Artificial Intelligence: Technologies, Applications, and Challenges

Cover
Half Title
Title Page
Copyright Page
Dedication
Table of Contents
Preface
Acknowledgments
Editors
Contributors
Section I: Introduction to Artificial Intelligence
	Chapter 1: Overview of Artificial Intelligence
		1.1 Introduction
		1.2 Definitions of AI
		1.3 History of AI
		1.4 The Importance of AI
		1.5 Processes Involved with AI
		1.6 AI as an Interdisciplinary Tool
		1.7 Types of AI
		1.8 Advantages and Disadvantages of AI
		1.9 Some Examples of AI
		1.10 Applications of AI
		1.11 Summary
		References
	Chapter 2: Knowledge Representation in Artificial Intelligence:: An Overview
		2.1 Introduction
		2.2 Types of Knowledge
		2.3 The Relation between Intelligence and Knowledge
		2.4 Life Cycle of Knowledge in AI
		2.5 Different Approaches to Knowledge Representation
		2.6 Basic Requirements for Knowledge Representation (KR) System
		2.7 Techniques of Knowledge Representation
		2.8 Real-Time Challenge
		2.9 Conclusion
		References
	Chapter 3: Programming Languages Used in AI
		3.1 Introduction
		3.2 An Overview of AI
		3.3 The Role of AI
			3.3.1 AI in Agriculture
			3.3.2 AI in Security
			3.3.3 AI in Education
			3.3.4 AI in Health Care
			3.3.5 AI in Industry
		3.4 Languages Used in AI
			3.4.1 Java
			3.4.2 C++
			3.4.3 Python
			3.4.4 LISP (LISt Processing)
			3.4.5 Prolog
			3.4.6 R
		3.5 Conclusion
		References
Section II: Artificial Intelligence: Tools and Technologies
	Chapter 4: Image Processing Using Artificial Intelligence:: Case Study on Classification of High-Dimensional Remotely Sensed Images
		4.1 Introduction
		4.2 Issues and Challenges
		4.3 Case Study on the Classification of Airborne ROSIS-3 Data Using ML Approach
			4.3.1 ROSIS-3 Hyperspectral Dataset
			4.3.2 Removal of Redundant Spectral Bands of ROSIS-3 Dataset
			4.3.3 Selection of Optimal Features
			4.3.4 Calibration and Optimization of RF Classifier Model Parameters
			4.3.5 Evaluation of RF Classifier
			4.3.6 Results and Discussion
		4.4 Conclusion and Future Directive
		References
	Chapter 5: Artificial Intelligence and Image Processing
		5.1 Introduction
		5.2 Image Processing
			5.2.1 Images
			5.2.2 Real-Time Usage of Image Processing
		5.3 Artificial Intelligence
		5.4 Artificial Intelligence in Image Processing
		5.5 Proposed Methodology
			5.5.1 Sobel Edge Detection
			5.5.2 Threshold
		5.6 Ant Colony Optimization
		5.7 Entropy
		5.8 Result Analysis
		5.9 Conclusion
		References
	Chapter 6: Deep Learning Applications on Very High-Resolution Aerial Imagery
		6.1 Introduction
		6.2 Machine Learning
		6.3 Deep Learning
			6.3.1 Comparison between ML and DL
			6.3.2 Types of Neural Network
			6.3.3 Convolutional Neural Network (CNN)
			6.3.4 Different CNN Architectures
			6.3.5 Loss Functions and Optimization
				6.3.5.1 Loss Functions for Regression
				6.3.5.2 Loss Functions for Classification
				6.3.5.3 Optimization
		6.4 Deep Learning Applications in Remote Sensing
			6.4.1 Image Scene Classification
			6.4.2 Object Detection
			6.4.3 Semantic Segmentation
			6.4.4 Object Tracking
		6.5 Case Study
			6.5.1 Objective
			6.5.2 Dataset Preparation and Preprocessing
			6.5.3 Network Architecture Design
			6.5.4 Hyperparameter Selection
			6.5.5 Inference Training
			6.5.6 Results
		6.6 Challenges with DL on Remote Sensing Data
		6.7 Conclusion
		References
	Chapter 7: Improved Combinatorial Algorithms Test for Pairwise Testing Used for Testing Data Generation in Big Data Applications
		7.1 Introduction
		7.2 Literature Review
