Subjects -> MATHEMATICS (Total: 1013 journals)
    - APPLIED MATHEMATICS (92 journals)
    - GEOMETRY AND TOPOLOGY (23 journals)
    - MATHEMATICS (714 journals)
    - MATHEMATICS (GENERAL) (45 journals)
    - NUMERICAL ANALYSIS (26 journals)
    - PROBABILITIES AND MATH STATISTICS (113 journals)

MATHEMATICS (714 journals)                  1 2 3 4 | Last

Showing 1 - 200 of 538 Journals sorted alphabetically
Abakós     Open Access   (Followers: 4)
Abhandlungen aus dem Mathematischen Seminar der Universitat Hamburg     Hybrid Journal   (Followers: 2)
Accounting Perspectives     Full-text available via subscription   (Followers: 4)
ACM Transactions on Algorithms (TALG)     Hybrid Journal   (Followers: 13)
ACM Transactions on Computational Logic (TOCL)     Hybrid Journal   (Followers: 5)
ACM Transactions on Mathematical Software (TOMS)     Hybrid Journal   (Followers: 6)
ACS Applied Materials & Interfaces     Hybrid Journal   (Followers: 43)
Acta Applicandae Mathematicae     Hybrid Journal   (Followers: 2)
Acta Mathematica Hungarica     Hybrid Journal   (Followers: 3)
Acta Mathematica Sinica, English Series     Hybrid Journal   (Followers: 5)
Acta Mathematica Vietnamica     Hybrid Journal  
Acta Mathematicae Applicatae Sinica, English Series     Hybrid Journal  
Advanced Science Letters     Full-text available via subscription   (Followers: 9)
Advances in Applied Clifford Algebras     Hybrid Journal   (Followers: 6)
Advances in Catalysis     Full-text available via subscription   (Followers: 7)
Advances in Complex Systems     Hybrid Journal   (Followers: 10)
Advances in Computational Mathematics     Hybrid Journal   (Followers: 16)
Advances in Decision Sciences     Open Access   (Followers: 4)
Advances in Difference Equations     Open Access   (Followers: 3)
Advances in Fixed Point Theory     Open Access  
Advances in Geosciences (ADGEO)     Open Access   (Followers: 20)
Advances in Linear Algebra & Matrix Theory     Open Access   (Followers: 6)
Advances in Materials Science     Open Access   (Followers: 21)
Advances in Mathematical Physics     Open Access   (Followers: 6)
Advances in Mathematics     Full-text available via subscription   (Followers: 18)
Advances in Numerical Analysis     Open Access   (Followers: 4)
Advances in Operations Research     Open Access   (Followers: 13)
Advances in Operator Theory     Hybrid Journal  
Advances in Pure Mathematics     Open Access   (Followers: 10)
Advances in Science and Research (ASR)     Open Access   (Followers: 9)
Aequationes Mathematicae     Hybrid Journal   (Followers: 2)
African Journal of Educational Studies in Mathematics and Sciences     Full-text available via subscription   (Followers: 8)
African Journal of Mathematics and Computer Science Research     Open Access   (Followers: 5)
Afrika Matematika     Hybrid Journal   (Followers: 2)
Air, Soil & Water Research     Open Access   (Followers: 6)
AKSIOMATIK : Jurnal Penelitian Pendidikan dan Pembelajaran Matematika     Open Access  
Al-Jabar : Jurnal Pendidikan Matematika     Open Access  
Al-Qadisiyah Journal for Computer Science and Mathematics     Open Access   (Followers: 3)
AL-Rafidain Journal of Computer Sciences and Mathematics     Open Access   (Followers: 4)
Algebra and Logic     Hybrid Journal   (Followers: 9)
Algebra Colloquium     Hybrid Journal   (Followers: 3)
Algebra Universalis     Hybrid Journal   (Followers: 3)
Algorithmic Operations Research     Open Access   (Followers: 6)
Algorithms     Open Access   (Followers: 14)
Algorithms Research     Open Access   (Followers: 1)
American Journal of Computational and Applied Mathematics     Open Access   (Followers: 4)
American Journal of Mathematical Analysis     Open Access   (Followers: 1)
American Journal of Mathematical and Management Sciences     Hybrid Journal  
American Journal of Mathematics     Full-text available via subscription   (Followers: 7)
American Journal of Operations Research     Open Access   (Followers: 6)
American Mathematical Monthly     Full-text available via subscription   (Followers: 3)
An International Journal of Optimization and Control: Theories & Applications     Open Access   (Followers: 12)
Analele Universitatii Ovidius Constanta - Seria Matematica     Open Access  
Analysis and Applications     Hybrid Journal   (Followers: 2)
Analysis and Mathematical Physics     Hybrid Journal   (Followers: 7)
Anargya : Jurnal Ilmiah Pendidikan Matematika     Open Access  
Annales Mathematicae Silesianae     Open Access  
Annales mathématiques du Québec     Hybrid Journal   (Followers: 3)
Annales Universitatis Mariae Curie-Sklodowska, sectio A – Mathematica     Open Access   (Followers: 1)
Annales Universitatis Paedagogicae Cracoviensis. Studia Mathematica     Open Access  
Annali di Matematica Pura ed Applicata     Hybrid Journal   (Followers: 1)
