Search

Browse Subject Areas

For Authors

Submit a Proposal

Causal Artificial Intelligence

Fundamentals and Applications
Edited by Rajdeep Chakraborty, Aleem Ali, Amit Paul, Nawaf R. Alharbe, S. Balamurugan
Series: Leading-Edge Breakthroughs in Artificial Intelligence
Copyright: 2026   |   Expected Pub Date:2026/09/30
ISBN: 9781394403998  |  Hardcover  |  
370 pages
Price: $225 USD
Add To Cart

One Line Description
Bridging cutting-edge theoretical foundations with high-impact, real-world applications across healthcare, cybersecurity, and autonomous systems, this essential guide empowers researchers, practitioners, and policymakers to move beyond brittle correlation models and lead the next wave of transparent, safe, and truly interpretable AI.

Audience
AI researchers, data scientists, academics, industry professionals, business leaders, medical researchers, and policymakers interested in advancing from traditional machine learning techniques to causal models.

Description
Causal Artificial Intelligence (CAI) represents a significant advancement in the development of AI systems, marking a shift from purely correlation-based models to those capable of understanding and reasoning cause-and-effect relationships. In the context of disciplinary and industry development, casual AI addresses critical challenges in AI’s ability to generalize, explain decisions, and make safe interventions across dynamic environments. Its emergence is reshaping fields like healthcare, economics, autonomous systems, and social sciences, offering a more reliable and interpretable form of AI that can predict the effects of actions, simulate outcomes, and inform decision-making more accurately. This book provides a comprehensive exploration of how causal reasoning can enhance the transparency, reliability, and ethical foundations of artificial intelligence systems. Addressing both theoretical and practical dimensions, it examines structural causal models, explainable AI, and privacy-preserving learning frameworks across diverse fields, including healthcare, climate science, manufacturing, automotive safety, and cybersecurity. It highlights innovative research in areas such as CNN-based causal inference for signal detection, explainable mobile AI for disease prediction, image processing for Ayurvedic material identification, and AI-driven systems for driver fatigue and collision detection. By bridging theoretical foundations with real-world applications, this book serves as a valuable resource for researchers, practitioners, and policymakers committed to developing transparent, secure, reliable, and ethically aligned intelligent technologies.
Readers will find the volume:
• Offers a deep dive into frameworks like structural causal models (SCMs), Bayesian networks, and do-calculus, allowing readers to explore how AI systems can identify and leverage cause-and-effect relationships;
• Emphasizes real-world applications of causal artificial intelligence through detailed case studies in fields such as healthcare, economics, and autonomous systems;
• Illustrates how causal models are applied in complex, dynamic environments, demonstrating casual AI’s potential to revolutionize industries by providing actionable insights;
• Focuses on the ethical implications and interpretability of AI systems built on causal reasoning.

Back to Top
Author / Editor Details
Rajdeep Chakraborty, PhD is a Professor in the Computer Science and Engineering Department at SAGE University, Indore, Madhya Pradesh, India, with two decades of teaching and research experience. He has made notable contributions through various publications, including patents, books, journal articles, and conference papers. His interests include cryptography, network security, Internet of Things, and blockchain.

Aleem Ali, PhD is a Professor and Research Coordinator in the Department of Computer Science and Engineering at Chandigarh University, Punjab, India. With over 17 years of academic and research experience, he has established himself as a leading contributor in the areas of Internet of Things, artificial intelligence, machine and deep learning, and network security. He has an extensive research portfolio with more than 65 peer-reviewed publications in reputed journals and conferences and six books.

Amit Paul, PhD is an Associate Professor of Computer Science and Engineering at St. Thomas’ College of Engineering and Technology, Kolkata, India. He has authored five journal articles and seven international conference papers. His research centers on causal inference and interpretable machine learning for biomedical applications.

Nawaf R. Alharbe, PhD is a Professor in the College of Computer Science and Engineering at Taibah University in Saudi Arabia. He has more than 20 publications in international journals and conferences of repute. His interests include knowledge management systems in smart healthcare operations using emerging technologies such as RFID, ZigBee, Internet of Things (IoT), and cloud computing.

