinear systems. Then, the time delays and signal quantization that often occur in network transmission are taken into account, and an integral-type event-triggered scheme is developed to improve the transmission channel utilization. Furthermore, non-parallel-distributed-compensation technique is introduced to increase the flexibility of filter design and the filter’s parameters can be obtained by solving several linear matrix inequalities. Finally, two numerical simulations and an application study to Catalytic Rod are provided to demonstrate the effectiveness and practicability of the proposed methodology.
       
  • Multiple-User Closest Keyword-Set Querying in Road Networks
    • Abstract: Publication date: Available online 10 September 2019Source: Information SciencesAuthor(s): Sen Zhao, Xin Cao Location-based group queries have attracted increasing attention due to the prevalence of location-based services (LBS) and location-based social networks (LBSN). An important and practical application in these queries is the multiple-user closest keyword-set (MCKS) query that aims to search a set of Points of Interest (POIs) for multiple users in road networks. These POIs cover the query keyword-set, are close to the locations of multiple users, and are close to each other. This problem has been proved to be NP-hard. Unfortunately, existing solutions cannot handle this query efficiently and effectively. Specifically, the existing exact approach does not scale well with the network sizes and the existing approximation approaches, though scalable, have large error bounds. To address the above issues, a series of enhanced algorithms are proposed for the MCKS query problem in this paper. Specifically, a 3-approximation feasible result search algorithm is first proposed. Then, using the cost of the result returned by this algorithm as an upper bound, we present an efficient exact algorithm and an approximation algorithm with better performance guarantee. The exact algorithm is designed based on a set of efficient optimizations. The approximation algorithm improves the best-known approximation ratio from 157 to 1.5. Extensive performance studies with two real datasets demonstrate the effectiveness and efficiency of our proposed algorithms, which outperform existing algorithms significantly.
       
  • Effective Rating Prediction Based on Selective Contextual Information
    • Abstract: Publication date: Available online 10 September 2019Source: Information SciencesAuthor(s): Rim Dridi, Saloua Zammali, Tagreed Alsulumani, Khedija Arour Many researchers have realized the importance of contextual information and focused on designing systems that predict user’s contextual preferences. In this respect, several researches have been devoted to Context-Aware Recommender Systems (CARS). One of the remaining issues in these systems especially the collaborative filtering based ones, is determining which contextual information can be adopted to make effective rating prediction. In fact, many contextual dimensions (e.g., location, time, mood etc.) may affect the user’s preferences, but not all of these dimensions are equally important for the rating prediction effectiveness. Many existing CARS approaches cannot fully capture the influence of relevant contextual dimensions and their interaction on the rating, and furthermore cannot obtain a better recommendation performance. To address these issues, we highlight contextual dimensions weighting, study the correlation between them to elicit the most useful ones, and propose two improved rating prediction methods based on collaborative filtering techniques, involving relevant and dependent contextual dimensions. Experimental results, with respect to rating prediction quality and recommendation performance on both public available and large created contextual datasets, show that our proposal outperforms the existing recommender systems especially on the created datasets.
       
  • Multi-view Laplacian Eigenmaps Based on Bag-of-Neighbors For RGB-D Human
           Emotion Recognition
    • Abstract: Publication date: Available online 9 September 2019Source: Information SciencesAuthor(s): Shenglan Liu, Shuai Guo, Wei Wang, Hong Qiao, Yang Wang, Wenbo Luo Human emotion recognition is an important direction in the fields of human-computer interaction and computer vision. However, most existing human emotion researches just focus on one view of the study objects. In this paper, we first introduce a RGB-D video-emotion dataset and a RGB-D face-emotion dataset for research, both of which are collected under psychological principles and methods. Then we propose a new supervised nonlinear multi-view laplacian eigenmaps (MvLE) approach and a multi-hidden-layer out-of-sample network (MHON) that can make full use of RGB view and Depth view of the two datasets. MvLE is employed to map the samples of both views from original spaces into a common subspace. As samples of RGB view and Depth view lie on different spaces, a new distance metric bag of neighbors (BON) introduced in MvLE can capture their similar distributions. Moreover, to adapt to large-scale applications, MHON is developed to get the low-dimensional representations of additional samples and predict their labels. MvLE and MHON can deal with the cases that RGB view and Depth view have different dimensions of original spaces, even different number of samples or categories. The experiment results indicate that the proposed methods achieve considerable improvement over some state-of-art methods.
       
  • Attention-based context-aware sequential recommendation model
    • Abstract: Publication date: Available online 9 September 2019Source: Information SciencesAuthor(s): Weihua Yuan, Hong Wang, Xiaomei Yu, Nan Liu, Zhenghao Li Recurrent neural networks (RNN) based recommendation algorithms have been introduced recently as sequence information plays an increasingly important role when modeling user preferences. However, these methods have numerous limitations: they usually give undue importance to sequential changes and place insufficient emphasis on the correlation between adjacent items; additionally, they typically ignore the impacts of context information. To address these issues, we propose an attention-based context-aware sequential recommendation model using Gated Recurrent Unit (GRU), abbreviated as ACA-GRU. First, we consider the impact of context information on recommendations and classify them into four categories, including input context, correlation context, static interest context, and transition context. Then, by redefining the update and reset gate of the GRU unit, we calculate the global sequential state transition of the RNN determined by these contexts, to model the dynamics of user interest. Finally, by leveraging the attention mechanism in the correlation context, the model is able to distinguish the importance of each item in the rating sequence. The impact of outliers that are less informative or less predictive decreases or is ignored. Experimental results indicate that ACA-GRU outperforms state-of-the-art context-aware models as well as sequence recommendation algorithms, demonstrating the effectiveness of the proposed model.
       
  • Two-Layer Fuzzy Multiple Random Forest for Speech Emotion Recognition in
           Human-Robot Interaction
    • Abstract: Publication date: Available online 6 September 2019Source: Information SciencesAuthor(s): Luefeng Chen, Wanjuan Su, Yu Feng, Min Wu, Jinhua She, Kaoru Hirota The two-layer fuzzy multiple random forest (TLFMRF) is proposed for speech emotion recognition. When recognizing speech emotion, there are usually some problems. One is that feature extraction relies on personalized features. The other is that emotion recognition doesn’t consider the differences among different categories of people. In the proposal, personalized and non-personalized features are fused for speech emotion recognition. High dimensional emotional features are divided into different subclasses by adopting the fuzzy C-means clustering algorithm, and multiple random forest is used to recognize different emotional states. Finally, a TLFMRF is established. Moreover, a separate classification of certain emotions which are difficult to recognize to some extent is conducted. The results show that the TLFMRF can identify emotions in a stable manner. To demonstrate the effectiveness of the proposal, experiments on CASIA corpus and Berlin EmoDB are conducted. Experimental results show the recognition accuracies of the proposal are 1.39%-7.64% and 4.06%-4.30% higher than that of back propagation neural network and random forest respectively. Meanwhile, preliminary application experiments are also conducted to investigate the emotional social robot system, and application results indicate that mobile robot can real-time track six basic emotions, including angry, fear, happy, neutral, sad, and surprise.
       
  • Leakage-Resilient Group Signature: Definitions and Constructions
    • Abstract: Publication date: Available online 4 September 2019Source: Information SciencesAuthor(s): Jianye Huang, Qiong Huang, Willy Susilo Group signature scheme provides a way to sign messages without revealing identities of the authentic signers. To achieve such functionality and to avoid the abuse of its power, anonymity and traceability are two essential properties for group signature scheme. In traditional group signature schemes, however, these two security properties are based on the perfectly-secure storage of secret information. Unfortunately, defective implementation of a cryptosystem always exists, and therefore unexpected information leakage is inevitable. In reality, side-channel attacks allow an adversary breaks the security of the whole system by eavesdropping a portion of secret information. To tackle this issue, in our work we present the security models of leakage-resilient group signature in bounded leakage setting and furthermore, propose three new black-box constructions of leakage-resilient group signature based on the proposed security models.
       
  • An online-learning-based evolutionary many-objective algorithm
    • Abstract: Publication date: January 2020Source: Information Sciences, Volume 509Author(s): Haitong Zhao, Changsheng Zhang When optimizing many-objective problems (MaOP), the same strategy might behave differently when facing problems with different features. Therefore, obtaining problem features helps to obtain high-quality solutions. However, in practice, the problem features are unknown during the optimization process. In this case, learning to adjust strategies to match the problem features is a challenging work. In this paper, a learning-based algorithm is proposed, aimed to enhance the generalization ability. On the basis of a decomposition-based many-objective optimization framework, a learning automaton (LA) is included in the algorithm. The LA adjusts the evolutionary strategies of the algorithm to adapt to the problem characteristics, according to the feedback information during the optimizing procedure. An external archive is employed to store the Pareto non-dominant solutions. Based on the external archive, a reference vector adjustment strategy is designed to enhance the capability of solving problems with a degenerate or discrete Pareto front (PF). To validate the performance of the proposed algorithm, a comparison experiment is conducted on a novel authority test suite. Five state-of-the-art algorithms are selected as peer algorithms. The results of the experiment indicate that the proposed algorithm obtains satisfactory performance in determining the convergence and the approximation of the PF.
       
  • Predicting tissue-specific protein functions using multi-part tensor
           decomposition
    • Abstract: Publication date: January 2020Source: Information Sciences, Volume 508Author(s): Sameh K. Mohamed Proteins are complex molecules that play many critical functions in the human body. They are expressed in different tissues in the body where their functions vary depending on the tissue they are expressed in. The disorder of protein interactome affects their biological functions which results in diseases. Therefore, understanding and assessing different tissue-specific protein functions in the human body is essential for disease diagnostics and therapeutics. However, it is a hard task as it requires laboratory experimentations and resources which are expensive and have limited scalability. Thus, multiple computational approaches were developed to predict tissue-specific protein functions. These approaches managed to provide predictions with high scalability and efficiency. However, they still suffer from high rates of false positives. In this work, we propose a new method for predicting tissue-specific protein functions using tensor factorisation with multi-part embeddings. We model proteins, functions, and their corresponding tissues as a tensor, and we apply tensor factorisation to learn scores for all possible protein-function associations for each of the studied tissues. We then show by experimental evaluation that our model outperforms the state-of-the-art models with a margin of 33.3% and 13% on the area under precision recall and ROC curves respectively.
       
  • Fully Probabilistic Design Unifies and Supports Dynamic Decision Making
           Under Uncertainty
    • Abstract: Publication date: Available online 3 September 2019Source: Information SciencesAuthor(s): Miroslav Kárný The fully probabilistic design (FPD) of decision strategies models the closed decision loop as well as decision aims and constraints by joint probabilities of involved variables. FPD takes the minimiser of cross entropy (CE) of the closed-loop model to its ideal counterpart, expressing the decision aims and constraints, as the optimal strategy. FPD: a) got an axiomatic basis; b) extended the decision making (DM) optimising a subjective expected utility (SEU); c) was nontrivially applied; d) advocated CE as a proper similarity measure for an approximation of a given probability distribution; d) generalised the minimum CE principle for a choice of the distribution, which respects its incomplete specification; e) has opened a way to the cooperation based on sharing of probability distributions. When trying to survey the listed results, scattered in a range of publications, we have found that the results under b), d) and e) can be refined and non-trivially generalised. This determines the paper aims: to provide a complete concise description of FPD with its use and open problems outlined.
       