Annals of Combinatorics     Hybrid Journal   (Followers: 3)
Annals of Data Science     Hybrid Journal   (Followers: 15)
Annals of Functional Analysis     Hybrid Journal   (Followers: 2)
Annals of Mathematics     Full-text available via subscription   (Followers: 5)
Annals of Mathematics and Artificial Intelligence     Hybrid Journal   (Followers: 13)
Annals of PDE     Hybrid Journal  
Annals of Pure and Applied Logic     Open Access   (Followers: 5)
Annals of the Alexandru Ioan Cuza University - Mathematics     Open Access   (Followers: 1)
Annals of the Institute of Statistical Mathematics     Hybrid Journal   (Followers: 1)
Annals of West University of Timisoara - Mathematics     Open Access   (Followers: 1)
Annals of West University of Timisoara - Mathematics and Computer Science     Open Access   (Followers: 2)
Annuaire du Collège de France     Open Access   (Followers: 6)
ANZIAM Journal     Open Access   (Followers: 1)
Applicable Algebra in Engineering, Communication and Computing     Hybrid Journal   (Followers: 3)
Applications of Mathematics     Hybrid Journal   (Followers: 3)
Applied Categorical Structures     Hybrid Journal   (Followers: 5)
Applied Computational Intelligence and Soft Computing     Open Access   (Followers: 16)
Applied Mathematics     Open Access   (Followers: 6)
Applied Mathematics     Open Access   (Followers: 6)
Applied Mathematics & Optimization     Hybrid Journal   (Followers: 7)
Applied Mathematics - A Journal of Chinese Universities     Hybrid Journal   (Followers: 1)
Applied Mathematics and Nonlinear Sciences     Open Access   (Followers: 1)
Applied Mathematics Letters     Full-text available via subscription   (Followers: 3)
Applied Mathematics Research eXpress     Hybrid Journal   (Followers: 1)
Applied Network Science     Open Access   (Followers: 3)
Applied Numerical Mathematics     Hybrid Journal   (Followers: 4)
Applied Spatial Analysis and Policy     Hybrid Journal   (Followers: 5)
Arab Journal of Mathematical Sciences     Open Access   (Followers: 3)
Arabian Journal of Mathematics     Open Access   (Followers: 1)
Archive for Mathematical Logic     Hybrid Journal   (Followers: 3)
Archive of Applied Mechanics     Hybrid Journal   (Followers: 4)
Archive of Numerical Software     Open Access  
Archives of Computational Methods in Engineering     Hybrid Journal   (Followers: 5)
Armenian Journal of Mathematics     Open Access  
Arnold Mathematical Journal     Hybrid Journal   (Followers: 1)
Artificial Satellites     Open Access   (Followers: 21)
Asia-Pacific Journal of Operational Research     Hybrid Journal   (Followers: 3)
Asian Journal of Algebra     Open Access   (Followers: 1)
Asian Research Journal of Mathematics     Open Access  
Asian-European Journal of Mathematics     Hybrid Journal   (Followers: 2)
Australian Mathematics Teacher, The     Full-text available via subscription   (Followers: 7)
Australian Primary Mathematics Classroom     Full-text available via subscription   (Followers: 5)
Australian Senior Mathematics Journal     Full-text available via subscription   (Followers: 1)
Automatic Documentation and Mathematical Linguistics     Hybrid Journal   (Followers: 5)
Axioms     Open Access   (Followers: 1)
Baltic International Yearbook of Cognition, Logic and Communication     Open Access   (Followers: 2)
Banach Journal of Mathematical Analysis     Hybrid Journal  
Basin Research     Hybrid Journal   (Followers: 6)
BIBECHANA     Open Access  
Biomath     Open Access  
BIT Numerical Mathematics     Hybrid Journal  
Boletim Cearense de Educação e História da Matemática     Open Access  
Boletim de Educação Matemática     Open Access  
Boletín de la Sociedad Matemática Mexicana     Hybrid Journal  
Bollettino dell'Unione Matematica Italiana     Full-text available via subscription  
British Journal for the History of Mathematics     Hybrid Journal   (Followers: 2)
British Journal of Mathematical and Statistical Psychology     Full-text available via subscription   (Followers: 17)
British Journal of Mathematics & Computer Science     Full-text available via subscription   (Followers: 1)
Buletinul Academiei de Stiinte a Republicii Moldova. Matematica     Open Access   (Followers: 2)
Bulletin des Sciences Mathamatiques     Full-text available via subscription   (Followers: 3)
Bulletin of Dnipropetrovsk University. Series : Communications in Mathematical Modeling and Differential Equations Theory     Open Access   (Followers: 3)
Bulletin of Mathematical Sciences     Open Access   (Followers: 1)
Bulletin of Symbolic Logic     Full-text available via subscription   (Followers: 4)
Bulletin of Taras Shevchenko National University of Kyiv. Series: Physics and Mathematics     Open Access  
Bulletin of the Australian Mathematical Society     Full-text available via subscription   (Followers: 2)