S. Balamurugan, PhD is the Director of Intelligent Research Consultancy Services, Coimbatore, India. He has published more than 70 books, 300 articles in international and national journals and conferences, and 300 patents. He is a research consultant for many companies, startups, SMEs, and MSMEs.

Back to Top

Table of Contents
Series Preface
Preface
Acknowledgement
Part I: Fundamentals
1. Causal Artificial Intelligence: Fundamentals and Applications
Barnali Gupta Banik and Geeta Ambildhuke
1.1 Introduction
1.1.1 Features of Causal AI
1.1.1.1 Causal Inference
1.1.1.2 Structural Causal Models
1.1.1.3 Counterfactual Reasoning
1.2 Literature Survey
1.3 Basics of Causal AI
1.3.1 Causal Graphs and Models
1.3.2 Structural Equation Modeling (SEM)
1.3.3 Do-Calculus and Interventions
1.3.4 Causal Discovery Algorithms
1.3.5 Structural Causal Models (SCMs)
1.3.6 Potential Outcomes Framework
1.4 Applications of AI
1.4.1 Churn Analysis and Customer Retention
1.4.2 Decision Support in Healthcare
1.4.3 Fraud Detection in the Finance Sector
1.4.4 Marketing Campaign and Its Optimization
1.4.5 Optimization of Supply Chain
1.4.6 Risk Management and Compliance
1.4.7 Innovation and Product Development
1.5 Benefits, Limitations, and Challenges
1.5.1 Benefits of Causal AI
1.5.2 Limitations of Causal AI
1.6 Conclusion and Future Scope
References
2. Unveiling the Power of Causal AI: From Structural Causal
Model to Bug Resolution Analysis
Reshmi Maulik, Subhajit Datta, Subhashis Majumder and Soumen Santra
2.1 Introduction
2.2 Literature Review
2.3 Methodology
2.3.1 Data Specification
2.3.2 Model Variables
2.3.3 Causal Discovery
2.4 Model Construction
2.4.1 DAG and SCM
2.4.2 Causal Inference
2.4.3 Testing the Validity of Causal Claims
2.5 Discussion
2.6 Sensitivity Analysis of Treatment Variables
2.7 Threats to Validity
2.8 Conclusion
2.9 Future Scope
References
3. Exploring Causal AI through Deep Learning: A CNN-Based
Framework for Signal Detection in Climate and Space Sciences
Aditya Sharma and Inderdeep Kaur
3.1 Introduction
3.2 Literature Review
3.3 Gravitational Waves and Their Detection
3.3.1 Detection of Gravitational Waves
3.3.2 Advanced Features and Techniques
3.3.3 Milestones in GW Astronomy
3.3.4 Future Prospects
3.4 Results and Discussion
3.4.1 Dataset
3.4.2 Preprocessing
3.4.3 Proposed Approach
3.4.3.1 Model Architecture Design
3.4.3.2 Model Compilation and Training
3.4.4 Evaluation and Performance Analysis
3.4.5 Comparison and Validation
3.4.6 Accuracy
3.5 Performance Evaluation
3.5.1 Accuracy and Loss Analysis
3.5.2 Class Correlation Matrix
3.5.3 Analyzing Model Performance
3.5.4 Significance of Achieved Accuracy
3.6 Conclusion
References
4. Predictive Health Mate: An Explainable AI for Disease Prognosis and Prevention on Android Device
Abhishek Roushan, Gurmeet Kaur, Inderdeep Kaur, Vatsala Singh, Harsh Yadav and Yash Srivastava
4.1 Introduction
4.2 Literature Review
4.3 Model Architecture
4.3.1 Graph Neural Networks (GNNs)
4.3.2 A Long-Short Term Memory Augmented LSTM
4.3.3 Explainable Artificial Intelligence (XAI) and SHAP
4.4 Conclusion
4.5 Future Scope
References
Part II: Applications
5. A Machine Learning-Based Approach for Identifying Ayurvedic Medicinal Raw Materials via Image Processing
Ankit Raj, Subhajit Chanda, Ashutosh Dubey, Dyuti Mitra and Debraj Chatterjee
5.1 Introduction
5.2 Literature Survey
5.3 Methodology
5.4 Results and Discussions
5.5 Key Findings
5.5.1 Algorithm Performance