		7.3 Combinatorial Testing
			7.3.1 Positives of Combinational Testing
		7.4 Applications of AI in Software Testing
		7.5 Big Data and Big Data Applications
			7.5.1 Significance of Applications
			7.5.2 Models of the Pairwise Testing
			7.5.3 Test Case Generation Engine
		7.6 Input Domain Model
		7.7 Failure of Pairwise Testing
		7.8 Improved Algorithm
		7.9 Limitations of This System
		7.10 Conclusion
		References
	Chapter 8: Potential Applications of Artificial Intelligence in Medical Imaging and Health Care Industry
		8.1 Introduction
			8.1.1 Diagnostic Imaging
				8.1.1.1 Biomedical Practices
			8.1.2 Biochemical Procedures
		8.2 Existing Structure and Design Issues
			8.2.1 CAT Scanner
				8.2.1.1 The Architecture
				8.2.1.2 Design Issues
			8.2.2 Robotic Surgeons
				8.2.2.1 Design Issues
		8.3 Implementation of AI-based CAT Scanner
		8.4 Implementation of AI-based Robotic Surgeries
		8.5 Applications
			8.5.1 Digital AI Doctors
			8.5.2 Creating Drugs
			8.5.3 Mental Health
			8.5.4 Medical Records
			8.5.5 Early and Accurate Cancer Detection
			8.5.6 AI in Pregnancy Management
			8.5.7 AI in Genomics
		8.6 Conclusion
		References
	Chapter 9: Virtual and Augmented Reality Mental Health Research and Applications
		9.1 Introduction
		9.2 Mental Health
		9.3 Virtual Reality
			9.3.1 Virtual Reality Clinical Research
			9.3.2 Virtual Reality and Related Measures
				9.3.2.1 Cognitive and Biological Measures
				9.3.2.2 Cognitive, Behavioral, and Emotional Engagement
				9.3.2.3 Head-tracking, Emotion, and Attention
		9.4 Augmented Reality
			9.4.1 Augmented Reality Clinical Research
		9.5 Summary and Future Directions
		References
	Chapter 10: Solar Potential Estimation and Management Using IoT, Big Data, and Remote Sensing in a Cloud Computing Environment
		10.1 Introduction
		10.2 Literature Review
		10.3 Study Area and Data Used
		10.4 Methodology
		10.5 Results and Discussions
		10.6 Conclusion
		References
Section III: Artificial Intelligence–Based Real-Time Applications
	Chapter 11: Object Detection under Hazy Environment for Real-Time Application
		11.1 Introduction
		11.2 Object Detection
		11.3 Video Tracking
		11.4 Applications
		11.5 Related Work
		11.6 Challenges
			11.6.1 Bootstrapping
			11.6.2 Camouflage
			11.6.3 Illumination Variation
			11.6.4 Foreground Aperture
			11.6.5 Motion in Background
			11.6.6 Occlusion
		11.7 Conclusion
		11.8 Future Scope
		References
	Chapter 12: Real-Time Road Monitoring Using Deep Learning Algorithm Deployed on IoT Devices
		12.1 Introduction
		12.2 Methodology
			12.2.1 Pothole Detection
			12.2.2 Tracking Potholes
			12.2.3 Deployment in IoT
		12.3 Results and Discussion
		12.4 Conclusion
		Acknowledgments
		References
	Chapter 13: AI-Based Real-Time Application:: Pattern Recognition Automatic License Plate and Vehicle Number Detection Using Image Processing and Deep Learning (with OpenCV)
		13.1 Introduction
		13.2 Literature Survey
		13.3 Various Applications
			13.3.1 Pattern Recognition and Its Application
			13.3.2 ANPR System and Its Application
		13.4 Research Methods
			13.4.1 Image Processing Using OpenCV
				13.4.1.1 Data Collection Module
				13.4.1.2 Pruning License Plate
					13.4.1.2.1 Optical Character Recognition (OCR)
				13.4.1.3 Edge Cases and Assumptions
				13.4.1.4 Technologies and Their Definitions
			13.4.2 ANPPR Using Deep Learning
		13.5 Results
		13.6 Conclusion
		References
	Chapter 14: Design of a Chess Agent Using Reinforcement Learning with SARSA Network
		14.1 Introduction
		14.2 Literature Survey
