Search

Browse Subject Areas

For Authors

Submit a Proposal

Explainable Artificial Intelligence

Bridging Concepts, Applications, and Future Challenges

Edited by Preethi Nanjundan, Sachi Nandan Mohanty, Shu Hu and Harish Garg
Series: Studies in Computational Intelligence and Smart Technologies
Copyright: 2026   |   Expected Pub Date:2026/04/30
ISBN: 9781394357758  |  Hardcover  |  
1152 pages

One Line Description
Unlock the power of transparent, trustworthy AI with this essential two-volume reference, where leading global experts deliver actionable frameworks and real-world strategies to make high-stakes artificial intelligence explainable, compliant, and reliable.

Audience
AI and machine learning engineers, data scientists, researchers, graduate students, industry professionals, and policymakers in computer science, data science, healthcare, and finance interested in ethical and explainable AI systems

Description
Explainable AI (XAI) has emerged as a pivotal area of research and innovation in response to the growing complexity and opacity of modern AI systems, particularly deep learning models. As AI is increasingly deployed in high-stakes domains such as healthcare diagnostics, financial forecasting, criminal justice, and autonomous systems, the need for models that can justify their decisions in human terms has become a necessity. These volumes explore one of the most critical frontiers in artificial intelligence: the need for transparent, understandable, and trustworthy AI systems. Providing a well-rounded introduction to the core principles of explainable AI (XAI), they examine current tools and methodologies and discuss real-world implementations across multiple domains. They explore a wide range of topics, including foundational frameworks, human-centric perspectives, and multi-industry implementation strategies, presenting a complete picture of this emerging technology. Bringing together insights from leading researchers and practitioners across the globe, these volumes serve as a comprehensive reference for both academic and professional audiences. This two-volume set situates itself at the intersection of these developments, offering readers a timely and practical guide to navigating the challenges and opportunities of explainable artificial intelligence.
Readers will find the volume:
• Offers a balanced mix of foundational concepts and practical applications of explainable AI across various domains;
• Features contributions from international experts, providing diverse insights into XAI trends;
• Addresses growing demand for ethical, transparent AI systems in line with current regulatory and societal concerns;
• Includes recent advances, frameworks, and case studies, making it a valuable reference for both academia and industry;
• Explores upcoming challenges and innovations in XAI, preparing readers for the next wave of AI development.

Back to Top
Author / Editor Details
Preethi Nanjundan, PhD is an Associate Professor in the Department of Data Science at Christ University and the Head of Research at the Lavasa Campus, Pune, India. With over 20 years of research and teaching experience, he has authored more than 70 papers in international conferences and journals, contributed to multiple books, and published five of her own. Her research interests include machine learning, natural language processing, the semantic web, and neural networks.

Sachi Nandan Mohanty, PhD is an Associate Professor in the School of Computer Science and Engineering at the Vellore Institute of Technology, Andhra Pradesh, India. He has published 42 books, and more than 120 articles in international journals of repute. His research interests include data mining, big data analysis, cognitive science, fuzzy decision making, brain-computer interface, and computational intelligence.

Shu Hu, PhD is an Assistant Professor in the Department of Computer and Information Technology and the Director of the Purdue Machine Learning and Media Forensics Lab at Purdue University, USA. He has more than 100 publications to his credit, including numerous articles in international journals and conferences of repute. His research focuses on machine learning, media forensics, and computer vision.

Harish Garg, PhD is an Associate Professor in the School of Mathematics at the Thapar Institute of Engineering and Technology, Patiala, India. He has authored more than 280 research papers and edited several books. His research interests encompass computational intelligence, fuzzy decision-making, multi-criteria decision analysis, and reliability analysis.