5.5.2 Technological Integration
5.5.3 Difficulties
5.6 Future Scope
5.6.1 Dataset Expansion
5.6.2 Enhanced Feature Extraction
5.6.3 Practical Applications
5.6.4 Interdisciplinary Integration
5.6.5 Algorithm Enhancements
5.6.6 Ecological and Ethical Considerations
5.6.7 Longitudinal Studies
References
6. AI and Machine Learning in Healthcare: Transforming Treatment, Ethics, and Resource Optimization
Aakansha Khanna, Inderdeep Kaur, Inzimam Ul Hassan and Pratyansh Singh
6.1 Introduction
6.1.1 Decision Support System in Healthcare Industry
6.2 What is Machine Learning?
6.2.1 Data Quality Quandaries
6.3 Categories of Machine Learning
6.3.1 Supervised Learning
6.3.2 Unsupervised Learning
6.3.3 Reinforcement Learning
6.4 Challenges and Architecture of the I-Healthcare System
6.4.1 I-Health System Challenges
6.5 Deep Learning
6.5.1 Neural Networks Reform the Deep Learning Architecture
6.6 Case Study and Applications
6.6.1 Use Cases
6.7 Conclusion
Bibliography
7. Real-Time Driver Fatigue Monitoring Using AI: An Ethical
and Non-Intrusive Approach to Road Safety
Sumanta Chatterjee and Amit Majumder
7.1 Introduction
7.2 Leveraging Artificial Intelligence for Safer Roads through
Real-Time Fatigue Monitoring
7.2.1 The Impact of Driver Fatigue on Road Safety
7.2.2 The Role of AI in Driver Fatigue Detection
7.2.3 Real-Time Fatigue Monitoring: The Key Issues
7.2.4 Challenges and Opportunities in Fatigue Detection
7.3 AI and ML Technologies for Drowsiness Detection
7.3.1 Understanding Drowsiness Detection
7.3.2 AI and ML Approaches to Drowsiness Detection
7.3.2.1 Computer Vision Techniques
7.3.2.2 Challenges in Computer Vision for Drowsiness Detection
7.3.2.3 Sensor-Based Monitoring Systems
7.3.2.4 Advantages of Sensor-Based Drowsiness Detection Systems
7.3.2.5 Data Fusion and Predictive Algorithms
7.3.2.6 Real-Time Alert Systems
7.4 Challenges in Driver Drowsiness Detection
7.4.1 Variation in Fatigue Signs
7.4.1.1 Individual Difference
7.4.1.2 Adapting to Changing Fatiguing States
7.4.2 Environmental Factors
7.4.2.1 Conditions of Light
7.4.2.2 Adverse Weather and Road Conditions
7.4.2.3 Interference of Passenger
7.4.3 Sensor Limitations
7.4.3.1 Problems of Cameras and Visual Tracking
7.4.3.2 Limitations on Physiological Monitoring
7.4.3.3 Invasive
7.4.4 Data Privacy and Ethical Issues
7.4.4.1 Privacy Concerns
7.4.4.2 Consent and Control
7.4.4.3 Equal Opportunities in AI
7.4.5 Drive Behavior and Human Factor
7.4.5.1 Cognitive Fatigue
7.4.5.2 Arousing Response of Drivers to Being Alerted
7.5 Future Directions and Innovations
7.5.1 Advancements in Sensor Technology
7.5.1.1 Multi-Modal Sensors for Enhanced Detection
7.5.1.2 Non-Intrusive Detection via Advanced Cameras
7.5.2 The Role of Artificial Intelligence and Machine Learning
7.5.2.1 Deep Learning for Real-Time Drowsiness Detection
7.5.2.2 Personalization of Drowsiness Detection
7.5.2.3 Predictive Analytics for Proactive Fatigue Management
7.5.3 Integration with Autonomous Vehicles
7.5.3.1 Bridging Human and Autonomous Systems
7.5.3.2 Full Integration into Fully Autonomous Vehicles
7.5.4 Ethical Considerations and Data Privacy
7.5.4.1 Data Privacy and Data Security
7.5.4.2 Transparency and Consent
7.5.4.3 Fairness and Avoiding Bias in AI Models
7.6 Conclusion
Bibliography
8. AI-Powered Collision Detection: A Neural Network System
for Automotive Safety
Sumanta Chatterjee and Amit Majumder
8.1 Introduction
8.2 Background and Literature Review
