Computational Intelligence: Theory and Applications

Chapter 1 Computational Intelligence Theory: An Orientation Technique
	1.1 Computational Intelligence
	1.2 Application Fields for Computational Intelligence
		1.2.1 Neural Networks
			1.2.1.1 Classification
			1.2.1.2 Clustering or Compression
			1.2.1.3 Generation of Sequences or Patterns
			1.2.1.4 Control Systems
			1.2.1.5 Evolutionary Computation
		1.2.2 Fuzzy Logic
			1.2.2.1 Fuzzy Control Systems
			1.2.2.2 Fuzzy Systems
			1.2.2.3 Behavioral Motivations for Fuzzy Logic
	1.3 Computational Intelligence Paradigms
		1.3.1 Artificial Neural Networks
		1.3.2 Evolutionary Computation (EC)
		1.3.3 Optimization Method
			1.3.3.1 Optimization
	1.4 Architecture Assortment
		1.4.1 Swarm Intelligence
		1.4.2 Artificial Immune Systems
	1.5 Myths About Computational Intelligence
	1.6 Supervised Learning in Computational Intelligence
		1.6.1 Performance Measures
			1.6.1.1 Accuracy
			1.6.1.2 Complexity
			1.6.1.3 Convergence
		1.6.2 Performance Factors
			1.6.2.1 Data Preparation
			1.6.2.2 Scaling and Normalization
			1.6.2.3 Learning Rate and Momentum
			1.6.2.4 Learning Rate
			1.6.2.5 Noise Injection
	1.7 Training Set Manipulation
	1.8 Conclusion
	References
Chapter 2 Nature-Inspired Algorithms for Computational Intelligence Theory—A State-of-the-Art Review
	2.1 Introduction
	2.2 Related Works
	2.3 Optimization and Its Algorithms
		2.3.1 Definition
		2.3.2 Mathematical Notations
		2.3.3 Gradient-Based Algorithms
		2.3.4 Gradient-Free Optimizers or Algorithms
	2.4 Metaheuristic Optimization Methods
		2.4.1 Ant Colony Algorithm
			2.4.1.1 Ant Colony Optimization Algorithm
		2.4.2 Flower Pollination Algorithm
		2.4.3 Genetic Algorithms
		2.4.4 Evolutionary Algorithm
		2.4.5 Method Based on Bats
		2.4.6 Cuckoo Searching Method
		2.4.7 Firefly Algorithm
		2.4.8 Particle Swarm Optimization Algorithm
		2.4.9 Krill Herd Algorithm
		2.4.10 Artificial Bee Colony (ABC)
	2.5 Computational and Autonomous Systems
		2.5.1 Computational Features of Nature-Inspired Computing
		2.5.2 Comparison with Legacy Algorithms
		2.5.3 Autonomous Criticality Systems
	2.6 Unresolved Issues for Continued Study
	References
Chapter 3 AI-Based Computational Intelligence Theory
	3.1 Computational Intelligence
	3.2 Designing Expert Systems
		3.2.1 Characteristics
	3.3 Core of Computational Intelligence
		3.3.1 Artificial Intelligence (AI)
		3.3.2 Machine Learning (ML)
		3.3.3 Neural Networks
		3.3.4 Evolutionary Computation
		3.3.5 Fuzzy Systems
		3.3.6 Swarm Intelligence
		3.3.7 Bayesian Networks
		3.3.8 Optimization Techniques
		3.3.9 Data Mining and Pattern Recognition
		3.3.10 Decision Support Systems
		3.3.11 Hybrid Approaches
	3.4 Research and Development
		3.4.1 Government Plans in Enriching AI-Based Computational Intelligence Theory
			3.4.1.1 Funding and Research Initiatives
			3.4.1.2 Policy and Regulation
			3.4.1.3 Standards and Interoperability
			3.4.1.4 Education and Workforce Development
			3.4.1.5 Industry Collaboration and Partnerships
			3.4.1.6 Ethical Guidelines and Responsible AI
			3.4.1.7 International Collaboration and Governance
	3.5 New Opportunities and Challenges
		3.5.1 Explainable AI (XAI)
		3.5.2 Adversarial Machine Learning
		3.5.3 AI for Edge Computing
		3.5.4 Continual Learning
		3.5.5 Meta-Learning
		3.5.6 AI for Cybersecurity
		3.5.7 AI for Healthcare
			3.5.7.1 AI for Healthcare-Based Recommendation System
		3.5.8 Responsible AI
		3.5.9 AI and Robotics Integration
		3.5.10 AI for Sustainability and Climate Change
		3.5.11 Quantum Computing and AI
		3.5.12 Human–AI Collaboration
	3.6 Applications
		3.6.1 Google-Waymo Car
		3.6.2 ChatGPT
		3.6.3 Boston Dynamics’ Atlas
		3.6.4 Netflix
		3.6.5 Trinetra
		3.6.6 Voice-Activated Backpack
	3.7 Case Study: YOLO v7 for Object Detection in TensorFlow
		3.7.1 YOLO v7
		3.7.2 Working and Its Features
		3.7.3 Configuration to Deploy YOLO V7
	3.8 Results
	3.9 Performance Analysis
	3.10 Challenges in Automation
		3.10.1 Marching Towards Solution
	3.11 Conclusion
	References
Chapter 4 Information Processing, Learning, and Its Artificial Intelligence
	4.1 Introduction—Artificial Intelligence
	4.2 Artificial Intelligence and Its Learning
	4.3 Artificial Intelligence’s Effects on IT
	4.4 Examples of Artificial Intelligence
		4.4.1 Smart Learning Content
		4.4.2 Intelligent Tutorial System Future
		4.4.3 Virtual Facilitators and Learning Environment
		4.4.4 Content Analytics
