Abstract: The knapsack feasibility problems have been intensively studied both because of their immediate applications in industry and financial management, but more pronounced for theoretical reasons, as knapsack problems frequently occur by relaxation of various integer programming problems. In this work, the large-scale knapsack feasibility problem is divided into two subproblems. The first subproblem is transforming of the knapsack feasibility problem into a polytope judgement problem which is based on lattice basis reduction. In the next subproblem, a distributed implementation of Dang and Ye’s fixed-point iterative algorithm is introduced to solve the polytope judgement problem generated in the former subproblem. Compared with the branch and bound method, numerical results show that this distributed fixed-point method is effective. PubDate: 2017-12-20
Abstract: Advances in causal discovery from data are becoming a widespread topic in machine learning these recent years. In this paper, studies on conditional independence-based causality are briefly reviewed along a line of observable two-variable, three-variable, star decomposable, and tree decomposable, as well as their relationship to factor analysis. Then, developments along this line are further addressed from three perspectives with a number of issues, especially on learning approximate star decomposable, and tree decomposable, as well as their generalisations to block star-causality analysis on factor analysis and block tree decomposable analysis on linear causal model. PubDate: 2017-12-12
Abstract: Functional connectivity at resting state was found altered in early-onset schizophrenia patients. However, its potential as biomarker of clinical diagnosis is unknown. To test whether resting-state functional connectivity can be a potential biomarker of classifying patients from controls, 39 early-onset schizophrenia patients and 31 healthy controls were included in our study. Resting-state functional MRI networks were built with the whole brain atlas as classification features to distinguish patients from healthy controls. Three-stage deep-learning network was used to deduce dimension reduction, and feedforward back propagation neural networks were used as classifier. As the result, the classification accuracy reached 79.3% (87.4% for sensitivity, 82.2% for specificity, p < 0.05 for permuted test). Our works showed us that resting-state connectivity presented good potential classification capacity and can be used as biomarker of clinical diagnosis. PubDate: 2017-12-06
Abstract: Generalized tonic–clonic seizure (GTCS) is characterized by the abnormal functional organization among distant brain regions. Previous studies in GTCS that have comprehensively examined connectivity abnormalities across the complete range of large-scale brain networks remain relatively rare. Here, we employed an amount of regions of interest to investigate the intra- and inter-connections among seven large-scale brain networks in GTCS and healthy controls. Network contingency analysis revealed that patients with GTCS exhibit significantly increased connectivity between default mode network (DMN) and frontoparietal network (FPN), between DMN and dorsal attention network, and between somatomotor network and limbic network, and decreased functional connectivity within FPN (all p values were Bonferroni corrected). Consistent with existing evidence, the disrupted functional architecture of the DMN and task-positive network may be related to self-related processes and deficits in cognitive control and attention in patients. These findings support the notion that GTCS is associated with disrupted architecture in large-scale brain networks, providing information for better understanding of the pathophysiological mechanisms of GTCS. PubDate: 2017-11-29
Abstract: This paper presents a simple and robust feature descriptor method, namely local dominant orientation feature histogram (LDOFH). In this method, the discriminant histogram contains dominant orientation, and the corresponding relative energy value is obtained by calculating the direction and the amplitude of the gradient of each pixel over a local patch. The LM-NNDA (Yang et al. in Pattern Recognit 44:1387–1402, 2011) method based on the principal component analysis (PCA) method is finally employed to reduce the redundancy information and get the low-dimensional and discriminative features. We apply this descriptor on AR, IMM face image databases. Experimental results demonstrate the effectiveness of the proposed LDOFH method. PubDate: 2017-11-17
Abstract: In this paper, we propose an end-to-end multiscale recurrent regression networks (MSRRN) approach for face alignment. Unlike conventional face alignment methods by utilizing handcrafted features which require strong prior knowledge by hand, our MSRRN aims to seek a series of hierarchical feature transformations directly from image pixels, which exploits the nonlinear relationship between the face images to the positions of facial landmarks. To achieve this, we carefully design a recurrent regression network architecture, where the parameters across different stages are shared to memorize the shape residual descents between the initial shape and the ground-truth. To further improve the performance, our MSRNN learns to exploit the context-aware information from multiscale face inputs in a coarse-to-fine manner. Experimental results on the benchmarking face alignment datasets show the effectiveness of our approach. PubDate: 2017-11-02
