Computer Science and Engineering—Theory and Applications (eBook)

Preface 6
Contents 8
1 A Comprehensive Context-Aware Recommender System Framework 10
Abstract 10
1 Introduction 10
2 Background and Related Work 12
2.1 Context and Context Awareness 12
2.1.1 Context Representation 13
2.2 Frameworks for Context-Aware Recommendations 14
2.3 Requirements for a Context-Aware Recommender System Framework 16
3 The Comprehensive Context-Aware Recommender System Framework 17
3.1 The Model 18
3.1.1 User Aspects 19
3.1.2 Context Aspects 19
3.1.3 Activity Information 19
3.1.4 Items Information 20
3.2 Data Management 20
3.2.1 Dataset Generator 21
3.3 Recommendation Algorithms 21
3.3.1 Traditional Recommendation Algorithms 22
3.3.2 Contextual Recommendation Algorithms 22
4 Evaluations 24
4.1 Comparative Assessment 24
4.2 Use Cases 25
4.2.1 Data Management Feature 26
4.2.2 Contextual Recommendation Feature 28
5 Conclusions and Future Work 29
Acknowledgements 30
References 31
2 Executive Functions and Their Relationship with Interaction Design 34
Abstract 34
1 Introduction 34
2 User Modelling and Interface Design 36
3 Executive Functions 38
3.1 Executive Functions and Interaction Design 39
3.2 The Problem of Cognitive Load 40
3.3 Can We Measure Cognitive Load? 41
3.3.1 Indirect Measures 41
3.3.2 Subjective Measures 41
3.3.3 Measurement Through a Secondary Task 42
3.3.4 Physiological Measures 42
4 Research Questions 43
5 Experimental Design 43
5.1 Objectives 43
5.2 Sample 44
5.3 Structure of the Study 44
5.4 Variables 44
5.5 Instruments 45
5.5.1 Nepsy II 45
5.5.2 Wisc-IV 46
5.5.3 Modified NASA-TLX Test for Children 46
5.6 Methodology 46
5.7 Results 47
5.7.1 Data Analysis 47
5.7.2 Interaction Rules 48
5.7.3 Analysis of Variance 51
5.7.4 Regression Analysis 51
6 Conclusions and Discussion 53
References 54
3 Integrating Learning Styles in an Adaptive Hypermedia System with Adaptive Resources 57
Abstract 57
1 Introduction 57
2 State of the Art 58
2.1 Index of Learning Styles Questionnaire 59
2.1.1 Active and Reflective Learners 59
2.1.2 Sensing and Intuitive Learners 59
2.1.3 Visual and Verbal Learners 59
2.1.4 Sequential and Global Learners 60
2.2 Learning Systems 60
2.3 Learning Objects 61
2.4 Simple Sequencing 61
3 Related Works 62
4 Arquitecture 63
4.1 System Architecture 65
4.2 User Modeling 66
4.3 Recommendation of Learning Activities 66
5 The Adaptive Hypermedia System 67
5.1 Welcome Screen 67
5.2 Learning Styles Questionnaire 67
5.3 Creation of Learning Activities 68
5.4 Creation of Courses 68
5.5 Course Presentation Window 69
5.6 Learning Activities 69
6 Results 70
7 Conclusion and Future Work 72
References 73
4 On Modeling Tacit Knowledge for Intelligent Systems 76
Abstract 76
1 Introduction 76
2 Tacit Knowledge 77
2.1 Types of Tacit Knowledge 79
2.2 Components of Knowledge 79
2.2.1 Particulars 79
2.2.2 Pre-concepts 80
2.2.3 Concepts 80
2.3 A Further Analysis of Knowledge 81
2.3.1 Inarticulable Tacit Knowledge 81
2.3.2 Articulable Tacit Knowledge 81
2.3.3 Explicit Knowledge 81
2.3.4 Relation Between Tacit and Explicit Knowledge 82
2.3.5 Know-What and Know-How 83
2.3.6 Synthesis of Knowledge 83
3 Tacit Knowledge’s Acquisition Process 84
4 Tacit Knowledge Acquisition Based on Rule Following 87
4.1 Proposed Interpretation of Rule Following 88
4.2 From Individual Tacit Knowledge to Collective (Social) Tacit Knowledge 89
5 A Proposal for Artificial Intelligence and Multiagent Systems 91
6 Conclusions 92
References 93
5 Influence of the Betweenness Centrality to Characterize the Behavior of Communication in a Group 95
Abstract 95
1 Introduction 95
2 Network Models 96
3 Barbell Graph 98
4 Types of Centrality Measures 99
4.1 Degree Centrality 99
4.2 Eigenvector Centrality 99
4.3 Closeness Centrality 99
4.4 Betweenness Centrality 100
5 Agent-Based Modeling 101
5.1 Proposed Agent-Based Model for Rumor Spreading 101
6 Results 105
7 Conclusions 106
8 Future Work 107
References 107
6 Multi-layered Network Modeled with MAS and Network Theory 108
Abstract 108
1 Introduction 108
2 Related Work 110
2.1 Complex Networks 110
2.2 Multilayer Networks 112
2.3 Multi-agent System 114
2.4 Multi-agent System Architectures 115
2.5 Negotiation 116
3 Proposed Model 118
4 Case Study 119
5 Results 126
6 Conclusion and Future Work 127
Acknowledgements 127
References 127
7 A Fuzzy Inference System and Data Mining Toolkit for Agent-Based Simulation in NetLogo 131
Abstract 131
1 Introduction 132
1.1 Fuzzy Logic as a Methodology 133
1.2 Related Work 134
2 The JT2FIS NETLOGO Tool-Kit 134
2.1 Develop Mamdani and Takagi-Sugeno Fuzzy Logic System 135