Bulletin of the Brazilian Mathematical Society, New Series     Hybrid Journal  
Bulletin of the Iranian Mathematical Society     Hybrid Journal  
Bulletin of the London Mathematical Society     Hybrid Journal   (Followers: 3)
Bulletin of the Malaysian Mathematical Sciences Society     Hybrid Journal  
Cadernos do IME : Série Matemática     Open Access  
Calculus of Variations and Partial Differential Equations     Hybrid Journal   (Followers: 1)
Canadian Journal of Mathematics / Journal canadien de mathématiques     Hybrid Journal  
Canadian Journal of Science, Mathematics and Technology Education     Hybrid Journal   (Followers: 20)
Canadian Mathematical Bulletin     Hybrid Journal  
Carpathian Mathematical Publications     Open Access  
Catalysis in Industry     Hybrid Journal  
CAUCHY     Open Access   (Followers: 1)
CEAS Space Journal     Hybrid Journal   (Followers: 5)
CHANCE     Hybrid Journal   (Followers: 5)
Chaos, Solitons & Fractals     Hybrid Journal   (Followers: 1)
Chaos, Solitons & Fractals : X     Open Access   (Followers: 1)
ChemSusChem     Hybrid Journal   (Followers: 8)
Chinese Annals of Mathematics, Series B     Hybrid Journal  
Chinese Journal of Catalysis     Full-text available via subscription   (Followers: 2)
Chinese Journal of Mathematics     Open Access  
Ciencia     Open Access  
CODEE Journal     Open Access  
Cogent Mathematics     Open Access   (Followers: 2)
Cognitive Computation     Hybrid Journal   (Followers: 3)
Collectanea Mathematica     Hybrid Journal  
College Mathematics Journal     Hybrid Journal   (Followers: 3)
COMBINATORICA     Hybrid Journal  
Combinatorics, Probability and Computing     Hybrid Journal   (Followers: 5)
Combustion Theory and Modelling     Hybrid Journal   (Followers: 20)
Commentarii Mathematici Helvetici     Hybrid Journal   (Followers: 1)
Communications in Combinatorics and Optimization     Open Access  
Communications in Contemporary Mathematics     Hybrid Journal  
Communications in Mathematical Physics     Hybrid Journal   (Followers: 3)
Communications On Pure & Applied Mathematics     Hybrid Journal   (Followers: 6)
Complex Analysis and its Synergies     Open Access   (Followers: 1)
Complex Variables and Elliptic Equations: An International Journal     Hybrid Journal  
Compositio Mathematica     Full-text available via subscription   (Followers: 2)
Comptes Rendus : Mathematique     Open Access  
Computational and Applied Mathematics     Hybrid Journal   (Followers: 3)
Computational and Mathematical Methods     Hybrid Journal  
Computational and Mathematical Methods in Medicine     Open Access   (Followers: 2)
Computational and Mathematical Organization Theory     Hybrid Journal   (Followers: 2)
Computational Complexity     Hybrid Journal   (Followers: 5)
Computational Mathematics and Modeling     Hybrid Journal   (Followers: 8)
Computational Mechanics     Hybrid Journal   (Followers: 11)
Computational Methods and Function Theory     Hybrid Journal  
Computational Optimization and Applications     Hybrid Journal   (Followers: 9)
Computers & Mathematics with Applications     Full-text available via subscription   (Followers: 10)
Confluentes Mathematici     Hybrid Journal  
Constructive Mathematical Analysis     Open Access  
Contributions to Discrete Mathematics     Open Access  
Contributions to Game Theory and Management     Open Access  
COSMOS     Hybrid Journal   (Followers: 1)
Cross Section     Full-text available via subscription   (Followers: 1)
Cryptography and Communications     Hybrid Journal   (Followers: 11)
Cuadernos de Investigación y Formación en Educación Matemática     Open Access  
Cubo. A Mathematical Journal     Open Access  
Current Research in Biostatistics     Open Access   (Followers: 8)
Czechoslovak Mathematical Journal     Hybrid Journal  
Daya Matematis : Jurnal Inovasi Pendidikan Matematika     Open Access  
Demographic Research     Open Access   (Followers: 14)
Design Journal : An International Journal for All Aspects of Design     Hybrid Journal   (Followers: 35)
Desimal : Jurnal Matematika     Open Access  
Dhaka University Journal of Science     Open Access  
Differential Equations and Dynamical Systems     Hybrid Journal   (Followers: 2)
Differentsial'nye Uravneniya     Open Access  
Digital Experiences in Mathematics Education     Hybrid Journal   (Followers: 3)
Discrete Mathematics     Hybrid Journal   (Followers: 7)
Discrete Mathematics & Theoretical Computer Science     Open Access   (Followers: 1)
Discrete Mathematics, Algorithms and Applications     Hybrid Journal   (Followers: 2)
Discussiones Mathematicae - General Algebra and Applications     Open Access  
Discussiones Mathematicae Graph Theory     Open Access   (Followers: 1)
Diskretnaya Matematika     Full-text available via subscription  
Doklady Akademii Nauk     Open Access  