Back to Top

Table of Contents
Preface
Part I: Foundations and Principles of Explainable AI
1. Introduction to Explainable AI: Concepts and Principles
Preethi Nanjundan, Prajwal Singh and Jossy P. George
1.1 Introduction to Explainable AI (XAI)
1.1.1 The Need for Explainability
1.1.2 The Black-Box Problem in AI
1.1.3 The Trade-Off between Accuracy and Interpretability
1.1.4 Goals of Explainable AI
1.2 The History and Evolution of Explainable AI
1.2.1 Early Artificial Intelligence: Expert Rule-Based Models and Symbolic Systems (1950s–1980s)
1.2.2 The Development of Black-Box Models and Machine Learning (1990s–2010s)
1.2.3 The Emergence of Explainable AI (2015–Present)
1.3 Key Explainability Techniques in AI
1.3.1 Intrinsic Explainability: Models Designed for Interpretability
1.3.2 Post-Hoc Explainability: Techniques for Black-Box Models
1.3.2.1 SHAP (SHapley Additive ExPlanations)
1.3.2.2 LIME (Local Interpretable Model-Agnostic Explanations)
1.3.2.3 Grad-CAM (Gradient-Weighted Class Activation Mapping)
1.3.2.4 Counterfactual Explanations
1.4 Ethical Implications of Explainable AI
1.5 Real-World Applications of Explainable AI
1.5.1 Healthcare and Medical Diagnosis
1.5.2 Finance and Banking
1.5.3 Legal and Criminal Justice
1.5.4 Autonomous Vehicles
1.5.5 Human Resources and Hiring
1.5.6 Retail and E-Commerce
1.5.7 Cybersecurity and Threat Detection
1.6 Challenges and Limitations of Explainable AI
1.6.1 Navigating the Accuracy–Interpretability Trade-Off
1.6.2 Model Complexity and Scalability
1.6.3 Ethical and Bias Concerns
1.6.4 Regulatory and Legal Challenges
1.6.5 Future Directions in Addressing XAI Challenges
1.7 Future Trends in Explainable AI
1.7.1 Causal Explainability in AI
1.7.2 Human-Centric Explainability
1.7.3 AI Governance and Global Regulations
1.7.4 Hybrid AI Models for Improved Transparency
1.7.5 The Road Ahead
1.8 Conclusion
References
2. Advancements in Explainable AI: A Historical Perspective
Ruchira Deokar, Preethi Nanjundan and Jossy P. George
2.1 Introduction
2.2 Historical Background
2.2.1 Decision Trees and Rule-Based Systems
2.2.2 Limitations of Initial Models
2.2.3 Transition to Black-Box Models
2.2.4 Renewed Focus on Transparency
2.3 Key Milestones in XAI Development
2.4 Current XAI Techniques
2.5 Recent Advances in XAI Research
2.5.1 Deep Learning and Explainability
2.5.2 Advances in Causal Inference for Explainability
2.5.3 User-Centered Design in XAI
2.6 Challenges and Limitations of XAI
2.6.1 Trade-Offs between Accuracy and Interpretability
2.6.2 Complexity of Models and Explanations
2.6.3 Ethical Considerations
2.7 Future Directions in XAI
2.7.1 Emerging Trends
2.7.2 The Role of Regulation and Standards
2.7.3 Future Research Opportunities and Challenges
2.8 Conclusion
Bibliography
3. XAI: The Evolution of Explainable AI Techniques
S. Mohana Saranya, T. Suganya, Prasanndh Raaju M. R., Roshni Magesh, Gokila S. and Kavyadarshini M.
3.1 Introduction
3.1.1 Overview of Explainable AI
3.1.2 Need for Explainability in AI
3.1.3 Historical Context
3.2 Foundational Concepts in Explainability
3.2.1 Foundational Concepts in Explainability
3.2.2 Transparency in Early AI Models
3.2.3 Complexity vs. Accuracy Trade-Off
3.3 The Rise of Black–Box Models
3.3.1 Deep Learning Boom
3.3.2 Challenges in Understanding Black-Box Models
3.3.3 Turning Key Points
3.4 Early XAI Techniques
3.4.1 Rule Based Explanation
3.4.2 Feature Importance Techniques
3.4.3 Decomposition Method
3.5 Model-Agnostic XAI Techniques
3.5.1 LIME (Local Interpretable Model-Agnostic Explanations)
3.5.2 SHAP (Shapley Additive Explanations)
3.5.3 Counterfactual Explanation
3.5.4 Partial Dependence Plots (PDPs)
3.6 Deep Learning-Specific XAI Techniques
3.6.1 Saliency Maps and Grad-CAM
3.6.2 Attention Mechanisms in NLP
3.6.3 Layer-Wise Relevance Propagation (LRP)
3.7 XAI in Reinforcement Learning and Generative Models
3.7.1 Interpretable RL Policies
3.7.2 XAI for GANs (Generative Adversarial Networks)
3.7.3 Adversarial Explanations
3.8 Evaluating XAI Techniques
3.8.1 Evaluation Metrics for XAI
3.8.2 User–Centric Evaluation
3.8.3 Quantitative vs. Qualitative Evaluation
3.9 Conclusion
References
4. The Evolution and Advancements of Explainable AI (XAI)
Techniques in Modern Applications
Ruchira Deokar, Preethi Nanjundan and Jossy P. George
4.1 Introduction
4.2 Emerging Trends in Explainable AI
4.2.1 Integration of XAI with Multimodal AI Systems
4.2.2 Personalized Explanations
4.2.3 Interactive and Real-Time Explanation Systems
4.2.4 Ethical and Fairness-Centric XAI
4.2.5 Integration with Edge Computing and IoT
4.2.6 Advances in Natural Language Explanations
4.3 Challenges Facing Explainable AI
4.3.1 Balancing Complexity and Simplicity
4.3.2 Quantifying Explainability
4.3.3 Scalability in Large-Scale Systems
4.3.4 Domain-Specific Constraints
4.3.5 Resistance to Adoption
4.3.6 Adversarial Exploitation
4.3.7 Regulatory and Legal Challenges
4.4 The Road Ahead
4.4.1 Develop Unified Frameworks for Creating and Evaluating Explanations
4.4.2 Promote Education and Awareness
4.4.3 Invest in Research Prioritizing the Dual Goals of Performance and Explainability
4.4.4 Foster International Collaboration to Tackle Regulatory and Ethical Challenges Collectively
4.5 Conclusion
References
5. Human-Centric Design in Explainable AI Systems: Frameworks, Applications and Challenges
Stuti Jalan and Lalatendu Kesari Jena
5.1 Introduction
5.2 Transition from EAI to Human Centric-EAI (HCEAI)
5.2.1 Principles for Developing HCEAI Systems
5.3 Theoretical Frameworks for Human-Centred EAI
5.3.1 Theoretical Frameworks Underpinning Human-Centric Principles
5.3.2 Theoretical Frameworks for Evaluating HCEAI Systems
5.4 Applications of Human-Centric Designs in EAI
5.5 Challenges for Human–Centric Designs in EAI
5.6 Future Directions and Conclusion
References
6. A Human-Centered Approach to Designing Explainable AI
Systems for Transparency and Trust
Peter V. Muttungal, Jossy P. George, Nishi Priya and Benny Godwin J. Davidson
