Smart and Intelligent Systems: The Human Elements in Artificial Intelligence, Robotics, and Cybersecurity (The Human Element in Smart and Intelligent Systems)

Description

In today’s digital world, the words “smart” and intelligent” are now used to label devices, machinery, systems, and even environments. What is a “smart” system? Is “smart” synonymous to “intelligent”? If not, what does an “intelligent system” mean? Are all the smart systems intelligent? This book tries to answer these questions through summarizing existing research in various areas and providing new research findings. This book presents new areas of smart and intelligent system design. It defines smart and intelligent systems, offers a human factors approach, discusses networking applications, and combines the human element with smart and intelligent systems. This book is perfect for engineering students in data sciences, artificial intelligence, practitioners at all levels in the field of human factors and ergonomics, systems engineering, computer science, software engineering and robotics. Cover Half Title Series Page Title Page Copyright Page Table of Contents Editor Contributors Introduction Chapter 1: Smart Educational System 1.1 Introduction 1.2 The Evolution of Smart Education and Smart Learning 1.3 Smart Education 1.3.1 Advanced and Immersive Computing Infrastructure 1.3.2 Internet of Things (IoT) 1.3.3 Artificial Intelligence and Machine Learning 1.3.4 Blockchain-Based Applications 1.3.5 Virtual, Augmented, Mixed Reality (X.R.), or Immersive Technology 1.3.6 Social Networking/Collaborating Technologies 1.3.7 Big Data and Data Analytics 1.3.8 Smart Learning Environment 1.3.9 Smart Pedagogical Approaches 1.3.9.1 Deep Learning Pedagogy 1.3.9.2 Personalized Learning Pedagogy 1.3.9.3 Adaptive Learning 1.3.9.4 Flexible or Open Learning Pedagogy 1.3.9.5 Interest-Driven Learning 1.3.9.6 Collaborative Learning Pedagogy 1.3.9.7 Engaged and Meaningful Learning 1.3.9.8 Formal and Informal Learning (Anywhere, Anytime, Anything and Any Place Learning) 1.3.9.9 Generative Learning 1.3.9.10 Assessment that Uses Continuous Learning 1.3.10 Smart Education and Collaboration with the Community 1.3.11 Implementation Support and Facilitation in Smart Education System 1.3.12 New Roles and Responsibilities for Teachers 1.3.13 Teachers as Co-Designers of Learning Materials and Resources 1.3.14 Universal Design for Learning and Accessibility 1.4 New Foundational Knowledge and Skills, Theoretical Frameworks, and Research 1.5 Conclusion References Chapter 2: Intelligent Affect-Sensitive Tutoring Systems: An Evaluative Case Study and Future Directions 2.1 Introduction 2.2 The Role of Affect in Learning 2.3 Affective  Tutoring Systems 2.4 Genetics with Jean 2.5 Evaluation of the Genetics with Jean ATS 2.5.1 Methodology 2.5.1.1 Development of Measurement Instruments 2.5.1.2 Content Knowledge 2.5.1.3 Perceived Learning 2.5.1.4 Enjoyment 2.5.2 Participants 2.5.3 Data Collection Session 2.5.4 Pilot 2.5.5 Does Affective Support Lead to Improvements in Students’ Knowledge? 2.5.6 Does Affective Support Lead to Improvements in Students’ Perceived Learning? 2.5.7 Does Affective Support Lead to Improvements in Students’ Enjoyment of Learning? 