8.2.1 Conventional Collision Detection and Its Limitations
8.2.2 Neural Networks for Collision Detection
8.2.3 Convolutional Neural Networks (CNNs)
8.2.4 Recurrent Neural Networks (RNNs) and Long Short-Term Memory Networks (LSTMs)
8.2.5 Integration of Neural Networks with Advanced Sensor Technologies
8.2.6 LiDAR and Neural Networks
8.2.7 Radar and Neural Networks
8.2.8 Cameras and Neural Networks
8.3 Proposed Framework
8.3.1 Data Acquisition
8.3.2 Preprocessing
8.3.2.1 Data Cleaning
8.3.2.2 Feature Engineering
8.3.2.3 Data Transformation
8.3.2.4 Normalization and Scaling
8.3.2.5 Data Balancing
8.4 Neural Network–Based Collision Detection: Architecture
Framework
8.4.1 Introduction to Neural Network Architecture for Collision Detection
8.4.2 Design Considerations for Neural Network Architecture
8.4.2.1 Input Data Types
8.4.2.2 Problem Type
8.4.2.3 Model Complexity and Overfitting
8.5 Components of Neural Network Architecture
8.5.1 Input Layer
8.5.2 Hidden Layers
8.5.3 Output Layer
8.5.4 Activation Functions
8.5.5 Loss Function
8.5.6 Optimizers
8.6 Training the Neural Network
8.7 Neural Network–Based Collision Detection: Collision Prediction Framework
8.7.1 Understanding Collision Prediction in Neural Networks
8.7.2 Input Data for Collision Prediction
8.7.3 Visual Data (Camera Images)
8.7.4 LiDAR and Radar Data (Point Clouds)
8.7.5 Time-Series Data (Velocity, Acceleration, and Position)
8.8 Neural Network Architecture for Collision Prediction
8.8.1 Convolutional Neural Networks (CNNs)
8.8.2 Recurrent Neural Networks (RNNs) and LSTMs
8.8.3 PointNet for Point Cloud Data
8.8.4 Fusion Networks
8.9 Collision Prediction Models
8.9.1 Binary Classification
8.9.2 Regression Model (Time-to-Collision)
8.10 Training the Collision Prediction Model
8.10.1 Loss Functions
8.10.2 Optimization
8.10.3 Evaluation Metrics
8.11 Neural Network–Based Collision Detection with System Integration Framework
8.11.1 Overview of System Integration
8.11.2 Sensor Fusion and Data Preprocessing
8.11.3 Data Fusion
8.11.4 Data Preprocessing
8.12 Neural Network Deployment
8.12.1 Edge Computing vs. Cloud Computing
8.12.2 Model Optimization
8.13 Real-Time Inference
8.13.1 Data Flow
8.13.2 Latency Considerations
8.14 Control and Feedback Loop
8.14.1 Decision-Making
8.14.2 Actuators
8.14.3 Feedback for Continuous Improvement
8.15 Testing and Validation
8.16 Applications and Benefits of Neural Network–Based Collision Detection Systems
8.16.1 Applications in Automotive Safety
8.17 Benefits of Neural Network–Based Collision Detection
8.17.1 Improved Accuracy
8.17.2 Adaptability to Changing Environments
8.17.3 Real-Time Decision-Making
8.17.4 Reduced Dependence on Rule-Based Algorithms
8.17.5 Enhanced Safety and Reduced Road Accidents
8.18 Conclusion
Bibliography
9. Facial Emotion Detection Using Causal AI
Esha Kundu and Arijit Ghosal
9.1 Introduction
9.2 Literature Survey
9.3 Proposed Approach
9.3.1 Machine Learning Methods
9.3.1.1 Dataset
9.3.1.2 Dataset Cleaning
9.3.1.3 Extraction of Facial Feature
9.3.2 Deep Learning Methods Convolutional Neural Network (CNN)
9.3.2.1 Dataset
9.3.2.2 Dataset Cleaning and Preprocessing
9.3.2.3 CNN Architecture
9.4 Experimental Results: Deep Learning Methods
9.4.1 Facial Emotion Detection on 7 Emotions
9.4.2 Facial Emotion Detection on 6 Emotions
9.4.3 Comparative Research Paper Analysis
9.5 Conclusion
References
10. Causal and Data-Driven Machine Learning Algorithm for Predicting Temperature Profiles in Friction Stir Additive