  • Group decision making based on multiplicative consistency and consensus of
           fuzzy linguistic preference relations
    • Abstract: Publication date: Available online 3 September 2019Source: Information SciencesAuthor(s): Zhiming Zhang, Shyi-Ming Chen, Chao Wang Fuzzy linguistic preference relations (FLPRs) are an efficient way to express qualitative judgments of decision makers (DMs). This paper proposes a new group decision making (GDM) method based on the multiplicative consistency and consensus of FLPRs. First, we propose the concepts of consistency index and acceptable multiplicative consistent FLPRs. Then, we propose a method to improve the consistency of a FLPR, by which an acceptable multiplicative consistent FLPR is derived. Subsequently, we propose the consensus index for measuring the agreement among DMs. With respect to some FLPRs have an unacceptable multiplicative consistency and an unacceptable consensus, we propose an integer programming model to make both their consistency and consensus better to yield improved FLPRs with acceptable multiplicative consistency and consensus. Furthermore, the DMs’ comprehensive weight vector is determined. Then, we propose a new GDM algorithm following the multiplicative consistency and consensus of FLPRs. Finally, the feasibility and the applicability of the proposed GDM method are illustrated via an application example and some comparative analyses with the existing GDM methods.
       
  • Neighbourhood-based Undersampling Approach for Handling Imbalanced and
           Overlapped Data
    • Abstract: Publication date: Available online 3 September 2019Source: Information SciencesAuthor(s): Pattaramon Vuttipittayamongkol, Eyad Elyan Class imbalanced datasets are common across different domains including health, security, banking and others. A typical supervised learning algorithm tends to be biased towards the majority class when dealing with imbalanced datasets. The learning task becomes more challenging when there is also an overlap of instances from different classes. In this paper, we propose an undersampling framework for handling class imbalance in binary datasets by removing potential overlapped data points. Our methods are designed to identify and eliminate majority class instances from the overlapping region. Accurate identification and elimination of these instances maximises the visibility of the minority class instances and at the same time minimises excessive elimination of data, which reduces information loss. Four methods based on neighbourhood searching with different criteria to identify potential overlapped instances are proposed in this paper. Extensive experiments using simulated and real-world datasets were carried out. Results show comparable performance with state-of-the-art methods across different common metrics with exceptional and statistically significant improvements in sensitivity.
       
  • An Unsupervised Constrained Optimization Approach to Compressive
           Summarization
    • Abstract: Publication date: Available online 2 September 2019Source: Information SciencesAuthor(s): Natalia Vanetik, Marina Litvak, Elena Churkin, Mark Last Automatic summarization is typically aimed at selecting as much information as possible from text documents using a predefined number of words. Extracting complete sentences into a summary is not an optimal way to solve this problem due to redundant information that is contained in some sentences. Removing the redundant information and compiling a summary from compressed sentences should provide a much more accurate result. Major challenges of compressive approaches include the cost of creating large summarization corpora for training the supervised methods, the linguistic quality of compressed sentences, the coverage of the relevant content, and the time complexity of the compression procedure. In this work, we attempt to address these challenges by proposing an unsupervised polynomial-time compressive summarization algorithm. The proposed algorithm iteratively removes redundant parts from original sentences. It uses constituency-based parse trees and hand-crafted rules for generating elementary discourse units (EDUs) from their subtrees (standing for phrases) and selects ones with a sufficient tree gain. We define a parse tree gain as a weighted function of its node weights, which can be computed by any extractive summarization model capable of assigning importance weights to terms. The results of automatic evaluations on a single-document summarization task confirm that the proposed sentence compression procedure helps to avoid redundant information in the generated summaries. Furthermore, the results of human evaluations confirm that the linguistic quality—in terms of readability and coherency —is preserved in the compressed summaries while improving their coverage. However, the same evaluations show that compression in general harms the grammatical correctness of compressed sentences though, in most cases, this effect is not significant for the proposed compression procedure.
       
  • Sampled-position states based consensus of networked multi-agent systems
           with second-order dynamics subject to communication delays
    • Abstract: Publication date: Available online 2 September 2019Source: Information SciencesAuthor(s): Yanping Yang, Xian-Ming Zhang, Wangli He, Qing-Long Han, Chen Peng This paper is concerned with the sampled-position states based consensus of networked multi-agent systems with second-order dynamics, where agents are connected through communication channels subject to time-varying communication delays. Note that consensus in such systems cannot be reached if using only the current sampled-position states. This paper investigates the positive effects of time-varying communication delays on the consensus. For two cases, where a directed graph has a fixed or switching topology, several sufficient conditions on consensus are derived by using a discretized Lyapunov-Krasovskii functional method. Based on the obtained conditions, suitable control protocols can be devised through tuning two parameters. Finally, simulation shows that consensus can be achieved using sampled-position states if the time-varying communication delays are within a certain time interval with its lower bound strictly greater than zero.
       
  • Dynamic Event-Triggered Mechanism for H ∞ Non-Fragile State Estimation
           of Complex Networks under Randomly Occurring Sensor Saturations
    • Abstract: Publication date: Available online 2 September 2019Source: Information SciencesAuthor(s): Qi Li, Zidong Wang, Weiguo Sheng, Fawaz E. Alsaadi, Fuad E. Alsaadi In this paper, the problem of non-fragile H∞ state estimation is investigated for a class of discrete-time complex networks subject to randomly occurring sensor saturations (ROSSs) under a dynamic event-triggered mechanism (DETM). The ROSS phenomenon is taken into account in the network measurements as a reflection of the probabilistic limitation of the physical sensors, and the DETM is implemented to govern the signal transmission from the sensor to its corresponding state estimator. The objective of the problem addressed is to design an H∞ non-fragile state estimator under the DETM that can tolerate the possible gain perturbations, thereby possessing the desired non-fragility. By constructing a novel Lyapunov function, a sufficient condition is established such that the estimation error dynamics is exponentially mean-square stable with a prescribed H∞ performance level, and then the estimator gains are parameterized according to certain matrix inequalities. A simulation example is provided to demonstrate the effectiveness of the proposed state estimation scheme.
       
  • Securing Visual Search Queries in Ubiquitous Scenarios Empowered by Smart
           Personal Devices
    • Abstract: Publication date: Available online 30 August 2019Source: Information SciencesAuthor(s): Bruno Carpentieri, Arcangelo Castiglione, Alfredo De Santis, Francesco Palmieri, Raffaele Pizzolante, Xiaofei Xing Smart personal devices are assuming a fundamental role in the ubiquitous communication and computing arena. They provide new sophisticated cameras and new visual search interfaces and facilities that can drastically improve their presence and role in complex IoT-based critical infrastructures, such as healthcare monitoring and emergency systems, or remote access control facilities and smart authentication services. This new scenario calls for strong secure and resilient visual query mechanisms for these devices. In this work we propose an innovative secure visual search system, which is well-suited for ubiquitous computing scenarios empowered by modern smart personal devices. More precisely, we show how to insert, at the visual data acquisition time, a watermark inside the already compressed descriptor characterizing an MPEG-CDVS data stream used in visual queries, to make it possible to decode the watermark on the server side in order to improve the robustness against image-based identity spoofing. Such a security enforcement solution may be practical in several real-life applications involving visual queries performed from personal trusted devices, and it is particularly suitable in all those application domains that require performing visual queries with a high degree of security. It has been extensively tested and achieved satisfactory results: the presence of such a watermark does not affect the image matching performance and functionality.
       
  • Deep Feature Learning for Histopathological Image Classification of Canine
           Mammary Tumors and Human Breast Cancer
    • Abstract: Publication date: Available online 30 August 2019Source: Information SciencesAuthor(s): Abhinav Kumar, Sanjay Kumar Singh, Sonal Saxena, K. Lakshmanan, Arun Kumar Sangaiah, Himanshu Chauhan, Sameer Shrivastava, Raj Kumar Singh Canine mammary tumors (CMTs) have high incidences and mortality rates in dogs. They are also considered excellent models for human breast cancer studies. Diagnoses of both, human breast cancer and CMTs, are done by histopathological analysis of haematoxylin and eosin (H&E) stained tissue sections by skilled pathologists: a process that is very tedious and time-consuming. The existence of heterogeneous and diverse types of CMTs and the paucity of skilled veterinary pathologists justify the need for automated diagnosis. Deep learning-based approaches have recently gained popularity for analyzing histopathological images of human breast cancer. However, so far, due to the lack of any publicly available CMT database, no studies have focused on the automated classification of CMTs. To the best of our knowledge, we have introduced for the first time a dataset of CMT histopathological images (CMTHis). Further, we have proposed a framework based on VGGNet-16, and evaluated the performance of the fused framework along with different classifiers on the CMT dataset (CMTHis) and human breast cancer dataset (BreakHis). We also explored the effect of data augmentation, stain normalization, and magnification on the performance of the proposed framework. The proposed framework, with support vector machines, resulted in mean accuracies of 97% and 93% for binary classification of human breast cancer and CMT respectively, which validates the efficacy of the proposed system.
       
  • A penalty-based adaptive secure estimation for power systems under false
           data injection attacks
    • Abstract: Publication date: Available online 29 August 2019Source: Information SciencesAuthor(s): Minjing Yang, Hao Zhang, Chen Peng, Yulong Wang This paper proposes a penalty-based adaptive secure estimation method for multi-area power systems under false data injection (FDI) attacks, the adaptive secure estimation method specifically takes the characteristics of FDI attacks into account. Firstly, a new measurement modeling is delicately constructed for subarea of power systems, in which both the state and FDI attack information are well considered. Secondly, for convenient solving of constructed mixed variational inequality (MVI), series virtual nodes are effectively introduced to transfer the multi-area power systems with boundary nodes to a boundary system. Then, a penalty-based distributed estimation method is proposed to estimate the state of multi-area power systems under FDI attacks, where the penalty parameter can be adaptively adjusted based on the dynamic internal error and boundary error. Compared with some existing methods, the efficiency and accuracy of proposed method are improved, and the state and attack signals can be estimated simultaneously. Finally, a case study shows the effectiveness of proposed method.
       
  • Finding the Maximal Adversary Structure from Any Given Access Structure
    • Abstract: Publication date: Available online 29 August 2019Source: Information SciencesAuthor(s): Chunming Tang, Qiuxia Xu, Gengran Hu Secure multi-party computation is an important research area in cryptography, and the secret sharing scheme (SSS) is one of the main tools for constructing multi-party computation protocols. The access structure and the adversary structure are two important subsets of participants in an SSS. In general, the collection of all qualified subsets that can reconstruct the secret s, is known as an access structure, while no information regarding this secret is available to any unqualified subsets, and the collection of unqualified subsets is described as an adversary structure. The maximal adversary, which will become a qualified subset if any one participant not in this unqualified subset is added. At present, there is no effective algorithm to determine the maximal adversary structure for any given access structure. In this paper, we propose two algorithms to determine the maximal adversary structure from any given access structure, in which a binary tree is introduced to construct such algorithms. Moreover, a special type of access structure is established, from which the maximal adversary structure can be directly characterized, and the maximal adversary structure in this case is shown to be the largest when the number of participants of each qualified polynomial in the access structure is three.
       