	4.5 Data Processing and AI in Human-Centered Manufacturing
	4.6 Information Learning
		4.6.1 Information Learning Through AI—Chatbots
		4.6.2 Information Learning Through AI—Virtual Reality (VR)
		4.6.3 Information Learning Through AI—Management of Learning (LMS)
		4.6.4 Information Learning Through AI—Robotics
		4.6.5 AI Invoice Processing is Not Fantastical— It is Fantastic
	4.7 Results
	4.8 Conclusion
	References
Chapter 5 Computational Intelligence Approach for Exploration of Spatial Co-Location Patterns
	5.1 Introduction
	5.2 Spatial Data Mining
		5.2.1 Spatial Co-Location Pattern Mining
	5.3 Preliminaries
		5.3.1 Basic Concepts
			5.3.1.1 Feature Instance
			5.3.1.2 Participation Ratio (PR)
			5.3.1.3 Participation Index (PI)
			5.3.1.4 Neighbor Relation
			5.3.1.5 Conditional Neighborhood
		5.3.2 Apache Hadoop—MapReduce
		5.3.3 Related Work
	5.4 Proposed Grid-Conditional Neighborhood Algorithm
		5.4.1 Module Description
			5.4.1.1 Search Neighbor
			5.4.1.2 Group Neighbors
			5.4.1.3 Pattern Search
			5.4.1.4 Top K Pattern Generation
	5.5 Experimental Setup and Analysis
		5.5.1 Dataset Used
		5.5.2 Performance Analysis
	5.6 Discussion and Conclusion
	References
Chapter 6 Computational Intelligence-Based Optimal Feature Selection Techniques for Detecting Plant Diseases
	6.1 Introduction
	6.2 Literature Survey
	6.3 Proposed Framework
	6.4 Simulation Results
	6.5 Summary
	References
Chapter 7 Protein Structure Prediction Using Convolutional Neural Networks Augmented with Cellular Automata
	7.1 Introduction
	7.2 Methods
	7.3 Design of the Model
	7.4 Results and Comparisons
	7.5 Conclusion
	References
Chapter 8 Modeling and Approximating Renewable Energy Systems Using Computational Intelligence
	8.1 Introduction
	8.2 Expert System
	8.3 Artificial Neural Networks
	8.4 ANN in Renewable Energy Systems
	8.5 Conclusion
	References
Chapter 9 Computational Intelligence and Deep Learning in Health Informatics: An Introductory Perspective
	9.1 Introduction
	9.2 Mobile Application in Health Informatics Using Deep Learning
	9.3 Health Informatics Wearables Using Deep Learning
	9.4 Electroencephalogram
	9.5 Conclusion
	References
Chapter 10 Computational Intelligence for Human Activity Recognition (HAR)
	10.1 Introduction
	10.2 Fuzzy Logic in Human Judgment and Decision-Making
		10.2.1 FL Algorithm
		10.2.2 Applications of FL
		10.2.3 Advantages of FL
		10.2.4 Disadvantages of FL
		10.2.5 Utilizing FLS and FIS in HAR Research and Health Monitoring
	10.3 Artificial Neural Networks: From Perceptrons to Modern Applications
		10.3.1 ANN Algorithm
		10.3.2 Applications of ANN
		10.3.3 Advantages of ANN
		10.3.4 Disadvantages of ANN
		10.3.5 Artificial Neural Networks in HAR Research
	10.4 Swarm Intelligence
		10.4.1 SI Algorithm
		10.4.2 Applications of SI
		10.4.3 Advantages of SI
		10.4.4 Disadvantages of SI
		10.4.5 Swarm Intelligence Techniques in HAR Research
	10.5 Evolutionary Computing
		10.5.1 EC Algorithm
		10.5.2 Applications of EC
		10.5.3 Advantages of EC
		10.5.4 Disadvantages of EC
		10.5.5 Harnessing Evolutionary Computation for HAR Research
	10.6 Artificial Immune System
		10.6.1 AIS Algorithm
		10.6.2 Applications of AIS
		10.6.3 Advantages of AIS
		10.6.4 Disadvantages of AIS
		10.6.5 Harnessing AIS for Preventive Measures
	10.7 Conclusion
	References
Chapter 11 Computational Intelligence for Multimodal Analysis of High-Dimensional Image Processing in Clinical Settings
	11.1 Basics of Machine Learning
	11.2 Feature Extraction
	11.3 Selection of Features
	11.4 Statistical Classifiers
	11.5 Neural Networks
	11.6 Biometric Analysis
	11.7 Data from High-Resolution Medical Imaging
	11.8 Computational Architectures
	11.9 Timing and Uncertainty
	11.10 AI and Risk of Harm
	11.11 Conclusion
	References
Chapter 12 A Review of Computational Intelligence-Based Biometric Recognition Methods
	12.1 Introduction
		12.1.1 Objective
	12.2 Computational Intelligence
	12.3 CI-Based Biometric Recognition
		12.3.1 Acquisition
		12.3.2 Segmentation
		12.3.3 Quality Assessment
		12.3.4 Enhancement
		12.3.5 Feature Extraction
		12.3.6 Matching
		12.3.7 Classification
		12.3.8 Score Normalization
		12.3.9 Anti-Spoofing
		12.3.10 Privacy
	12.4 Applications
		12.4.1 Business
		12.4.2 Education
		12.4.3 Military
		12.4.4 Health Care
		12.4.5 Banking
	12.5 Conclusion
	References
Chapter 13 Seeing the Unseen: An Automated Early Breast Cancer Detection Using Hyperspectral Imaging