Introduction
Benefits and Implementation of XAI
Explainable AI Techniques
Human-Centric Measures
Human-Centric Design
Core Challenges in Human-Centric Design
Explainable AI and Human-Centric Design
Grounding XAI in Human Behavior
Developing the Human-Centric XAI Framework
Evaluating User Interaction Experiences
Moving from Post Hoc Measures
Meaningful XAI-Future of XAI
Conclusion
References
7. Making AI Understandable: The Power of Explainability
Pankaj Kumar Madhukar
7.1 Introduction to Explainable AI: Key Concepts
7.1.1 Key Concepts of Explainable AI
7.1.2 Key Pillars of AI Explainability
7.2 The Evolution of Explainable AI Techniques
7.2.1 Early Stages: Simple and Interpretable Models
7.2.2 Rise of Complex Models and the Black-Box Problem
7.2.3 Emergence of Explainability Techniques
7.2.4 The Modern Era: Post-Hoc Explainability and Beyond
7.2.5 Future Directions: Hybrid Models and Responsible AI
7.3 Trust and Accountability at the Core
7.3.1 Why Trust Matters in AI
7.3.2 Accountability in AI Systems
7.3.3 The Consequences of Lacking Trust and Accountability
7.3.4 Establishing Trust and Accountability in AI
7.4 Ethical Foundations of Explainable AI: Key Considerations
7.4.1 Key Ethical Considerations in Explainable AI
7.4.2 Mitigating Ethical Risks in Explainable AI
7.5 Explainable AI in Diverse Domains
7.5.1 Healthcare
7.5.2 Retail and E-Commerce
7.5.3 Energy and Utilities
7.5.4 Education
7.5.5 Finance
7.6 Human-Centric Design in Explainable AI Systems
7.6.1 Key Principle
7.6.2 Understanding the User Context
7.6.3 Methods for Human-Centric XAI Design
7.7 Interpretable Machine Learning Models for Cross-Domain
Analysis
7.7.1 Techniques for Interpretability
7.8 Explainable AI in Healthcare: Enhancing Patient Understanding
7.9 Explainable AI in Finance: Ensuring Transparency and Compliance
7.10 Understanding Bias and Fairness in AI Models
7.10.1 Types of Bias in AI Models
7.10.2 Fairness in AI Models
7.11 Explainable AI in Legal and Regulatory Compliance
7.12 Explainable AI in for Autonomous Systems: Ensuring Safety and Reliability
7.13 Addressing Privacy Concerns in Explainable AI
7.14 Explainable AI in Customer Service: Improving User
Experience
7.15 Explainable AI Education: Supporting Learning and Decision-Making
7.16 Explainable AI in Social Media: Enhancing User Trust and Engagement
7.17 Explainable AI in Environmental Monitoring: Insights for Sustainability
7.18 Explainable AI in Supply Chain Management: Enhancing
Efficiency and Visibility
7.19 Explainable AI for Risk Assessment and Decision Support
7.20 Future Trends and Challenges in Explainable AI
7.20.1 Emerging Trends in Explainable AI
7.20.2 Challenges Facing Explainable AI
Conclusion
References
Part II: Explainable AI in Domain-Specific Applications
8. Smart Healthcare System Evolution: A Comprehensive Review
K. Prableen, G. Ritu and S. Manik
8.1 Introduction
8.1.1 Smart Healthcare Parameters
8.1.2 Statistics of Smart Healthcare
8.2 Evolutionary Techniques
8.3 Related Works and Publication Trends of Articles
8.4 Need of XAI Based Smart Healthcare System
8.5 Design of Smart XAI Based Healthcare System
8.6 Challenges of XAI in Healthcare
Conclusion
Consent for Publication
Acknowledgements
References
9. Explainable Artificial Intelligence in Finance: Transparency and Compliance
Pooja Devi and Rakesh Kumar
9.1 Introduction
9.1.1 Regulatory Frameworks for Explainable AI (XAI)
9.1.2 Key Regulatory Requirements
9.1.2.1 GDPR Stands for General Data Protection Regulation
9.1.2.2 Article 22
9.1.2.3 European Commission’s AI Act
9.1.2.4 The FCA Stands for the Financial Conduct Authority
9.1.3 Key Components of XAI
9.1.4 Background of Explainable AI in Finance
9.1.5 Need for Explainable AI (XAI) in Finance
9.1.6 Challenges for XAI in Finance Sector
9.2 Methodology of XAI
9.2.1 Post-Hoc Explainability
9.2.2 Intrinsic Explainability
9.3 Case Study of Data Rails AI Tool
9.4 Success Story of Accounting Firm Named Think Plumb
9.5 Conclusion
References
10. A Comprehensive Survey on Advanced CNN Based Approaches for Cardiac Abnormality Detection
Sowmya D., Vaitheki K. and Anousouya Devi M.
10.1 Introduction
10.2 Related Works
10.2.1 Deep Learning Methods
10.2.1.1 Convolutional Neural Network (CNN)
10.2.2 Feed Forward Neural Network
10.2.3 Recurrent Neural Network
10.2.4 Generative Adversarial Network (GAN)
10.2.5 Artificial Neural Network (ANN)
10.2.6 Multi-Layer Perceptron (MLP)
10.2.7 Back Propagation Neural Network
10.2.8 Deep Belief Network
10.2.9 Machine Learning Methods
10.2.10 Logistic Regression
10.3 Discussion
10.4 Conclusions
References
11. Sentiment Analysis of Product Reviews for Enhanced
Customer Feedback
Lalitha Somasundharam, Chinthala Harsha Vardhan, Sagi Bhimeswara Akshay Varma and Vandrapu Siva Ganesh
11.1 Introduction
11.2 Literature Review
11.3 BERT and Transformer Models Comparison
11.4 Data Collection
11.5 Data Preprocessing
11.6 Implementation and Evaluation
11.7 Model Architecture
11.8 Training and Evaluation
11.9 Prediction and Deployment
11.10 Results
11.11 Future Work
11.12 Conclusion
11.13 Acknowledgment
References
12. Explainable AI in Education: Enhancing Learning and Informed Decision-Making
Vasim Ahmad and Rakesh Kumar
12.1 Introduction
12.2 Key Concepts of Explainable AI
12.2.1 Key Differences between Explainable and Non‑Explainable AI
12.3 Regulatory and Ethical Landscape
12.3.1 Ethical Considerations for AI Use in Educational Settings
12.3.2 Key Requirements for Transparency and Decision-Making
12.3.3 Data Privacy and Security Concerns in Education
12.4 Ethical Considerations for AI Use in Educational Settings
12.5 Cases of Explainable AI in Education
12.5.1 Case Studies and Illustrations
12.5.2 Student Performance Evaluation
12.5.3 Real-World Applications and Benefits
12.5.4 Administrative Decision
12.6 Techniques for Explainable AI
12.7 Challenges in Implementing Explainable AI
12.8 Conclusion
References
