Schweitzer Fachinformationen
Wenn es um professionelles Wissen geht, ist Schweitzer Fachinformationen wegweisend. Kunden aus Recht und Beratung sowie Unternehmen, öffentliche Verwaltungen und Bibliotheken erhalten komplette Lösungen zum Beschaffen, Verwalten und Nutzen von digitalen und gedruckten Medien.
Comprehensive guide offering actionable strategies for enhancing human-centered AI, efficiency, and productivity in industrial and systems engineering through the power of AI.
Advances in Artificial Intelligence Applications in Industrial and Systems Engineering is the first book in the Advances in Industrial and Systems Engineering series, offering insights into AI techniques, challenges, and applications across various industrial and systems engineering (ISE) domains. Not only does the book chart current AI trends and tools for effective integration, but it also raises pivotal ethical concerns and explores the latest methodologies, tools, and real-world examples relevant to today's dynamic ISE landscape.
Readers will gain a practical toolkit for effective integration and utilization of AI in system design and operation. The book also presents the current state of AI across big data analytics, machine learning, artificial intelligence tools, cloud-based AI applications, neural-based technologies, modeling and simulation in the metaverse, intelligent systems engineering, and more, and discusses future trends.
Written by renowned international contributors for an international audience, Advances in Artificial Intelligence Applications in Industrial and Systems Engineering includes information on:
Advances in Artificial Intelligence Applications in Industrial and Systems Engineering is a timely, essential reference for engineering, computer science, and business professionals worldwide.
WALDEMAR KARWOWSKI is a Pegasus Professor and Chair in the Department of Industrial Engineering and Management Systems at the University of Central Florida. He is an elected member of The Academy of Science, Engineering and Medicine of Florida (ASEMFL).
VINCENT DUFFY is a Professor of Industrial Engineering and Agricultural & Biological Engineering at Purdue University and a Fulbright Senior Scholar.
GAVRIEL SALVENDY is a University Distinguished Professor at the University of Central Florida, a member of the National Academy of Engineering, and founding Department Head of Industrial Engineering at Tsinghua University in China.
About the Editors xxiii
Preface xxv
1 Introduction to Industrial Artificial Intelligence 1
Dai-Yan Ji, Hanqi Su, Takanobu Minami, and Jay Lee, USA
1.1 Fundamental Problems in Industry 1
1.2 The Purpose of Industrial AI 2
1.3 Difference Between AI and Industrial AI 4
1.4 Definition and Meaning of Industrial AI 5
1.5 Key Elements in Industrial AI: ABCDE 7
1.6 CPS Framework for Industrial AI 8
1.7 Technological Elements of CPS Framework 9
1.8 Developing Industrial AI Talents 10
1.9 Training Industrial AI Talents Using Open-source Datasets 10
1.10 Issues in Industrial AI 14
1.11 Conclusion 16
References 17
2 Autonomous Systems and Intelligent Agents 19
Babak Ebrahimi Soorchaei, Arash Raftari, and Yaser Fallah, USA
2.1 Definitions and Scopes 19
2.1.1 What Are Autonomous Systems? 19
2.1.2 What Are Intelligent Agents? 20
2.1.3 Degrees of Autonomy: From Manual to Full Autonomy 20
2.1.4 Overview of Applications and Impact on Various Industries 21
2.2 Core Concepts and Components 21
2.2.1 Artificial Intelligence and Machine Learning 21
2.2.1.1 Basics of AI and ML 22
2.2.1.2 Role in Autonomous Systems 22
Table of Contents
ftoc.indd 9 6/19/2025 2:48:48 PM
x Table of Contents
2.2.2 Perception, Decision-making, and Action 22
2.2.2.1 Perception 22
2.2.2.2 Decision-making Processes, Planning, and Navigation 23
2.2.2.3 Actuation and Interaction with the Environment 24
2.2.3 Communication and Interaction 26
2.2.3.1 Agent Communication Languages and Protocols 26