Abstract: Many methods have been proposed to learn image priors from natural images for the ill-posed image restoration tasks. However, many prior learning algorithms assume that a general prior distribution is suitable for over all kinds of images. Since the contents of the natural images and the corresponding low-level statistical characteristics vary from scene to scene, we argue that learning a universal generative prior for all natural images may be imperfect. Although the universal generative prior can remove artifacts and reserve a natural smoothness in image restoration, it also tends to introduce unreal flatness and clutter textures. To address this issue, in this paper, we present to learn a scene-aware image prior based on the high-order Markov random field (MRF) model (SA-MRF). With this model, we jointly learn a set of shared low-level features and different potentials for specific scene contents. In prediction, a good prior can be adapted to the given degenerated image with the scene content perception. Experimental results on the image denoising and inpainting tasks demonstrate the efficiency of the SA-MRF on both numerical evaluation and visual compression. PubDate: 2017-10-30
Abstract: OLAP (Online Analytical Processing) system appears as a revolutionary technology that provides adequate analytic solutions for decision support. Using OLAP, analysts and policymakers are able to process and analyze data in an interactive, fast, and effective way according to several axes. This provides a clear vision of their business at any time and in real time. However, these systems suffer from certain limitations related to the consideration of both the multicriteria and fuzzy aspects of multidimensional data when making decisions. To overcome these limitations, we propose an integrated decision-making prototype based on OLAP system and multicriteria analysis (MCA) to generate a hybrid analysis process dealing with complex multicriteria decision-making situations. This proposed solution, based on our previous contributions, allows the analyst to extract data from OLAP data cube model and analyze them using OLAP operators and MCA methods. PubDate: 2017-10-30
Abstract: Precise neural encoding of varying pitch is crucial for speech perception, especially in Mandarin. A valid evaluation of the listeners’ auditory function which accounts for the perception of pitch variation can facilitate the strategy of hearing compensation for hearing-impaired people. This auditory function has been evaluated by behavioral test in previous studies, but the objective measurement of auditory-evoked potentials, for example, is rarely studied. In this study, we investigated the scalp-recorded frequency-following responses (FFRs) evoked by frequency-modulated sweeps, and its correlation with behavioral performance on the just-noticeable differences (JNDs) of sweep slopes. The results showed that (1) the indices of FFRs varied significantly when the sweep slopes were manipulated; (2) the indices were all strongly negatively correlated with JNDs across listeners. The results suggested that the listener’s subjective JND could be predicted by the objective index of FFRs to tonal sweeps. PubDate: 2017-10-23
Abstract: Nowadays, more and more people use social network to share their lives and communicate with each other. In real social network, a person is influenced by others and also influences others at the same time. So the status of a person in the network can be determined by his influence power. In other words, a person with larger influence power always plays more important role and is more likely to act as a core of a community. Different from most of existing community detection algorithms which concentrate on the topology of networks, we propose an algorithm based on influence power to discover potential core members from which the community structure can be revealed. Extensive experiments confirm that our proposed algorithm has good performance in detecting community in real social network. PubDate: 2017-10-05
Abstract: Due to the progress of deep neural networks (DNN), DNN has been employed to cross-media retrieval. Existing cross-media retrieval methods based on DNN can convert separate representation of each media type to common representation by inter-media and intra-media constraints. By using common representation, we can measure similarities between heterogeneous instances and perform cross-media retrieval. However, it is challenging to optimize common representation learning due to the inter-media and intra-media constraints, which is a multi-objective optimization problem. This paper proposes residual correlation network (RCN) to address this issue. RCN optimizes common representation learning with a residual function, which can fit the optimal mapping from separate representation to common representation and relieve the multi-objective optimization problem. The experiments show that proposed approach achieves the best accuracy compared with 10 state-of-the-art methods on 3 datasets. PubDate: 2017-10-05
