Computational Intelligence

T. Ananth Kumar, PhD, is an associate professor at the Indo French Educational Trust College of Engineering, Anna University, Chennai, India. He has presented papers in various national and international conferences and journals, as well as many book chapters. Additionally, he is a lifetime member of the Indian Society of Technical Education and has many patents spanning across various domains. E. Golden Julie, PhD, is currently working as a Senior Assistant Professor in the department of Computer Science and Engineering, Anna University, Tirunelveli, India. She has more than 12 years of experience in teaching, has published more than 34 papers in various international journals, presented more than 20 papers in both national and international conferences, and written ten book chapters. She has given many guest lectures on various subjects such as multicore architecture, operating systems, and compiler design in premier institutions. Additionally, she is an active lifetime member of the Indian Society of Technical Education. Venkata Raghuveer Burugadda is a senior solution architect and technology leader with over 16 years of experience across the United States and India in product delivery and technology transformation, driving growth for a global network in remittances and payments. He modernized a point of sale solution with new and organizational common architecture to deliver a fast and efficient user experience and allow easy integration of new capabilities through the adoption of cloud migration, devops, test driven principles, and user-centric solutions. Abhishek Kumar, PhD, is currently working as an associate professor and the assistant director of the Computer Science & Engineering Department at Chandigarh University, Punjab, India. He has more than 11 years of teaching experience and has been a session chair and keynote speaker for many international conferences and webinars. In addition to his experience, he has more than 100 publications in reputed, peer-reviewed national and international journals, books, and conferences, has authored or co-authored seven books published, and edited an additional 27 books. Puneet Kumar, PhD, is a professor and the head of the Department of Computer Science & Engineering at the University Institute of Engineering, Chandigarh University, Mohali, India. He has more than 18 years of teaching, research, and industrial experience and has published various research papers and articles in national and international journals, many of which are widely cited across the world. He is also the recipient of several software copyrights from the Ministry of Human Resource and Development, Government of India.

• Introduction xvii1 Computational Intelligence Theory: An Orientation Technique 1S. Jaisiva, C. Kumar, S. Sakthiya Ram, C. Sakthi Gokul Rajan and P. Praveen Kumar1.1 Computational Intelligence 21.2 Application Fields for Computational Intelligence 41.2.1 Neural Networks 41.2.1.1 Classification 41.2.1.2 Clustering or Compression 51.2.1.3 Generation of Sequences or Patterns 51.2.1.4 Control Systems 51.2.1.5 Evolutionary Computation 61.2.2 Fuzzy Logic 61.2.2.1 Fuzzy Control Systems 61.2.2.2 Fuzzy Systems 61.2.2.3 Behavioral Motivations for Fuzzy Logic 71.3 Computational Intelligence Paradigms 71.3.1 Artificial Neural Networks 71.3.2 Evolutionary Computation (EC) 101.3.3 Optimization Method 111.3.3.1 Optimization 111.4 Architecture Assortment 121.4.1 Swarm Intelligence 141.4.2 Artificial Immune Systems 141.5 Myths About Computational Intelligence 151.6 Supervised Learning in Computational Intelligence 161.6.1 Performance Measures 171.6.1.1 Accuracy 171.6.1.2 Complexity 181.6.1.3 Convergence 191.6.2 Performance Factors 191.6.2.1 Data Preparation 191.6.2.2 Scaling and Normalization 191.6.2.3 Learning Rate and Momentum 201.6.2.4 Learning Rate 201.6.2.5 Noise Injection 201.7 