13. Explainable AI in Customer Service: Improving User Experience
Jossy P. George, Peter V. Muttungal and Benny Godwin J. Davidson
Introduction
Features of the Service Industry
Transition of the Service Industry
Understanding the 21st Century Consumer
Need for Explainable AI in the Service Industry
Models of XAI
Analysis and Prediction of XAI
Case Study of XAI in Different Service Sectors
Challenges of XAI
Future Implications of the XAI Systems
Conclusion
References
14. Diabetic Retinopathy Classification Using Transfer Learning with Ensemble Methods
Meghana Choudhary
14.1 Introduction
14.2 Related Works
14.3 Methodology
14.3.1 Dataset Collection and Description
14.3.2 Data Preprocessing
14.3.2.1 Grey Scale Cropping
14.3.2.2 Circular Cropping
14.3.2.3 Ben Graham’s Filter
14.3.3 Data Augmentation
14.3.4 Model Development
14.4 Results and Discussion
14.5 Conclusion and Future Work
Bibliography
15. Explainable AI in Social Media: Enhancing User Trust and Engagement
Ruchira Deokar, Preethi Nanjundan and Lijo Thomas
15.1 Introduction
15.2 Theoretical Background of XAI
15.2.1 Defining XAI
15.2.2 Historical Evolution
15.3 Applications of XAI in Social Media
15.3.1 Personalized Recommendations
15.3.2 Content Moderation
15.3.3 Sentiment Analysis and Trend Detection
15.4 Enhancing User Trust
15.4.1 Transparency and Accountability
15.4.2 Ethical AI Practices
15.4.3 User Empowerment
15.5 Challenges in Implementing XAI in Social Media
15.5.1 Computational Complexity
15.5.2 Balancing Interpretability and Accuracy
15.5.3 Privacy Concerns
15.6 Case Studies
15.6.1 Facebook’s Explainable Recommendations
15.6.2 Counterfactual Explanations on Twitter
15.7 Future Directions
15.7.1 Advanced XAI Techniques
15.7.2 Regulation and Standardization
15.7.3 User-Centric Design
15.8 Conclusion
Bibliography
16. Explainable AI for Advanced Natural Calamity Prediction: Integrating Satellite Imagery with ConvLSTM Networks
Akash R., Mouli Krishna V., Varun Anto Priyans R., Vidhya V. and Nirmala Venkatachalam
16.1 Introduction
16.2 Background and Motivation
16.2.1 The Growing Threat of Natural Disasters
16.2.2 ConvLSTM Networks
16.2.3 Explainable AI (XAI)
16.2.4 Current Limitations of Traditional Models
16.2.5 Importance of Interpretable Models in Disaster Management
16.3 Methodology
16.3.1 Data Acquisition
16.3.2 Preprocessing
16.3.3 ConvLSTM Architecture
16.3.4 Integration of Explainable AI (XAI)
16.4 Applications
16.4.1 Flood Prediction
16.4.2 Landslide Prediction
16.4.3 Earthquake Prediction
16.4.4 Disaster Response
16.5 Challenges and Solutions
16.5.1 Quality of Data
16.5.2 Interpretability of the Model
16.5.3 Computational Complexity
16.5.4 Computational Complexity
16.6 Future Directions
16.6.1 Integration with Climate Models
16.6.2 Improved Data Fusion
16.6.3 Autonomous Systems
16.6.4 Community Engagement
16.7 Conclusion
References
17. Leveraging Explainable AI for Optimizing Edge Computing
in IoT-Based Healthcare: Foundations, Innovations, and Applications
Siraj Mohamed, M. Azees, D. S. S. N. Raju, Sai Babu Veesam and D.D. Siva Prasad
17.1 Introduction
17.2 Technology Concerned
17.2.1 Cloud Computing
17.2.2 Fog Computing
17.2.3 Edge Computing
17.2.4 Blockchain
17.2.5 Internet of Things
17.3 Future Access
17.4 Research Problems
17.5 Accomplishments of Background Study and Related Work
17.5.1 Significance of Healthcare Data
17.5.2 Growth of Healthcare Data
17.5.3 Preservation of Healthcare Data
17.6 Emerging Edge Technology in Smart Healthcare Systems
17.6.1 Challenges Faced by Health Care Data with Cloud
17.6.2 Influence of Artificial Intelligence in Edge Computing
17.6.3 Influence of Machine Learning (ML) Algorithms in Edge Computing
17.6.4 Applications of ML Based Algorithms for Healthcare Data Analysis
17.7 Discussion and Summary
References
18. Empowering Fitness with XAI: A Cloud-Centric Framework
for Calorie Intake and Burn Prediction
Geetika Munjal, Vaibhav Sharma, Priyanshi Chauhan, Nupur Bhardwaj and Naman Mittal
Introduction
Literature Review
Need of Cloud-Based System
XAI Its Applications in Healthcare
Proposed Framework
Unboxing Most Contributing Features Using XAI
Local Interpretable Model-Agnostic Explanations
Conclusion and Future Scope
Bibliography
19. Explainable AI in Environmental Monitoring: Insights for Sustainability
Preethi Nanjundan, Lijo Thomas and Arushi Sharma
19.1 Introduction to Explainable AI (XAI) in Environmental Monitoring
19.1.1 Definition and Importance of Explainable AI (XAI)
19.1.2 Role of AI in Environmental Sustainability
19.1.3 Challenges of Black-Box AI in Ecological Decision-Making
19.2 Key Applications of XAI in Environmental Monitoring
19.2.1 Air Quality Monitoring and Pollution Control
19.2.2 Water Resource Management and Contamination Detection
19.2.3 Deforestation and Land Use Change Detection
19.2.4 Wildlife Conservation and Biodiversity Protection
19.2.5 Climate Change Modeling and Prediction
19.3 Techniques and Methods for Explainable AI in Environmental Science
19.3.1 Rule-Based AI and Decision Trees
19.3.2 SHAP (Shapley Additive Explanations) and LIME (Local Interpretable Model-Agnostic Explanations)
19.3.3 Feature Importance and Attention Mechanisms in Neural Networks
19.3.4 Bayesian Networks and Probabilistic Models for Uncertainty Estimation
19.4 Data Sources and Integration for XAI under Environmental Authority
19.4.1 Satellite and Remote Measurement Data
19.4.2 IoT Sensors and Real-Time Monitoring Systems
19.4.3 Open Data Repositories and Government Datasets
19.4.4 Challenges in Data Quality, Bias, and Ethical Considerations
19.5 Case Studies on Explainable AI for Sustainability
19.5.1 AI-Powered Air Quality Forecasting in Urban Areas
19.5.2 Machine Learning for Water Contamination Detection
19.5.3 XAI in Forest Fire Prediction and Prevention
19.5.4 Transparent AI Models for Sustainable Agriculture
19.6 Ethical, Legal, and Social Implications of XAI in Sustainability
19.6.1 Fairness and Bias in Environmental AI Models