2.2.3.2 Communication's Role in Coordination and Cooperation and Challenges 26
2.3 Applications and Case Study: Autonomous Vehicle 27
2.3.1 System Architecture in AVs 27
2.3.1.1 Modular (Layered) Architecture 27
2.3.1.2 End-to-End Architecture 28
2.3.2 Perception in AVs 30
2.3.2.1 Sensing 30
2.3.2.2 Object Detection 30
2.3.2.3 Multi-object Tracking 31
2.3.2.4 Semantic Segmentation 32
2.3.2.5 Localization and Mapping 32
2.3.3 Planning and Decision-making 33
2.3.3.1 Path (Route) Planning 33
2.3.3.2 Behavior Planning 33
2.3.3.3 Motion (Trajectory) Planning 33
2.3.4 Control System, Actuation, and Interaction with the Environment 34
2.3.4.1 Lateral Control 34
2.3.4.2 Longitudinal Control 34
2.3.4.3 Actuators 35
2.3.5 Vehicular Communication and Cooperative Intelligence 35
2.3.5.1 Cooperative AI in Autonomous Driving 36
2.4 Challenges and Future Directions 37
References 38
3 Natural Language Processing for Industrial and Systems Engineering 43
Daniel Braun, Germany
3.1 Introduction 43
3.2 Advances and Trends in NLP 44
3.2.1 Large Language Model 44
3.2.2 Unsupervised Approaches 46
3.2.3 Knowledge Graphs 47
3.3 Domain-specific Challenges in ISE 47
3.3.1 Domain-specific Vocabulary 48
3.3.2 Multimodality 48
3.3.3 Complexity 49
3.3.4 Liability and Accountability 49
ftoc.indd 10 6/19/2025 2:48:48 PM
Table of Contents xi
3.4 Applications of NLP in ISE 50
3.4.1 Technology Scouting 50
3.4.2 Analysis of Requirements Documents 51
3.4.3 Analysis of Regulatory and Legal Documents 51
3.4.4 Engineering Education 52
3.5 Outlook 52
3.5.1 Local Inference 53
3.5.2 Multimodality 53
3.5.3 Transparency 53
3.5.4 Retrieval-augmented Generation 53
3.5.5 Reinforcement Learning from Human Feedback 54
References 54
4 Smart Manufacturing, Robotics, and AI Systems 61
Xifan Yao, Huifeng Yan, Jiajun Zhou, Yongxiang Li, and Hongnian Yu, China/UK
4.1 Introduction to Smart Manufacturing 61
4.1.1 Evolution of Manufacturing Paradigms 61
4.1.2 Industry 4.0 62
4.1.3 Key Components of Smart Manufacturing/Industry 4.0 62
4.2 Smart Manufacturing System Integration and Interoperability 63
4.2.1 Smart Manufacturing Reference Model 63
4.2.2 Extended Smart Manufacturing System Integration and
Interoperability 63
4.2.3 Cyber-physical Production Systems 64
4.2.4 Extended CPPS 65
4.2.4.1 Socio-Cyber-physical Production System 65
4.2.4.2 Autonomous Cyber-physical Production Systems 65
4.2.4.3 Human-centric CPPS 65
4.2.4.4 Metaverse CPPS 65
4.2.5 The Intersection of Robotics and AI in Manufacturing 65
4.3 Robotics in Manufacturing 67
4.3.1 The Rise of Robotics in Manufacturing 67
4.3.2 Cobots in Manufacturing 67
4.3.3 AGVs in Manufacturing 68
4.3.4 Chatbots in Design/Manufacturing 69
4.4 AI in Manufacturing 70
4.4.1 Integration of AI with Manufacturing Systems 70
4.4.2 ML Applications in Predictive Maintenance 71
4.4.3 ML Models in Quality Control 72
4.4.4 Optimizing Production Scheduling with AI Algorithms 73
Acknowledgments 74
References 75
ftoc.indd 11 6/19/2025 2:48:48 PM
xii Table of Contents
5 Artificial Intelligence in Healthcare 79
Vinita Gangaram Jansari, USA
5.1 History of Artificial Intelligence in Healthcare 79
5.1.1 Challenges and Limitations 80
5.2 New Age of Healthcare with the Use of AI 81
5.2.1 Large Language Model for Healthcare Domain 81
5.2.2 Generative AI for Healthcare Domain 83
5.3 AI-enabled Medical Devices 85
5.4 Explainable AI for Healthcare 86
5.5 Medical Decision Support Systems 87
5.6 Precision/Personalized Medicine Using AI 88
5.7 Smart Healthcare 89
5.8 Healthcare 5.0 90
5.8.1 Remote Patient Monitoring 91
5.8.2 Assisted Surgery and Surgical Robots 91
5.8.3 Drug Design and Development 92
5.8.4 Assisted Living 93
5.8.5 Cancer Diagnostics and Treatment 94
5.9 Ethics, Bias, and Fairness Constraints 94
5.9.1 Addressing Ethics, Bias, and Fairness Constraints 95
5.10 Concluding Remarks 96
5.11 Future Directions 96
References 97