	13.1 Introduction
		13.1.1 Conventional Imaging Methods for Detecting BC
		13.1.2 Optical Imaging Techniques to Detect BC
	13.2 Hyperspectral Imaging (HSI)
		13.2.1 How Does HSI Setup Look Like?
	13.3 State-of-the-Art Techniques for BC Detection
		13.3.1 Breast Cancer Ex Vivo Analysis
		13.3.2 Breast Cancer In Vivo Analysis
	13.4 Artificial Intelligence in BC Detection Using HSI
		13.4.1 Deep Learning in HSI
		13.4.2 Convolutional Neural Networks
		13.4.3 Deep Belief Networks Using HSI
		13.4.4 Residual Networks
	13.5 Discussion and Conclusion
	References
Chapter 14 Shedding Light into the Dark: Early Oral Cancer Detection Using Hyperspectral Imaging
	14.1 Introduction
	14.2 HSI in HNC Detection
	14.3 Deep Learning in In Vivo HSI
		14.3.1 Endoscopic
	14.4 Conclusion and Future Research Directions
	References
Chapter 15 Machine Learning Techniques for Glaucoma Screening Using Optic Disc Detection
	15.1 Introduction
		15.1.1 Ophthalmic Process
		15.1.2 Digital Imaging
			15.1.2.1 Image Processing
		15.1.3 Eye and Its Parts
			15.1.3.1 Optic Disc
			15.1.3.2 Aqueous Humor
			15.1.3.3 Choroid
			15.1.3.4 Ciliary Body
			15.1.3.5 Ciliary Muscle
			15.1.3.6 Iris
			15.1.3.7 Pupil
			15.1.3.8 Retina
			15.1.3.9 Photoreceptor Cells
			15.1.3.10 Retinal Blood Vessels
			15.1.3.11 Sclera
			15.1.3.12 Uvea
			15.1.3.13 Visual Axis
			15.1.3.14 Visual Cortex
			15.1.3.15 Visual Fields
			15.1.3.16 Vitreous
			15.1.3.17 Zonules
			15.1.3.18 Macula (Yellow Spot)
			15.1.3.19 Optic Nerve
		15.1.4 Eye Diseases
			15.1.4.1 Myopia
			15.1.4.2 Hyperopia
			15.1.4.3 Astigmatism
			15.1.4.4 Presbyopia
			15.1.4.5 Strabismus
			15.1.4.6 Amblyopia
			15.1.4.7 Cataracts
			15.1.4.8 Glaucoma
		15.1.5 Indications of Glaucoma
		15.1.6 Causes of Glaucoma
			15.1.6.1 Dietary
			15.1.6.2 Ethnicity and Gender
			15.1.6.3 Genetics
		15.1.7 Analytical Methods of Glaucoma
	15.2 Glaucoma Screening with Optic Disc and Classification
		15.2.1 Optic Disc Detection
		15.2.2 Cropping ROI
		15.2.3 Optic Disc Segmentation
		15.2.4 Optic Cup Segmentation
		15.2.5 Post-Processing
			15.2.5.1 Cup–Disc Ratio
			15.2.5.2 Evaluation of the NRR Area in the ISNT Quadrants
			15.2.5.3 Superpixel Method
			15.2.5.4 Level Set Method
	15.3 Experimental Section
		15.3.1 Dataset Description
		15.3.2 Experimental Images
		15.3.3 Experimental Testing Phase
		15.3.4 Performance Analysis
	15.4 Conclusion
	References
Chapter 16 Role of Artificial Intelligence in Marketing
	16.1 Introduction
		16.1.1 Impact of AI in Marketing
		16.1.2 Benefits of AI in Marketing
		16.1.3 AI in Marketing Functions
		16.1.4 Applications of AI in Marketing
		16.1.5 Challenges of AI in Marketing
		16.1.6 Future of AI in Marketing
	16.2 New Trends of AI in Marketing
		16.2.1 Companies Using AI in Marketing
	16.3 Aspects of AI in Marketing across Different Industries
	16.4 Conclusion
	References
About the Editors
Index
Also of Interest