Intelligence Science III: 4th IFIP TC 12 International Conference, ICIS 2020, Durgapur, India, February 24–27, 2021, Revised Selected Papers: 623 ... and Communication Technology, 623)

This book constitutes the refereed post-conference proceedings of the 4th International Conference on Intelligence Science, ICIS 2020, held in Durgapur, India, in February 2021 (originally November 2020). The 23 full papers and 4 short papers presented were carefully reviewed and selected from 42 submissions. One extended abstract is also included. They deal with key issues in brain cognition; uncertain theory; machine learning; data intelligence; language cognition; vision cognition; perceptual intelligence; intelligent robot; and medical artificial intelligence. Preface Organization Contents Brain Cognition Mind Modeling in Intelligence Science 1 The Age of Intelligence 2 Mind Modeling 2.1 Symbolic Mind Model 2.2 Connectionist Mind Model 2.3 Hybrid Mind Model 3 Brain Computer Integration 4 Conclusions References Some Discussions on Subjectivity of Machine and its Function 1 Introduction 2 Major Aspects of Subjectivity of Machine 2.1 A Priori and Internal Cogitating 2.2 Active Perception 2.3 Self Awareness 2.4 Dynamic Action 3 Functions of Subjectivity of Machine 3.1 Go Game 3.2 Image Recognition 3.3 Natural Language Processing 3.4 Controlling System 4 Further Discussions on Dynamic Action References Hexagon of Intelligence 1 ``Artificial Intelligence'' and the Challenge of the Correlated Field 2 Two Different Kinds of Reasoning 3 Logic(s) and Artificial Intelligence 4 The Theory of Oppositions References Uncertain Theory Interactive Granular Computing Model for Intelligent Systems 1 Introduction 2 Basis of Interactive Granular Computing 3 Control and Computation over ic-Granules 3.1 Two Kinds of Transition Properties of ic-Granules Realised by Control 3.2 Computation over the ic-Granules Directed by Control 4 Reasoning in the Context of Complex Granules: Future Directions References A Framework for the Approximation of Relations 1 Introduction 2 Formalizing the Problem 2.1 Operations on Binary Relations 2.2 Perception Constructors 2.3 Perception Constructors and Galois Adjunctions 3 Approximating Heterogeneous Relations 4 Unilateral Lower Approximation Operators 4.1 Nominal Unilateral Lower Approximation Operators 4.2 Generic Unilateral Lower Approximation Operators 4.3 Computing Procedure 4.4 Unilateral Upper Approximation Operators 4.5 The Injective Cases 5 Reconstruction of a Relation 5.1 Bilateral Approximation of a Relation with Reference Relation 5.2 Refinement and Simulation References Logical Treatment of Incomplete/Uncertain Information Relying on Different Systems of Rough Sets 1 Introduction 2 Background 2.1 General Approximation Space 2.2 Role of Base Sets 3 Influences of Embedded Knowledge on Membership Relations 3.1 Rough Membership Relations 3.2 Rough Membership Measurement on Finite Universe 4 Partial First-Order Logic (PFoL) Relying on Different Generalized Characteristic Functions 4.1 Language of PFoL 4.2 Semantics of PFoL 4.3 Central Semantic Notions 5 Conclusion and Future Work References Possibility Theory and Possibilistic Logic: Tools for Reasoning Under and About Incomplete Information 1 Introduction 2 Possibility Theory 3 Connections Between Possibility Theory and Other Representations of Incomplete Knowledge 4 Possibilistic Logic and Its Applications 5 Generalized Possibilistic Logic 6 Concluding Remarks References Machine Learning Similarity-Based Rough Sets with Annotation Using Deep Learning 1 Introduction 2 Theoretical Background 3 Correlation Clustering 