6 Artificial Intelligence in Cybersecurity for Industrial and Systems Engineering 111
Robin Yeman, Hasan Yasar, Suzette Johnson, and Tracy Bannon, USA
6.1 Introduction to Cybersecurity and Artificial Intelligence for Industrial and
Systems Engineering 111
6.1.1 Application Areas 112
6.1.2 Challenges 113
6.2 Cyber Threat Landscape for CPS 113
6.3 AI in Cybersecurity for CPS 113
6.4 Risk Assessment, Compliance, and Regulatory Considerations 115
6.4.1 Risk Assessment 115
6.4.2 Compliance 115
6.4.3 Regulatory 116
6.5 Threat Detection and Prevention 116
6.5.1 Behavior Analysis 116
6.5.2 Threat Intelligence Integration 117
6.5.3 Security Information and Event Integration 117
6.5.4 Intrusion Detection System 117
6.5.5 Endpoint Detection and Response 117
ftoc.indd 12 6/19/2025 2:48:48 PM
Table of Contents xiii
6.5.6 Log Analysis and Correlation 117
6.5.7 Network Traffic Analysis 118
6.5.8 Vulnerability Scanning and Assessment 118
6.6 Incident Response and Management 118
6.6.1 Preparation 118
6.6.2 Detect and Analyze 119
6.6.3 Contain, Eradicate, and Recover 119
6.6.4 Post-incident Recovery 120
6.7 Anti-phishing 120
6.8 Dependable Authentication 120
6.9 Behavior Analytics 121
6.10 Conclusion 121
References 122
7 Artificial Intelligence in Defense 125
Dylan Schmorrow, Robert Sottilare, Jack Zaientz, John Sauter, Randolph Jones, Charles Newton,
Joseph Cohn, Jon Sussman-Fort, Robert Bixler, Brice Colby, Victor Hung, Jeffrey Craighead,
Le Nguyen, and Ullice Pelican, USA
7.1 Introduction 125
7.2 Ethical Considerations and Challenges 126
7.2.1 Ethical Principles in Defense AI 126
7.2.2 Challenges in Ethical AI Deployment 127
7.2.3 Regulatory and Policy Frameworks 128
7.3 AI-driven Innovations in C2 Systems 129
7.3.1 Planning and COA Generation 130
7.3.1.1 Distributed Scheduling and Task Allocation 130
7.3.1.2 Reinforcement Learning 131
7.3.1.3 Large Language Models 131
7.3.2 Plan Monitoring and Risk Assessment 131
7.3.3 Object Detection and Classification 132
7.4 AI Applications in Uncrewed Systems 132
7.4.1 Military Applications and Benefits 132
7.4.2 AI Technologies in Support of Autonomy 133
7.4.3 Challenges and Future Directions 133
7.4.4 Conclusion 134
7.5 Application of AI to Cyber Operations 134
7.5.1 Representation of Cyber Tactics, Techniques, and Procedures 134
7.5.2 Cyber Attack AI Models 135
7.5.3 Cyber Defense AI Models 136
7.5.4 Cyber Social AI Models 136
7.6 AI-enabled Training and Simulation Systems 137
7.6.1 Training Preparation Process 138
ftoc.indd 13 6/19/2025 2:48:48 PM
xiv Table of Contents
7.6.1.1 Curriculum Development 138
7.6.1.2 Skills Gap Analysis 138
7.6.1.3 Scheduling and Resource Optimization 138
7.6.2 Training Execution Process 139
7.6.2.1 Adaptive Learning 139
7.6.2.2 Simulation and Gamification 140
7.6.2.3 Intelligent Virtual Instructors and Virtual Entities 141
7.6.3 Training Review Process 141
7.6.3.1 Performance Analysis 142
7.6.3.2 Feedback Development 142
7.6.3.3 Interventions for Continuous Improvement 143
7.7 AI-enabled HMI Technologies 143
7.7.1 Intuitive User Interfaces 144
7.7.2 Personalized HMIs 144
7.7.3 Future Directions for Intuitive and Personalized HMIs 145
7.8 Integrating Machine Reasoning and Explanation for Dynamic Decision-making 146
7.9 Responsible AI in Predictive Systems and Medical/Defense Health Readiness 148
7.9.1 ELSI: A Framework for Responsible AI in Defense Healthcare 149
7.9.2 Context of Defense Healthcare Systems 149
7.9.3 Applying AI in Defense Health Systems 149
7.9.4 ELSI Considerations with AI in Defense Health Systems 149
7.9.5 Mitigations 150
7.9.6 Summary 150
7.10 Future Directions 150
7.10.1 Future Directions in C2 Systems 151
7.10.2 Future Directions in UxS 151
7.10.3 Future Directions in Cyber Operations 151
7.10.4 Future Directions in Training and Simulation 152
7.10.5 Future Directions in HMI Technologies 152
7.10.6 Future Directions in Machine Reasoning and Dynamic Decision-making 152
7.10.7 Future Directions in Defense Healthcare 153