Training Set Manipulation 211.8 Conclusion 21References 212 Nature-Inspired Algorithms for Computational Intelligence Theory—A State-of-the-Art Review 25B. Akoramurthy, K. Dhivya and B. Surendiran2.1 Introduction 252.2 Related Works 272.3 Optimization and Its Algorithms 282.3.1 Definition 282.3.2 Mathematical Notations 282.3.3 Gradient-Based Algorithms 292.3.4 Gradient-Free Optimizers or Algorithms 312.4 Metaheuristic Optimization Methods 322.4.1 Ant Colony Algorithm 322.4.1.1 Ant Colony Optimization Algorithm 322.4.2 Flower Pollination Algorithm 342.4.3 Genetic Algorithms 352.4.4 Evolutionary Algorithm 362.4.5 Method Based on Bats 372.4.6 Cuckoo Searching Method 382.4.7 Firefly Algorithm 392.4.8 Particle Swarm Optimization Algorithm 412.4.9 Krill Herd Algorithm 422.4.10 Artificial Bee Colony (ABC) 432.5 Computational and Autonomous Systems 442.5.1 Computational Features of Nature-Inspired Computing 442.5.2 Comparison with Legacy Algorithms 452.5.3 Autonomous Criticality Systems 462.6 Unresolved Issues for Continued Study 47References 493 AI-Based Computational Intelligence Theory 53Jana Selvaganesan, S. Arunmozhiselvi, E. Preethi and S. Thangam3.1 Computational Intelligence 543.2 Designing Expert Systems 553.2.1 Characteristics 563.3 Core of Computational Intelligence 563.3.1 Artificial Intelligence (AI) 563.3.2 Machine Learning (ML) 573.3.3 Neural Networks 573.3.4 Evolutionary Computation 583.3.5 Fuzzy Systems 583.3.6 Swarm Intelligence 593.3.7 Bayesian Networks 603.3.8 Optimization Techniques 603.3.9 Data Mining and Pattern Recognition 603.3.10 Decision Support Systems 613.3.11 Hybrid Approaches 613.4 Research and Development 623.4.1 Government Plans in Enriching AI-Based Computational Intelligence Theory 623.4.1.1 Funding and Research Initiatives 623.4.1.2 Policy and Regulation 623.4.1.3 Standards and Interoperability 633.4.1.4 Education and Workforce Development 633.4.1.5 Industry Collaboration and Partnerships 633.4.1.6 Ethical Guidelines and Responsible AI 633.4.1.7 International Collaboration and Governance 643.5 New Opportunities and Challenges 643.5.1 Explainable AI (XAI) 643.5.2 Adversarial Machine Learning 653.5.3 AI for Edge Computing 653.5.4 Continual Learning 673.5.5 Meta-Learning 683.5.6 AI for Cybersecurity 693.5.7 AI for Healthcare 703.5.7.1 AI for Healthcare-Based Recommendation System 723.5.8 Responsible AI 723.5.9 AI and Robotics Integration 733.5.10 AI for Sustainability and Climate Change 743.5.11 Quantum Computing and AI 753.5.12 Human–AI Collaboration 763.6 Applications 773.6.1 Google-Waymo Car 773.6.2 ChatGPT 793.6.3 Boston Dynamics’ Atlas 803.6.4 Netflix 813.6.5 Trinetra 823.6.6 Voice-Activated Backpack 833.7 Case Study: YOLO v7 for Object Detection in TensorFlow 843.7.1 Yolo V 7 843.7.2 Working and Its Features 853.7.3 Configuration to Deploy YOLO V 7 873.8 Results 883.9 Performance Analysis 893.10 Challenges in Automation 913.10.1 Marching Towards Solution 923.11 Conclusion 93References 934 Information Processing, Learning, and Its Artificial Intelligence 97P. Praveenkumar, Pragati M., Prathiba S., Mirthulaa G., Supriya P., Jayashree B. and Jayasri R.4.1 Introduction—Artificial Intelligence 984.2 Artificial Intelligence and Its Learning 994.3 Artificial Intelligence’s Effects on IT 1004.4 Examples of Artificial Intelligence 1014.4.1 Smart Learning Content 1014.4.2 Intelligent Tutorial System Future 1034.4.3 Virtual Facilitators and Learning Environment 1044.4.4 Content Analytics 1054.5 Data Processing and AI in Human-Centered Manufacturing 1064.6 Information Learning 1074.6.1 Information Learning Through AI—Chatbots 1074.6.2 Information Learning Through AI—Virtual Reality (vr) 1084.6.3 Information Learning Through AI—Management of Learning (LMS) 1104.6.4 Information Learning Through AI—Robotics 1114.6.5 AI Invoice Processing is Not Fantastical— It is Fantastic 1134.7 Results 1134.8 Conclusion 114References 