        1 2 3 4 | Last

Similar Journals
Journal Cover
Cognitive Computation
Journal Prestige (SJR): 0.908
Citation Impact (citeScore): 4
Number of Followers: 3  
 
  Hybrid Journal Hybrid journal (It can contain Open Access articles)
ISSN (Print) 1866-9964 - ISSN (Online) 1866-9956
Published by Springer-Verlag Homepage  [2467 journals]
  • Fast and General Incomplete Multi-view Adaptive Clustering

    • Free pre-print version: Loading...

      Abstract: Abstract With the development of data collection technologies, multi-view clustering (MVC) has become an emerging research topic. The traditional MVC method cannot process incomplete views. In recent years, although many incomplete multi-view clustering methods have been proposed by many researchers, these methods still suffer from some limitations. For example, these methods all have parameters that need to be adjusted, or have high computational complexity and are not suitable for processing large-scale data. To make matters worse, these methods are not suitable for cases where there are no paired samples among multiple views. The above limitations make existing methods difficult to apply in practice. This paper proposes a Fast and General Incomplete Multi-view Adaptive Clustering (FGPMAC) method. The FGPMAC adopts an adaptive neighbor assignment strategy to independently construct the similarity matrix of each view, thereby it can handle the cases where there are no paired samples among multiple views, and eliminating the necessary to adjust the parameters. Moreover, by adopting a non-iterative approach, FGPMAC has low computational complexity and is suitable for large-scale datasets. Results of experiments on multiple real datasets fully demonstrate the advantages of FGPMAC, such as simplicity, effectiveness and superiority.
      PubDate: 2022-12-01
       
  • Stein Variational Gradient Descent with Multiple Kernels

    • Free pre-print version: Loading...

      Abstract: Abstract Bayesian inference is an important research area in cognitive computation due to its ability to reason under uncertainty in machine learning. As a representative algorithm, Stein variational gradient descent (SVGD) and its variants have shown promising successes in approximate inference for complex distributions. In practice, we notice that the kernel used in SVGD-based methods has a decisive effect on the empirical performance. Radial basis function (RBF) kernel with median heuristics is a common choice in previous approaches, but unfortunately, this has proven to be sub-optimal. Inspired by the paradigm of Multiple Kernel Learning (MKL), our solution to this flaw is using a combination of multiple kernels to approximate the optimal kernel, rather than a single one which may limit the performance and flexibility. Specifically, we first extend Kernelized Stein Discrepancy (KSD) to its multiple kernels view called Multiple Kernelized Stein Discrepancy (MKSD) and then leverage MKSD to construct a general algorithm Multiple Kernel SVGD (MK-SVGD). Further, MK-SVGD can automatically assign a weight to each kernel without any other parameters, which means that our method not only gets rid of optimal kernel dependence but also maintains computational efficiency. Experiments on various tasks and models demonstrate that our proposed method consistently matches or outperforms the competing methods.
      PubDate: 2022-11-24
       
  • Spatiotemporal EEG Dynamics of Prospective Memory in Ageing and Mild
           Cognitive Impairment

    • Free pre-print version: Loading...

      Abstract: Abstract Prospective memory (PM, the memory of future intentions) is one of the first complaints of those that develop dementia-related disease. Little is known about the neurophysiology of PM in ageing and those with mild cognitive impairment (MCI). By using a novel artificial neural network to investigate the spatial and temporal features of PM related brain activity, new insights can be uncovered. Young adults (n = 30), healthy older adults (n = 39) and older adults with MCI (n = 27) completed a working memory and two PM (perceptual, conceptual) tasks. Time-locked electroencephalographic potentials (ERPs) from 128-electrodes were analysed using a brain-inspired spiking neural network (SNN) architecture. Local and global connectivity from the SNNs was then evaluated. SNNs outperformed other machine learning methods in classification of brain activity between younger, older and older adults with MCI. SNNs trained using PM related brain activity had better classification accuracy than working memory related brain activity. In general, younger adults exhibited greater local cluster connectivity compared to both older adult groups. Older adults with MCI demonstrated decreased global connectivity in response to working memory and perceptual PM tasks but increased connectivity in the conceptual PM models relative to younger and healthy older adults. SNNs can provide a useful method for differentiating between those with and without MCI. Using brain activity related to PM in combination with SNNs may provide a sensitive biomarker for detecting cognitive decline. Cognitively demanding tasks may increase the amount connectivity in older adults with MCI as a means of compensation.
      PubDate: 2022-11-23
       
  • Emotion Analysis of COVID-19 Vaccines Based on a Fuzzy Convolutional
           Neural Network

    • Free pre-print version: Loading...