7.10.8 Future Directions for the General Application of AI in Defense 153
7.11 Conclusion 154
References 154
8 AI-Driven Management and Modeling Decision Optimization as a Timely Opportunity
at the US Department of Defense 159
Link Parikh, USA
8.1 Why Act Now and Why Engineering Lifecycle and AI? 159
8.1.1 The Global Driver for AI 159
8.1.2 Urgency 160
8.1.3 No Math Gets Us "There" with What We Have Today 160
ftoc.indd 14 6/19/2025 2:48:48 PM
Table of Contents xv
8.1.4 DoD Program-level Challenges 161
8.1.5 Realization and Subsequent Brave Decision by NASA to Outsource
Low Earth Orbit Launch 162
8.1.6 The Automotive Industry 162
8.1.7 What Are the Consequences of Inaction? 162
8.1.8 Culture, Mindset, or Perspective? 162
8.1.9 Beyond the United States 162
8.2 Who Needs to Make Changes in the Ecosystem? 163
8.2.1 Key Participants in Decision Support and Optimization 164
8.2.2 Upgrading DoD Management and Operations to Meet the Needs of AI Injection 165
8.2.3 AI Lifecycle Management 165
8.2.4 Solving the Classified Data Problem with a Data Fabric 166
8.2.5 Sample Application: AI Autonomy 166
8.2.6 AI and Change Management 167
8.3 How to Implement the AI-driven Ecosystems Management and Modeling Regime 167
8.3.1 PPTI Framework Has Assisted Executives for Decades 167
8.3.2 Solutions Based on Insights from the Field 167
8.4 Key Elements of AI-driven Ecosystem Management and Modeling 169
8.4.1 We Must Integrate Program Management and Systems Engineering 170
8.4.2 Harmonize Agile Development with Traditional Acquisition 171
8.4.3 Ensure Requirements Quality for Testable Language 172
8.4.4 Increase Concurrency in Simulation and Training 172
8.4.5 Enhance Cybersecurity with MBSE 173
8.4.6 Embed Human Factors into MBSE 173
8.4.7 Implement Early End-user Participation 173
8.4.8 Prioritize Sustainment Planning from Program Start 173
8.4.9 Understand and Utilize "V and V" and "IV and V" 174
8.4.10 Enable Impact Analysis for All 174
8.4.11 Conduct Rigorous Prototyping Projects with Top Experts 175
8.4.12 Engage Small Businesses in Ideation Diversity: Neuro Diversity 176
8.4.13 Implement Virtual and Augmented Reality (VR/AR) and Metaverse Tools
in Program Engineering 176
8.4.14 Accelerate Source Selection with Remote, Model-based Capabilities 176
8.4.15 Use Integrated, Model-based Compliance 176
8.4.16 Fully Integrate AI Management into the Total Lifecycle 176
8.4.17 NLP and Pretrained COTS Models 176
8.4.18 Machine Learning 177
8.4.19 Deep Learning (DL) and Neural Networks 177
8.4.20 AI Model Accelerators 177
8.4.21 Generative AI Concepts 177
8.4.22 Implement Digital Twins with Digital Threads 177
8.4.23 Leverage Quantum Computing 177
ftoc.indd 15 6/19/2025 2:48:48 PM
xvi Table of Contents
8.4.24 Implement a Data Fabric 178
8.5 Enhance Workforce Development and Mentorship 178
8.5.1 Layer 1: Domain Knowledge 178
8.5.2 Layer 2: Practice Knowledge 178
8.5.3 Layer 3: Tools and Platforms 178
8.5.4 Layer 4: Techniques 179
8.6 When Can We Acquire Dramatic Speed and Precision? 179
8.7 Which Elements Exist in "AI Ecosystem Management and Modeling?" 179
8.7.1 Integrated Object-oriented Model(s) 179
8.7.2 Integrated Modeling with the Right Profile, UAFML 180
8.7.3 Integrated Engineering Lifecycle Platform Foundation 181
8.7.4 Integrated Justifications That Drive Requirements Generation and Traceability 181
8.7.5 Integrated Program Method for Standardization, Improvement, and
Business Continuity 182
8.7.6 Integrated Requirements Generation, Traceability, Management 182
8.7.7 Integrated Requirements Quality Scanner 183
8.7.8 Integrated Portfolio/Project Management and Workflow Management 183
8.7.9 Integrated Change Management 183
8.7.10 Integrated "Commenting" on Program Assets by Stakeholders, Performers
(and AI Agents) 184
8.7.11 Integrated Software Build Automation and Continuous Integration/Delivery 184
8.7.12 Integrated Testing, "V and V," and "IV and V" 185
