Search

Browse Subject Areas

For Authors

Submit a Proposal

Neuro-Symbolic Artificial Intelligence

Edited by R. Nidhya, A. Dineshkumar, Sheng-Lung Peng, S Karthik and S. Balamurugan
Series: Leading-Edge Breakthroughs in Artificial Intelligence
Copyright: 2026   |   Expected Pub Date:2026/04/30
ISBN: 9781394355570  |  Hardcover  |  


One Line Description
Master the next frontier of artificial intelligence with this essential guide to uniting the pattern recognition of deep learning with the transparent, logical reasoning of symbolic AI.

Audience
Engineering research scholars and students, IT professionals, network administrators, artificial intelligence and deep learning experts, and government research agencies.

Description
The field of artificial intelligence has witnessed rapid advancements in recent years, driven primarily by deep learning and data-centric approaches. Despite their impressive performance, purely neural methods often lack interpretability, logical reasoning capabilities, and the ability to generalize beyond training data. In contrast, symbolic AI, rooted in formal logic and structured representations, offers transparency and reasoning strength, but struggles with adaptability and learning from raw data. In response to these challenges, neuro-symbolic AI has emerged as a compelling paradigm that unifies the strengths of both approaches. This book is a comprehensive exploration of one of the most transformative frontiers in artificial intelligence. By combining the pattern recognition power of neural networks with the logical reasoning capabilities of symbolic systems, neuro-symbolic AI promises to deliver systems that are not only accurate but also interpretable, adaptable, and aligned with human cognitive processes.
This book brings together a diverse range of research contributions that showcase both foundational theory and practical applications across domains like natural language processing, healthcare, intelligent transport, cybersecurity, and ethical AI. Spanning topics such as hybrid architectures, logic-enhanced deep learning, graph neural networks, transfer learning, and explainable AI, the volume addresses the technical and conceptual challenges of building trustworthy intelligent systems. Each chapter provides technical depth, experimental insights, and future directions, making this guide a vital resource for researchers, graduate students, and professionals in AI and machine learning.
Readers will find the volume introduces the fundamental concepts of neuro-symbolic AI, explores real-world applications in healthcare, natural language processing, and ethical AI, and presents a forward-looking perspective on the next generation of robust, transparent, and trustworthy AI technologies.

Back to Top
Author / Editor Details
R. Nidhya, PhD is a Professor in the Department of Computer Science and Engineering, Manipal Institute of Technology and Science, Madanapalle, India, with more than 16 years of teaching experience. She has published many research papers in refereed international journals and conferences. Her research interests include machine learning, wireless body area networks, and network security.

A. Dineshkumar, PhD is an Associate Professor at Koneru Lakshmaiah Education Foundation, Vijayawada, Andhra Pradesh, India. He completed his PhD at Anna University in Chennai in 2018. His current research interests include wireless body area networks, wireless sensor networks, network security, and artificial intelligence.

Sheng-Lung Peng, PhD is a Professor and the Director of the Department of Creative Technologies and Product Design, National Taipei University of Business, Taiwan. He has edited several special issues of journals and published more than 100 research articles. His research interests are in designing and analyzing algorithms for bioinformatics, combinatorics, data mining, and networks.

S. Karthik, PhD is a Professor and Dean in the Department of Computer Science and Engineering, SNS College of Technology, Anna University, Chennai, Tamil Nadu, India. He has published more than 150 papers in refereed international journals and 125 papers in international conferences. His research interests include network security, big data, cloud computing, web services, and wireless systems.

S. Balamurugan, PhD is the Director of Research, Intelligent Research Consultancy Services, Coimbatore, Tamil Nadu, India. He has published 100 books, 300 papers in international journals and conferences, and 300 patents. With 20 years of research on various cutting-edge technologies, he provides expert guidance in technology forecasting and decision-making for leading companies and startups.

