Biometric and Intelligent Decision Making Support (2015) .. by Arturas Kaklauskas
Contents
1 Introduction to Intelligent Decision Support Systems … 1
1.1 Introduction … 1
1.2 Development of Intelligent Decision Support Systems: Based on Artificial Intelligence Methods with Special Emphasis on Technology … 4
1.3 Intelligent User Interface … 7
1.4 Integration of Artificial Intelligent and DBMS Technologies … 14
References … 25
2 Intelligent Decision Support Systems … 31
2.1 Recommender, Advisory and Expert Systems and Their Integration with Decision Support Systems … 31
2.2 Text Analytics and Mining Based DSSs … 35
2.3 Data Mining as an Important Component of Intelligent Decision Support Systems … 42
2.4 Integration of Data Analytics and Decision Support Systems … 48
2.5 Artificial Neural Networks in Decision Support Systems and Biometrics … 50
2.6 Integration of Remote Sensing into a Decision Support Systems … 56
2.7 Biometrics-Based Decision Support Systems … 58
2.7.1 Voice Recognition Decision Support Systems … 58
2.7.2 Speech Recognition and Understanding Decision Support Systems … 59
2.7.3 Adaptive Biometrics-Based Decision Support Systems … 60
2.7.4 Other Biometrics-Based Decision Support Systems … 61
2.8 Ambient Intelligence and the Internet of a Things-Based Decision Support Systems … 62
2.9 Other Intelligent Decision Support Systems … 68
2.9.1 GA-Based Decision Support Systems … 68
2.9.2 Fuzzy Sets IDSS … 69
2.9.3 Rough Sets … 69
2.9.4 Intelligent Agent-Assisted Decision Support Systems … 70
2.9.5 Process Mining Integration to Decision Support … 72
2.9.6 Adaptive Decision Support Systems … 73
2.9.7 Computer Vision Based DSS … 75
2.9.8 Sensory Decision Support Systems … 75
2.9.9 Robotic Decision Support Systems … 76
References … 76
3 Passive House Model for Quantitative and Qualitative Analyses and Its Intelligent System … 87
3.1 Introduction … 87
3.2 Passive House Model for Quantitative and Qualitative Analyses and Illustration of Its Several Stages … 88
3.2.1 Passive House Model for Quantitative and Qualitative Analyses … 88
3.2.2 Passive House Socio-cultural Aspects … 90
3.2.3 Self-expression Values, Environmentalism, Global Warming and the Passive House … 96
3.2.4 Low Energy Dwelling Weaknesses in Lithuania … 101
3.3 The Intelligent Passive House Design System … 103
3.4 Case Study … 106
References … 110
4 Biometric and Intelligent Self-Assessment of Student Progress System … 113
4.1 Introduction … 113
4.2 Reliability of Self-Assessment … 115
4.3 Biometric and Intelligent Self-Assessment of Student Progress (BISASP) System … 117
4.4 Self-Assessment Integrated Grading Model … 121
4.5 Self-Assessment Integrated Grading Adjustment Model … 123
4.6 Case Studies … 124
4.6.1 Case Study 1: Analysis on the Interdependencies Between Microtremors, Stress and Student Marks … 125
4.6.2 Case Study 2: Comparison of Marks Assigned to Students During the Psychological Examination, Prior to the e-Test and During the e-Test … 129
References … 134
5 Web-based Biometric Computer Mouse Advisory System to Analyze a User’s Emotions and Work Productivity … 137
5.1 Introduction … 138
5.2 Dependency of Human Blood Pressures, Heart Rate, Skin Conductance and Temperature on Experienced Stress and Emotions … 139
5.2.1 Effect of Experienced Emotions on Blood Pressure, Heart Rate, Skin Conductance and Body Temperature … 141
5.2.2 Dependence of Blood Pressures and Heart Rate on a Person’s Experienced Stress … 144
5.3 Web-based Biometric Computer Mouse Advisory System to Analyze a User’s Emotions and Work Productivity … 145
5.3.1 e-Self-assessment Subsystem … 146
5.3.2 Biometric Computer Mouse … 147
5.3.3 Mouse Events Capture, Collection and Feature Extraction Subsystem … 152
5.3.4 Biometric Finger … 154
5.3.5 User’s Biometric Database … 155
5.3.6 Maslow’s Pyramid Tables … 156
5.3.7 Model-Base Management System and Model Base … 158
5.4 Case Study: Determining Stress Level and Providing Recommendations … 161
5.5 Scenario Used to Test and Validate the Advisory System and Its Composite Parts … 166
5.5.1 Statistical Analysis of Average Temperature Dependency on Anxiety … 168
5.6 Calculating Reliability of Stress Dependencies on Diastolic and Systolic Blood Pressures and Finger Temperature by Analyzing the Entire User’s Biometric Database … 169
References … 170
6 Student Progress Assessment with the Help of an Intelligent Pupil Analysis System … 175
6.1 Introduction … 175
6.2 Intelligent Pupil Analysis System … 177
6.2.1 Database Management System and Intelligent Database … . 178
6.2.2 Model-base Management Subsystem and Model-bases … 179
6.2.3 Student’s Answer Correctness Estimate per Pupillary Response Model … 183
6.3 Case Studies … 187
6.3.1 Case Study 1: A Sample of IPA System’s Recommendations to a Tutor … 187
6.3.2 Case Study 2: Study of the Dependence Linking a Student’s Pupil Size to the Student’s Psychological and Emotional State During an Examination … 188
References … 191
7 Recommender System to Analyze Student’s Academic Performance … 195
7.1 Introduction … 195
7.2 Analysis of the Interdependence Linking Physiological Parameters of Students to Their Learning Productivity and Interest in Learning … 198
7.3 Recommender System to Analyze Student’s Academic Performance … 203
7.3.1 Introduction … 203
7.3.2 Equipment Subsystem … 203
7.3.3 Intelligent Database and Database Management System … . 204
7.3.4 Model-base Management System and Model Base … 210
7.4 Development of Learning Materials on a Students’ Learning Productivity and the Level of Interestingness … 210
7.5 Case Study: The Recommender System as a Means to Increase Student Productivity in Learning and to Improve Their Achievements … 212
7.6 Reliability Analysis of the Influence of Physiological Parameters on Interest in Learning Using the Entire
Student’s Physiological Database … 215
References … 217