2.6 Discussion 2.7 Conclusion and Future Directions References Chapter 3: User State Assessment in Adaptive Intelligent Systems 3.1 Introduction 3.2 Multidimensional Definition of User State 3.3 Studies on User State Assessment in Adaptive Systems 3.4 Measurement Techniques 3.4.1 Criteria to Evaluate Measurement Techniques 3.4.2 Subjective Rating 3.4.3 Performance-Based Measures 3.4.4 Physiological and Behavioral Measures 3.4.4.1 Measures of the Visual System 3.4.4.2 Measures of Brain Activity 3.4.4.3 Peripheral-Physiological and Behavioral Measures 3.4.5 Conclusion 3.5 Implications for Adaptive System Design 3.5.1 Challenges and Recommendations 3.5.1.1 Confounding Factors 3.5.1.2 Reliability and Temporal Stability 3.5.1.3 Individual Differences 3.5.1.4 Self-Regulation Strategies of the Human Operator 3.5.1.5 Root-Cause Analysis 3.5.1.6 Oscillation 3.5.1.7 Realistic Work Environments 3.5.1.8 Summary 3.5.2 Holistic View on User State 3.6 Real-Time Assessment of Multidimensional User State (RASMUS) 3.6.1 Diagnostic Concept 3.6.2 Implementation for an Anti-Air-Warfare Task 3.6.2.1 Task Environment 3.6.2.2 User States and Indicators 3.6.2.3 Rule Base 3.6.2.4 Validation 3.6.3 Using RASMUS Diagnostics for Adaptation Management 3.7 Concluding Remarks References Chapter 4: Agent Transparency 4.1 Introduction 4.2 Operator Performance Issues 4.2.1 Operator Performance and Workload 4.2.2 Operator Trust and Perceptions of Transparent Agents 4.2.3 Individual and Cultural Differences 4.3 Situation Awareness-Based Agent Transparency 4.4 Implementation of Transparency in Complex Human–Agent Systems 4.4.1 Human Interaction with a Small Robot 4.4.2 Multiagent Systems 4.4.3 Human–Swarm Interaction 4.5 Challenges and Future Research References Chapter 5: Smart Telehealth Systems for the Aging Population 5.1 Introduction 5.2 Remote Monitoring 5.2.1 Remote Patient Monitoring 5.2.2 Remote Activity Monitoring 5.2.3 RM for Medication Adherence 5.2.4 Electronic Diaries and Queries 5.2.5 Smart Homes 5.2.6 Chronic, Acute, and Ambulatory Motivations for RM 5.3 Decision Support Systems 5.4 Health Coaching Systems 5.5 Integrated Telehealth System 5.6 Review Methods 5.7 Effectiveness of Telehealth to Support Successful Aging in Place 5.8 Conclusions References Chapter 6: Social Factors in Human-Agent Teaming 6.1 Social Factors in Human-Agent Teaming 6.2 Theoretical Foundations 6.3 Verbal Communication 6.4 Nonverbal Communication 6.5 Social Groups 6.6 Individual Traits 6.7 General Discussion 6.8 Author Note References Chapter 7: Human Elements in Machine Learning-Based Solutions to Cybersecurity 7.1 Introduction 7.2 ML-Based Solutions for Cybersecurity 7.2.1 Phishing Detection 7.2.2 Malware Detection 7.2.3 Intrusion Detection Systems (IDS) 7.3 Challenges and Limitations of ML-Based Solutions 7.4 Addressing the Challenges and Limitations: Human-in-the-Loop Model Building 7.5 Human Elements in ML-Based Solutions 7.6 Interpretive Machine Learning 7.7 Conclusion References Chapter 8: Cybersecurity in Smart and Intelligent Manufacturing Systems 8.1 Introduction 8.2 Intelligent and Smart Manufacturing 8.2.1 Motivation of Cyberattackers 8.2.2 Manufacturing Cyber Vulnerability 8.2.2.1 Security Consideration at Design of the Systems 8.2.2.2 Heterogeneity of the Manufacturing Systems 8.2.2.3 Update and Upgrade 8.2.2.4 Performance versus Security 8.3 Cybersecurity in Manufacturing Systems 8.3.1 Encryption 8.3.2 Authentication and Access Management 8.3.3 Operator Access Authentication 8.4 Machine Tools Security 8.4.1 Insider Threat 8.4.2 Internet of Things (IoT) 8.4.3 Malware 8.4.4 Phishing 8.5 Assessment and Protective Technologies 8.5.1 Intrusion Detection Systems (IDS) 8.5.2 Vulnerability Scanning (VS) 8.5.3 Insider Attacks Detection 8.5.4 Honeypots and Deception Techniques Detection 8.5.5 Risk Management and the Cybersecurity Framework 8.5.6 Penetration Testing of Manufacturing System 8.6 Conclusion References Index