Back to Top

Table of Contents
Series Preface
Preface
Acknowledgements
Part 1: Neuro-Symbolic AI: Concepts
1. Cataract Detection Systems Using Deep Learning Technique: A Survey
Arveti Mallikharjuna Rao and Suma Kamalesh Gandhimathi
1.1 Introduction
1.2 Deep Learning Models
1.3 Conclusion and Future Work
References
2. Agentic AI Workflows for Financial Large Language Models Using LlaMA and LangChain Framework
Mantri Udaya Jyothi, John Deva Prasanna D. S., Shanthini A. and Balasubramani S.
2.1 Introduction
2.2 Predict Stock Using Financial Analysis
2.3 Stock Market Prediction Using Agentic AI Using LLM
2.4 Llama Framework
2.4.1 LLM Agent for Stock Price Prediction for a Portfolio
2.4.2 Llama Framework with Agentic AI for Stock Prediction
2.4.2.1 Search Algorithms for Real-Time Stock Prediction in Llama Framework
2.5 Llama Framework Reduces AI Trading Risks
2.6 Working Principle of Agents
2.7 Results
2.8 Conclusion
References
3. Brain-Inspired Artificial Neural Network for Energy-Efficient and Adaptive Learning
R. Dhanalakshmi, Sahaya Beni Prathiba, Kavisankar L., Balasubramani S. and Pandiyanathan M.
3.1 Introduction
3.2 Literature Review
3.3 Methodology
3.4 Proposed System
3.5 Simulation Results
3.6 Conclusion
3.6.1 Future Scope
References
4. Neuro-Symbolic AI with a CNN-Based Framework for Detecting Tomato Leaf Diseases
Khaleelullah Shaik and Mohammed Ali Shaik
4.1 Introduction
4.2 Related Work
4.3 Methodology
4.3.1 Feature Extraction with Symbolic Reasoning
4.3.2 Classification Layer
4.4 Performance Analysis
4.5 Conclusion
References
5. Early Detection of Breast Cancer Using Multi-Modal Deep Learning Framework
Salma Mohammad and Mohammed Ali Shaik
5.1 Introduction
5.2 Related Work
5.3 Methodology
5.3.1 Data Acquisition and Preprocessing
5.3.2 Preprocessing
5.3.3 Mammogram Subnetwork
5.3.4 Fusion Mechanism
5.3.5 Classification Model
5.4 Results and Discussion
5.4.1 Training and Testing Validation
5.5 Conclusion
References
6. Neuro-Symbolic Transfer Learning Model with Logic-Based Intrusion Detection System in IoT
Deepak V., S. John Justin Thangaraj, Yogaraja C. A. and Iswariya S.
6.1 Introduction
6.2 Literature Review
6.3 Neuro-Symbolic Transfer Learning + BiLSTM Model
6.3.1 IoT Data Preprocessing
6.3.2 Transfer Learning-Based Feature Extractor
6.3.3 BiLSTM Feature Extraction
6.3.4 Transfer Learning and Domain Adaptation
6.3.5 Neuro-Symbolic Integration
6.4 Results and Discussion
6.5 Conclusion
References
7. Integrating Artificial Intelligence in Neuro-Symbolic: Challenges, Applications, and Future Directions
J. D. Dorathi Jayaseeli, D. Malathi, R. S. Ponmagal, G. Abirami, S. Nagadevi and M. Senthil Raja
7.1 Introduction
7.2 Neuro-Symbolic AI: An Overview
7.2.1 Neuro-Symbolic Properties
7.3 Evolution of Neuro-Symbolic AI
7.4 Neural-Symbolic Integration
7.4.1 Symbolic Neuro-Symbolic Model
7.4.2 Symbolic Model
7.4.3 Neural Learning + Symbolic Solver Model
7.5 Applications of Neuro-Symbolic AI
7.5.1 Natural Language Processing
7.5.2 Medical Applications
7.5.3 Neuro-Symbolic AI in Robotics
7.5.4 Neuro-Symbolic AI in Computer Vision