Abstract: Complex systems are usually illustrated by networks which capture the topology of the interactions between the entities. To better understand the roles played by the entities in the system, one needs to uncover the underlying community structure of the system. In recent years, systems with interactions that have various types or can change over time between the entities have attracted much research attention. However, algorithms aiming at solving the key problem—community detection—in multilayer networks are still limited. In this work, we first introduce the multilayer network model representation. Then based on this model, we naturally derive the multilayer modularity—a widely adopted objective function of community detection in networks—from a static perspective to evaluate the quality of the communities detected in multilayer networks. It enables us to better understand the essence of the modularity by pointing out the specific kind of communities that will lead to a high modularity score. We also propose a spectral method called mSpec for the optimization of the proposed modularity function based on the supra-adjacency representation of the multilayer networks. Experiments on the electroencephalograph network and the comparison results on several empirical multilayer networks demonstrate the feasibility and reliable performance of the proposed method. PubDate: 2017-05-08
Abstract: In the current competitive global market, organizations are implementing information and communication technology (ICT) that could add value to their products, processes, and satisfaction of their users. The adoption, implementation and use of homegrown enterprise resource planning (ERP) systems is one of these mechanisms being globally used for recording, processing, storing, and exchanging organizational information anytime anywhere. Although organizations have been utilizing ERP systems, the acceptance of homegrown ERP systems is given less attention as compared to commercial off-the shelf (COTS) software. Hence, this research studied factors that determine acceptance of homegrown ERP through the extension of unified theory of acceptance and use of technology (UTAUT) model. The finding revealed that performance expectancy, effort expectancy, social influence, competitive advantage, cost effectiveness, and facilitations functions are determinants of homegrown ERP system acceptance in Ethiopia. Moreover, experience and voluntariness are found to be significant moderators of the study. PubDate: 2017-03-14
Abstract: In this paper, we focus on the use of quaternary tree instead of binary tree to speed up the decoding time for Huffman codes. It is usually difficult to achieve a balance between speed and memory usage using variable-length binary Huffman code. Quaternary tree is used here to produce optimal codeword that speeds up the way of searching. We analyzed the performance of our algorithms with the Huffman-based techniques in terms of decoding speed and compression ratio. The proposed decoding algorithm outperforms the Huffman-based techniques in terms of speed while the compression performance remains almost same. PubDate: 2017-01-07
Abstract: In the past few decades, video display terminals (VDTs) and computer use have been associated with various skin symptoms in several published reports. In addition, internet beauty sites report that extended computer use leads to acne or accelerated facial aging. For example, the term “computer face” is used to describe premature aging caused by sitting for long periods of time in front of the screen (http://www.marieclaire.com/beauty/news/a12937/computer-screen-skin-problems/). We wished to determine, using instrumental and expert assessment, if prolonged/extended computer use could be associated with certain skin conditions. This study focused on long-term (10 years or more) office VDT work and was designed to include a wide range of confounding variables. One hundred Chinese women were recruited, 50 in each of two groups characterized as either (a) computer users with 8 or more hours per day, or (b) non-users who use computers 1 h or less per day. All subjects lived in Guangzhou and worked in the same building. Confounders were assessed by survey, and included age, smoking, sun exposure history, exercise, and other factors. Skin conditions, which included acne, sebum, wrinkles, and pigment spots, were assessed by instrumental measurements and blinded dermatologist assessment. Age and skin conditions were subjected to logistic regression analysis to determine major contributors which could separate, or distinguish, the computer group from the non-computer group. From this analysis, the office computer users were found to be statistically significantly associated with a higher incidence of acne, higher sebum levels, and a higher risk of self-reported sensitive skin when compared with the non-computer group. The final