  • RDF-TR: Exploiting Structural Redundancies to boost RDF Compression
    • Abstract: Publication date: Available online 29 August 2019Source: Information SciencesAuthor(s): Antonio Hernández-Illera, Miguel A. Martínez-Prieto, Javier D. Fernández The number and volume of semantic data have grown impressively over the last decade, promoting compression as an essential tool for RDF preservation, sharing and management. In contrast to universal compressors, RDF compression techniques are able to detect and exploit specific forms of redundancy in RDF data. Thus, state-of-the-art RDF compressors excel at exploiting syntactic and semantic redundancies, i.e., repetitions in the serialization format and information that can be inferred implicitly. However, little attention has been paid to the existence of structural patterns within the RDF dataset; i.e. structural redundancy. In this paper, we analyze structural regularities in real-world datasets, and show three schema-based sources of redundancies that underpin the schema-relaxed nature of RDF. Then, we propose RDF-Tr (RDF Triples Reorganizer), a preprocessing technique that discovers and removes this kind of redundancy before the RDF dataset is effectively compressed. In particular, RDF-Tr groups subjects that are described by the same predicates, and locally re-codes the objects related to these predicates. Finally, we integrate RDF-Tr with two RDF compressors, HDT and k2-triples. Our experiments show that using RDF-Tr with these compressors improves by up to 2.3 times their original effectiveness, outperforming the most prominent state-of-the-art techniques.
       
  • Infrared and visible image fusion based on target-enhanced multiscale
           transform decomposition
    • Abstract: Publication date: January 2020Source: Information Sciences, Volume 508Author(s): Jun Chen, Xuejiao Li, Linbo Luo, Xiaoguang Mei, Jiayi Ma In this study, we propose a target-enhanced multiscale transform (MST) decomposition model for infrared and visible image fusion to simultaneously enhance the thermal target in infrared images and preserve the texture details in visible images. The Laplacian pyramid is initially used to separately decompose two pre-registered source images into low- and high-frequency bands. The common “max-absolute” fusion rule is performed for fusion for high-frequency bands. We use the decomposed infrared low-frequency information to determine the fusion weight of low-frequency bands and highlight the target. Meanwhile, a regularization parameter is introduced to dominate the proportion of the infrared features in a gentle manner, which can be further adjusted according to user requirements. Finally, we use inverse transform with the Laplacian pyramid (LP) to reconstruct the fused image. Qualitative and quantitative experimental results on publicly available datasets demonstrate that the proposed method can generate fused images with clearly highlighted targets and abundant details. These images exhibit better visual effects and objective metric values than those of five other commonly used MST decomposition methods.
       
  • Surrogate-assisted classification-collaboration differential evolution for
           expensive constrained optimization problems
    • Abstract: Publication date: January 2020Source: Information Sciences, Volume 508Author(s): Zan Yang, Haobo Qiu, Liang Gao, Xiwen Cai, Chen Jiang, Liming Chen Expensive Constrained Optimization Problems (ECOPs) widely exist in various scientific and industrial applications. Surrogate-Assisted Evolutionary Algorithms (SAEAs) have recently exhibited great ability in solving these expensive optimization problems. This paper proposes a Surrogate-Assisted Classification-Collaboration Differential Evolution (SACCDE) algorithm for ECOPs with inequality constraints. In SACCDE, the current population is classified into two subpopulations based on certain feasibility rules, and a classification-collaboration mutation operation is designed to generate multiple promising mutant solutions by not only using promising information in good solutions but also fully exploiting potential information hidden in bad solutions. Afterwards, the surrogate is utilized to identify the most promising offspring solution for accelerating the convergence speed. Furthermore, considering that the population diversity may decrease due to the excessive incorporation of greedy information brought by the classified solutions, a global search framework that can adaptively adjust the classification-collaboration mutation operation based on the iterative information is introduced for achieving an effective global search. Therefore, the proposed algorithm can strike a well balance between local and global search. The experimental results of SACCDE and other state-of-the-art algorithms demonstrate that the performance of SACCDE is highly competitive.
       
  • The assessment of small bowel motility with attentive deformable neural
           network
    • Abstract: Publication date: January 2020Source: Information Sciences, Volume 508Author(s): Xing Wu, Mingyu Zhong, Yike Guo, Hamido Fujita The small bowel is the longest part of the gastrointestinal tract and quick assessment of its motility using Cine-MRI is conducive to the diagnosis of gastroenteric diseases. Because of the complex shape changes that occur frequently in the small bowel, approaches involving human designed features and simple convolutional neural network (CNN) methods fail to achieve satisfactory performance on massive datasets. To meet the challenge of assessing small bowel motility automatically, we propose the integration of deformable convolutional networks into attentive encoder–decoder. With the help of deformable convolution, a tailored CNN can track small bowel segments in different shapes from each MR image of a Cine-MRI sequence. The proposed attentive encoder–decoder performed significantly better than conventional recurrent neural network (RNN) in the assessment of small bowel motility. Experimental results demonstrate that the proposed method not only automatically assesses small bowel motility correctly, but also outperforms state-of-the-art methods. Furthermore, it provides useful information about the physiology of small bowel motility patterns, which can be used in the diagnosis of gastroenteric diseases.
       
  • Low-rank local tangent space embedding for subspace clustering
    • Abstract: Publication date: January 2020Source: Information Sciences, Volume 508Author(s): Tingquan Deng, Dongsheng Ye, Rong Ma, Hamido Fujita, Lvnan Xiong Subspace techniques have gained much attention for their remarkable efficiency in representing high-dimensional data, in which sparse subspace clustering (SSC) and low-rank representation (LRR) are two commonly used prototypes in the fields of pattern recognition, computer vision and signal processing. Both of them aim at constructing a block sparse matrix via linearly representing data to make them be embedded into linear subspaces. However, few datasets satisfy the linear subspace assumption in the real world. In this paper, data are peered from viewpoint of manifold architecture under the framework of sparse representation. A globally low-rank representation with the Frobenius norm minimization is constructed under the constraint of local manifold embedding and a novel low-rank local embedding representation (LRLER) model for subspace clustering of datasets is proposed. In this model, the local as well as global manifold structures of a dataset are concerned. Clusters of a dataset are considered as sub-manifolds embedded in low-dimensional subspaces. To represent and segment samples with hybrid neighbors or interlaced manifold structures, the local tangent space analysis strategy is introduced to characterize the local structure of neighborhood of samples. The coefficients of locally linear embedding are rectified according to the relationship between local tangent spaces of samples and their neighbors. A local tangent space based low-rank local embedding representation model (LRLTSER) is built to deal with data with neighborhood aliasing distortion. Extensive experiments on synthetic datasets and real-world datasets are implemented and experimental results show superior performance of the proposed methods for subspace clustering compared to the state-of-the-art techniques.
       
  • Three-way decision based on improved aggregation method of interval loss
           function
    • Abstract: Publication date: Available online 28 August 2019Source: Information SciencesAuthor(s): Yi Xu, Xusheng Wang Given a hybrid incomplete information table consisting both of the incomplete information table and loss function, the loss function of each object is denoted as an interval. The loss function of similarity class is defined as the aggregation of interval loss functions of all objects in its similarity class. However, existing optimistic aggregation method utilizes the union of interval loss functions of all objects in similarity class, which make the length of the aggregated interval loss function too broad. Pessimistic aggregation method utilizes the intersection of interval loss functions of all objects in similarity class, which make the length of the aggregated interval loss function too narrow. In order to get reasonable aggregated interval loss function, we propose a new aggregation method based on the principle of justifiable granularity, which make the length of the aggregated interval loss function neither too broad nor too narrow. That is, the aggregation result includes the interval loss functions of all objects in similarity class as much as possible and the aggregation result is as specific as possible. Based on the proposed aggregation method, we propose a new three-way decision model. Examples and experimental results demonstrate the effectiveness of the proposed method.
       
  • Hesitancy degree-based correlation measures for hesitant fuzzy linguistic
           term sets and their applications in multiple criteria decision making
    • Abstract: Publication date: Available online 28 August 2019Source: Information SciencesAuthor(s): Huchang Liao, Xunjie Gou, Zeshui Xu, Xiao-Jun Zeng, Francisco Herrera The hesitant fuzzy linguistic term set (HFLTS) turns out to be useful in representing people's hesitant qualitative information. The aim of this paper is to investigate new correlation measures between HFLTSs and apply them in decision-making process. Firstly, the concepts of mean and hesitancy degree of hesitant fuzzy linguistic elements are introduced. Based on them, we address the drawbacks of the existing correlation measures between HFLTSs. Then, a new correlation coefficient between HFLTSs is established. Additionally, the hesitancy degree of the hesitant fuzzy linguistic correlation coefficient is proposed, which is composed by the upper and lower bounds of the hesitant fuzzy linguistic correlation coefficient. To show the applicability of the proposed correlation measures, a correlation coefficient-based method is developed for multiple criteria decision making in the cases that the weights of criteria are either known or unknown. A practical example concerning the strategic management of Sichuan liquor brands in China is given to validate the proposed method. It is verified that the proposed correlation coefficients between HFLTSs is more convincing than the existing ones and the developed correlation coefficient-based hesitant fuzzy linguistic MCDM with the weights of criteria being either completely known or unknown is applicable.
       
  • Multi-factor one-order cross-association fuzzy logical relationships based
           forecasting models of time series
    • Abstract: Publication date: Available online 28 August 2019Source: Information SciencesAuthor(s): Fang Li, Fusheng Yu In the existing multi-factor one-order (MFOO) forecasting models, each fuzzy logical relation (FLR) has one consequent and more than one premise reflecting the association between the fuzzy values at two consecutive moments, and its premises are related to all the factors involved in forecasting. When using such FLRs to realize prediction, no matched FLR cases happened often and thus no logical prediction can be made. Two shortcomings are found for that: one is that more premises make FLRs matching more difficult; the other is that there are no enough FLRs. To overcome these shortcomings, this paper proposes two kinds of FLRs: short cross-association FLRs and long cross-association FLRs, which mean the influence on the consequent is from a part of the factors instead of all the factors. Specifically, the long cross-association FLRs aim at finding the association between fuzzy values at two non-consecutive moments. Such cross-associations exist in reality, the construction of them allows more FLRs to be mined from history observations. They can raise the possibility of finding available FLRs for forecasting. Based on the proposed FLRs, two MFOO forecasting models are proposed. Experiments show the advantage of the new FLRs and the good performance of the proposed models.
       
  • Non-fragile H ∞ consensus tracking of nonlinear multi-agent systems with
           switching topologies and transmission delay via sampled-data control
    • Abstract: Publication date: Available online 28 August 2019Source: Information SciencesAuthor(s): Xiangli Jiang, Guihua Xia, Zhiguang Feng, Tao Li In this paper, the sampled-data non-fragile H∞ consensus tracking problem for Lipschitz nonlinear multi-agent systems with switching topologies and exogenous disturbances is investigated. Each possible interaction topology in the switching topologies set is assumed to contain a directed spanning tree. With introducing a sampled-data mechanism, the information is only capable of being aperiodically transmitted in the network at each sampling instant and unavoidably subject to a transmission delay. Then a protocol collecting the delayed sampled-data information from neighboring agents is proposed not only to provide robustness against some level of controller gain perturbations, but also to regulate consensus performance with an H∞ disturbance attenuation level. By using tools from algebraic graph theory and Lyapunov-Krasovskii functional technique, it is proved that the concerned consensus tracking problem is solvable if the resultant consensus error system can be asymptotically stabilized. Simulation results verify the theoretical analysis.
       