8.7.13 Integrated Communities of Interest 185
8.7.14 Integrated Automated Publishing 186
8.7.15 Integrated AI Governance Platform 186
8.7.16 Integrated Insights from Program and External Data 187
8.7.17 Integrated ML for Predictivity 188
8.7.18 Integrated DL for Answers and Options to Achieve Decision Optimization 188
8.7.19 Generative AI 188
8.7.20 AI Autonomy 189
8.7.21 Should We Ban All Research on Conscious AI Research? 190
8.8 Sample Applications of Dramatic Speed and Precision 191
8.8.1 Model-based Acquisition and Source Selection 191
8.8.2 Innovation Process from Ideation to Program Injection and DOTMLPF Entry 191
8.8.3 Integrated Ideation 191
8.8.4 Integrated Software Development and Continuous Integration/Delivery 192
8.8.5 Physical Simulation and Digital Twin 192
8.8.6 Capability Summary 192
8.9 AI-driven Ecosystem Management and Modeling Solution and Toolset 192
8.9.1 Foundational Concepts and Canonical View 192
8.9.2 Solution Elements and Platform Architecture 193
8.9.3 Solution Capabilities and Tools 194
8.10 Summary 194
ftoc.indd 16 6/19/2025 2:48:48 PM
Table of Contents xvii
9 Enhancing Cryptocurrency Market Forecasting: Advanced Machine Learning
Techniques and Industrial Engineering Contributions 197
Jannatun Nayeem Pinky and Ramya Akula, USA
9.1 Introduction 197
9.2 Background 199
9.3 Methods 201
9.3.1 Linear Models 201
9.3.1.1 Linear Regression 202
9.3.1.2 Bayesian Ridge Regression 203
9.3.1.3 Support Vector Machine 204
9.3.1.4 Linear Discriminant Analysis 205
9.3.1.5 Multiple Linear Regression 206
9.3.1.6 Logistic Regression 206
9.3.2 Tree-based Models 207
9.3.2.1 Random Forest 208
9.3.2.2 Gradient Boosting 209
9.3.2.3 XGBoost 209
9.3.2.4 LightGBM 210
9.3.3 Probabilistic and Clustering Models 210
9.3.3.1 Naïve Bayes 211
9.3.3.2 Latent Dirichlet Allocation 212
9.3.4 Deep Learning Algorithms 212
9.3.4.1 Multilayer Perceptron 213
9.3.4.2 Long Short-term Memory 214
9.3.4.3 Gated Recurrent Unit 214
9.3.4.4 Bidirectional LSTM 215
9.3.4.5 Bidirectional CNN-RNN Architecture (CGWELSTM) 216
9.3.4.6 DL-GuesS: System Model 218
9.3.4.7 AT-LSTM-MLP Model 218
9.3.5 Ensemble Models 219
9.3.6 Transformer-based Models 220
9.3.7 Large Language Models 223
9.4 Dataset 224
9.5 Evaluation 236
9.5.1 Price Prediction Models 236
9.5.1.1 Regression and Classification Models 236
9.5.1.2 Deep Learning Models 237
9.5.2 Sentiment Analysis Models 242
9.5.2.1 Traditional ML Approaches 242
9.5.2.2 DL Models 245
9.5.3. Hybrid Models 247
9.5.4 Market Dynamics and External factors 251
9.6 Limitations 253
ftoc.indd 17 6/19/2025 2:48:49 PM
xviii Table of Contents
9.7 Future Recommendations 254
9.7.1 Advanced Modeling Techniques and Performance Enhancement 255
9.7.2 Sentiment Analysis and Social Media Integration 256
9.7.3 Market Dynamics and Behavioral Analysis 256
9.8 Conclusion 257
References 258
10 Artificial Intelligence in Aviation 263
Dr. Dimitrios Ziakkas, USA
10.1 Introduction to Artificial Intelligence in Aviation 263
10.1.1 Historical Context and Evolution of AI in Aviation 263
10.1.2 Significance of AI in Aviation 263
10.2 AI in Flight Operations and Training 264
10.2.1 AI in Pilot Training 265
10.2.2 Virtual and Augmented Reality in Pilot Training 265
10.2.3 SiPO and Advanced Air Mobility 266
10.2.4 Predictive Analytics for Aircraft Health Monitoring 266
10.3 AI in Air Traffic Management 267
10.3.1 AI-driven ATC Systems 267
10.3.2 AI in UAS and Drone Management 268
10.3.3 Predictive Analytics in ATM 268
10.4 AI in Airport Operations 268
10.4.1 AI Applications in Airport Security and Surveillance 269
10.4.2 AI-enabled Remote Towers and Ground Operations 269
10.4.3 AI in Predictive Maintenance and Energy Management 269
10.5 AI in Customer Experience and Service 270
10.5.1 AI-driven Virtual Assistants and Chatbots 270
10.5.2 Dynamic Pricing and AI-enhanced Revenue Management 270
10.5.3 AI in Personalized Recommendations and Customer Loyalty Programs 271