model suggests that the major contributors in separating the two groups are acne and pigmented spots (UV and brown). These results indicate that facial skin of women within the Chinese population who use computers for 8 h or more a day may be at higher risk for acne; however, they had lower levels of attributes associated with photoaging, such as lentigines and facial wrinkles. Separate pairwise assessment of other variables such as lifetime cumulative sun exposure, sleep quality, smoking behavior, exercise, and cosmetic product use or procedures showed no significant differences between the two groups. This indicates that the results obtained from objective and subjective measurements were not biased due to these potential confounders, but does not reveal the mechanism for the observed differences in skin conditions between computer/VDT users and non-users. PubDate: 2017-01-07
Abstract: The ability to accurately and effectively search for 3D shape is crucial for many applications. In this study, we proposed a novel framework for 3D shape retrieval. We compensate the loss of high frequencies of heat kernel signature from two aspects. One is to introduce the weight for each point to highlight the details of the salient points. The other is to directly capture microgeometry structure through wave kernel’s access to high frequencies. Thus, our method can capture geometric features at different frequencies of a shape, which satisfy the property of an ideal descriptor. We conduct shape retrieval experiments on a standard benchmark and compared with another heat kernel-based method. Experimental results demonstrate that the proposed method is effective and accurate. PubDate: 2017-01-06
Abstract: In an effort to improve outcome of patients with sepsis, we developed and implemented a disease-specific alert and order set for our computerized physician order entry system. This alert and order set were implemented in 2015. We have produced a progressive decrease in mortality for patients at our hospital with diagnosis of sepsis. We see a significant decrease in mortality for patients who had the sepsis order set used compared to those who did not have the order set used. We recommend use of an order set for patients with sepsis. PubDate: 2017-01-05
Abstract: Based on ranking of fuzzy numbers which deals with fuzzy-valued multi-objective programming problem and the modified crisp model, a modified approach is proposed. Also, two algorithms that play a pivotal role in the proposed method are introduced. The first one returns a ranking function to a given fuzzy number and the second algorithm uses the modified crisp model to deliver a Pareto optimal solution. Moreover, we investigate the stability of the first kind of the solution which is obtained using these algorithms. Finally, a numerical example is given to illustrate our modified approach, using Maple program. PubDate: 2017-01-05
Abstract: Different from standard sampling strategy in compressive sensing (CS), we present a compressive partial sampling framework called adaptive-random sampling and recovery (ASR) for image. It could faithfully recover images by hybridizing random samples with edge-extracted pixels with much lower sampling rate. The new framework preserves edge pixels containing essential information of images, and meanwhile employs the edge-preserving total variation (TV) regularizer. Assisted with the edges, three steps are adopted to recover the high-quality image. First, we extract the edges of a coarse image recovered with completely random measurements in our sampling framework. Then, the TV algorithm in the CS theory is employed for solving the Lagrangian regularization problem. Finally, we refine the coarse image to obtain a high-quality one with both the extracted edges and previous random measurements. Experimental results show that the novel ASR strategy achieves significant performance improvements over the current state-of-the-art schemes. PubDate: 2016-12-28
Abstract: Sleep spindles are thought to be related to some sleep diseases and play an important role in memory consolidation. They were traditionally identified by physiology experts based on rules and recently detected by automatic algorithms. However, many automatic approaches were validated on the different electroencephalogram (EEG) using various assessment methods, making it difficult to appraised a method objectively and fairly. In this paper, we proposed a sliding window-based probability estimation (SWPE) method for sleep spindle detection. We performed a continuous wavelet transform with Mexican hat wavelet function, following by a sliding window to find out the candidate spindle points corresponding to the large wavelet coefficients at the frequencies of spindles and estimated their probabilities. To enhance the results, we used the envelope of the rectified signal to reject some false sleep spindle candidates. This was an enhanced method and we called it SWPE-E in this paper. Finally, we compared our approaches with four approaches on the same public available EEG database, and the result showed the significative improvement of our proposed approaches. PubDate: 2016-12-08