      Abstract: Abstract COVID-19 created immense global challenges in 2020, and the world will live under its threat indefinitely. Much of the information on social media supported the government in addressing this major public health event. On January 9, to control the virus, the Chinese government announced universal vaccinations. However, due to a range of varied interpretations, people held different attitudes towards vaccination. Therefore, the success of the mass immunization strategy greatly depended on the public perception of the COVID-19 vaccine. This article explores the changes in people’s emotional attitudes towards vaccines and the reasons behind them in the context of the global pandemic in an effort to help mankind overcome this ongoing crisis. For this article, microblogs from January to September containing Chinese people’s responses to the COVID-19 vaccines were collected. Based on fuzzy logic and deep learning, we advance the hypothesis that fuzzy vector adaptive improvements will make it possible to better express language emotion and that fuzzy emotion vectors can be integrated into deep learning models, thus making these models more interpretable. Based on this assumption, we design a deep learning model with a fuzzy emotion vector. The experimental results show the positive effect of this model. By applying the model in analyses of people’s attitudes towards vaccines, we can obtain people’s attitudes towards vaccines in different time periods. We discovered that the most negative emotions about the vaccine appeared in April and that the most positive emotions about the vaccine appeared in February. Combined with word cloud technology and the LDA model, we can effectively explore the reasons for the changes in vaccine attitudes. Our findings show that people’s negative emotions about the vaccine are always higher than their positive emotions about the vaccine and that people’s attitudes towards the vaccine are closely related to the progress of the epidemic. There is also a certain relationship between people’s attitudes towards the vaccine and those towards the vaccination.
      PubDate: 2022-11-16
       
  • A Deep Learning Approach for Robust, Multi-oriented, and Curved Text
           Detection

    • Free pre-print version: Loading...

      Abstract: Abstract Automatic text localization and segmentation in a normal environment with vertical or curved texts are core elements of numerous tasks comprising the identification of vehicles and self-driving cars, and preparing significant information from real scenes to visually impaired people. Nevertheless, texts in the real environment can be discovered with a high level of angles, profiles, dimensions, and colors which is an arduous process to detect. In this paper, a new framework based on a convolutional neural network (CNN) is introduced to obtain high efficiency in detecting text even in the presence of a complex background. Due to using a new inception layer and an improved ReLU layer, an excellent result is gained to detect text even in the presence of complex backgrounds. At first, four new m.ReLU layers are employed to explore low-level visual features. The new m.ReLU building block and inception layer are optimized to detect vital information maximally. The effect of stacking up inception layers (kernels with the dimension of 3 × 3 or bigger) is explored and it is demonstrated that this strategy is capable of obtaining mostly varying-sized texts further successfully than a linear chain of convolution layers (Conv layers). The suggested text detection algorithm is conducted in four well-known databases, namely ICDAR 2013, ICDAR 2015, ICDAR 2017, and ICDAR 2019. Text detection results on all mentioned databases with the highest recall of 94.2%, precision of 95.6%, and F-score of 94.8% illustrate that the developed strategy outperforms the state-of-the-art frameworks.
      PubDate: 2022-11-14
       
  • TEDT: Transformer-Based Encoding–Decoding Translation Network for
           Multimodal Sentiment Analysis

    • Free pre-print version: Loading...

      Abstract: Abstract Multimodal sentiment analysis is a popular and challenging research topic in natural language processing, but the impact of individual modal data in videos on sentiment analysis results can be different. In the temporal dimension, natural language sentiment is influenced by nonnatural language sentiment, which may enhance or weaken the original sentiment of the current natural language. In addition, there is a general problem of poor quality of nonnatural language features, which essentially hinders the effect of multimodal fusion. To address the above issues, we proposed a multimodal encoding–decoding translation network with a transformer and adopted a joint encoding–decoding method with text as the primary information and sound and image as the secondary information. To reduce the negative impact of nonnatural language data on natural language data, we propose a modality reinforcement cross-attention module to convert nonnatural language features into natural language features to improve their quality and better integrate multimodal features. Moreover, the dynamic filtering mechanism filters out the error information generated in the cross-modal interaction to further improve the final output. We evaluated the proposed method on two multimodal sentiment analysis benchmark datasets (MOSI and MOSEI), and the accuracy of the method was 89.3% and 85.9%, respectively. In addition, our method outperformed the current state-of-the-art methods. Our model can greatly improve the effect of multimodal fusion and more accurately analyze human sentiment.
      PubDate: 2022-11-14
       
  • Hybrid Convolutional Neural Network-Multilayer Perceptron Model for Solar
           Radiation Prediction

    • Free pre-print version: Loading...

      Abstract: Abstract Urgent transition from the dependence on fossil fuels towards renewable energies requires more solar photovoltaic power to be connected to the electricity grids, with reliable supply through accurate solar radiation forecasting systems. This study proposes an innovative hybrid method that integrates convolutional neural network (CNN) with multi-layer perceptron (MLP) to generate global solar radiation (GSR) forecasts. The CMLP model first extracts optimal topological and structural features embedded in predictive variables through a CNN-based feature extraction stage followed by an MLP-based predictive model to generate the GSR forecasts. Predictive variables from observed data and global climate models (GCM) are used to predict GSR at six solar farms in Queensland, Australia. A hybrid-wrapper feature selection method using a random forest-recursive feature elimination (RF-RFE) scheme is used to eradicate redundant predictor features to improve the proposed CMLP model efficiency. The CMLP model has been compared and bench-marked against seven artificial intelligence–based and seven temperature-based deterministic models, showing excellent performance at all solar energy study sites tested over daily, monthly, and seasonal scales. The proposed hybrid CMLP model should be explored as a viable modelling tool for solar energy monitoring and forecasting in real-time energy management systems.
      PubDate: 2022-11-07
       
  • ConvXAI: a System for Multimodal Interaction with Any Black-box Explainer

    • Free pre-print version: Loading...