  • Class-specific Attribute Value Weighting for Naive Bayes
    • Abstract: Publication date: Available online 28 August 2019Source: Information SciencesAuthor(s): Huan Zhang, Liangxiao Jiang, Liangjun Yu Naive Bayes (NB) is one of the top 10 data mining algorithms. However, its assumption of conditional independence rarely holds true in real-world applications. To alleviate this assumption, numerous attribute weighting approaches have been proposed. However, few of these simultaneously pay attention to the horizontal granularity of attribute values and vertical granularity of class labels. In this study, we propose a new paradigm for fine-grained attribute weighting, named class-specific attribute value weighting. For each class, this approach discriminatively assigns a specific weight to each attribute value. We refer to the resulting improved model as class-specific attribute value weighted NB (CAVWNB). In CAVWNB, the class-specific attribute value weight matrix is learned by either maximizing the conditional log-likelihood (CLL) or minimizing the mean squared error (MSE). Thus, two versions are proposed, which we denote as CAVWNBCLL and CAVWNBMSE, respectively. Extensive experimental results on a large number of datasets show that both CAVWNBCLL and CAVWNBMSE significantly outperform NB and all the other existing state-of-the-art attribute weighting approaches used for comparison.
       
  • Uncertain multi-attribute group decision making based on linguistic-valued
           intuitionistic fuzzy preference relations
    • Abstract: Publication date: Available online 28 August 2019Source: Information SciencesAuthor(s): Pengsen Liu, Hongyue Diao, Li Zou, Ansheng Deng The preference relations have shown some advantages in handling multi-attribute group decision making problems, which can assist decision makers to set priorities and make a reasonable decision. In real-life situations, decision makers sometimes express their preference with fuzzy and uncertain linguistic information including positive and negative sides at the same time. In order to deal with the decision-making problems with uncertain linguistic information, we propose an approach for uncertain multi-attribute group decision making based on linguistic-valued intuitionistic fuzzy preference relations (LIFPR). The presented LIFPR based on linguistic truth-valued intuitionistic fuzzy lattice can better express positive and negative evaluation information in the meanwhile. To aggregate linguistic information and reduce information loss of aggregation process, we propose linguistic-valued intuitionistic fuzzy 2-tuple representation model (LIF 2-tuple) and two kinds of linguistic-valued intuitionistic fuzzy aggregation operators. To deal with incomparable LIF 2-tuples, we present positive and negative LIF 2-tuple reference nearness degrees according to preferences. For the inconsistent LIFPR caused by subjective uncertainty, a consistency checking algorithm based on linguistic-valued intuitionistic fuzzy similarity is introduced to check and repair the consistency of a LIFPR. For the incomplete LIFPR caused by objective uncertainty, an improved LIFPR based on additive transitivity is presented to complement the LIFPR. We discuss the procedure of group decision making based on LIFPR with positive and negative evaluation information. An illustrate example shows the proposed approach for group decision making seems more effective for decision making under an uncertain linguistic environment.
       
  • A New Similarity Combining Reconstruction Coefficient with Pairwise
           Distance for Agglomerative Clustering
    • Abstract: Publication date: Available online 27 August 2019Source: Information SciencesAuthor(s): Zhiling Cai, Xiaofei Yang, Tianyi Huang, William Zhu Agglomerative clustering is a mainstream clustering method that can produce an informative hierarchical structure of clusters. Existing similarities in agglomerative clustering are typically based on the pairwise distance. Although this type of similarity captures the local structure of data well, it is sensitive to noise and outliers because it considers only the distance between data points. In this paper, we propose a new similarity called RCPD by combining the reconstruction coefficient, which is robust to noise and outliers, with the pairwise distance for agglomerative clustering. Our new similarity takes advantage of both the distance between data points and the linear representation among data points. Thus, RCPD not only captures the local structure of data well but is also robust to noise and outliers. The experimental results on 11 real-world benchmark datasets show that our new clustering method consistently outperforms many state-of-the-art clustering approaches.
       
  • An Incentive-Based Protection and Recovery Strategy for Secure Big Data in
           Social Networks
    • Abstract: Publication date: Available online 27 August 2019Source: Information SciencesAuthor(s): Youke Wu, Haiyang Huang, Ningyun Wu, Yue Wang, Md Zakirul Alam Bhuiyan, Tian Wang Big data sources, such as smart vehicles, IoT devices, and sensor networks, differ from traditional data sources in both output volume and variety. Big data is usually stored on various types of network nodes, which is prone to data security and privacy problems, such as virus infection. In particular, the spread of viruses through social networks can cause large-scale destruction and privacy leakage in the network. This paper aims to provide a solution to protect the security of big data. First, the users are divided into five states according to their reactions to data virus: susceptible, contagious, doubt, immune, and recoverable. Then, we propose a novel model for studying the propagation mechanism of data virus. To control the spread of virus and protect data security, an incentive mechanism is introduced. After that, a protection and recovery strategy (PRS) is developed to reduce infected users and increase the immunized. The experimental results on two data sets indicate that our model gives a good description of the data virus propagation process, and PRS is better than both acquaintance immunization and target immunization methods, which validates the privacy preserving strategy for big data in networks.
       
  • Towards A Distributed Local-search Approach for Partitioning Large-scale
           Social Networks
    • Abstract: Publication date: Available online 27 August 2019Source: Information SciencesAuthor(s): Bin Zheng, Ouyang Liu, Jing Li, Yong Lin, Chong Chang, Bo Li, Tefeng Chen, Hao Peng Large-scale social graph data poses significant challenges for social analytic tools to monitor and analyze social networks. A feasible solution is to parallelize the computation and leverage distributed graph computing frameworks to process such big data. However, it is nontrivial to partition social graphs into multiple parts so that they can be computed on distributed platforms. In this paper, we propose a distributed local search algorithm, named dLS, which enables quality and efficient partition of large-scale social graphs. With the vertex-centric computing model, dLS can achieve massive parallelism. We employ a distributed graph coloring strategy to differentiate neighbor nodes and avoid interference during the parallel execution of each vertex. We convert the original graph into a small graph, Quotient Network, and obtain local search solution from processing the Quotient Network, thus further improving the partition quality and efficiency of dLS. We have evaluated the performance of dLS experimentally using real-life and synthetic social graphs, and the results show that dLS outperforms two state-of-the-art algorithms in terms of partition quality and efficiency.
       
  • An Expanded Particle Swarm Optimization Based on Multi-Exemplar and
           Forgetting Ability
    • Abstract: Publication date: Available online 27 August 2019Source: Information SciencesAuthor(s): Xuewen Xia, Ling Gui, Guoliang He, Bo Wei, Yinglong Zhang, Fei Yu, Hongrun Wu, Zhi-Hui Zhan There are two phenomena in human society and biological systems. One is that people prefer to extract knowledge from multiple exemplars to obtain better learning ability. The other one is the forgetting ability that helps the encoding and consolidation of new information by removing unused or unwanted memories. Inspired by these phenomena, this paper transplants the multi-exemplar and forgetting ability to particle swarm optimization (PSO), and proposes an eXpanded PSO, called XPSO. Firstly, XPSO expands the “social-learning” part of each particle from one exemplar to two exemplars, learning from both the locally and the globally best exemplars. Secondly, XPSO assigns different forgetting abilities to different particles, simulating the forgetting phenomenon in the human society. Under the multi-exemplar learning model with forgetting ability, XPSO further adopts an adaptive scheme to update the acceleration coefficients and selects a reselection mechanism to update the population topology. The effectiveness of these additional proposed strategies is verified by extensive experiments. Moreover, comparison results among XPSO and other 9 popular PSO as well as 3 non-PSO algorithms on CEC’13 test suite suggest that XPSO attains a very promising performance for solving different types of functions, contributing to both higher solution accuracy and faster convergence speed.
       
  • Event-triggered synchronization control of networked Euler-Lagrange
           systems without requiring relative velocity information
    • Abstract: Publication date: Available online 27 August 2019Source: Information SciencesAuthor(s): Xiang-Yu Yao, Hua-Feng Ding, Ming-Feng Ge, Ju H. Park This paper investigates the single- and multi-synchronization control problems of networked Euler-Lagrange systems subject to parameter uncertainties, time-varying disturbances and scarce control resources in a unified framework. Several novel event-triggered control algorithms are developed without requiring relative velocity information, which is capable of significantly mitigating the cost of unnecessary controller updates, signal transmission and computation, while possessing satisfactory control performances. Additionally, based on the Lyapunov stability techniques, the rigorous sufficient criteria for the asymptotic convergence of the synchronization errors are established, and the positive lower bounds of execution intervals are derived to exclude Zeno behaviors. Finally, by further proposing other comparative control algorithms and conceiving a performance index named trigger rate, numerical examples are performed to demonstrate the effectiveness and superiority of the theoretical results.
       
  • False Data Injection Attacks against State Estimation in the presence of
           Sensor Failures
    • Abstract: Publication date: Available online 26 August 2019Source: Information SciencesAuthor(s): An-Yang Lu, Guang-Hong Yang This paper investigates false data injection attacks (FDIAs) in power networks equipped with state estimator and bad data detection (BDD) system in the presence of sensor failures. Compared with the existing attacks designed in the noiseless case, a class of sparse undetectable attacks (SUAs) is designed to worsen the estimation performance even in the presence of failures. First, necessary and sufficient conditions for the existence of SUAs in the presence of failures are provided with the help of the concept of orthogonal complement matrix. Second, based on the obtained conditions, an intelligent SUA design strategy is proposed. It is shown that by estimating the failure vector, an SUA can be designed such that the estimator provides incorrect state estimate and the detector does not raise alarm even in the presence of sensor failures. Finally, the effectiveness of the proposed attack design schemes are evaluated numerically for IEEE 5, 9, and 30-bus systems.
       
  • Measuring Trust in Social Networks Based on Linear Uncertainty Theory
    • Abstract: Publication date: Available online 26 August 2019Source: Information SciencesAuthor(s): Zaiwu Gong, Hui Wang, Weiwei Guo, Zejun Gong, Guo Wei In social networks, trust relationships are the basis for interactions among decision nodes. Trust relationships are subjective and dynamic, and there are only few sample data to measure the strength of these connections. Uncertainty theory is a mathematical system that studies the belief degree of experts and provides a new method for measuring trust in social networks. In this paper, uncertainty theory is applied to the modeling of social networks. For any feature where certain information cannot be directly obtained, the recommended trust is derived based on direct trust values, and the constraints of single-path trust chains are established. To avoid secondary uncertainties caused by subjective weighting while considering multi-node, multi-path chains, two weighted trust aggregation operators are developed to accomplish a multi-trust transitive aggregation model. The belief degrees of the nodes, the trust chains and the whole network are quantified, and a social network trust measurement model based on uncertainty theory is constructed. In the case of a lack of data on the trust chain, a trust threshold constraint is used to calculate the range of the incomplete chain.
       
  • Security control of cyber-physical switched systems under Round-Robin
           protocol: input-to-state stability in probability
    • Abstract: Publication date: Available online 25 August 2019Source: Information SciencesAuthor(s): Haijuan Zhao, Yugang Niu, Tinggang Jia This work addresses the sliding mode control (SMC) problem for a class of cyber-physical switched systems, in which both the Round-Robin (RR) protocol scheduling and the deception attacks may happen on the controller-to-actuator (C/A) channels. Under the regulation of RR protocol, only one controller node at each instant can access the network and transmit its signal to the corresponding actuator node, that is, the other actuators cannot obtain any new control information. Especially, the transmitted signal could be contaminated by randomly injecting false data. Thus, a key problem is how to design a suitable sliding surface and a desirable sliding mode controller for guaranteeing the dynamic performance of the closed-loop switched systems. To this end, a compensation strategy is proposed for those actuator nodes that don’t receive any new control signals at certain instant, based which a token-dependent SMC law is designed. Besides, the method of input-to-state stability in probability (ISSiP) is introduced and the sufficient conditions are established for the reachability of the specified sliding surface and the ISSiP of the resultant switched systems. Finally, some numerical simulation results are provided.
       
