Artificial Intelligence: Applications and Innovations (Chapman & Hall/Distributed Computing and Intelligent Data Analytics Series)

Cover
Half Title
Series Information
Title Page
Copyright Page
Table of Contents
Preface
Editor Biographies
Contributors
Chapter 1 Introduction to Artificial Intelligence
	1.1 Human and Artificial Intelligence
		1.1.1 The Turing Test
		1.1.2 Cognitive Modelling – Thinking Humanly
		1.1.3 The Laws of Thought Approach
		1.1.4 The Rational Agent Approach
	1.2 AI – An Overview
		1.2.1 Goals of AI
		1.2.2 Advantages of AI Systems
		1.2.3 Challenges of AI Systems
			1.2.3.1 Computing Power
			1.2.3.2 Trust Deficit
			1.2.3.3 Limited Knowledge
			1.2.3.4 Human-Level
			1.2.3.5 Data Privacy and Security
			1.2.3.6 The Bias Problem
			1.2.3.7 Data Scarcity
	1.3 AI’s History
	1.4 AI Working
	1.5 Types of AI
		1.5.1 Artificial Narrow Intelligence (ANI)
		1.5.2 Artificial General Intelligence (AGI)
		1.5.3 Artificial Super Intelligence (ASI)
	1.6 Applications of AI
		1.6.1 AI in Astronomy
		1.6.2 AI in Healthcare
		1.6.3 AI in Gaming
		1.6.4 AI in Finance
		1.6.5 AI in Data Security
		1.6.6 AI in Social Media
		1.6.7 AI in Travel and Transport
		1.6.8 AI in the Automotive Industry
		1.6.9 AI in Robotics
		1.6.10 AI in Entertainment
		1.6.11 AI in Agriculture
		1.6.12 AI in E-Commerce
		1.6.13 AI in Education
	1.7 Future of AI
	References
Chapter 2 Machine Learning – Principles and Algorithms
	2.1 Introduction
	2.2 ML Applications
	2.3 ML Key Elements
	2.4 Types of Learning
		2.4.1 Supervised Learning
			2.4.1.1 Decision Tree Algorithm
			2.4.1.2 Naive Bayes Algorithm
			2.4.1.3 Support Vector Machines
			2.4.1.4 Random Forest Algorithm
			2.4.1.5 Linear Regression
			2.4.1.6 Ordinary Least Squares Regression Algorithm
			2.4.1.7 Logistic Regression
			2.4.1.8 Ensemble Methods
		2.4.2 Unsupervised Learning
			2.4.2.1 K-Means for Clustering Algorithm
			2.4.2.2 Apriori Algorithm
			2.4.2.3 Principal Component Analysis (PCA)
			2.4.2.4 Singular Value Decomposition
			2.4.2.5 Independent Component Analysis
		2.4.3 Reinforcement Learning
			2.4.3.1 Learn the Model
			2.4.3.2 Given the Model – Alpha Zero Approach
			2.4.3.3 Model-Free Reinforcement Learning
			2.4.3.4 Policy Optimization Approach
	2.5 Summary
	References
Chapter 3 Applications of Machine Learning and Deep Learning
	3.1 Machine Learning Applications
		3.1.1 Image Recognition
		3.1.2 Speech Recognition
		3.1.3 Traffic Prediction
		3.1.4 Product Endorsement
		3.1.5 Self-Driving Cars
		3.1.6 Email Spam and Malware Filtering
		3.1.7 Virtual Personal Assistant
		3.1.8 Online Fraud Detection
		3.1.9 Stock Market Trading
		3.1.10 Medical Diagnosis
		3.1.11 Automatic Language Translation
	3.2 Deep Learning
	3.3 Machine Learning Vs. Deep Learning
	3.4 How Deep Learning Works
	3.5 Applications of Deep Learning
		3.5.1 Law Enforcement
		3.5.2 Financial Services
		3.5.3 Customer Service
		3.5.4 Healthcare
	3.6 Deep Learning Algorithms
		3.6.1 Convolutional Neural Networks (CNNs)
		3.6.2 Long Short-Term Memory Networks (LSTMs)
		3.6.3 Recurrent Neural Networks (RNNs)
		3.6.4 Generative Adversarial Networks (GANs)
		3.6.5 Radial Basis Function Networks (RBFNs)
		3.6.6 Multilayer Perceptrons (MLPs)
		3.6.7 Self-Organizing Maps (SOMs)
		3.6.8 Deep Belief Networks (DBNs)
		3.6.9 Restricted Boltzmann Machines (RBMs)
		3.6.10 Autoencoders
	3.7 Summary
	References
Chapter 4 Environmental Monitoring in Wireless Sensor Networks Using AI
	4.1 Introduction of Environmental Monitoring
	4.2 Applications of Wireless Sensor Network (WSN)
		4.2.1 Air Monitoring
		4.2.2 Water Monitoring
		4.2.3 Biodiversity
		4.2.4 Waste Monitoring
		4.2.5 Distant Sensing
		4.2.6 Enterprise Monitoring
	4.3 WSN for Environmental Monitoring
		4.3.1 Autonomy
		4.3.2 Reliability
		4.3.3 Robustness
	4.4 Climate Monitoring System Applications
	4.5 Agricultural Monitoring
	4.6 Habitat Monitoring
	4.7 Artificial Intelligence and WSN
	4.8 Remote Sensor Networks
	4.9 Human-Made Consciousness and Multi-Agent Systems
		4.9.1 Remote Sensor Networks and AI
	References
Chapter 5 Applications of Machine Learning – Fire Detection
	5.1 Introduction
		5.1.1 Artificial Intelligence (AI)
		5.1.2 The Most Important Trends in Fire Alarm Systems
		5.1.3 Internet of Things (IoT) in Fire Safety Systems
		5.1.4 Connected Detectors With IoT Capability
	5.2 Technological Advances in Central Alarm Systems
		5.2.1 Detection Using Multiple Sensors