10.5.4 AI in Real-time Customer Feedback and Sentiment Analysis 271
10.6 AI in Maintenance and Technical Support 272
10.6.1 Predictive Maintenance and Aircraft Health Monitoring 272
10.6.2 Fault Detection, Diagnosis, and Prognosis 273
10.6.3 AI in Supply Chain and Spare Parts Management 273
10.6.4 AI in Automated Technical Support Systems 274
10.7 Human Factors and AI Integration 274
10.7.1 Human-AI Interaction in Aviation 274
10.7.2 Training and Skill Development for Operators 275
10.8 Ethical and Regulatory Challenges 275
10.9 AI Case Studies and Future Prospects 276
10.9.1 Successful AI Implementation in Aviation 276
10.9.2 Challenges and Lessons Learned from AI Integration 277
10.10 The Future of AI in Aviation 278
References 278
ftoc.indd 18 6/19/2025 2:48:49 PM
Table of Contents xix
11 Enhancing Engineering Education: A Multimodal Approach to Personalization
and Adaptation Using Artificial Intelligence in Game-based Learning 281
Roger Azevedo, Daryn Dever, and Megan Wiedbusch, USA
11.1 Context: Challenges in Engineering Education 281
11.2 GBLEs for Engineering Education: Are They Effective? 283
11.3 Personalization and Adaptivity in GBLEs 284
11.4 Personalization and Adaptivity in GBLEs for Engineering Education:
Are They Effective? 284
11.5 Augmenting Personalization and Adaptivity in GBLEs in Engineering Education with
Multimodal Trace Data 286
11.6 AI Techniques for Handling Multimodal Approaches to Individualization and
Adaptation 288
11.7 Essential SRL Processes from Multimodal Trace Data with GBLEs in Engineering
Education 289
11.7.1 Goal Setting 290
11.7.2 Self-monitoring 291
11.7.3 Strategic Planning 292
11.7.4 Self-reflection 292
11.7.5 Time Management 293
11.7.6 Help-seeking 295
11.7.7 Resource Management 296
11.8 Open Questions, Future Directions, and Conclusions 297
Acknowledgments 299
References 299
12 Securing Artificial Intelligence Systems in the Era of Large Language Models 307
Carmen-Gabriela Stefanita, USA
12.1 The Need for an Artificial Intelligence Risk Management Framework in an Evolving Artificial
Intelligence Landscape 307
12.1.1 Threats of Cyberattacks Against AI Require Proactive Measures 307
12.1.2 Security Risks Associated with Private, Public, or Hybrid Cloud Implementation 308
12.1.3 Business, Legal and Cybersecurity Risks 310
12.2 Security for AI Threat Model 313
12.2.1 Conventional Threat Model Foundation 314
12.2.2 Conventional Threat Management 314
12.2.3 Conventional Threats Take on New Meanings 315
12.2.4 New Threat Landscape: Generative AI Specific Risks 316
12.3 Implementing a Security for AI Framework 317
12.3.1 Matrix of Security Controls 318
12.3.2 Enforcement of Security Controls 319
12.3.3 Security Controls Extended to LLMs 320
12.4 Conclusion 323
Acknowledgments 324
Notes 324
ftoc.indd 19 6/19/2025 2:48:49 PM
xx Table of Contents
13 Responsible Artificial Intelligence Applications for Social Good 327
Ozlem Garibay and Brent Winslow, USA
13.1 Introduction 327
13.2 Ethical Aspects of AI for Social Good Applications 328
13.2.1 Definitions, Applications, and Mitigation Strategies for Bias and Fairness 328
13.2.2 Definitions, Applications, and Mitigation Strategies for Interpretability and
Explainability 330
13.2.3 Definitions, Applications, and Mitigation Strategies for Privacy and Security 331
13.3 AI Applications for Healthcare 331
13.3.1 Remote Health Monitoring and Intervention 332
13.3.2 Drug Discovery and Personalized Medicine 332
13.3.3 Epidemic Prediction and Management 333
13.3.4 AI in Medical Imaging and Diagnostics 334
13.3.5 Ethical Considerations in Healthcare AI 334
13.4 AI for Environmental Sustainability 335
13.4.1 Introduction 335
13.4.2 AI for Climate Change Monitoring and Modeling 336
13.4.3 AI for Sustainable Agriculture and Food Production 336
13.4.4 AI for Wildlife Conservation 337
13.4.5 AI for Renewable Energy Optimization 337