  • A comparative study of decision implication, concept rule and granular
           rule
    • Abstract: Publication date: Available online 24 August 2019Source: Information SciencesAuthor(s): Shaoxia Zhang, Deyu Li, Yanhui Zhai, Xiangping Kang Decision implication is a basic form of knowledge representation of formal concept analysis in the setting of decision-making. Concept rules are decision implications that reveal the dependencies between condition concepts and decision concepts. Granular rules are concept rules that reveal the dependencies between condition object concepts and decision object concepts. This paper conducts a comparative study of decision implication, concept rule and granular rule. First, we conclude that both concept rules and granular rules are not complete w.r.t. decision implications, and that granular rules are not complete w.r.t. concept rules, implying that there exists information loss when studying decision implications by using only concept rules or granular rules, or when studying concept rules by using only granular rules. Next, with the help of decision implication logic, we identify accurately the information loss in concept rules and granular rules, and explore the underlying reason behind the information loss in concept rules and granular rules. Finally, by using the obtained results, we revisit some work on concept rule and granular rule, make some insightful remarks on the non-redundancy of concept rules and clarify some seemingly misleading statements on the representation of concept rules by granular rules.
       
  • HAPE: A Programmable Big Knowledge Graph Platform
    • Abstract: Publication date: Available online 23 August 2019Source: Information SciencesAuthor(s): Ruqian LU, Chaoqun FEI, Chuanqing WANG, Shunfeng GAO, Han QIU, Songmao ZHANG, Cungen CAO Heaven Ape (HAPE) is an integrated big knowledge graph platform supporting the construction, management, and operation of large to massive scale knowledge graphs. Its current version described in this paper is a prototype, which consists of three parts: a big knowledge graph knowledge base, a knowledge graph browser on the client side, and a knowledge graph operation system on the server side. The platform is programmed in two high level scripting languages: JavaScript for programming the client side functions and Python for the server side functions. For making the programming more suitable for big knowledge processing and more friendly to knowledge programmers, we have developed two versions of knowledge scripting languages, namely K-script-c and K-script-s, for performing very high level knowledge programming of client resp. server side functions. HAPE borrows ideas from some well-known knowledge graph processing techniques and also invents some new ones as our creation. As an experiment, we transformed a major part of the DBpedia knowledge base and reconstructed it as a big knowledge graph. It works well in some application tests and provides acceptable efficiency.
       
  • Proximity semantics for topic-based abstract argumentation
    • Abstract: Publication date: Available online 22 August 2019Source: Information SciencesAuthor(s): Maximiliano C.D. Budán, Maria Laura Cobo, Diego C. Martinez, Guillermo R. Simari As we engage in a debate with other parties, it is usual that several issues might come under discussion. Many of these issues are interrelated by the topic they address, while others represent a departure from the focus of the discussion. In this work, we propose to extend Dung’s abstract argumentation frameworks by decorating arguments with a set of interrelated topics. These topics represent what the arguments are addressing and provide a supporting structure for the analysis of multi-topic argumentation. The introduction of a notion of distance between two topics associated with the arguments permits to consider the proximity of an argument to the focus of the debate, supporting in that manner an enriched semantic analysis.
       
  • Data-driven Software Defined Network Attack Detection : State-of-the-Art
           and Perspectives
    • Abstract: Publication date: Available online 22 August 2019Source: Information SciencesAuthor(s): Puming Wang, Laurence T. Yang, Xin Nie, Zhian Ren, Jintao Li, Liwei Kuang SDN (Software Defined Network) has emerged as a revolutionary technology in network, a substantial amount of researches have been dedicated to security of SDNs to support their various applications. The paper firstly analyzes State-of-the-Art of SDN security from data perspectives. Then some typical network attack detection (NAD) methods are surveyed, including machine learning based methods and statistical methods. After that, a novel tensor based network attack detection method named tensor principal comments analysis (TPCA) is proposed to detect attacks. After surveying the last data-driven SDN frameworks, a tensor based big data-driven SDN attack detection framework is proposed for SDN security. In the end, a case study is illustrated to verify the effectiveness of the proposed framework.
       
  • An Adaptive Hybrid Evolutionary Immune Multi-objective Algorithm Based on
           Uniform Distribution Selection
    • Abstract: Publication date: Available online 12 August 2019Source: Information SciencesAuthor(s): Junfei Qiao, Fei Li, Shengxiang Yang, Cuili Yang, Wenjing Li, Ke Gu In general, for the iteration process of an evolutionary algorithm (EA), there exists the problem of uneven distribution of individuals in the target space for both multi-objective and single-objective optimization problems. This uneven distribution significantly degrades the population diversity and convergence speed. This paper proposes an adaptive hybrid evolutionary immune algorithm based on a uniform distribution selection mechanism (AUDHEIA) for solving MOPs efficiently. In AUDHEIA, the individuals in the population are mapped to a hyperplane, which is correlated with the objective space and are clustered to increase the diversity of solutions. To improve the distribution of the solutions, the mapped hyperplane is evenly sectioned. With the constantly changing distribution during the iteration, a threshold as a standard for judging the distribution level is adjusted adaptively. When the threshold is not satisfied in the corresponding interval, the distribution enhancement module is activated. Then, the same number of individuals should be selected in each interval. However, sometimes, there are insufficient or no individuals in the interval during the iterative process. To obtain sufficient individuals, the limit optimization variation strategy of the best individual is adopted. Experiments show that this algorithm can escape from local optima and has a high convergence speed. Moreover, the distribution and convergence of this algorithm are superior to the peer algorithms tested in this paper.
       
  • A novel approach for panel data: An ensemble of weighted functional margin
           SVM models
    • Abstract: Publication date: Available online 20 February 2019Source: Information SciencesAuthor(s): Bi̇rsen Eygi Erdogan, Süreyya Özöğür-Akyüz, Pınar Karadayı Ataş Ensemble machine learning methods are frequently used for classification problems and it is known that they may boost the prediction accuracy. Support Vector Machines are widely used as base classifiers during the construction of different types of ensembles. In this study, we have constructed a weighted functional margin classifier ensemble on panel financial ratios to discriminate between solid and unhealthy banks for Turkish commercial bank case. We proposed a novel ensemble generation method enhanced by a pruning strategy to increase the prediction performance and developed a novel aggregation approach for ensemble learning by using the idea of weighted sums. The prediction performances are compared with a panel logistic regression which is considered a benchmark method for panel data. The results show that the proposed ensemble method is more successful than the straight SVM and the classical generalized linear model approach.
       
  • Privacy-preserving task recommendation with win-win incentives for mobile
           crowdsourcing
    • Abstract: Publication date: Available online 11 February 2019Source: Information SciencesAuthor(s): Wenjuan Tang, Kuan Zhang, Ju Ren, Yaoxue Zhang, Xuemin (Sherman) Shen Mobile crowdsourcing enables mobile requesters to publish tasks, which can be accomplished by workers with awards. However, existing task allocation schemes face tradeoff between effectiveness and privacy preservation, and most of them lack consideration of win-win incentives for both requesters and workers participation. In this paper, we propose a privacy-preserving task recommendation scheme with win-win incentives in crowdsourcing through developing advanced attribute-based encryption with preparation/online encryption and outsourced decryption technologies. Specifically, we design bipartite matching between published tasks and participant workers, to recommend tasks for eligible workers with interests and provide valuable task accomplishment for requesters in a win-win manner. Furthermore, our scheme reduces encryption cost for requesters by splitting encryption into preparation and online phases, as well as shifts most of the decryption overhead from the worker side to the service platform. Privacy analysis demonstrates requester and worker privacy preservation under chosen-keyword attack and chosen-plaintext attack. Performance evaluation shows cost-efficient computation overhead for requesters and workers.
       
  • APCN: A scalable architecture for balancing accountability and privacy in
           large-scale content-based networks
    • Abstract: Publication date: Available online 29 January 2019Source: Information SciencesAuthor(s): Yuxiang Ma, Yulei Wu, Jun Li, Jingguo Ge Balancing accountability and privacy has become extremely important in cyberspace, and the Internet has evolved to be dominated by content transmission. Several research efforts have been devoted to contributing to either accountability or privacy protection, but none of them has managed to consider both factors in content-based networks. An efficient solution is therefore urgently demanded by service and content providers. However, proposing such a solution is very challenging, because the following questions need to be considered simultaneously: (1) How can the conflict between privacy and accountability be avoided' (2) How is content identified and accountability performed based on packets belonging to that content' (3) How can the scalability issue be alleviated on massive content accountability in large-scale networks' To address these questions, we propose the first scalable architecture for balancing Accountability and Privacy in large-scale Content-based Networks (APCN). In particular, an innovative method for identifying content is proposed to effectively distinguish the content issued by different senders and from different flows, enabling the accountability of a content based on any of its packets. Furthermore, a new idea with double-delegate (i.e., source and local delegates) is proposed to improve the performance and alleviate the scalability issue on content accountability in large-scale networks. Extensive NS-3 experiments with real trace are conducted to validate the efficiency of the proposed APCN. The results demonstrate that APCN outperforms existing related solutions in terms of lower round-trip time and higher cache hit rate under different network configurations.
       
  • A privacy-preserving cryptosystem for IoT E-healthcare
    • Abstract: Publication date: Available online 28 January 2019Source: Information SciencesAuthor(s): Rafik Hamza, Zheng Yan, Khan Muhammad, Paolo Bellavista, Faiza Titouna Privacy preservation has become a prerequisite for modern applications in the cloud, social media, Internet of things (IoT), and E- healthcare systems. In general, health and medical data contain images and medical information about the patients and such personal data should be kept confidential in order to maintain the patients’ privacy. Due to limitations in digital data properties, traditional encryption schemes over textual and structural one-dimension data cannot be applied directly to e-health data. In addition, when personal data are sent over the open channels, patients may lose privacy of data contents. Hence, a secure lightweight keyframe extraction method is highly required to ensure timely, correct, and privacy-preserving e-health services. Besides this, it is inherently difficult to achieve a satisfied level of security in a cost-effective way while considering the constraints of real-time e-health applications. In this paper, we propose a privacy preserving chaos-based encryption cryptosystem for patients’ privacy protection. The proposed cryptosystem can protect patient’s images from a compromised broker. In particular, we propose a fast probabilistic cryptosystem to secure medical keyframes that are extracted from wireless capsule endoscopy procedure using a prioritization method. The encrypted images produced by our cryptosystem exhibits randomness behavior, which guarantee computational efficiency as well as a highest level of security for the keyframes against various attacks. Furthermore, it processes the medical data without leaking any information, thus preserving patient’s privacy by allowing only authorized users for decryption. The experimental results and security analysis from different perspectives verify the excellent performance of our encryption cryptosystem compared to other recent encryption schemes.
       