      Abstract: Abstract Several studies have addressed the importance of context and users’ knowledge and experience in quantifying the usability and effectiveness of the explanations generated by explainable artificial intelligence (XAI) systems. However, to the best of our knowledge, no component-agnostic system that accounts for this need has yet been built. This paper describes an approach called ConvXAI, which can create a dialogical multimodal interface for any black-box explainer by considering the knowledge and experience of the user. First, we formally extend the state-of-the-art conversational explanation framework by introducing clarification dialogue as an additional dialogue type. We then implement our approach as an off-the-shelf Python tool. To evaluate our framework, we performed a user study including 45 participants divided into three groups based on their level of technology use and job function. Experimental results show that (i) different groups perceive explanations differently; (ii) all groups prefer textual explanations over graphical ones; and (iii) ConvXAI provides clarifications that enhance the usefulness of the original explanations.
      PubDate: 2022-11-07
       
  • Granular Computing and Three-way Decisions for Cognitive Analytics

    • Free pre-print version: Loading...

      PubDate: 2022-11-01
       
  • Multimodal Emotion Distribution Learning

    • Free pre-print version: Loading...

      Abstract: Background Emotion recognition is an interesting and challenging problem and has attracted much attention in recent years. To more accurately express emotions, emotion distribution learning (EDL) introduces the emotion description degree to form an emotion distribution at a fine granularity, which is used to describe the fusion of multiple basic emotions at different levels. Challenge Existing EDL research has shown a strong representation ability on emotion recognition, but all studies are based on unimodal information, meaning the results may be one-sided. Method As the first pioneering investigation of multimodal emotion distribution learning, we present a corresponding learning method named MEDL. First, for each modality, we learn an emotion distribution and obtain the corresponding label correlation matrix. Second, we constrain the consistency of label correlation matrices between different modalities to utilize modal complementarity. Finally, the final emotion distribution is achieved based on a simple decision fusion strategy. Results and Conclusions The experimental results demonstrate that our proposal performs better than some state-of-the-art multimodal emotion recognition methods and unimodal emotion distribution learning methods.
      PubDate: 2022-11-01
       
  • 3-Way Concept Analysis Based on 3-Valued Formal Contexts

    • Free pre-print version: Loading...

      Abstract: Abstract As the basic form of data presentation, formal contexts play an elementary and important role in formal concept analysis and in 3-way concept analysis. In fact, many data tables are similar in form to formal contexts. Therefore, these data tables can be studied collectively in a similar framework, and such a study can be significant in knowledge discovery. We propose the notion of 3-valued formal contexts after analyzing the shared characteristics of different data forms such as incomplete formal contexts, conflict situations and other similar cases. After close studies of 3-valued formal contexts, this paper adopts 3-way concept analysis to define 3-valued operators and construct 3-valued concept lattices and finally interpret the meaning of 3-valued operators and discuss the relationship between 3-valued lattices and existing approximation concept lattices. The essence of this method is to present, via 3-way concept analysis, potential information and structure. And 3-way concept analysis shows the common properties of the objects, jointly possessed or jointly not possessed, positive or negative, even the uncertain information. So, this paper actually provides a new model for cognition. Apart from the universal applicability, 3-valued contexts can also be fixed into formal concept analysis. That is, many problems can be studied in the framework of formal concept analysis.
      PubDate: 2022-11-01
       
  • Optimal Granule Combination Selection Based on Multi-Granularity Triadic
           Concept Analysis

    • Free pre-print version: Loading...

      Abstract: Abstract The thinking mode based on granule structure in granular computing essentially simulates the pattern of human thinking to solve problem. Such thinking for the study of knowledge discovery is also of significant importance in cognitive computing. Under such circumstances, the theory of multi-granularity formal concept analysis (MG-FCA) was proposed. But MG-FCA has not been applied to the analysis of three-dimensional data. Because three-dimensional data is very common and an important type of data in the real world, multi-granularity and knowledge discovery of three-dimensional data are two meaningful topics. In this paper, in order to solve the problem of three-dimensional data granularity, the idea of granularity of attributes is first introduced into triadic contexts on the basis of the relationship between triadic concept analysis and formal concept analysis. Moreover, the definition of multi-granularity triadic context is proposed, and some useful properties are studied. Then, for the purpose of realizing cross-granularity knowledge discovery in multi-granularity triadic contexts, two kinds of triadic contexts are given. As a matter of fact, for a specific problem, people often only need a solution to meet their needs. Thus, the problem of optimal granule combination selection is investigated, and the corresponding algorithms are explored. At last, for better understanding, an example with certain semantics is used to explain the proposed methods for multi-granularity triadic contexts. The main contribution as well as the significant feature of this study is to construct multi-level three-dimensional data structure and realize cross-granularity knowledge discovery. Our work will provide multi-granularity cognitive research method based on three-dimensional data.
      PubDate: 2022-11-01
       
  • An Approach to Emotion Recognition Using Brain Rhythm Sequencing and
           Asymmetric Features

    • Free pre-print version: Loading...