19.6.2 Regulatory Frameworks for Transparent AI in Ecology
19.6.3 Public Trust and Stakeholder Engagement in AI-Driven Decisions
19.7 Future Trends and Innovations in Explainable AI for Environmental Monitoring
19.7.1 Advances in AI Transparency and Interpretability
19.7.2 Integration of AI with Citizen Science and Community Monitoring
19.7.3 Role of Quantum AI and Edge Computing in Sustainability
19.7.4 AI for Circular Economy and Carbon Footprint Reduction
19.8 Conclusion and Policy Recommendations
19.8.1 Key Takeaways from Transparent AI in Environmental Sustainability
19.8.2 Policy Suggestions for AI Governance in Ecology
19.8.3 Future Research Directions and Collaborative Opportunities
Bibliography
20. Explainable AI in Supply Chain Management: Enhancing
Efficiency and Visibility
Preethi Nanjundan, Lijo Thomas and Akhand Tiwari
20.1 Introduction
20.1.1 Overview of Explainable AI (XAI)
20.1.2 Importance of AI in Supply Chain Management
20.1.3 Need for Explainability in AI-Driven Supply Chains
20.2 Fundamentals of Explainable AI (XAI)
20.2.1 Definition and Key Concepts
20.2.2 Types of Explainable AI Approaches
20.2.3 Benefits and Challenges of XAI in Decision-Making
20.3 Applications of Explainable AI in Supply Chain Management
20.3.1 Demand Forecasting and Inventory Optimization
20.3.2 Supplier Selection and Risk Management
20.3.3 Logistics and Route Optimization
20.3.4 Warehouse and Order Fulfillment Efficiency
20.4 Enhancing Efficiency through Explainable AI
20.4.1 Automating and Optimizing Supply Chain Operations
20.4.2 Reducing Delays and Improving Response Times
20.4.3 Minimizing Costs and Waste Reduction
20.4.4 Case Studies: Successful Implementation of XAI for Efficiency
20.5 Improving Supply Chain Visibility with Explainable AI
20.5.1 Real-Time Data Insights and Transparency
20.5.2 Enhancing Supplier and Customer Collaboration
20.5.3 Mitigating Risks and Ensuring Compliance
20.5.4 Case Studies: Real-World Examples of Improved Visibility
20.6 Challenges and Future Prospects of XAI in Supply Chain Management
20.6.1 Ethical and Privacy Concerns
20.6.2 Technical and Integration Challenges
20.6.3 Future Trends and Innovations in XAI for Supply Chains
20.7 Enhancing Supply Chain Management with Explainable AI
20.7.1 The Role of Explainable AI in Modern Supply Chains
20.7.2 The Road Ahead for Explainable AI in Supply Chains
20.7.3 Final Thoughts on Balancing AI Efficiency and Transparency
Conclusion
References
Part III: Financial, Legal, and Ethical Aspects of XAI
21. Attacking Important Pixels for Anchor-Free Detectors
Yunxu Xie, Peng Huang, Shu Hu, Xin Wang, Quanyu Liao, Bin Zhu, Siwei Lyu and Xi Wu
21.1 Introduction
21.2 Related Work
21.2.1 Anchor-Based and Anchor-Free Detectors
21.2.2 Adversarial Attacks on Object Detection
21.3 Problem Formulation
21.4 Methodology
21.4.1 Sparse Category-Wise Attack (SCA)
21.4.2 Dense Category-Wise Attack (DCA)
21.5 Experiments
21.5.1 Experimental Settings
21.5.2 Experimental Results on Object Detection
21.5.3 Sensitivity Analysis of Hyperparameters
21.5.4 Experimental Results on Human Pose Estimation
21.6 Conclusion
Appendix A
References
22. Explainable AI in Ethico-Legal and Regulatory Compliance
Ananya Pandey, Jipson Joseph and A. Agnel Samy
22.1 Introduction
22.2 Explainable AI: An Overview
22.2.1 Explanation
22.2.2 Meaningfulness
22.2.3 Explanation Accuracy
22.2.4 Knowledge Limits
22.3 Applications of Explainable AI in the Contemporary World
22.3.1 Healthcare
22.3.2 Environment Monitoring
22.3.3 Finance
22.4 Explainable AI and Sustainability
22.5 Ethico-Legal Perspective of Explainable AI
22.5.1 Transparency
22.5.2 Accountability/Liability
22.5.3 Bias and Fairness
22.5.4 Human Involvement
22.5.5 Intellectual Property Rights (IPRs)
22.5.6 Data Privacy and Security
22.6 Global Governance on XAI
22.6.1 OECD Principles
22.6.2 General Data Protection Regulation (GDPR)
22.6.3 DARPA XAI Initiative
22.6.4 Digital Transformation Strategy
22.6.5 Lei Geral de Proteção de Dados (LGPD)
22.7 Need for a Policy Framework
22.8 Conclusion
References
23. Regulatory Compliance and Explainable AI: What Challenges Remain
Nitish Ojha and Abhishek Vaish
Introduction
Literature Review
Cyber Law Before 2000
Cyber Law After 2000
Use of AI in Decision Making
Conclusion
Bibliography
24. A Comprehensive Analysis of The Utilization of Explainable Artificial Intelligence in the Banking and Financial Industry
Varun Kesavan and Aruna Polisetty
24.1 Introduction
24.1.1 The Meaning of Explainable AI
24.1.2 The Four Approaches to the XAI Models
24.1.3 The Distinction between the Explainable AI and Traditional AI Models
24.2 The Birth of Explainable AI
24.3 Core Principles of Explainable AI
24.3.1 The Need for Transparency in AI
24.3.2 Merits of XAI in Decision-Making Process
24.4 The Applications of Explainable AI in Banking and Finance
Sector
24.4.1 Advantages of XAI in Banking Hazard Administration
24.5 Different Kinds of Explainable AI are Required in the Bank and Finance Industry
24.5.1 The Implementation of Explainable AI in Banking and Finance Sector
24.5.2 Key Stakeholders in AI in Finance Sector
24.5.3 The Power of AI in Money Sector
24.6 The Application of XAI in Other Sectors
24.6.1 XAI Adoption in Healthcare Sector
24.6.2 XAI Implementation in Finance Sector
24.6.3 Explainable AI Implementation in Legal and Compliance Arena
24.6.4 Methods for Accomplishing XAI
24.6.5 Tools for Visualizing Data or Information
24.7 Encounters in Executing XAI
24.8 Conclusion
References
25. Addressing Privacy Concerns in Explainable AI
Savithri M.
25.1 Introduction to Privacy in Explainable AI
25.1.1 Importance of Privacy in AI
25.1.2 Balancing Transparency and Privacy
25.1.3 Ethical Considerations
25.2 Data Privacy Challenges in Explainable AI
25.2.1 Risks of Exposing Sensitive Information
25.2.2 Membership Inference Attacks
25.2.3 Model Inversion Attacks
25.2.4 Data Leakage in Explainability Methods
25.3 Privacy-Preserving Techniques in Explainable AI