13.4.6 Ethical Considerations in Environmental AI 337
13.5 AI for Education and Accessibility 338
13.5.1 Pe
Dai-Yan Ji, Hanqi Su, Takanobu Minami, and Jay Lee
Center for Industrial Artificial Intelligence, Department of Mechanical Engineering, University of Maryland, College Park, MD, USA
Digital transformation is a journey to develop data-centric operations with great visibility and productivity. Through the fourth industrial revolution efforts, companies can generate substantial financial and operational advantages, improving productivity and increasing customer satisfaction. The fundamental problem is digital transformation is to address productivity issues on flexibility, quality, and speed. Flexibility is achieved through the collaboration of machines and humans, forming a responsive, on-demand production system capable of adapting in real time. Quality is enhanced through real-time plant monitoring and the application of just-in-time maintenance. The degradation of manufacturing equipment and tools affects product quality and reduces productivity by increasing the occurrence of unplanned downtime. Thus, intelligent prognostic and health management (PHM) tools are essential for timely maintenance, guaranteeing the provision of high-quality products, minimizing unplanned downtime, and enhancing customer satisfaction. Speed is attained by improving interconnectivity between different sectors within the manufacturing process, impacting the entire product lifecycle. The synchronization and integration of data across companies, both vertically and horizontally, promotes transparency and cohesion across departments and functions, greatly boosting manufacturing efficiency.
However, many production sites have found it difficult to quickly implement these technologies on a broad scale due to three major problems including:
Classical machine learning (ML) has created broad use cases to address these problems across manufacturing, such as predicting and preventing defects and failures. But generative AI is just beginning to be explored. Industrial AI emerges as a potent solution to these difficulties, providing substantial benefits for manufacturing improvements by enhancing the quality, structure, and vital aspects of manufacturing processes. The ability to train machines on large and unstructured datasets unlocks an entire suite of knowledge bases that can ultimately mimic human problem-solving capabilities using domain-based and data-rich sources in manufacturing processes. By standardizing workflows with data, industrial AI promotes the rapid accumulation of experience and aids in effective knowledge transfer. The strategic use of data not only uncovers latent problems in manufacturing systems but also supports transparent management of equipment health, stabilizes process parameters, and boosts overall efficiency. Furthermore, data serve as a medium for increasing user value, improving the functionality and reliability of products and equipment, enhancing operational efficiency, and bolstering the sustainable profitability of enterprises. Thus, incorporating industrial AI into manufacturing tackles these three critical problems through the application of data-driven insights and automation. It addresses discipline problems by boosting workforce competency and management skills with intelligent insights. System problems are alleviated by enhancing equipment design, manufacturing processes, and system integration, thereby making the entire manufacturing process more transparent and effective. Additionally, intrinsic problems associated with customer value creation are solved by evolving business models and technologies, which foster collaborative innovation and continuous service enhancement. In summary, the necessity for AI intervention in the industry is highlighted by these challenges, demonstrating industrial AI's vital role in driving manufacturing excellence.