		14.3 Applications of Reinforcement Learning
		14.4 Architecture Design of the Proposed Chess Agent Using SARSA Network
			14.4.1 Components of the SARSA Network
		14.5 Implementation of the Chess Agent Using SARSA Network-Module Description
		14.6 Results
		14.7 Conclusion
		References
	Chapter 15: Moving Objects Detection in Video Processing:: A Graph Signal Processing Approach for Background Subtraction
		15.1 Introduction
		15.2 Active Background Subtraction
			15.2.1 Notation
			15.2.2 Background
			15.2.3 Instance Segmentation
			15.2.4 Background Estimation and Nodes Representation
			15.2.5 Graph Construction
			15.2.6 Blue-Noise Sampling for Unseen Videos
			15.2.7 Semi-supervised Learning Algorithm
		15.3 Experimental Framework
			15.3.1 Dataset and Evaluation Measures
			15.3.2 Experiments
		15.4 Results and Discussions
		15.5 Conclusion
		References
	Chapter 16: Application of Artificial Intelligence in Disaster Response
		16.1 Introduction
		16.2 Application of AI to Understand Natural Disasters
			16.2.1 Applicaton of AI to Understand Earthquakes
			16.2.2 Application of AI to Understand Floods
			16.2.3 Application of AI to Understand Volcanoes
			16.2.4 Application of AI to Understand Landslides
			16.2.5 Application of AI to Understand Wildfires
		16.3 Caution in Using AI for Disaster Response
		16.4 Conclusion
		References
	Chapter 17: Use of Robotics in Surgery:: Current Trends, Challenges, and the Future
		17.1 Introduction
		17.2 Literature Review
		17.3 Surgical Robots
			17.3.1 Master–Slave Type
			17.3.2 Handheld Robotic Forceps
		17.4 Clinical Applications of Robotic Surgery
			17.4.1 Robotic Prostate Surgery
			17.4.2 Robotic Kidney Surgery
			17.4.3 Robotic Gynecological Surgery
			17.4.4 Robotic Gallbladder Surgery
				17.4.5 Robotic Colorectal Surgery
		17.5 Advantages of Robotics Surgery
		17.6 Challenges of Robotic Surgery
		17.7 Future of Robotics surgery
		17.8 Conclusion
		References
	Chapter 18: Brain-Computer Interface:: State-of-Art, Challenges, and the Future
		18.1 Introduction
		18.2 BCI Invasive and Noninvasive Devices
			18.2.1 Visual P300 and BCI Closed Loop
			18.2.2 Machine Learning Algorithm
			18.2.3 Brain–Computer Interface Speller
			18.2.4 Event-Related Potentials (ERPs)
			18.2.5 Movement Imagination
		18.3 Quantum Brain Model
		18.4 Specificity of the Architecture of Our Brain and the Brain Smart Activities
		18.5 The Basic Mechanism of Turning Thoughts into Computer or Robotic Action
		18.6 Brain Modularity
		18.7 Soft Computing Algorithms
		18.8 Molecular Machines
			18.8.1 Synthetic Machines
			18.8.2 Biological Molecular Machines
			18.8.3 Nanorobots
			18.8.4 Cell Repair Machines
			18.8.5 Neuro-electronic Interfaces
			18.8.6 Quantum Robot
		18.9 Future Visions of the Brain Computer Interface
		18.10 Recent Application of BCI Technology
		18.11 Conclusion
		References
	Chapter 19: Artificial Intelligence:: Challenges and Future Applications
		19.1 Introduction
		19.2 Challenges of AI
			19.2.1 Reengineering
			19.2.2 Data Quality and Quantity
			19.2.3 Integration of Data
			19.2.4 Data Privacy and Security
			19.2.5 Algorithms and Data
			19.2.6 Software Malfunctioning
			19.2.7 Algorithm Bias
			19.2.8 Scarcity of Field Specialists
			19.2.9 Lack of Investment
			19.2.10 Building Trust
			19.2.11 Implementation Strategies
			19.2.12 Legal Issues
			19.2.13 Higher Expectations
			19.2.14 AI Can Be Dangerous
		19.3 AI as a Job Creator
		19.4 Next-Generation AI
		19.5 Market Potential of AI
		19.6 Summary
		References
Index