25.3.1 Differential Privacy
25.3.2 Federated Learning
25.3.3 Homomorphic Encryption
25.3.4 Secure Multiparty Computation (SMPC)
25.4 Trade-Offs Between Explainability and Privacy
25.4.1 Impact of Explainability on Data Security
25.4.2 How Too Much Transparency Can Lead to Vulnerabilities
25.4.3 Finding a Balance Between Interpretability and Protection
25.5 Regulations and Compliance in AI Privacy
25.5.1 GDPR, CCPA, and Other Legal Frameworks
25.5.2 Privacy Policies for AI-Driven Decisions
25.6 Privacy-Aware Explainability Methods
25.7 Case Studies and Real-World Applications
25.7.1 Financial Sector AI and Customer Data Protection
25.7.2 Social Media AI Models and User Privacy Risks
25.8 Future Directions and Challenges
25.9 Conclusion
References
26. Understanding Bias and Fairness in AI Models
Priyanshu Gourav Sarangi and Rudranarayan Pradhan
26.1 Introduction
26.2 Introduction to Bias
26.2.1 Definition of Bias
26.2.2 Types of Bias
26.2.3 Sources of Bias
26.2.4 Reduction Techniques of Bias in AI
26.2.5 Possible Problems in the Mitigation Techniques
26.2.6 Real World Example of Bias in AI
26.3 Introduction to Fairness
26.3.1 Definition of Fairness
26.3.2 Types of Fairness
26.3.3 Different Methodologies to Ensure Fairness in AI Systems
26.3.4 Evaluation Metrics of Fairness in ML Systems
26.3.5 Problems in Methodologies to Ensure Fairness in AI
26.3.6 Real-World Example of Fairness in AI
26.3.7 Fairness Accuracy Tradeoff
26.4 Introduction to Variance
26.4.1 Definition of Variance
26.4.2 Variance and Bias Combinations
26.4.3 Mitigation Techniques of Variance
26.4.4 Bias Variance Trade-Off
26.5 Conclusion
26.6 The Possibility of Making AI Fair and Equitable for All
References
27. Explainable AI for Risk Assessment and Decision Support
Preethi Nanjundan, Lijo Thomas and Devang Singh
27.1 Introduction
27.1.1 The Role of AI in Risk Assessment and Decision Making
27.2 Fundamentals of Explainable AI (XAI)
27.2.1 Definition and Importance of XAI
27.2.2 Types of Explainability
27.2.2.1 Global vs. Local Explainability
27.2.3 Interpretability vs. Accuracy: The Trade-Off
27.2.4 Metrics for Measuring Explainability
27.2.5 Metrics for Measuring Explainability
27.3 Risk Assessment and Decision Support: An Overview
27.3.1 Understanding Risk in Different Domains
27.3.1.1 Financial Risk
27.3.1.2 Healthcare Risk
27.3.1.3 Cybersecurity Risk
27.3.1.4 Operational and Supply Chain Risks
27.3.2 Decision Support Systems (DSS): Key Concepts
27.3.3 AI vs. Traditional Risk Assessment Approaches
27.4 XAI Techniques for Risk Assessment
27.4.1 Feature Importance-Based Methods
27.4.2 Model-Specific Explainability
27.4.3 Post Hoc Explanation Methods
27.4.4 Visual Explanation Techniques
27.5 Applications of XAI in Risk Assessment
27.5.1 Financial Sector
27.5.2 Healthcare Sector
27.5.3 Cybersecurity and IT Risk Management
27.5.4 Supply Chain and Operational Risks
27.6 Challenges and Ethical Considerations
27.6.1 Bias and Fairness in AI Risk Models
27.6.2 Transparency vs. Proprietary AI Models
27.6.3 Regulatory and Compliance Considerations
27.6.4 Human-AI Collaboration: Who Holds the Final Decision
27.7 Conclusion
References
Bibliography
Part IV: Technical Advances and Deep Learning in XAI
28. A Deep Learning Approach to Detect Deep-Fake Audio
Mst. Sumaiya Afrin Mim, Faisal Imran, Afridi Bin Hafiz, Md. Mohashin Hossain and Mahedy Hasan Foysal
28.1 Introduction
28.2 Literature Review
28.2.1 Background
28.3 Methodology
28.3.1 Methodology of Paper [1]
28.3.2 Methodology of Paper [2]
28.3.3 Methodology of Paper [3]
28.4 Result Analysis
28.5 Conclusion
Bibliography
29. Enhanced Wild Animal Detection Using YOLOv3 with Adaptive Preprocessing and Dynamic Feature Extraction
Rahul P. More and Rais Abdul Hamid Khan
Abbreviations
29.1 Introduction
29.2 Literature Survey
29.3 Major Challenges
29.4 Proposed Methodology
29.4.1 NLM Filter
29.4.2 Local Gabor XOR Patterns (LGXP)
29.4.3 Adaptive Network Based Fuzzy Inference System (ANFIS)
29.4.4 Quantum Dilated Convolution Neural Network (QDCNN)
29.5 Result Analysis
29.6 Conclusion
Acknowledgments
References
30. A Novel Autoencoder-Based Similarity Measure for Scale-Invariant NIR-VIS Face Recognition
Amruta Nagesh Chitari, Sharanabasava Inamdar and Pradip Salve
30.1 Introduction
30.2 Background and Related Work
30.3 Proposed Methodology
30.3.1 Preprocessing Images
30.3.2 Autoencoder Setup
30.3.3 Face Recognition Inference
30.4 Dataset Description
30.5 Results and Analysis
30.6 Conclusion
30.7 Limitation and Future Scope
Acknowledgment
References
31. Vehicle Number Plate Recognition Using YOLO with LLM-Powered OCR
Bhagyashree Lambture, Ketaki Nerkar, Priyanka Rote and Vedah Nawale
31.1 Introduction
31.2 Related Works
31.3 Methodology
31.3.1 Login and Number Plate Registration
31.3.2 Preprocessing
31.3.3 Plate Detection Using YOLO
31.3.4 Number Plate Extraction
31.3.5 Text Extraction via OCR with LLM Enhancement
31.3.6 Database Integration and Real-Time Image Cross-Checking
31.3.7 Vehicle Entry and Exit Alert System Using Email Notifications
31.4 Mathematical Model
31.5 Results and Discussion
31.6 Limitations and Future Work
31.7 Conclusion
Bibliography
32. Identifying the Historical Era of MODI Manuscripts Using Deep Learning Techniques
Sagar Rajebhosale and Jayashri Bagade
Abbreviations
32.1 Introduction
32.2 Literature Survey
32.2.1 Historical Context and Significance of Modi Script
32.2.2 Optical Character Recognition and Handwritten Texts
32.2.3 Line Segmentation in OCR for Historical Manuscripts
32.2.4 Challenges in Recognizing Low-Resource Languages Manuscripts
32.2.5 Modi Script Translation and Digitization
32.3 Methodology
32.3.1 Preprocessing
32.3.2 Deep Learning Model
32.3.3 Preliminary Result Analysis
32.3.4 Challenges Encountered
32.3.5 Future Work to Overcome the Challenges
32.4 Preliminary Results
32.4.1 Recognition Overview
32.4.2 Future Implications for Manuscript Analysis
32.5 Performance Analysis
32.5.1 Accuracy and Recognition Rate