2.1.1 Inputs 136
2.1.2 Outputs 137
2.1.3 Members Functions 137
2.1.4 Rules 137
2.1.5 Data Evaluation 138
2.2 Clustering 140
2.3 Export NetLogo 140
2.3.1 Executing FIS in NetLogo 142
3 Use Cases 142
3.1 Use Case 1: Empirical Configuration FIS 143
3.2 Use Case 2: Data Mining Configuration FIS 145
4 Discussion and Applications 148
4.1 From Simplistic to Realistic Model 148
4.2 Fuzziness and Uncertainty in Agent Behavior 149
4.3 Opportunity Areas for FISs Applications 150
5 Conclusions and Future Work 150
Acknowledgements 151
References 151
8 An Approach to Fuzzy Inference System Based Fuzzy Cognitive Maps 154
Abstract 154
1 Introduction 154
2 Fuzzy Cognitive Maps 155
3 Type-1 Fuzzy Inference Systems 157
4 Proposal of Fuzzy Inference System Based Fuzzy Cognitive Maps 159
5 Experimental Results and Discussion 162
6 Conclusions 167
Acknowledgements 167
References 167
9 Detecting Epilepsy in EEG Signals Using Time, Frequency and Time-Frequency Domain Features 170
Abstract 170
1 Introduction 170
2 Background 172
2.1 Epileptic States 172
2.2 Related Work 172
3 Applied Methods 173
3.1 Feature Extraction and Selection 174
3.1.1 Time Domain 174
3.1.2 Frequency Domain 175
3.1.3 Time-Frequency Domain 176
3.1.4 ReliefF 177
3.2 Classification Methods 177
4 Experimental Setup and Results 178
4.1 Dataset and Problem Formulation 178
4.2 Experimental Procedure 179
5 Results and Discussion 180
6 Conclusions and Future Work 183
Acknowledgements 184
References 184
10 Big Data and Computational Intelligence: Background, Trends, Challenges, and Opportunities 186
Abstract 186
1 Introduction 186
2 Evolution of Data Analysis 187
3 Emergence of Big Data 188
4 Big Data Value Chain 190
5 Challenge of Big Data 191
6 Areas of Application of Big Data 192
7 Computational Intelligence 192
8 Conclusions 196
References 197
11 Design of a Low-Cost Test Plan for Low-Cost MEMS Accelerometers 200
Abstract 200
1 Introduction 200
2 MEMS Accelerometer 202
3 Accelerometer Model 203
4 Testing Stages 203
4.1 Data Logging 203
4.2 Preliminary Evaluation 204
4.3 Static Testing 205
4.3.1 Multi-position Test 205
4.3.2 Long Term Stability Test 210
4.3.3 Repeatability Test 210
4.4 Dynamic Testing 211
4.4.1 Free Fall Test 211
4.4.2 Centrifuge Test 212
5 Conclusions 213
Acknowledgements 213
References 213
12 Evaluation of Scheduling Algorithms for 5G Mobile Systems 216
Abstract 216
1 Introduction 216
1.1 Long Term Evolution (LTE) 218
1.2 Scheduling Fundamentals 219
2 Model-Based Design Approach 220
3 System Development 221
3.1 The Radio Resource Management Model 222
3.2 Environment Model 224
4 Experimental Setup 224
4.1 Maximum Rate Scheduler 224
4.2 Round Robin Scheduler 225
4.3 Proportional Fair Scheduler 226
4.4 UE-Based Maximum Rate Scheduler 228
5 Results Analysis 228
6 Conclusion and Future Trends 233
References 233
13 User Location Forecasting Based on Collective Preferences 237
Abstract 237
1 Introduction 237
1.1 Collecting Location Data Issues 238
1.2 Collective Preferences Rule Our Lives 239
2 User Mobility 239
2.1 Markovian Chain Among POIs 241
3 Spatio-temporal Prediction Model 242
3.1 Modeling User Mobility as a Hidden Markov Model 242
3.2 Defining User Prediction Model 242
3.3 Identifying Points of Interest 243
3.4 User Mobility Similarity 244
3.5 Converting User Mobility into a Vector 244
3.6 Updating POIs 245
3.7 Predictability of the User Mobility 245
4 Collaborative Filtering 245
4.1 User-User Collaborative Filtering 246
4.2 Item-Item Collaborative Filtering 246
4.3 Stages of CF 247
4.3.1 Building a User Profile 247
4.3.2 Measuring User Similarity 247
4.3.3 Generating a Prediction 247
5 User Location and CF 248
5.1 Building User Profile 248
5.2 Measuring User Similarity 250
5.3 Avoiding Missing Points of Interest 250
6 Evaluation 251
6.1 Dataset 251
6.2 Training Prediction Models 251
6.3 Defining User Profile 252
6.4 Predictions 253
6.5 Effectiveness of the Prediction Model 253
7 Results 253
7.1 POIs 253
7.2 Matrix R Vectors ru 254
7.3 Vectors Similarity 254
7.4 Incorporating POIs 256
7.5 Prediction 256
References 258
14 Unimodular Sequences with Low Complementary Autocorrelation Properties 260
Abstract 260
1 Introduction 260
2 Fundamental Concepts 262
3 System Identification Using Cyclostationary Statistics 265
3.1 SL System Identification 265
3.1.1 Second Order Characterization 269
3.2 WL System Identification 271
4 Sequences with Low Aperiodic Complementary Autocorrelation 278
4.1 Design of Sequences for an Aperiodic Second Order Characterization 278
5 Conclusions 282
Acknowledgements 282
References 282