      Abstract: Abstract Emotion can be influenced during self-isolation, and to avoid severe mood swings, emotional regulation is meaningful. To achieve this, efficiently recognizing emotion is a vital step, which can be realized by electroencephalography signals. Previously, inspired by the knowledge of sequencing in bioinformatics, a method termed brain rhythm sequencing that analyzes electroencephalography as the sequence consisting of the dominant rhythm has been proposed for seizure detection. In this work, with the help of similarity measure methods, the asymmetric features are extracted from the sequences generated by different channel data. After evaluating all asymmetric features for emotion recognition, the optimal feature that yields remarkable accuracy is identified. Therefore, the classification task can be accomplished through a small amount of channel data. From a music emotion recognition experiment and a public DEAP dataset, the classification accuracies of various test sets are approximately 80–85% when employing an optimal feature extracted from one pair of symmetrical channels. Such performances are impressive when using fewer resources is a concern. Further investigation revealed that emotion recognition shows strongly individual characteristics, so an appropriate solution is to include the subject-dependent properties. Compared to the existing works, this method benefits from the design of a portable emotion-aware device used during self-isolation, as fewer scalp sensors are needed. Hence, it would provide a novel way to realize emotional applications in the future.
      PubDate: 2022-11-01
       
  • Improving Zero-Shot Learning Baselines with Commonsense Knowledge

    • Free pre-print version: Loading...

      Abstract: Abstract Zero-shot learning — the problem of training and testing on a completely disjoint set of classes — relies greatly on its ability to transfer knowledge from train classes to test classes. Traditionally semantic embeddings consisting of human-defined attributes or distributed word embeddings are used to facilitate this transfer by improving the association between visual and semantic embeddings. In this paper, we take advantage of explicit relations between nodes defined in ConceptNet, a commonsense knowledge graph, to generate commonsense embeddings of the class labels by using a graph convolution network-based autoencoder. Our experiments performed on three standard benchmark datasets surpass the strong baselines when we fuse our commonsense embeddings with existing semantic embeddings, i.e., human-defined attributes and distributed word embeddings. This work paves the path to more brain-inspired approaches to zero-short learning.
      PubDate: 2022-11-01
       
  • A Novel Functional Network Based on Three-way Decision for Link Prediction
           in Signed Social Networks

    • Free pre-print version: Loading...

      Abstract: Abstract Aiming to reveal the potential relationships between users, link prediction has been considered as a fundamental research issue in signed social networks. The key of the link prediction is to measure the similarity between users. Many existing researches use connections between users and their common neighbors to measure the similarities, and these methods rely too much on the structure of social networks. Most of them use the deep neural network to enhance the prediction accuracy. However, the complete structure of the huge social network cannot be captured easily, and the models learnt by the deep neural network are unexplainable and uncontrolled. As an explainable model, functional network is a recent replacement for standard neural network. Therefore, we revise the traditional strategy of functional network and propose a novel functional network framework. Firstly, the attributes are preprocessed through the cloud model to define their importance before inputting them into the functional network. Then the association algorithm is used to do aggregate computation in computing neurons for defining the connections between neurons well. Finally, we use three-way decisions to process the samples in the boundary to optimize the performance of model. Experiments executed on six real datasets show that our method has significantly higher link prediction precision than the state-of-the-art works. From our discussions, the improved functional network can be a valid replacement for neural networks in some fields.
      PubDate: 2022-11-01
       
  • Modeling Tweet Dependencies with Graph Convolutional Networks for
           Sentiment Analysis

    • Free pre-print version: Loading...

      Abstract: Abstract Nowadays, individuals spend significant time on online social networks and microblogging websites, consuming news and expressing their opinions and viewpoints on various topics. It is an excellent source of data for various data mining applications, such as sentiment analysis. Mining this type of data presents several challenges, including the posts’ short length and informal language. On the other hand, microblog posts contain a high degree of interdependence, which can help to improve sentiment classification based on text. This data can be represented as a graph, with nodes representing posts and edges representing the various relationships between them. By using recently developed deep learning models for graph structures, this approach enables efficient sentiment analysis of microblog posts. This paper utilizes graphs to represent microblog posts and their various relationships, such as user, friendship, hashtag, sentimental similarity, textual similarity, and common friends. It then employs graph neural networks to perform context-aware sentiment analysis. To make use of the knowledge contained in multiple graphs, we propose a stacking model that simultaneously employs multiple graph types. The findings demonstrate the relevance of sociological theories to the analysis of social media. Experimental results on HCR (a real-world Twitter sentiment analysis dataset), indicate that the proposed approach outperforms baselines and state-of-the-art models.
      PubDate: 2022-11-01
       
  • Granule Description of Incomplete Data: A Cognitive Viewpoint

    • Free pre-print version: Loading...