  • PRTA: A Proxy Re-encryption based Trusted Authorization scheme for nodes
           on CloudIoT
    • Abstract: Publication date: Available online 28 January 2019Source: Information SciencesAuthor(s): Mang Su, Bo Zhou, Anmin Fu, Yan Yu, Gongxuan Zhang In CloudIoT platform, the data is collected and shared by different nodes of Internet of Things (IoT), and data is processed and stored based on cloud servers. It has increased the abilities of IoT on information computation. Meanwhile, it also has enriched the resource in cloud and improved integration of the Internet and human world. All of this offer advantages as well as the new challenges of information security and privacy protection. As the energy limitation of the nodes in IoT, they are particularly vulnerable. It is much easier to hijack the nodes than to attack the data center for hackers. Thus, it is a crucial and urgent issue to realize the trusted update of authorization of nodes. When some nodes are hijacked, both of the behaviors to upload data to servers and to download information from servers should be forbidden. Otherwise, it might cause the serious damage to the sensitive data and privacy of servers. In order to solve this problem, we proposed a Proxy Re-encryption based Trusted Authorization scheme for nodes on CloudIoT (PRTA). PRTA is based on the proxy re-encryption (PRE), and the cloud server will play the roles of data storing and re-encrypting, which would reach the full potential of cloud computing and reduce the cost of nodes. The node’s status is taken as one of the parameters for data re-encryption and it is under the authorization servers’ control, which could ensure the security and reliability of the data and be beneficial for the privacy protection in CloudIoT. Also, the authorization servers are divided into the downloading and uploading kinds, which will make the application range much wider.
       
  • A novel many-objective evolutionary algorithm based on transfer matrix
           with Kriging model
    • Abstract: Publication date: Available online 17 January 2019Source: Information SciencesAuthor(s): Lianbo Ma, Rui Wang, Shengminjie Chen, Shi Cheng, Xingwei Wang, Zhiwei Lin, Yuhui Shi, Min Huang Due to the curse of dimensionality caused by the increasing number of objectives, it is very challenging to tackle many-objective optimization problems (MaOPs). Aiming at this issue, this paper proposes a novel many-objective evolutionary algorithm, called Tk-MaOEA, based on transfer matrix assisted by Kriging model. In this approach, for the global space optimization, a transfer matrix is used as a map tool to reduce the number of objectives, which can simplify the optimization process. For the objective optimization, the Kriging model is incorporated to further reduce the computation cost. In addition, the fast non-dominated sorting and farthest-candidate selection (FCS) methods are used to guarantee the diversity of solutions. Comprehensive experiments on a set of benchmark functions have been conducted. Experimental results show that Tk-MaOEA is effective for solving complex MaOPs.
       
  • An angle dominance criterion for evolutionary many-objective optimization
    • Abstract: Publication date: Available online 7 January 2019Source: Information SciencesAuthor(s): Yuan Liu, Ningbo Zhu, Kenli Li, Miqing Li, Jinhua Zheng, Keqin Li It is known that Pareto dominance encounters difficulties in many-objective optimization. This strict criterion could make most individuals of a population incomparable in a high-dimensional space. A straightforward approach to tackle this issue is modify the Pareto dominance criterion. This is typically done by relaxing the dominance region. However, this modification is often associated with one or more parameters of determining the relaxation degree, and the performance of the corresponding algorithm could be sensitive to such parameters. In this paper, we propose a new dominance criterion, angle dominance, to deal with many-objective optimization problems. This angle dominance criterion can provide sufficient selection pressure towards the Pareto front and be exempt from the parameter tuning. In addition, an interesting property of the proposed dominance criterion, in contrast to existing dominance criteria, lies in its capability to reflect an individual’s extensity in the population. The angle dominance is integrated into NSGA-II (instead of Pareto dominance) and has demonstrated high competitiveness in many-objective optimization in comparison with a range of peer algorithms.
       
  • Targeting customers for profit: An ensemble learning framework to support
           marketing decision-making
    • Abstract: Publication date: Available online 21 May 2019Source: Information SciencesAuthor(s): Stefan Lessmann, Johannes Haupt, Kristof Coussement, Koen W. De Bock Marketing messages are most effective if they reach the right customers. Deciding which customers to contact is an important task in campaign planning. The paper focuses on empirical targeting models. We argue that common practices to develop such models do not account sufficiently for business goals. To remedy this, we propose profit-conscious ensemble selection, a modeling framework that integrates statistical learning principles and business objectives in the form of campaign profit maximization. Studying the interplay between data-driven learning methods and their business value in real-world application contexts, the paper contributes to the emerging field of profit analytics and provides original insights how to implement profit analytics in marketing. The paper also estimates the degree to which profit-concious modeling adds to the bottom line. The results of a comprehensive empirical study confirm the business value of the proposed ensemble learning framework in that it recommends substantially more profitable target groups than several benchmarks.
       
  • HOBA: A novel feature engineering methodology for credit card fraud
           detection with a deep learning architecture
    • Abstract: Publication date: Available online 16 May 2019Source: Information SciencesAuthor(s): Xinwei Zhang, Yaoci Han, Wei Xu, Qili Wang Credit card transaction fraud costs billions of dollars to card issuers every year. A well-developed fraud detection system with a state-of-the-art fraud detection model is regarded as essential to reducing fraud losses. The main contribution of our work is the development of a fraud detection system that employs a deep learning architecture together with an advanced feature engineering process based on homogeneity-oriented behavior analysis (HOBA). Based on a real-life dataset from one of the largest commercial banks in China, we conduct a comparative study to assess the effectiveness of the proposed framework. The experimental results illustrate that our proposed methodology is an effective and feasible mechanism for credit card fraud detection. From a practical perspective, our proposed method can identify relatively more fraudulent transactions than the benchmark methods under an acceptable false positive rate. The managerial implication of our work is that credit card issuers can apply the proposed methodology to efficiently identify fraudulent transactions to protect customers’ interests and reduce fraud losses and regulatory costs.
       
  • Combining unsupervised and supervised learning in credit card fraud
           detection
    • Abstract: Publication date: Available online 16 May 2019Source: Information SciencesAuthor(s): Fabrizio Carcillo, Yann-Aël Le Borgne, Olivier Caelen, Yacine Kessaci, Frédéric Oblé, Gianluca Bontempi Supervised learning techniques are widely employed in credit card fraud detection, as they make use of the assumption that fraudulent patterns can be learned from an analysis of past transactions. The task becomes challenging, however, when it has to take account of changes in customer behavior and fraudsters’ ability to invent novel fraud patterns. In this context, unsupervised learning techniques can help the fraud detection systems to find anomalies. In this paper we present a hybrid technique that combines supervised and unsupervised techniques to improve the fraud detection accuracy. Unsupervised outlier scores, computed at different levels of granularity, are compared and tested on a real, annotated, credit card fraud detection dataset. Experimental results show that the combination is efficient and does indeed improve the accuracy of the detection.
       
  • Predicting the active period of popularity evolution: A case study on
           Twitter hashtags
    • Abstract: Publication date: Available online 17 April 2019Source: Information SciencesAuthor(s): Jianyi Huang, Yuyuan Tang, Ying Hu, Jianjiang Li, Changjun Hu The active period of popularity evolution indicates how long online content receives continuous attention from people. Although predicting popularity evolution has largely been explored, researches on predicting active period still remain open. If we know the duration of active period ahead of time, caching systems, online advertising, etc. can run more effectively. Therefore, predicting active period is of great importance, but it is a non-trivial task because of the two major challenges. First, numerous factors can influence the duration of active period. To predict active period accurately, it's difficult to consider what factors and how to embed them in DNN model. Second, the triggering time to predict different active periods must be decided carefully, because the durations of active periods differed from one another. This paper addresses these two challenges, focusing on Twitter hashtags as a case study. To deal with the first challenge, a DNN-based prediction framework is proposed, embedding dynamic and static factors by using LSTM and CNN respectively. To deal with the second challenge, an appropriate value of cumulative popularity is set to trigger predicting active period. Experimental and comparative results show the superiority of our prediction solution, comparing with spikeM and SVR.
       
  • Efficient and accurate 3D modeling based on a novel local feature
           descriptor
    • Abstract: Publication date: Available online 12 April 2019Source: Information SciencesAuthor(s): Bao Zhao, Juntong Xi Registration is a key step in 3D modeling. In this paper, we propose an efficient and accurate 3D modeling algorithm composed of pairwise registration and multi-view registration. In pairwise registration, we propose a novel local descriptor named divisional local feature statistics (DLFS) which is generated by first dividing a local space into several partitions along projected radial direction, and then performing the statistics of one spatial and three geometrical attributes on each partition. For improving the compactness of DLFS, a principal component analysis (PCA) technique is used to compress it. Based on the compressed DLFS descriptor together with a game theoretic matching technique and two variants of ICP, the pairwise registration is efficiently and accurately performed. On this basis, a multi-view registration is performed by combining shape growing based registration technique and simultaneous registration method. In this process, a correspondence transition technique is proposed for efficiently and accurately estimating the overlap ratio between any two inputting scans. Extensive experiments are conducted to verify the performance of our algorithms. The results show that the DLFS descriptor has strong robustness, high descriptiveness and efficiency. The results also show that the proposed 3D modeling algorithm is very efficient and accurate.
       
  • Objective reduction for visualising many-objective solution sets
    • Abstract: Publication date: Available online 8 April 2019Source: Information SciencesAuthor(s): Liangli Zhen, Miqing Li, Dezhong Peng, Xin Yao Visualising a solution set is of high importance in many-objective optimisation. It can help algorithm designers understand the performance of search algorithms and decision makers select their preferred solution(s). In this paper, an objective reduction-based visualisation method (ORV) is proposed to view many-objective solution sets. ORV attempts to map a solution set from a high-dimensional objective space into a low-dimensional space while preserving the distribution and the Pareto dominance relation between solutions in the set. Specifically, ORV sequentially decomposes objective vectors which can be linearly represented by their positively correlated objective vectors until the expected number of preserved objective vectors is reached. ORV formulates the objective reduction as a solvable convex problem. Extensive experiments on both synthetic and real-world problems have verified the effectiveness of the proposed method.
       
  • An adaptive penalty-based boundary intersection method for many-objective
           optimization problem
    • Abstract: Publication date: Available online 20 March 2019Source: Information SciencesAuthor(s): Yutao Qi, Dazhuang Liu, Xiaodong Li, Jiaojiao Lei, Xiaoying Xu, Qiguang Miao Compared with domination-based methods, the multi-objective evolutionary algorithm based on decomposition (MOEA/D) is less prone to the difficulty caused by an increase in the number of objectives. It is a promising algorithmic framework for solving many-objective optimization problems (MaOPs). In MOEA/D, the target MaOP is decomposed into a set of single-objective problems by using a scalarizing function with evenly specified weight vectors. Among the available scalarizing functions, penalty-based boundary intersection (PBI) with an appropriate penalty parameter is known to perform well. However, its performance is heavily influenced by the setting of the penalty factor (θ), which can take a value from zero to +∞. A limited amount of work has thus far considered the choice of an appropriate value of θ. This paper presents a comprehensive experimental study on WFG and WFG-extend problems featuring two to 15 objectives. A range of values of θ is investigated to understand its influence on the performance of the PBI-based MOEA/D (MOEA/D-PBI). Based on the observations, the range of values of θ are divided into three sub-regions, and a two-stage adaptive penalty scheme is proposed to adaptively choose an appropriate value from 0.001 to 8000 during an optimization run. The results of experiments show that, the robustness of MOEA/D-PBI can be significantly enhanced using the proposed scheme.
       