7.5.5 Neuro-Symbolic AI in Optimization Techniques
7.6 Challenges and Future Directions in Neuro-Symbolic AI
7.6.1 Architectural Complexity and Integration Difficulty
7.6.2 Differentiable Reasoning and Optimization
7.6.3 Knowledge Representation and Abstraction
7.6.4 Scalability and Computational Cost
7.6.5 Lack of Unified Benchmarks and Evaluation Metrics
7.6.6 Data and Supervision Requirements
7.6.7 Generalization and Transferability
7.6.8 Explainability and Trust
7.6.9 Robustness to Noise and Ambiguity
7.7 Conclusion
References
Part 2: Neuro-Symbolic AI: Applications
8. A Rule-Based Decision Framework for Accident Prevention in Intelligent Transport Systems
D. Pavithra, T. Deepa, Shaik Naseema, R. Nidhya, G. Smilarubavathy and C. Kumar
8.1 Introduction
8.2 Related Work
8.3 Rule-Based Accident Prevention System
8.3.1 Data Acquisition Module
8.3.2 Normalization Process
8.3.3 Rule-Based Inference Engine
8.3.4 Real-Time Decision and Alert Generation
8.4 Simulation Results
8.5 Conclusion
References
9. A Hybrid Logic-Driven and Neural Parsing Framework for Enhanced Emotion Recognition in Natural Language Processing
R. Nidhya, V. Arun, T. Maragatham, D. J. Ashpin Pabi, Ajaypradeep N. and Manish Kumar
9.1 Introduction
9.2 Literature Review
9.3 Methodology
9.3.1 Logic-Driven Neural Parsing Algorithm (LDNPA)
9.3.2 Emotion Classification Layer
9.4 Results and Discussion
9.5 Conclusion
References
10. A Neuro-Symbolic AI Approach for Lumbar Spinal Stenosis Detection Using Graph Convolutional Networks and Fuzzy Logic
Gurusamy Murugesan, Sabenabanu Abdulkadhar, Selvamuthukumar T., Velkumar K. and Rajkumar K.
10.1 Introduction
10.2 Materials and Methods
10.2.1 Neuro-Symbolic AI Framework
10.2.1.1 Graph Convolutional Neural Network
10.2.1.2 Symbolic Module
10.2.1.3 Combine Symbolic Adjustments
10.3 Results and Discussion
10.3.1 Datasets
10.3.2 Model Performance
10.3.3 Discussion
10.4 Conclusion and Future Work
References
11. Adaptive Filtering Framework for Medical Image Denoising across Spatial and Wavelet Filters
Naveen Kumar Penjarla, Tejaswi Vallabhapurapu, Syamala Rao P., Nissankara Lakshmi Prasanna, Kamesh Sonti and P. Vishnu Priya
11.1 Introduction
11.2 Literature Review
11.3 Methodology
11.4 Results and Discussion
11.5 Conclusion
References
12. Heritage Monument Classification Using Hybrid Deep Attention-Based Architecture for Cultural Preservation
A. Satya Phani Kumari, Kalai Vani Y.S., Savitha S., Sujata Kulkarni and Jyothi N. M.
12.1 Introduction
12.2 Literature Survey
12.3 Methodology
12.3.1 ViT + CBAM Hybrid Architecture
12.3.2 Evaluation Metrics
12.4 Experimentation
12.5 Results
12.6 Discussion
12.7 Conclusion
References
13. Comparative Analysis and Classification of Age-Related Medical Conditions Applying Neural Network and Transformer-Based Deep Models
Levina Tukaram, Umme Najma, D. Chandravathi, Bh. Padma and Jyothi N. M.
13.1 Introduction
13.2 Literature Survey
13.3 Methodology
13.3.1 FCNN
13.3.2 CNN
13.3.3 LSTM
13.3.4 Transformers
13.3.5 Dataset Description
13.3.6 Data Preprocessing
13.3.7 Feature Engineering