      Abstract: Abstract Granule description is one of the main challenges to realize explainable AI technologies through information granules. Specifically, granule description of incomplete data is still an open, interesting and important topic. In this study, this problem is studied systematically based on extent–intent view. Concretely, at first we define stable concepts and evanescent concepts in an incomplete formal context and propose their acquisition approaches, respectively. And then, we classify granules into two categories, i.e., basic granules and indefinable granules. After that, we present the descriptions of basic granules via stable concepts and evanescent concepts. Finally, we make some discussions on how to describe indefinable granules. The main contribution as well as the significant feature of this study is granule description of incomplete data based on ordinary formal concepts rather than approximate concepts. The analysis shows that the ordinary concept-based granule description is more concise and less complex than the approximate concept-based granule description, and meanwhile, the ordinary concept-based method can also maintain the same recall of granule description as that of the latter method. Our work will provide cognitive research method to the description of incomplete formal context with the help of concept cognition units.
      PubDate: 2022-11-01
       
  • Deep Transfer Learning on the Aggregated Dataset for Face Presentation
           Attack Detection

    • Free pre-print version: Loading...

      Abstract: Abstract Presentation attacks are becoming a serious threat to one of the most common biometric applications, namely face recognition (FR). In recent years, numerous methods have been presented to detect and identify these attacks using publicly available datasets. However, such datasets are often collected in controlled environments and are focused on one specific type of attack. We hypothesise that a model’s accurate performance on one or more public datasets does not necessarily guarantee generalisation across other, unseen face presentation attacks. To verify our hypothesis, in this paper, we present an experimental framework where the generalisation ability of pre-trained deep models is assessed using four popular and commonly used public datasets. Extensive experiments were carried out using various combinations of these datasets. Results show that, in some circumstances, a slight improvement in model performance can be achieved by combining different datasets for training purposes. However, even with a combination of public datasets, models still could not be trained to generalise to unseen attacks. Moreover, models could not necessarily generalise to a learned format of attack over different datasets. The work and results presented in this paper suggest that more diverse datasets are needed to drive this research as well as the need for devising new methods capable of extracting spoof-specific features which are independent of specific datasets.
      PubDate: 2022-11-01
       
  • Three-Way Decision Models Based on Multi-granulation Rough Intuitionistic
           Hesitant Fuzzy Sets

    • Free pre-print version: Loading...

      Abstract: Abstract In practice, people may hesitate to evaluate uncertain things. As an extension of fuzzy sets, intuitionistic hesitant fuzzy sets use multiple membership and non-membership degrees to express uncertain evaluations. Multi-granulation rough set theory is utilized to deal with information in an intuitionistic hesitant fuzzy decision information system, and three-way decision models are established to make decisions. First, rough intuitionistic hesitant fuzzy sets and four multi-granulation rough intuitionistic hesitant fuzzy set models are proposed, and their properties are discussed. Second, we define the combination formula for the upper and lower approximations of multi-granulation rough intuitionistic hesitant fuzzy sets, and present a new intuitionistic hesitant fuzzy cross-entropy. Then, the conditional probabilities under four cases are calculated by the TOPSIS approach. Third, the thresholds in intuitionistic hesitant fuzzy decision-theoretic rough sets are calculated, and corresponding three-way decision rules are given. Finally, four kinds of three-way decision models based on the proposed multi-granulation rough intuitionistic hesitant fuzzy sets are constructed. Furthermore, the decision rule extraction algorithm is designed. The example proved that the four kinds of three-way decision models can evaluate objects with different attitudes and provide decision-making solutions, which demonstrates the feasibility and effectiveness of the proposed algorithm.
      PubDate: 2022-11-01
       
  • Improving Incremental Nonnegative Matrix Factorization Method for
           Recommendations Based on Three-Way Decision Making

    • Free pre-print version: Loading...

      Abstract: Abstract Nonnegative matrix factorization is comprehensively used in recommendation systems. In an effort to reduce the recommended cost of newly added samples, incremental nonnegative matrix factorization and its variants have been extensively studied in recommendation systems. However, the recommendation performance is incapable of particular applications in terms of data sparsity and sample diversity. In this paper, we propose a new incremental recommend algorithm by improving incremental nonnegative matrix factorization based on three-way decision, called Three-way Decision Recommendations Based on Incremental Non-negative Matrix Factorization (3WD-INMF), in which the concept of positive, negative, and boundary regions are employed to update the new coming samples’ features. Finally, experiments on six public data sets demonstrate the error induced by 3WD-INMF is decreasing as the addition of new samples and deliver state-of-the-art performance compared with existing recommendation algorithms. The results indicate our method is more reasonable and efficient by leveraging the idea of three-way decision to perform the recommendation decision process.
      PubDate: 2022-11-01
       
 
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
 


Your IP address: 44.192.52.167
 
Home (Search)
API
About JournalTOCs
News (blog, publications)
JournalTOCs on Twitter   JournalTOCs on Facebook

JournalTOCs © 2009-