32.5.2 Challenges in Character Recognition
32.5.3 Error Analysis
32.5.4 Impact of Preprocessing Techniques
32.5.5 Future Improvements
32.6 Conclusion
Bibliography
33. Implementing Finite State Machines and Evaluating A*
Pathfinding for Enemy AI in Unity-Based Games
Shivaji Patil, Jiya Moolya, Heramb Patil, Pushkar Patil, Riddhi Mirajkar and Pravin Futane
33.1 Introduction
33.2 Literature Survey
33.3 Proposed System
33.3.1 Finite State Machine Design
33.3.1.1 Base Class
33.3.1.2 Patrol State
33.3.1.3 Chase State
33.3.1.4 Attack State
33.3.1.5 Flee and Heal State
33.3.2 Navigation Mesh
33.3.3 A* Pathfinding Algorithm
33.4 Results
33.5 Conclusion
33.6 Future Scope
Biblography
34. Bridging Financial Data Gaps with WGAN-GP: Generating Synthetic Time Series for Robust Models
Rishabh Shah, Fayed Hakim, Armaan Attar, Harsh Samant, Nilesh Patil and Chinmay Raut
34.1 Introduction
34.1.1 Related Work
34.2 Methodology
34.2.1 Data Collection
34.2.2 Preprocessing
34.2.3 Model Architecture
34.2.4 Model Training
34.3 Results
34.4 Conclusion
34.5 Future Scope
References
35. A Hybrid Deep Learning Approach for Energy Consumption
Forecasting: Insights from LSTM, DE, and DNN
Mehzabin F. Pathan, Kavita Kolpe, Onkar Kundaram, Prajwal Khobragade, Vishwas Kude, Shreyas Patil and Madhuri Amol Suryavanshi
35.1 Introduction
35.1.1 Literature Survey
35.1.2 Household Energy Consumption Prediction: A Deep Neuroevolution Approach
35.2 Summer Electricity Consumption Patterns in Households
Using Appliance Load Profiles
35.3 Research on Building Energy Consumption Prediction Based on Extreme Time Series Prediction
35.4 Residential Energy Consumption Prediction Using Inter-
Household Energy Data and Socioeconomic Information
35.5 Evolutionary Deep Learning-Based Energy Consumption Prediction for Buildings
35.6 Machine Learning Optimization Model for Reducing the Electricity Loads in Residential Energy Forecasting
35.7 Energy Consumption Forecasting for Smart Industry Using ARIMA and VAR Model
35.8 Predictive Analytics of Energy Usage by IoT-Based Smart
Home Appliances
35.8.1 Differential Evolution (DE) Algorithm Overview
35.8.2 Optimization and Evaluation Approach
35.8.3 Final Model and Analysis
35.8.4 Auto Encoder (AE) for Feature Extraction
35.8.5 Deep Neural Network (DNN) Layer
35.9 Conclusion
Bibliography
36. A Machine Learning Approach for Cognitive Decline Detection Using Neuroimaging Data
Kalyani Bhosale, Namrta Budde, Pragati Dhobale and Vidya Dhamdhere
36.1 Introduction
36.2 Literature Review
36.2.1 Project Idea
36.2.2 Motivation of the Project
36.3 Proposed Solution
36.4 Literature Survey
36.5 Future Scope
36.6 Conclusion
References
37. Prediction of Rainfall in Maharashtra Using Machine
Learning Techniques
Sushilkumar R. Kalmegh and Dhanaji P. Bhanvase
37.1 Introduction
37.2 Literature Review
37.2.1 Overview of Rainfall Prediction
37.3 Methodology
37.3.1 Load Dataset
37.3.2 Feature Extraction
37.3.3 Apply Machine Learning Classification Algorithms
37.3.3.1 KNN
37.3.3.2 Random Forest
37.3.3.3 Naïve Bayes
37.3.3.4 Gradient Boosting
37.4 Performance Analysis
37.4.1 Confusion Report (Gradient Boosting)
37.4.2 Comparative Analysis
37.5 Conclusion
References
38. Unified Multimodal Approach for Data Agnostic Annotations with Integrated Augmentations and Auto Annotations
Vandana Rupnar, Sakshi Gawande, Vaishnavi Adsure, Mohit Kirtane, Prathamesh Gayake and Pradnya Mehta
Abbreviations
38.1 Introduction
38.2 Related Work
38.2.1 Medical Image Annotation
38.2.2 Clinical Text Annotation
38.2.3 Multimodal Medical Approaches
38.3 Methodology
38.3.1 System Architecture
38.3.2 Image Annotation
38.3.3 Iterative Annotation Pipeline
38.3.4 Threshold Management System
38.3.5 CNN Architecture and Progressive Model Deployment
38.3.5.1 YOLO Architecture Selection
38.3.5.2 Progressive Model Deployment
38.3.6 Auto-Annotation Process Flow
38.3.7 Image Segmentation with U-Net
38.3.8 Text Annotation
38.3.9 Integrating with Existing Components
38.3.10 Performance Optimization
38.3.11 Data Export
38.4 Experimental Setup
38.4.1 Datasets
38.4.2 Evaluation Tasks
38.4.3 Evaluation Metrics
38.5 Discussion
38.5.1 Anticipated Benefits
38.5.2 Potential Limitations and Challenges
38.6 Future Scope and Limitations
38.6.1 Future Scope
38.6.1.1 Advanced AI Integration
38.6.1.2 Enhanced Multimodal Capabilities
38.6.1.3 Workflow Integration
38.6.1.4 Quality Assurance and Validation
38.6.2 Technical Limitations
38.6.2.1 Computational Constraints
38.6.2.2 Data Privacy and Security
38.6.2.3 Model Limitations
38.6.3 Operational Limitations
38.6.3.1 Expertise Requirements
38.6.3.2 Integration Challenges
38.6.3.3 Scalability Constraints
38.7 Conclusion
Acknowledgment
Bibliography
Part V: Emerging Innovations and Case Studies
39. Emerging Trends and Challenges in Explainable AI
Ruchira Deokar, Preethi Nanjundan and Jossy P. George
39.1 Introduction
39.2 Emerging Trends in Explainable AI
39.2.1 Integration of XAI with Multimodal AI Systems
39.2.2 Personalized Explanations
39.2.3 Interactive and Real-Time Explanation Systems
39.2.4 Ethical and Fairness-Centric XAI
39.2.5 Integration with Edge Computing and IoT
39.2.6 Advances in Natural Language Explanations
39.3 Challenges Facing Explainable AI
39.3.1 Balancing Complexity and Simplicity
39.3.2 Quantifying Explainability
39.3.3 Scalability in Large-Scale Systems
39.3.4 Domain-Specific Constraints
39.3.5 Resistance to Adoption
39.3.6 Adversarial Exploitation
39.3.7 Regulatory and Legal Challenges
39.4 The Road Ahead
39.4.1 Develop Unified Frameworks for Creating and Evaluating Explanations
39.4.2 Promote Education and Awareness
39.4.3 Invest in Research Prioritizing the Dual Goals of Performance and Explainability
39.4.4 Foster International Collaboration to Tackle Regulatory and Ethical Challenges Collectively
39.5 Conclusion
References
40. Future Trends and Challenges in Explainable AI
Vasim Ahmad and Rakesh Kumar
40.1 Introduction