		5.2.2 Voice Detection Systems
	5.3 AI Applications in Fire and Safety
		5.3.1 AI for Front-Line Personnel
		5.3.2 AI to Combat Wildfires
	5.4 Sensor-Based Strategy
		5.4.1 System Classifications of the NFPA
		5.4.2 Fire Alarm System in the Central Station
		5.4.3 Municipal Fire Alarm System
		5.4.4 Fire Alarm System With a Proprietary Supervising Station
		5.4.5 Protected Premises Fire Alarm System (Local)
		5.4.6 Remote Supervising Station Fire Alarm System
	5.5 Supervisory Signal
		5.5.1 Trouble Signal and (Device/Circuit) Supervision
	5.6 Research Methodology
		5.6.1 Color
		5.6.2 Chromatic Filtering
		5.6.3 Image Morphology Processing
		5.6.4 Candidate Regions’ Geographical Location
	5.7 Detection of Smoke
		5.7.1 Flame Detection Algorithm
		5.7.2 Experimentation Findings
		5.7.3 Dataset
	References
Chapter 6 Structural Health Monitoring
	6.1 Introduction
	6.2 Classification of Structural Health Monitoring Based On Different Structures
	6.3 Various Technologies Used in Structural Health Monitoring
		6.3.1 Impedance Measurement
		6.3.2 Admittance Measurement
	6.4 Sensors Used and Placement of Sensors
	6.5 Methodology
	References
Chapter 7 Application of Machine Learning in Agriculture With Some Examples
	7.1 Introduction: Background and Motivation
	7.2 Classification for Agriculture
	7.3 Technology in Agriculture
	7.4 Machine Learning Structure for Agriculture
	7.5 Different Algorithms Used in Machine Learning
	7.6 Applications of Machine Learning in Agriculture
	7.7 Companies Associated With the Agriculture Sector
	7.8 Indian Start-Up
	7.9 Some Useful Examples Associated With the Agriculture Sector
		7.9.1 Soil Analysis and Prediction of Suitable Crop
		7.9.2 Proposed System
		7.9.3 Use of Machine Learning
		7.9.4 Data Sets
		7.9.5 Fertilizer Recommendation
	7.10 Conclusion
	7.11 Algorithms
	References
Chapter 8 Deep Learning in Smart Agriculture Applications
	8.1 Introduction: Background and Motivation
	8.2 Popular Deep Learning Architectures Used in the Agricultural Domain
		8.2.1 Convolutional Neural Networks
		8.2.2 Recurrent Neural Networks
		8.2.3 Generative Adversarial Networks
	8.3 Application of Deep Learning in Agriculture
	8.4 CNNs in Agriculture RNNs
	8.5 Deep RNNs in Agriculture GANs
	8.6 GANs in Agriculture
	8.7 Challenges in Agriculture
	8.8 Some Useful Examples Associated With the Agriculture Sector
		8.8.1 Methodology
	8.9 Weather Forecasting Using Deep Learning and Machine Learning for Agricultural Modernization
	8.10 Detection of Leaf Disease Using Machine Learning and Deep Learning
	References
Chapter 9 Applications of Deep Learning in Aerial Robotics
	9.1 Introduction
	9.2 Overview of Aerial Robotics
	9.3 Classification of Aerial Robotics
	9.4 Application of Aerial Robotics
		9.4.1 Use of Aerial Robotics for Farming
		9.4.2 Use of Aerial Robotics for Logistics
		9.4.3 Use of Aerial Robotic for Surveillance
		9.4.4 Use of Aerial Robotics for Natural Disaster
	9.5 Role of Deep Learning in Aerial Robotics
	9.6 Air Robots’ Architecture and Components
	9.7 Application of Deep Learning in Aerial Robotics
		9.7.1 The Deep Learning Application for Feature Extraction in Aerial Robotics
		9.7.2 Deep Learning Applications for Planning in Aerial Robotics
		9.7.3 Deep Learning Applications for Motion Control in Aerial Robotics
		9.7.4 Deep Learning Applications for Situation Awareness in Aerial Robotics
		9.7.5 Summary of Deep Learning Applications in Aerial Robots
	9.8 Conclusion
	References
Chapter 10 The Memristor and Its Implementation in Deep Neural Network Designing: A Review
	10.1 Introduction
		10.1.1 Memeristor
	10.2 Memristor Implementation in Building Artificial Neural Networks
	10.3 Deep Learning
	10.4 Memristor Crossbar Architecture
	10.5 Spike Neural Networks
	10.6 Feed-Forward Neural Networks
	10.7 Multilevel Neural Networks
	10.8 Convolutional Neural Networks
	10.9 Recurrent Neural Networks
	10.10 Hopfield Neural Networks
	10.11 Neural Network Algorithms and Learning
	10.12 Hardware Implementation of Deep Neural Network Application
	10.13 Conclusion
	References
Chapter 11 Machine Learning Applications to Recognize Autism and Alzheimer’s Disease
	11.1 Introduction
	11.2 Brain Disorders
		11.2.1 Autism Spectrum Disorder (ASD)
		11.2.2 Alzheimer’s Disease (AD)
		11.2.3 Mild Cognitive Impairment
	11.3 Deep Learning
		11.3.1 ASD and Deep Learning
		11.3.2 Alzheimer’s and Deep Learning
	11.4 Conclusion
	References
Index