The interpretation of industrial AI systems varies between academic and industrial sectors. Definitions of industrial AI as a unique technology or solution sometimes overlook critical questions such as the precise settings of intelligence required in industrial environments, the unsolved problems and challenges that current methods do not resolve, and the function of AI in overcoming these deficiencies. Furthermore, the role of industrial AI should not be limited to merely displaying the capabilities of data scientists in revolutionizing conventional industrial models. Instead, it should concentrate on uncovering and addressing the hidden problems within industrial ecosystems.
Industrial AI goes beyond merely adapting general AI technologies to industrial environment settings. The distinct characteristics of these settings - such as their fragmented nature, individualized challenges, and need for specialization - demand an integrated approach that merges computer science, AI, and domain-specific knowledge. Unlike conventional rule-based or mechanistic approaches, the true strength of data-driven industrial intelligence lies in its predictive analytics capabilities. These capabilities are founded on insights and evidence derived from data that facilitate the creation of intelligent management tools for tackling previously unknown challenges. Additionally, it assists in revealing complex interdependencies, thereby fostering the generation of new knowledge and supporting the evolution of a system that intelligently adapts and improves over time.
Challenges of industrial systems (Lee et al. 2019) can be generally divided into two main areas as depicted in Figure 1.1. Visible problems include issues such as machine failures, reduced production yield, and deteriorating product quality. On the other hand, invisible challenges encompass aspects like machine wear, component deterioration, and inadequate lubrication. Commonly identifiable problems such as equipment malfunctions, quality defects, and productivity declines are typically managed through continuous improvements and standardized practices, reflecting the conventional approach to manufacturing (located in the lower left quadrant). Modern manufacturers are increasingly adopting AI algorithms to gain a competitive advantage. This approach is directly toward designing, producing, and delivering high-quality products more rapidly than competitors, thereby focusing on problem-solving (located in the upper left quadrant). Recent efforts by various companies have led to the development of new methods and techniques aimed specifically at addressing invisible challenges (positioned in the lower right quadrant). The adoption of an industrial AI-driven approach offers the potential to open up new opportunities for value creation in smart manufacturing, especially in environments that are dynamic and unpredictable (found in the upper right quadrant). Extensive implementation of industrial AI's fundamental components not only aids in addressing visible problems but also in avoiding invisible ones.
Figure 1.1 Visible and invisible problems in industrial systems and opportunities for industrial AI.
Industrial AI also plays a critical role in achieving the 3W's of smart manufacturing, namely work reduction, waste reduction, and worry-free manufacturing. The idea of "worry" in modern manufacturing systems is frequently derived from invisible difficulties such as machine degradation, process variation, and operation uncertainties. To address these difficulties, it is critical to implement industrial AI technologies in a systematic approach. Furthermore, the aim of reducing workloads and waste may be achieved by identifying the visible aspects of these difficulties and proactively resolving their possible future consequences using adaptive AI modules.
There are clear differences (Lee 2020) between AI in general and industrial AI. These differences extend beyond the domain of application and include differences in functional requirements and algorithmic techniques. Before diving into these differences, it is necessary to define both terms. AI is a field of cognitive science that includes considerable study in image analysis and machine vision, natural language processing (NLP), robotics, and ML, among other topics. Despite its intense perspective, AI is usually veiled in mystery, with critics citing a lack of verifiable proof to back up its usefulness, repeatability, and financial return on investment in an industrial environment.
Conversely, industrial AI is described as a systematic discipline for the creation, validation, and rapid deployment of ML algorithms customized for industrial use cases, resulting in sustained performance. This domain focuses on developing intelligent systems for...
Dateiformat: ePUBKopierschutz: Adobe-DRM (Digital Rights Management)
Systemvoraussetzungen:
Das Dateiformat ePUB ist sehr gut für Romane und Sachbücher geeignet – also für „fließenden” Text ohne komplexes Layout. Bei E-Readern oder Smartphones passt sich der Zeilen- und Seitenumbruch automatisch den kleinen Displays an. Mit Adobe-DRM wird hier ein „harter” Kopierschutz verwendet. Wenn die notwendigen Voraussetzungen nicht vorliegen, können Sie das E-Book leider nicht öffnen. Daher müssen Sie bereits vor dem Download Ihre Lese-Hardware vorbereiten.Bitte beachten Sie: Wir empfehlen Ihnen unbedingt nach Installation der Lese-Software diese mit Ihrer persönlichen Adobe-ID zu autorisieren!
Weitere Informationen finden Sie in unserer E-Book Hilfe.