4 Similarity-Based Rough Sets 5 Partiality in Logical Systems 6 Similarity-Based Rough Sets with Annotation 7 Conclusion and Future Work References P-T Probability Framework and Semantic Information G Theory Tested by Seven Difficult Tasks 1 Introduction 2 P-T Probability Framework and Semantic Information G Theory 2.1 From Shannon’s Probability Framework to P-T Probability Framework 2.2 From Shannon’s Information Measure to Semantic Information Measure 3 To Complete Seven Difficult Tasks 3.1 Clarifying the Relationship Between Minimum Information and Maximum Entropy 3.2 R(G) Function for Compressing Data According to Visual Discrimination 3.3 Multilabel Learning for Labels’ Extensions or Truth Functions 3.4 The Channels Matching Algorithm for Maximum Mutual Information (MMI) Classifications 3.5 The Convergence Proof and the Improvement of the EM Algorithm for Mixture Models 3.6 To Resolve the Problem with Popper’s Verisimilitude and Explain the RLS Criterion 3.7 To Provide Practical Confirmation Measures and Clarify the Raven Paradox 4 Summary References Trilevel Multi-criteria Decision Analysis Based on Three-Way Decision 1 Introduction 2 Three-Way Decision and Trilevel Analysis 3 A Trilevel Framework of Multi-criteria Decision Making 3.1 Trilevel Thinking in Multi-criteria Decision Analysis 3.2 Single-Criterion Level 3.3 Multi-criteria Level 3.4 Multi-methods Level 4 Conclusion and Future Work References Recurrent Self-evolving Takagi–Sugeno–Kan Fuzzy Neural Network (RST-FNN) Based Type-2 Diabetic Modeling 1 Introduction 2 Proposed Method 2.1 Type-2 Diabetes Simulator (T2DS) 2.2 Recurrent Self-evolving TSK Fuzzy Neural Network (RST-FNN) for Prediction 2.3 Automated Insulin Control System 3 Results and Discussion 4 Conclusion References Granulated Tables with Frequency by Discretization and Their Application 1 Introduction 2 Tables with Continuous Attribute Values 2.1 Rules and Discretization of Continuous Attribute Values 2.2 An Example of the Iris Data Set 3 Rule Generation from Discretized Tables with Frequency 4 An Apriori-Based Rule Generator for and Some Experiments 5 Concluding Remarks References Data Intelligence Person Authentication by Gait Data from Smartphone Sensors Using Convolutional Autoencoder 1 Introduction 2 Related Work 3 Proposed Method and Comparative Study 3.1 Convolutional Autoencoder (CAE) 3.2 Deep Neural Network Models Used for Comparison 4 Simulation Experiments and Results 4.1 Datasets 4.2 Simulation Results 5 Summarization and Conclusion References Research on Personal Credit Risk Assessment Model Based on Instance-Based Transfer Learning 1 Introduction 2 Related Works 3 The Construction of Personal Credit Risk Assessment Model 3.1 The Build of Instance-Based Transfer Learning 3.2 Base Learner Selection 4 Compare Experiments and Results Analysis 4.1 The Source of the Dataset 4.2 Missing Values Processing 4.3 Feature Selection 4.4 Experimental Results and Comparative Analysis Results 5 Conclusion References Language Cognition From Texts to Classification Knowledge 1 Introduction 2 Motivation 3 Methods 3.1 Discharge Summary 3.2 Motivation for Feature Selection 3.3 Mining Process 4 Experimental Evaluation 4.1 Mining Process 4.2 Classification Results 5 Discussion 5.1 Misclassified Cases 5.2 Execution Time 5.3 Next Step 6 Conclusion References ANAS: Sentence Similarity Calculation Based on Automatic Neural Architecture Search 1 Introduction 2 Related Work 3 Our Approach 3.1 Neural Architecture Search Technology 3.2 Model Implementation and Evaluation Optimization 4 Experiment 4.1 Datasets 4.2 Evaluation Index 4.3 Experimental Results