Manufacturing of Aluminum Alloy A16061
MD Masud Rana
10.1 Introduction
10.1.1 Literature Review: FSAM and Machine Learning
10.1.2 Main Contributions
10.1.3 Outline
10.2 Friction Stir Additive Manufacturing Process
10.3 Problem Statement Related to Friction Stir Additive Manufacturing
10.4 Proposed Machine Learning Algorithm for Parameter Predictions of the FSAM Process
10.5 Results and Discussions
10.6 Conclusion
References
11. Enhancing Cybersecurity in EVs: Causal and Resilient ML-Based Detection of False Data Injection and Denial of Service Attacks
MD Masud Rana, Amir Shahirinia, Amer Dawoud and Ahad Ali
11.1 Introduction
11.2 Problem Statement
11.3 Proposed Methodology
11.4 Simulation Results and Discussions
11.5 EV Cyberattack CVSS Assessment
11.6 Conclusion and Future Work
References
12. Cyber Resilience in Industry 4.0: Causal and Ethical
ML-Based Detection of Cyberattacks in Smart Manufacturing Systems
MD Masud Rana
12.1 Introduction
12.1.1 Research Gap
12.1.2 Contributions and Goals
12.2 Proposed Methodology and Algorithm
12.3 Simulation Results and Discussions
12.4 End-to-End Software Development Life Cycle
12.5 Action Recommendations
12.6 Intellectual Merit and Broader Impacts
12.7 Conclusions
References
13. Explainable Privacy-Preserving Federated LLM Fine-Tuning on Distributed Edge Healthcare Infrastructure
Amit Chakraborty, Chirantana Mallick, Saptarshi Das, Madhvi Chakraborty and Abhijnan Chakraborty
13.1 Introduction
13.2 Literature Review and Gap Identification
13.3 Prerequisites
13.3.1 Federated Learning
13.3.2 Fine-Tuning of LLMs
13.4 Privacy Enhancement Technique
13.4.1 Concerns of Centralized Training of Machine Learning Models in Private Data
13.4.2 Characteristics of Private Data and Related Compliances
13.5 Dataset
13.6 Proposed Architecture
13.6.1 Federated Fine-Tuning of LLMs
13.6.2 Federation Architecture
13.6.3 Distributed Computing Infrastructure for the Architecture
13.7 Architectural Telemetry
13.8 Explainability
13.9 Conclusion
13.10 Future Work
References
14. Enhancing the Robustness of Causal AI Systems against
Adversarial Threats
Sakshi Thakur, Mohit Singh Bisht and Dinesh Singh Dhakar
14.1 Introduction
14.1.1 Importance of Robustness in Causal AI
14.1.2 Growing Threats of Adversarial Attacks
14.1.3 Objectives of This Chapter
14.2 Fundamentals of Causal AI
14.2.1 Brief Overview of Causal Inference and Modeling
14.2.2 Common Vulnerabilities in Causal Models
14.3 Nature of Adversarial Threats in Causal AI
14.3.1 There are Categories of Adversarial Attacks
14.3.1.1 Data Poisoning
14.3.1.2 Model Evasion
14.3.2 Real-World Examples and Implications
14.4 Challenges in Ensuring Robustness
14.4.1 Unique Challenges Faced by Causal Models
14.4.2 Limitations of Traditional Defense Mechanisms
14.5 Strategies for Enhancing Robustness
14.5.1 Data Sanitization and Robust Training
14.5.2 Adversarial Training Specific to Causal Inference
14.5.3 Model Verification and Validation Techniques
14.5.4 Applications of Explainability to Identify Anomalies
14.6 Case Studies and Experiments
14.6.1 Empirical Analysis of Robustness Improvements
14.6.2 Practical Implementations and Results
14.7 Future Directions
14.7.1 Emerging Research Areas
14.7.2 Open Challenges and Opportunities
14.8 Conclusion
14.8.1 Summary of Key Points
14.8.2 Concluding Reflections on Defending Causal AI Systems
References
Index

Back to Top



Description
Author/Editor Details
Table of Contents
Bookmark this page