1145 Computational Intelligence Approach for Exploration of Spatial Co-Location Patterns 117S. LourduMarie Sophie, S. Siva Sathya, S. Sharmiladevi and J. Dhakshayani5.1 Introduction 1185.2 Spatial Data Mining 1205.2.1 Spatial Co-Location Pattern Mining 1205.3 Preliminaries 1235.3.1 Basic Concepts 1235.3.1.1 Feature Instance 1245.3.1.2 Participation Ratio (PR) 1245.3.1.3 Participation Index (PI) 1255.3.1.4 Neighbor Relation 1255.3.1.5 Conditional Neighborhood 1265.3.2 Apache Hadoop—MapReduce 1265.3.3 Related Work 1285.4 Proposed Grid-Conditional Neighborhood Algorithm 1305.4.1 Module Description 1315.4.1.1 Search Neighbor 1315.4.1.2 Group Neighbors 1325.4.1.3 Pattern Search 1335.4.1.4 Top K Pattern Generation 1335.5 Experimental Setup and Analysis 1345.5.1 Dataset Used 1345.5.2 Performance Analysis 1365.6 Discussion and Conclusion 138References 1406 Computational Intelligence-Based Optimal Feature Selection Techniques for Detecting Plant Diseases 145Karthickmanoj R., S. Aasha Nandhini and T. Sasilatha6.1 Introduction 1456.2 Literature Survey 1466.3 Proposed Framework 1516.4 Simulation Results 1526.5 Summary 156References 1567 Protein Structure Prediction Using Convolutional Neural Networks Augmented with Cellular Automata 159Pokkuluri Kiran Sree, Prasun Chakrabarti, Martin Margala and SSSN Usha Devi N.7.1 Introduction 1607.2 Methods 1627.3 Design of the Model 1647.4 Results and Comparisons 1677.5 Conclusion 172References 1728 Modeling and Approximating Renewable Energy Systems Using Computational Intelligence 175B. Balaji, P. Hemalatha, T. Rampradesh, G. Anbarasi and A. Eswari8.1 Introduction 1768.2 Expert System 1788.3 Artificial Neural Networks 1798.4 ANN in Renewable Energy Systems 1828.5 Conclusion 185References 1869 Computational Intelligence and Deep Learning in Health Informatics: An Introductory Perspective 189J. Naskath, R. Rajakumari, Hamza Aldabbas and Zaid Mustafa9.1 Introduction 1909.2 Mobile Application in Health Informatics Using Deep Learning 1919.3 Health Informatics Wearables Using Deep Learning 1979.4 Electroencephalogram 2029.5 Conclusion 203References 20710 Computational Intelligence for Human Activity Recognition (HAR) 213Thangapriya and Nancy Jasmine Goldena10.1 Introduction 21410.2 Fuzzy Logic in Human Judgment and Decision-Making 21510.2.1 FL Algorithm 21610.2.2 Applications of FL 21710.2.3 Advantages of FL 21710.2.4 Disadvantages of FL 21810.2.5 Utilizing FLS and FIS in HAR Research and Health Monitoring 21810.3 Artificial Neural Networks: From Perceptrons to Modern Applications 21910.3.1 ANN Algorithm 22110.3.2 Applications of ANN 22210.3.3 Advantages of ANN 22210.3.4 Disadvantages of ANN 22210.3.5 Artificial Neural Networks in HAR Research 22310.4 Swarm Intelligence 22310.4.1 SI Algorithm 22410.4.2 Applications of SI 22410.4.3 Advantages of SI 22510.4.4 Disadvantages of SI 22510.4.5 Swarm Intelligence Techniques in HAR Research 22510.5 Evolutionary Computing 22610.5.1 EC Algorithm 22610.5.2 Applications of EC 22710.5.3 Advantages of EC 22810.5.4 Disadvantages of EC 22810.5.5 Harnessing Evolutionary Computation for HAR Research 22810.6 Artificial Immune System 22810.6.1 AIS Algorithm 22910.6.2 Applications of AIS 23010.6.3 Advantages of AIS 23010.6.4 Disadvantages of AIS 23010.6.5 Harnessing AIS for Preventive Measures 23110.7 Conclusion 231References 23211 Computational Intelligence for Multimodal Analysis of High-Dimensional Image Processing in Clinical Settings 235B. Balaji, P. Pugazhendiran, N. Sivanantham, N. Velammal and P. Vimala11.1 Basics of Machine Learning 23611.2 Feature Extraction 23711.3 Selection of Features 23811.4 Statistical Classifiers 23911.5 Neural Networks 24211.6 Biometric Analysis 24411.7 Data from High-Resolution Medical Imaging 25111.8 Computational Architectures 25511.9 Timing and Uncertainty 25611.10 AI and Risk of Harm 25811.11 Conclusion 259References 25912 A Review of Computational