and Analysis 5 Conclusion References Fully Interval Integer Transhipment Problem - A Solution Approach 1 Introduction 2 Preliminaries 2.1 Interval Numbers 2.2 Ranking of Interval Numbers 2.3 A New Interval Arithmetic 3 Main Results 3.1 Mathematical Formulation for Using Fully Interval Transhipment Problem 4 Improved Interval Vogel’s Approximation Algorithm 5 Numerical Example 6 Conclusion References Vision Cognition Novel Image Compression and Deblocking Approach Using BPN and Deep Neural Network Architecture 1 Introduction 2 Proposed Methodology 2.1 Image Preprocessing 2.2 Backpropagation Neural Networks 2.3 Arithmetic Coding 2.4 Image Deblocker 3 Performance Analysis and Discussion 4 Conclusion References Characterization of Orderly Behavior of Human Crowd in Videos Using Deep Learning 1 Introduction 2 Proposed Methodology 2.1 Feature Extraction 2.2 Crowd Classification 3 Results 3.1 Video Dataset 3.2 Classification Results 4 Conclusion and Future Scopes References Perceptual Intelligence Stability Analysis of Imprecise Prey-Predator Model 1 Introduction 2 Related Work 3 Mathematical Preliminaries 3.1 Basic Concept of ``e'' and ``g'' Operators 3.2 Use of ``e'' and ``g'' Operators to Fuzzy Dynamical System 4 Assumption and Notations 5 Formulation of the Model in Crisp Environment 6 Formulation and Stability Analysis of the Imprecise Model 6.1 Case-I 6.2 Local Stability Analysis of Case-I 6.3 Numerical Experiment Case-I 6.4 Case-II 6.5 Local Stability Analysis of Case-II 6.6 Numerical Experiment-2 7 Discussion 8 Conclusion References Comparative Performance Study on Human Activity Recognition with Deep Neural Networks 1 Introduction 2 Related Work 2.1 Machine Learning Methods 2.2 Deep Neural Network Methods 3 Comparative Performance Study 3.1 Datasets 3.2 Methodology 4 Simulation Experiments and Results 5 Conclusion References Intelligent Robot Beam and Ball Plant System Controlling Using Intuitionistic Fuzzy Control 1 Introduction 2 Preliminaries 3 Ball and Beam Mathematical Model 4 Controller Design 5 Numerical Solution 6 Conclusion References Application of Pinching Method to Quantify Sensitivity of Reactivity Coefficients on Power Defect 1 Introduction 2 Calculation Methodology 2.1 Calculation of Power Defect 2.2 Notation for Probability Box 2.3 Random Sampling from Normal Distribution 2.4 Methodology for Sensitivity Analysis 3 Results and Discussions 3.1 Temperature Response with Respect to the Power Variation 3.2 Estimation of Probability Box for Power Defect 3.3 Sensitivity Analysis 4 Conclusions References Computation with Democracy: An Intelligent System 1 Introduction 2 Self-replication 3 Self-organization and Artificial Life 4 Fault Tolerance and Distributed System 5 To Move Forward References Medical Artificial Intelligence Economy and Unemployment Due to COVID19: Secondary Research 1 Introduction 2 Data Analysis 3 Effect on World Economy 4 Employment Rates in India 4.1 Employment Rates in India 5 Conclusion References Optimal Control of Dengue-Chikungunya Co-infection: A Mathematical Study 1 Introduction 2 Formulation of Co-infection Model 3 Application of Optimal Control 4 Numerical Experiment 5 Discussion 6 Sensitivity Analysis 7 Conclusion References Comparative Analysis of Machine Learning Algorithms for Categorizing Eye Diseases 1 Introduction 1.1 Related Work 2 Materials and Methods 2.1 Image Acquisition 2.2 Image Enhancement 2.3 Feature Extraction and Selection 2.4 Classification 3 Results and Discussion 4 Conclusion References Extended Abstract Extensions of Dynamic Programming for Combinatorial Optimization and Data Mining References Author Index