  • Fast hypervolume approximation scheme based on a segmentation strategy
    • Abstract: Publication date: Available online 27 February 2019Source: Information SciencesAuthor(s): Weisen Tang, Hai-Lin Liu, Lei Chen, Kay Chen Tan, Yiu-ming Cheung Hypervolume indicator based evolutionary algorithms have been reported to be very promising in many-objective optimization, but the high computational complexity of hypervolume calculation in high dimensions restrains its further applications and developments. In this paper, we develop a fast hypervolume approximation method with both improved speed and accuracy than the previous approximation methods via a new segmentation strategy. The proposed approach consists of two crucial process: segmentation and approximation. The segmentation process recursively finds areas easy to be measured and quantified from the original geometric figure as many as possible, and then divides the measurement of the rest areas into several subproblems. In the approximation process, an improved Monte Carlo simulation is developed to estimate these subproblems. Those two processes are mutually complementary to simultaneously improve the accuracy and the speed of hypervolume approximation. To validate its effectiveness, experimental studies on four widely-used instances are conducted and the simulation results show that the proposed method is ten times faster than other comparison algorithms with a same measurement error. Furthermore, we integrate an incremental version of this method into the framework of SMS-EMOA, and the performance of the integrated algorithm is also very competitive among the experimental algorithms.
       
  • APS: Attribute-aware privacy-preserving scheme in location-based services
    • Abstract: Publication date: Available online 22 February 2019Source: Information SciencesAuthor(s): Weihao Li, Chen Li, Yeli Geng As one of the most significant factors for privacy protection, side information has been considered in designing privacy-preserving schemes in Location-Based Services (LBSs) over recent years. However, most existing schemes consider this concept through a straightforward way, such as query probability. In this paper, we consider the basic attribute associating with each location and design an Attribute-aware Privacy-preserving Scheme (APS) to enhance mobile user’s location privacy. Specifically, we first extract basic attributes from the local map, and specialize the Attribute-Aware Side Information (AASI). Then we build an attribute-based hierarchical tree (A-tree), which classifies locations into different categories in term of each location’s attribute. Based on such information, we design APS, which consists of two algorithms, Voronoi Dividing Algorithm (VDA) and Dummy Determining Algorithm (DDA). In VDA, we divide the local map into different Voronoi polygons based on the properties of Voronoi Diagram, which guarantees the selected locations are dispersed. In DDA, we utilize the Four Color Map Theorem to color these Voronoi polygons, which helps mobile users to choose the dummy locations as far as possible. Therefore, our APS provides an optimal dummy set to protect mobile user’s location privacy and query privacy. Finally, thorough analysis and evaluation results illustrate the effectiveness and efficiency of our proposed scheme.
       
  • tcc2vec: RFM-informed representation learning on call graphs for churn
           prediction
    • Abstract: Publication date: Available online 20 February 2019Source: Information SciencesAuthor(s): Sandra Mitrović, Bart Baesens, Wilfried Lemahieu, Jochen De Weerdt Applying social network analytics for telco churn prediction has become indispensable for almost a decade. However, in the current literature, the uptake does not reflect in a significantly increased leverage of the available information that these networks convey. First, network featurization in general is a very cumbersome process due to the complex nature of networks and the lack of a respective methodology. This results in ad hoc approaches and hand-crafted features. Second, deriving certain structural features in very large graphs is computationally expensive and, as a consequence, often neglected. Third, call networks are mostly treated as static in spite of their inherently dynamic nature. In this study, we propose tcc2vec, a panoptic approach aiming at devising representation learning (to address the first problem) on enriched call networks that integrate interaction and structural information (to overcome the second problem), which are being sliced in different time periods in order to account for different temporal granularities (hence addressing the third problem). In an extensive experimental analysis, insights are provided regarding an optimal choice of interaction and temporal granularities, as well as representation learning parameters.
       
  • Cloud-based Lightweight Secure RFID Mutual Authentication Protocol in IoT
    • Abstract: Publication date: Available online 4 August 2019Source: Information SciencesAuthor(s): Kai Fan, Qi Luo, Kuan Zhang, Yintang Yang Radio Frequency Identification (RFID) is a supporting technology for the Internet of things (IoT). RFID enables all physical devices to be connected to IoT. When RFID is widely used and developing rapidly, its security and privacy issues cannot be ignored. The wireless broadcast channel between the tag and the reader may be subject to many security attacks, such as interception, modification, and replay. Messages from unverified tags or readers are also untrustworthy. A secure and stable RFID authentication scheme is critical to IoT. This paper puts forward an efficient and reliable cloud-based RFID authentication scheme. In order to reduce the RFID tag's overhead, the proposed authentication scheme explores the rotation and enhanced permutation to encrypt data. The proposed protocol not only resists the above common attacks and protects the privacy of the tag, but also adds the cloud server to the RFID system. Performance simulation shows that permutation and rotation are efficient. Security analysis shows that our protocol can resist various attacks, such as tracking, replay, and desynchronization attack. Mutual authentication and backward security are also achieved. Finally, we apply BAN logic to prove the security of the protocol.
       
  • Privacy-preserving computation in cyber-physical-social systems: A survey
           of the state-of-the-art and perspectives
    • Abstract: Publication date: Available online 26 July 2019Source: Information SciencesAuthor(s): Jun Feng, Laurence T. Yang, Nicholaus J. Gati, Xia Xie, Benard S. Gavuna Cyber-physical-social systems (CPSSs) are leading digital revolutions in academia, industry and government. Due to the rise of big data analytics, tensor computations are currently used in CPSSs. With the increasing popularity of cloud computing or fog computing, big data in CPSSs are usually sent to clouds or fogs for computations. Recently, some studies about privacy-preserving computation have been conducted to address security concerns which enable data analysis and processing in cloud or fog environments in a privacy-preserving way. To fully understand the state-of-the-art advances and discover the research directions of this field, in this survey, both previous and current privacy-preserving schemes are comprehensively reviewed and studied. In addition, a novel privacy-preserving tensor computation framework, a case study, and several future research directions are presented for CPSSs.
       
  • Exploiting location-related behaviors without the GPS data on smartphones
    • Abstract: Publication date: Available online 22 May 2019Source: Information SciencesAuthor(s): Fenghua Li, Xinyu Wang, Ben Niu, Hui Li, Chao Li, Lihua Chen The concerns about location privacy has received considerable attention with the development of Location-based Services (LBSs) over the recent years. Most smartphone users ignore the fact that Apps can infer their locations through accessing WiFi list, although they carefully set location-related permissions to preserve their privacy. Therefore, it is crucial to the public to investigate severe such consequence of WiFi list leakage. In this paper, we develop a tracking scheme for Android, called TrackU, which validate that it is possible to obtain user’s location data as well as their location-related behaviors, just by monitoring the WiFi list without any GPS data. Firstly, it periodically scans available Access Points (APs) nearby and queries the geo-location of the device from LBS providers. Secondly, a drift adjusting algorithm proposed obtains the exact locations considering a set of factors, such as historical location information, average signal strength and changing of WiFi list. To preserve the battery life, an optimization is made to dynamically adjust the positioning interval. Based on the obtained data, we design an activity detection algorithm precisely to infer users’ daily activities, and identify their travel modes, i.e., hovering, walking, and vehicles. Finally, we implement TrackU and carry out a series of experiments with 39 volunteers from seven cities of China. The experiment results show that our design can detect 91.6% of activities by monitoring the WiFi list, and accurately recognize 94.6% of user’s travel mode.
       
  • Incentive Mechanism for Cooperative Authentication: an Evolutionary Game
           Approach
    • Abstract: Publication date: Available online 16 July 2019Source: Information SciencesAuthor(s): Liang Fang, Guozhen Shi, Lianhai Wang, Yongjun Li, Shujiang Xu, Yunchuan Guo In mobile opportunistic networks (MONs), cooperative authentication is an efficient way to filter false or misleading messages. However, due to privacy issues and concerns related to the consumption of resources, without adequate incentives, most mobile users (or nodes) with limited resources often act selfishly. These users are frequently uninterested to help others to authenticate such messages. In this study, a cooperative authentication model was formulated in the form of an evolutionary game. This model addresses the problems caused when cooperative nodes do not have all the information regarding other neighboring nodes, which makes them inadequately rational. Herein, the behavior dynamics and evolutionary stable strategy (ESS) of neighboring nodes were derived. We showed that the behavior dynamics converge to the ESS. This induces the neighboring nodes to independently decide whether to participate in authentication or not, without depending on information from other nodes (therefore, our approach can be implemented in the de-centralized manner). Further, a scheme to help the source node was also designed to determine an optimal budget. Experiments were conducted both on simulated as well as real datasets. The results demonstrate that our approach exhibits overwhelming advantages to incentivize selfish nodes in MONs to cooperate.
       
  • H ∞ bumpless transfer reliable control of Markovian switching LPV
           systems subject to actuator failures
    • Abstract: Publication date: Available online 15 July 2019Source: Information SciencesAuthor(s): Dong Yang, Guangdeng Zong, Sing Kiong Nguang In this paper, the H∞ bumpless transfer reliable control problem of Markovian switching linear parameter-varying (LPV) systems subject to actuator failures is addressed. A bumpless transfer reliable control constraint is introduced to describe the transient performance for such systems. By the use of the parameter-dependent Lyapunov function approach to reduce control bumps generated by the Markovian switching, a reliable switching controller which is also parameter-dependent is constructed to attenuate external disturbances. A criterion checking the solvability of the H∞ bumpless transfer reliable control problem is provided. As an application, a turbofan-engine model is used to verify the validity of the proposed design method.
       
  • An Efficient Approach for Secure Multi-party Computation without
           Authenticated Channel
    • Abstract: Publication date: Available online 14 July 2019Source: Information SciencesAuthor(s): Duy-Hien Vu, The-Dung Luong, Tu-Bao Ho Secure multi-party sum is one of the most important secure multi-party computation protocols. It has been widely applied to solve many privacy-preservation problems such as privacy-preserving data mining, secure auction, secure electronic voting, and privacy-preserving statistical data analysis. To guarantee the correctness of the final output and to enhance the security level, the existing secure multi-party sum protocols have to use authenticated channels, even secure channels for participants to communicate, however such a usage requirement significantly reduces their performance. Furthermore, these secure multi-party sum protocols are impossible to run on public networks. In this paper, we propose a new secure multi-party sum protocol that can ensure the correctness of the output result as well as securely protecting the parties’ privacy against attacks without requiring any authenticated/secure channel. The proposed protocol is based on a multi-party sum function employing a variant of ElGamal encryption and a Schnorr signature-derived authentication method, in which both these cryptographic tools use the same the private and public parameters. Additionally, our comparative evaluation shows that the proposed protocol is efficient and practical.
       
  • A Privacy-Preserving RFID Authentication Protocol Based on El-Gamal
           Cryptosystem for Secure TMIS
    • Abstract: Publication date: Available online 9 July 2019Source: Information SciencesAuthor(s): Fatty M. Salem, Ruhul Amin The healthcare environment now provides the facility for patients to communicate with doctors from home via the Internet; this facility is very useful for seriously ill patients. Errors in medication are hazardous and can cause significant harm to patients; therefore, patient medication and information safety are essential issues in such a healthcare environment. To protect this sensitive information, an authentication protocol is needed. Moreover, in the context of sharing data including a patient's personal information, privacy leakage has become one of the most challenging issues in a telecare medicine information system (TMIS). In this paper, we propose a privacy-preserving radio frequency identification (RFID) authentication protocol based on the El-Gamal cryptosystem, for enhancing patient medication safety in a TMIS. The proposed protocol can achieve a number of security services and can also resist several types of attacks. We have also shown the results obtained by conducting an "Automated Validation of Internet Security Protocols and Applications" (AVISPA) simulation of our protocol. The simulation results verify that the proposed protocol is safe against active and passive attacks. The results of an informal security analysis also indicate that patient information is highly private, and the system is protected against possible related attacks. Our protocol is not only better in terms of protecting the privacy of patients but it also achieves better performance than similar existing protocols.
       