13.4 Experimentation
13.4.1 Training
13.4.2 Parameter and Hyperparameter Setting
13.5 Results
13.6 Discussion
13.6.1 Comparative Analysis of the Various Metrics of the Results
13.6.2 Cross-Validation
13.6.3 Benchmark
13.7 Conclusion and Future Enhancements
References
14. Integrating Locality Sensitive Hashing and Embeddings into Collaborative Filtering for the Visual-Image-Based View
Balaji Maram, Rekha Sundari, Anupama Angadi, Satya Keerthi Gorripati and Venubabu Rachapudi
14.1 Introduction
14.2 Related Works
14.2.1 Recommender Systems
14.2.2 Transfer Learning
14.2.3 LSH Similarity Metric
14.3 Methodology
14.3.1 Basic Idea
14.3.2 The Proposed Method
14.3.2.1 Feature Extraction Phase
14.3.2.2 Dimensionality Reduction
14.3.2.3 Feature Normalization
14.3.2.4 Data Augmentation
14.3.2.5 Determining Similarity
14.4 Experimental Results and Analysis
14.4.1 Dataset
14.4.2 Performance Evolution
14.5 Conclusion
References
15. Adversarial Architectures and BERT for Mitigating Gender Bias in Word Embeddings towards Ethical AI Systems
Saraswathi Rangaraju, P. Lakshmilavanya, Karunsagar Kanda, Bh. Padma, Kothapalli Ramesh Chandra and Jyothi N. M.
15.1 Introduction
15.2 Literature Survey
15.3 Methodology
15.3.1 Dataset Description
15.3.2 Pre-Processing
15.3.3 BERT Embedding Generation
15.4 Results
15.4.1 Visualizing Gender Bias in Static Embeddings
15.4.2 Cosine Similarity Heatmap for Word Embeddings
15.4.3 PCA Visualization of Word Embeddings (2D)
15.4.4 Bias Comparison for Selected Words
15.4.5 Correlation Heatmap of Word Embeddings
15.4.6 Pairwise Euclidean Distance Heatmap of Word Embeddings
15.4.7 t-SNE Visualization of Word Embeddings
15.4.8 Clustering with K-Means (PCA Visualization)
15.4.9 Gender Bias Identification and Mitigation Results
15.4.10 Comparison of Gender Bias Before and After Neutralization (GloVe)
15.4.11 Bias Analysis and Mitigation in BERT Embeddings
15.4.12 Comparison: Gender Bias Before and After Neutralization (BERT)
15.4.13 GloVe Embeddings Before and After Neutralization (PCA Scatter Plot)
15.4.14 Comparison of Gender Bias Neutralization Methods
15.5 Discussion
15.5.1 Evaluation of Bias Mitigation Using WEFAT
15.5.2 Impact of Bias Mitigation on Neighbor Similarities
15.6 Conclusion
References
16. Exploring Machine Learning in Voice‑Based Parkinson’s Disease Diagnosis: A Comprehensive Survey
G. Smilarubavathy and K. Vijayakumar
16.1 Introduction
16.2 Background
16.3 Flowchart
16.3.1 Voice-Based Data in PD Diagnosis
16.3.2 Dataset Overview
16.3.3 Key Dataset Description
16.3.4 Features Extracted
16.3.5 Machine Learning Techniques
16.4 Performance Metrics
16.5 Comparative Analysis
16.6 Challenges and Limitations
16.7 Future Directions
Conclusion
References
17. Neuro-AI-Driven Image Augmentation and Data Leak Prevention via Automated Classification Agents
S. M. Keerthana and K. Vijayakumar
17.1 Introduction
17.2 Background
17.3 Methods
17.3.1 Preprocessing and Automatic Annotating
17.3.2 Architecture
17.4 Result
Conclusion
References
Index

Back to Top



Description
Author/Editor Details
Table of Contents
Bookmark this page