40.2 Current State of Explainable AI
40.2.1 Explainable AI in Various Domains
40.3 Emerging Trends in Explainable AI
40.3.1 Role of Natural Language Processing in XAI
40.3.2 Explainable Deep Learning Models
40.4 Technological Advancements and Innovations
40.5 Regulatory and Ethical Considerations
40.6 Case Studies and Real-World Applications
40.6.1 Healthcare
40.6.2 Finance
40.6.3 Autonomous Systems
40.6.4 Retail
40.6.5 Manufacturing
40.6.6 Energy Sector
40.7 Human–AI Interaction
40.8 Future Challenges, Trends, and Directions in Explainable AI
40.9 Conclusion
References
41. Decoding Sarcasm: Understanding Its Role in Social Media Discourse
Yuvraj G. Nikam, Amit Kumar Pathak and Dhanshri Amol Shinde
41.1 Introduction
41.2 Literature Survey
41.3 Gap Analysis
41.4 Suggested Method
41.4.1 Collection
41.4.2 Sampling Dataset and Model Blomming
41.4.3 Model Assessment
41.4.4 Examination
41.4.5 Assessment Criteria
41.5 Problems with Sarcasm Recognition
41.5.1 Annotation Problem
41.5.2 The Problem with Sentiment as a Feature
41.5.3 Unbalanced Dataset Issue
41.6 Comparative Analysis
41.7 Conclusion and Future Work
Acknowledgments
Bibliography
42. Arthritis Neglected Health Priorities: A Bibliometric Analysis and Future Research Directions
Archana Y. Chaudhari, Megha V. Kadam, Sarika T. Deokate and Mangesh D. Salunke
42.1 Introduction
42.2 Bibliometric Analysis
42.2.1 Keyword Strategy
42.2.2 Preliminary Data Highlights
42.2.3 Publication Trends
42.2.4 Geographical Regional Analysis
42.2.5 Keywords Statistics
42.2.6 Affiliation Statistics
42.2.7 Journal Statistics by Year
42.2.8 Authors Researching Trend
42.2.9 Research Funders
42.2.10 Subject Areas
42.2.11 Citation Analysis
42.2.12 Patent Analysis
42.3 Future Research Direction
42.4 Conclusion Summary
References
43. Depression Detection Using Social Media Psychological
Analysis Based on the Lexicon Approach
Gokul Pawade and Mininath Bendre
43.1 Introduction
43.2 Literature Survey
43.3 Overview of Depression
43.3.1 Depression Definition
43.3.2 Depression Rate
43.3.3 Depression Causes
43.3.4 Depression Symptoms
43.3.5 Psychiatrist’s Diagnosis of Depression
43.3.6 Restrictions on the Manual Diagnosis of Depression
43.4 Overview of Depression
43.5 Proposed System
43.5.1 System Architecture
43.5.2 Algorithm Used
43.5.3 Benefits of this System
43.5.4 Sentiment, Stress, and Relaxation Analysis
43.6 Conclusion
Bibliography
44. Real-Time Personalized Meal Recommendations Tailored to Dietary Preferences and Health Goals
Vaasu Goel, Salman Khan, Shashank Teotia and Waseem Ahmed
44.1 Introduction
44.2 Literature Review
44.3 Methodology
44.4 Challenges
44.4.1 Future Scope
Acknowledgments
Bibliography
45. Anemia Level Detection and Prediction in Pregnant Women
Using Machine Learning and Deep Learning
Tejaswini Sunil Bhoye and Nikhil Mhala
45.1 Introduction
45.1.1 Background
45.1.2 Research Problem
45.1.3 Objectives
45.2 Literature Review
45.2.1 Overview of Anemia and Pregnancy
45.2.2 Importance of Anemia Detection in Pregnant Women
45.2.3 Summary of Papers
45.3 Methods of Machine Learning for the Identification of Anaemia
45.3.1 Logistic Regression
45.3.2 Random Forest
45.3.3 Neural Networks
45.3.4 Feature Selection Methods and Their Relevance
45.3.5 Performance Evaluation Metrics Used in Existing Studies
45.3.6 Challenges and Gaps in Anemia Detection
45.3.7 Data Scarcity and Limitations
45.3.8 Generalizability and Transferability of Models
45.3.9 Interpretability of Machine Learning Models in Clinical Practice
45.3.10 Resource Constraints and Real-Time Implementation
45.4 Research Methodology
45.4.1 Data Collection
45.4.2 Feature Selection
45.4.3 Model Development
45.4.4 Experimental Setup
45.4.5 Real-Time Detection and Integration
45.4.6 Benchmarking and Performance Evaluation
45.5 Proposed System/Model
45.6 Conclusion
Bibliography
46. Smart Management of Electric Vehicle Charging Station
Using Google Map API
Kunal Chaudhari, Jagruti Gulhane, Lingram Gurude and Geeta Atkar
46.1 Introduction
46.2 Literature Survey
46.3 Module Description
46.3.1 User App/Web Portal
46.3.2 Admin App/Web Portal
46.3.3 Backend Services
46.3.4 User Management Service
46.3.5 Booking Service
46.3.6 Charging Station Management Service
46.3.7 Databases
46.4 IoT Device (Battery Management System)
46.5 Results and Evaluation
46.6 Conclusion
Bibliography
47. Advanced Analysis of Geospatial Data Patterns
Priyadarshani Kalbandhe, Omkar Nilawar, Kirtan Chandak and Sunita Nandgave
47.1 Introduction
47.2 Literature Review
47.3 Methodology
47.4 Architecture Diagram
47.5 Cluster Analysis
47.6 Results
47.7 Technology Stack
Acknowledgment
47.8 Conclusion
Bibliography
48. DNA Sequence Generation and Analysis Using Transformer
and XAI
Prashant Singh and Rajkumari Bidyalakshmi Devi
48.1 Introduction
48.1.1 Related Work
48.2 Methodology
48.2.1 Data Set Preparation
48.2.2 Fine Tuning of the GPT2 Model and Explaining It’s Generation
48.2.3 Training of BERT Model and Explaining Its Classification
48.2.4 SHAP (SHapley Additive exPlanations)
48.2.5 LIME (Local Interpretable Model-Agnostic Explanations)
48.2.6 Transformer Interpreter
48.2.7 Explaining Model Predictions Using Traditional Methods
48.3 Experimentation Results and Discussion
48.3.1 Performance Metrics of the BERT Model
48.3.2 Analysis of Generated Variants by the GPT-2 Model
48.3.3 Explainability with SHAP and LIME
48.3.3.1 SHAP Analysis
48.3.3.2 Token Attribution Visualization
48.3.3.3 Sequence Attribution Visualization
48.3.3.4 Response-Based Token Attribution Visualization
48.3.3.5 LIME Results
48.3.4 Limitations
48.3.5 Using Traditional Methods
48.4 Conclusion
References
49. Utilizing Convolutional Neural Networks for Identification and Categorization of Plant Diseases
Harshit Singh and Pragya Tewari
49.1 Introduction
49.2 Methodology
49.3 CNN
49.4 Model Evaluation and Performance Analysis
49.5 Conclusion
References
Index

Back to Top



Description
Author/Editor Details
Table of Contents
Bookmark this page