  • Face Hallucination via Multiple Feature Learning with Hierarchical
           Structure
    • Abstract: Publication date: Available online 18 June 2019Source: Information SciencesAuthor(s): Licheng Liu, Han Liu, Shutao Li, C. L. Philip Chen In the past few years, neighbor-embedding (NE) based methods have been widely exploited for face hallucination. However, the existing NE based methods in spatial domain just employ single type of features for data representation, ignoring the compensatory information among multiple image features, resulting in bias in high resolution (HR) face image reconstruction. To tackle such problem, this paper presents a novel Multiple feature Learning model with Hierarchical Structure (MLHS) for face hallucination. Compared with conventional NE based methods, the proposed MLHS makes full use of multi-level information of face images, which can effectively remedy the flaw caused by just using single type of spatial pixel features, and adopts hierarchical structure to better maintain the manifold consistency hypothesis between the HR and low resolution (LR) patch spaces. The multiple learning strategy and hierarchical structure admit the proposed MLHS to well reconstruct the face details such as eyes, nostrils and mouth. The validity of the proposed MLHS method is confirmed by the comparison experiments in some public face databases.
       
  • Robust Face Hallucination via Locality-constrained Multiscale Coding
    • Abstract: Publication date: Available online 17 June 2019Source: Information SciencesAuthor(s): Na Li, Licheng Liu, Shutao Li, Hui Lin Face hallucination (FH) is to produce face images with High Resolution (HR) from Low Resolution (LR) observations. Unfortunately, most existing FH methods fail to make full use of the local geometrical information, especially when the LR images are corrupted by noise. Inspired by the observation that regions with large scales can provide much useful information, in this paper we propose a Robust Locality-constrained Multiscale Coding (RLMC) based method to forecast HR face images while suppressing noise and outliers. In RLMC, a weight vector is used in the loss function to ease the effect of outliers in data representation. Furthermore, inspired by the observation that abundant local information can be exploited by jointly representing overlapping patches with multiple scales. Simultaneously encoding multiple scale patches encourages different scales to share complementary information, which admits the proposed method to generate more appropriate coefficients for super-resolution reconstruction. Experimental results verified the effectiveness of the proposed method in terms of both quantitative measurements and visual impressions.
       
  • Sparsity in function and derivative approximation via the Empirical
           Feature Space
    • Abstract: Publication date: Available online 14 June 2019Source: Information SciencesAuthor(s): Sumit Soman, Jayadeva, Rajat Thakur, Mayank Sharma, Suresh Chandra Several practical applications require estimation of the values of a function and its derivative at specific sample locations.This is a challenging task particularly when the explicit forms of the function and its derivative are not known. There have been a few methods proposed in the literature to learn an approximant that simultaneously uses values of a function as well as values of its derivatives or partial derivatives. These methods typically use Support Vector Regression (SVR) and solve a Quadratic Programming Problem (QPP) for the task, which results in a learning model that can estimate the function and derivative values. In this paper, we propose an alternative novel approach that focuses on introducing sparsity in such a learning model, that is based on minimizing the model complexity in the Empirical Feature Space (EFS). Sparsity in such a model is useful when it needs to be evaluated a large number of times as it entails lower computational cost compared to a dense model. The proposed approach, called the EFSRD (EFS Regression for Function and Derivative approximation), involves solving a Linear Programming Problem (LPP). On a number of benchmark examples, EFSRD learns models that offer comparable or better performance, while learning models that are nearly a fourth the size of those obtained by existing approaches.
       
  • Smoothed Self-Organizing Map for robust clustering
    • Abstract: Publication date: Available online 13 June 2019Source: Information SciencesAuthor(s): Pierpaolo D’Urso, Livia De Giovanni, Riccardo Massari In this paper a Self-Organizing Map (SOM) robust to the presence of outliers, the Smoothed SOM (S-SOM), is proposed. S-SOM improves the properties of input density mapping, vector quantization, and clustering of the standard SOM in the presence of outliers by upgrading the learning rule in order to smooth the representation of outlying input vectors onto the map. The upgrade of the learning rule is based on the complementary exponential distance between the input vector and its closest codebook. The convergence of the S-SOM to a stable state is proved. Three comparative simulation studies and a suggestive application to digital innovation data show the robustness and effectiveness of the proposed S-SOM. Supplementary materials for this article are available.
       
  • Note on Entropies of Hesitant Fuzzy Linguistic Term Sets and Their
           Applications
    • Abstract: Publication date: Available online 9 June 2019Source: Information SciencesAuthor(s): Cuiping Wei, Peng Li, Rosa M. Rodríguez Hesitant fuzzy linguistic term set (HFLTS) is very useful in depicting the situations where people are hesitant to provide their opinions or assessments. In a HFLTS, it should be considered two types of uncertainty, fuzziness and hesitation. This paper is aimed to investigate the problem of how apply different uncertainty facets in different decision making settings. First, a new construction method of a fuzzy entropy for HFLTSs is proposed and it is compared with other methods already introduced in the literatures. Afterwards, these entropy formulas are used to propose two algorithms for deriving the criteria weights and experts weights. Different from the existing applications, it is stressed that in the process of deriving the criteria weights, only the hesitancy of the HFLTS should be considered, while in the process of deriving the experts weights with hesitant fuzzy preference relation information, both the fuzziness and hesitancy of the evaluation information should be involved.
       
  • Optimal performance of LTI systems over power constrained erasure channels
    • Abstract: Publication date: Available online 4 June 2019Source: Information SciencesAuthor(s): Xiao-Wei Jiang, Xiang-Yong Chen, Ming Chi, Ming-Feng Ge In this paper, the optimal performance of multiple-input multi-output (MIMO) linear time-invariant (LTI) plant is investigated. The communication channel is modeled as a power constrained channel with packet dropouts. The covariance of error signal between reference input and system’s output is chosen as the performance index. Based on the frequency domain analysis method, the exact expressions of the tracking performance limitation are derived. The results reveal that the best performance of NCSs not only has strong connection with both the nonminimum phase zeros and unstable poles of the plant, but also has close relation with the essential feature of reference input signal and communication parameters. Finally, a simulation example is discussed to validate the conclusions.
       
  • Finite-time containment control for nonlinear multi-agent systems with
           external disturbances
    • Abstract: Publication date: Available online 31 May 2019Source: Information SciencesAuthor(s): Hui Lü, Wangli He, Qing-Long Han, Xiaohua Ge, Chen Peng This paper is concerned with the finite-time containment control for a second-order nonlinear multi-agent system in the presence of external disturbances. First, two finite-time containment control protocols are skillfully developed, of which one is based on a terminal sliding mode and the other is based on a non-singular terminal sliding mode. Second, criteria for designing desired containment control protocols are derived such that the containment performance of the resulting closed-loop leader-following multi-agent system can be guaranteed within a finite time horizon. It is shown that the settling time of the closed-loop system convergence can be estimated under the proposed protocols. Furthermore, finite-time containment control in the scenario of general switching and directed topology is also addressed and the corresponding result is derived. Finally, three illustrative examples are given to verify the effectiveness of the proposed finite-time containment control method.
       
  • Building a Dynamic Searchable Encrypted Medical Database for Multi-client
    • Abstract: Publication date: Available online 24 May 2019Source: Information SciencesAuthor(s): Lei Xu, Chungen Xu, Joseph K. Liu, Cong Zuo, Peng Zhang E-medical record is an emerging health information exchange model based on cloud computing. As cloud computing allows companies and individuals to outsource their data and computation, the medical data is always stored at a third party such as cloud, which brings a variety of risks, such as data leakage to the untrusted cloud server, unauthorized access or modification operations. To assure the confidentiality of the data, the data owner needs to encrypt the sensitive data before uploading to the third party. Yet, issues like encrypted data search, flexible access and control on sensitive data have also remained the most significant challenges. In this paper, we investigate a novel searchable encrypted e-medical framework for multi-client which provides both confidentiality and searchability. Different from previous privacy protecting works in secure data outsourcing, we focus on providing a fine-grained access control encrypted data search scheme including clients and data. Our scheme also enables secure data update of the encrypted database by leveraging a secure dynamic searchable encryption. Furthermore, we implement the proposed scheme based on some existed cryptography library, and conduct several experiments on a selected dataset to evaluate its performance. The results demonstrate that our scheme provides a balance between security and efficiency.
       
  • A Trajectory Privacy-preserving Scheme Based on a Dual-K Mechanism for
           Continuous Location-based Services
    • Abstract: Publication date: Available online 23 May 2019Source: Information SciencesAuthor(s): Shaobo Zhang, Xinjun Mao, Kim-Kwang Raymond Choo, Tao Peng, Guojun Wang Location-based services (LBSs) have increasingly provided by a broad range of devices and applications, but one associated risk is location disclosure. To solve this problem, a commonly method is to adopt K-anonymity in the centralized architecture based on a single trusted anonymizer. However, this strategy may compromise user privacy involving continuous LBSs. In this study, we propose a dual-K mechanism (DKM) to protect the users’ trajectory privacy for continuous LBSs. The proposed DKM method firstly inserted multiple anonymizers between the user and the location service provider (LSP), and K query locations are sent to different anonymizers to achieve K-anonymity. Simultaneously, we combined the dynamic pseudonym and the location selection mechanisms to improve user trajectory privacy. Hence, neither the LSP nor the anonymizer can obtain the user trajectory. Security analyses demonstrates that our proposed scheme can effectively enhance user trajectory privacy protection, and the simulation results prove that the DKM scheme can preserve user trajectory privacy with low overhead on a single anonymizer.
       
  • Efficient Privacy Preservation of Big Data for Accurate Data Mining
    • Abstract: Publication date: Available online 22 May 2019Source: Information SciencesAuthor(s): M.A.P. Chamikara, P. Bertok, D. Liu, S. Camtepe, I. Khalil Computing technologies pervade physical spaces and human lives, and produce vast amount of data that is available for analysis. However, there is a growing concern that potentially sensitive data may become public if the collected data are not appropriately sanitized before being released for investigation. Although there are more than a few privacy-preserving methods available, they are not efficient, scalable or have problems with data utility, and/or privacy. This paper addresses these issues by proposing an efficient and scalable nonreversible perturbation algorithm, PABIDOT, for privacy preservation of big data via optimal geometric transformations. PABIDOT was tested for efficiency, scalability, resilience, and accuracy using nine datasets and five classification algorithms. Experiments show that PABIDOT excels in execution speed, scalability, attack resilience and accuracy in large-scale privacy-preserving data classification when compared with two other, related privacy-preserving algorithms.
       
 
 
JournalTOCs
School of Mathematical and Computer Sciences
Heriot-Watt University
Edinburgh, EH14 4AS, UK
Email: journaltocs@hw.ac.uk
Tel: +00 44 (0)131 4513762
Fax: +00 44 (0)131 4513327
 
Home (Search)
Subjects A-Z
Publishers A-Z
Customise
APIs
Your IP address: 34.236.170.48
 
About JournalTOCs
API
Help
News (blog, publications)
JournalTOCs on Twitter   JournalTOCs on Facebook

JournalTOCs © 2009-