Intelligence-Based Biometric Recognition Methods 263T. IlamParithi, K. Antony Sudha and D. Jessintha12.1 Introduction 26312.1.1 Objective 26412.2 Computational Intelligence 26412.3 CI-Based Biometric Recognition 26612.3.1 Acquisition 26612.3.2 Segmentation 26612.3.3 Quality Assessment 26912.3.4 Enhancement 27012.3.5 Feature Extraction 27012.3.6 Matching 27112.3.7 Classification 27212.3.8 Score Normalization 27212.3.9 Anti-Spoofing 27212.3.10 Privacy 27312.4 Applications 27312.4.1 Business 27312.4.2 Education 27412.4.3 Military 27512.4.4 Health Care 27612.4.5 Banking 27612.5 Conclusion 277References 27713 Seeing the Unseen: An Automated Early Breast Cancer Detection Using Hyperspectral Imaging 281Sravan Kumar Sikhakolli, Suresh Aala, Sunil Chinnadurai and Inbarasan Muniraj13.1 Introduction 28213.1.1 Conventional Imaging Methods for Detecting BC 28313.1.2 Optical Imaging Techniques to Detect BC 28413.2 Hyperspectral Imaging (HSI) 28513.2.1 How Does HSI Setup Look Like? 28613.3 State-of-the-Art Techniques for BC Detection 28713.3.1 Breast Cancer Ex Vivo Analysis 28713.3.2 Breast Cancer In Vivo Analysis 29013.4 Artificial Intelligence in BC Detection Using HSI 29113.4.1 Deep Learning in HSI 29113.4.2 Convolutional Neural Networks 29213.4.3 Deep Belief Networks Using HSI 29313.4.4 Residual Networks 29313.5 Discussion and Conclusion 293References 29414 Shedding Light into the Dark: Early Oral Cancer Detection Using Hyperspectral Imaging 301Suresh Aala, Sravan Kumar Sikhakolli, Inbarasan Muniraj and Sunil Chinnadurai14.1 Introduction 30214.2 HSI in HNC Detection 30514.3 Deep Learning in In Vivo HSI 31314.3.1 Endoscopic 31314.4 Conclusion and Future Research Directions 315References 31615 Machine Learning Techniques for Glaucoma Screening Using Optic Disc Detection 321V. Subha, S. Niraja P. Rayen and Manivanna Boopathi15.1 Introduction 32215.1.1 Ophthalmic Process 32415.1.2 Digital Imaging 32415.1.2.1 Image Processing 32515.1.3 Eye and Its Parts 32615.1.3.1 Optic Disc 32715.1.3.2 Aqueous Humor 32715.1.3.3 Choroid 32715.1.3.4 Ciliary Body 32715.1.3.5 Ciliary Muscle 32715.1.3.6 Iris 32815.1.3.7 Pupil 32815.1.3.8 Retina 32815.1.3.9 Photoreceptor Cells 32815.1.3.10 Retinal Blood Vessels 32815.1.3.11 Sclera 32915.1.3.12 Uvea 32915.1.3.13 Visual Axis 32915.1.3.14 Visual Cortex 32915.1.3.15 Visual Fields 32915.1.3.16 Vitreous 32915.1.3.17 Zonules 33015.1.3.18 Macula (Yellow Spot) 33015.1.3.19 Optic Nerve 33015.1.4 Eye Diseases 33015.1.4.1 Myopia 33015.1.4.2 Hyperopia 33015.1.4.3 Astigmatism 33015.1.4.4 Presbyopia 33115.1.4.5 Strabismus 33115.1.4.6 Amblyopia 33115.1.4.7 Cataracts 33115.1.4.8 Glaucoma 33215.1.5 Indications of Glaucoma 33215.1.6 Causes of Glaucoma 33215.1.6.1 Dietary 33215.1.6.2 Ethnicity and Gender 33215.1.6.3 Genetics 33315.1.7 Analytical Methods of Glaucoma 33315.2 Glaucoma Screening with Optic Disc and Classification 33415.2.1 Optic Disc Detection 33515.2.2 Cropping ROI 33715.2.3 Optic Disc Segmentation 33815.2.4 Optic Cup Segmentation 33815.2.5 Post-Processing 34015.2.5.1 Cup–Disc Ratio 34015.2.5.2 Evaluation of the NRR Area in the ISNT Quadrants 34115.2.5.3 Superpixel Method 34115.2.5.4 Level Set Method 34215.3 Experimental Section 34215.3.1 Dataset Description 34215.3.2 Experimental Images 34315.3.3 Experimental Testing Phase 34315.3.4 Performance Analysis 34415.4 Conclusion 345References 34616 Role of Artificial Intelligence in Marketing 349G. Muruganantham and R.S. Aswanth16.1 Introduction 35016.1.1 Impact of AI in Marketing 35116.1.2 Benefits of AI in Marketing 35216.1.3 AI in Marketing Functions 35416.1.4 Applications of AI in Marketing 35416.1.5 Challenges of AI in Marketing 35616.1.6 Future of AI in Marketing 35716.2 New Trends of AI in Marketing 35816.2.1 Companies Using AI in Marketing 35916.3 Aspects of AI in Marketing across Different Industries 36216.4 Conclusion 364References 365About the Editors 369Index 371