Artificial Intelligence Theory, Models, and Applications

✍ Scribed by P Kaliraj (editor), T. Devi (editor)

• Publisher: Auerbach Publications
• Year: 2021
• Tongue: English
• Leaves: 507
• Edition: 1
• Category: Library

✦ Synopsis

This book examines the fundamentals and technologies of Artificial Intelligence (AI) and describes their tools, challenges, and issues. It also explains relevant theory as well as industrial applications in various domains, such as healthcare, economics, education, product development, agriculture, human resource management, environmental management, and marketing. The book is a boon to students, software developers, teachers, members of boards of studies, and researchers who need a reference resource on artificial intelligence and its applications and is primarily intended for use in courses offered by higher education institutions that strive to equip their graduates with Industry 4.0 skills.

FEATURES:

• Gender disparity in the enterprises involved in the development of AI-based software development as well as solutions to eradicate such gender bias in the AI world
• A general framework for AI in environmental management, smart farming, e-waste management, and smart energy optimization
• The potential and application of AI in medical imaging as well as the challenges of AI in precision medicine
• AI’s role in the diagnosis of various diseases, such as cancer and diabetes
• The role of machine learning models in product development and statistically monitoring product quality
• Machine learning to make robust and effective economic policy decisions
• Machine learning and data mining approaches to provide better video indexing mechanisms resulting in better searchable results

ABOUT THE EDITORS:

Prof. Dr. P. Kaliraj is Vice Chancellor at Bharathiar University, Coimbatore, India.

Prof. Dr. T. Devi is Professor and Head of the Department of Computer Applications, Bharathiar University, Coimbatore, India.

 

✦ Table of Contents

Cover
Half Title
Title Page
Copyright Page
Contents
Preface
Acknowledgments
Editors
Contributors
1. Artificial Intelligence: A Complete Insight
1.1 Introduction
1.2 Artificial Intelligence: What and Why?
1.3 History of AI
1.3.1 Turing Test
1.4 Foundations of AI
1.4.1 Logic and Reasoning
1.4.2 Pattern Recognition
1.4.3 Cognitive Science
1.4.4 Heuristics
1.4.5 Philosophy
1.4.6 Mathematics
1.4.7 Psychology
1.4.8 Linguistics
1.5 The AI Environment
1.6 Application Domains of AI
1.6.1 Gaming
1.6.2 Education
1.6.3 Healthcare
1.6.4 Agriculture
1.6.5 Entertainment
1.6.6 Manufacturing
1.6.7 Banking and Insurance
1.6.8 Automobiles
1.7 AI Tools
1.8 Challenges in AI
1.8.1 Loss of Self-Thinking
1.8.2 Bias in the Design of Artificial Intelligence
1.8.3 Limitation on Data
1.8.4 Threat to Manpower
1.8.5 Lifestyle Changes
1.8.6 Security Threats
1.9 Future Prospects of AI
1.9.1 Applicability
1.9.2 Dynamism in AI Model
1.9.3 Economic Feasibility
1.9.4 User Training
1.10 Summary
References
2. Artificial Intelligence and Gender
2.1 What Is Artificial Intelligence?
2.2 What Is Machine Learning?
2.2.1 Supervised Learning
2.2.2 Unsupervised Learning
2.2.3 Reinforcement Learning
2.3 What Is Deep Learning?
2.4 Artificial Intelligence Enterprise Applications
2.5 Artificial Intelligence and Gender
2.5.1 Artificial Intelligence Is Gender-Biased, But Why?
2.5.2 Limited Data for Training
2.5.3 Workplace Bias
2.5.4 Indifferent Approach to the "Female Genius"
2.5.5 Artificial Intelligence-Based Harassment
2.5.6 Art Reflects Life
2.5.7 Virtual Agents
2.5.8 Who Will Artificial Intelligence Replace?
2.5.9 India Is No Different
2.5.10 Steps Artificial Intelligence Teams Should Take to Avoid Gender Bias
2.6 Concluding Thoughts
References
3. Artificial Intelligence in Environmental Management
3.1 Current Work in AI for Environment
3.1.1 Organizations and Their Initiatives
3.1.2 General Framework for AI in Environmental Management
3.2 AI for Cleaner Air - Smart Pollution Control
3.2.1 Current Challenges
3.2.2 Potential AI Applications
3.2.3 Sample Case Study
3.3 AI for Water Preservation - Smart Water Management
3.3.1 Current Challenges
3.3.2 Potential AI Applications
3.3.3 Sample Case Study
3.4 AI for Better Agriculture - Smart Farming
3.4.1 Current Challenges
3.4.2 Potential AI Applications
3.4.3 Sample Case Study
3.5 AI for Better e-Waste Management - Smart Monitoring/Control
3.5.1 Current Challenges
3.5.2 Potential AI Applications
3.5.3 Sample Case Study
3.6 AI for Climate Control - Smart Energy Optimization
3.6.1 Current Challenges
3.6.2 Potential AI Applications
3.6.3 Sample Case Study
3.7 Risks and Rewards of AI in Environmental Management
References
4. Artificial Intelligence in Medical Imaging
Objectives
4.1 Introduction to Medical Imaging
4.2 Applying Artificial Intelligence (AI) in Medical Imaging
4.2.1 Computer-Aided Detection (CAD)
4.2.2 Principles of Computer-Aided Image Analysis in Medical Imaging
4.2.3 Machine Learning (ML) and Deep Learning (DL)
4.2.4 Content-Based Image Retrieval (CBIR)
4.2.5 Radiomics and Radiogenomics
4.3 AI in Various Medical Imaging Modalities
4.4 AI in Computed Tomography
4.4.1 CT Reconstruction Algorithms: From Concept to Clinical Necessity
4.4.2 Importance of AI-Based Detection in CT
4.4.3 Present and Future Developments
4.5 AI in Mammography
4.5.1 Limitations of Human Observers
4.5.2 Computer Vision (CV) and AI
4.5.3 Detection of Microcalcifications and Breast Masses
4.5.4 Present Status and Future Directions
4.6 AI in Magnetic Resonance Imaging (MRI)
4.6.1 Developments of AI in MRI
4.6.2 Future Directions
4.7 AI in Medical Ultrasound(US)
4.7.1 DL Architectures
4.7.2 Applications of DL in Medical US Image Analysis
4.7.3 Future Perspectives
4.8 AI in Nuclear Medicine Imaging
4.8.1 Define a Radiomic Diagnostic Algorithm
4.8.2 Applications of AI in Nuclear Medicine
4.8.3 Future Scenarios
4.9 Salient Features of AI in Medical Imaging
4.9.1 Opportunities and Applications
4.9.2 Challenges
4.9.3 Pitfalls
4.9.4 Guidelines for Success
4.9.5 Regulatory and Ethical Issues
References
5. Artificial Intelligence (AI): Improving Customer Experience (CX)
Objective
5.1 Introduction to Artificial Intelligence (AI)
5.1.1 What Is AI? - The Basics
5.2 Customer Experience (CX) and the Use of AI
5.2.1 Customer Journey
5.2.2 Customer Touchpoints
5.2.3 Customer Journey Mapping and Touchpoints
5.3 Customer Expectations from CX
5.4 Customer Journeys and the Use of Artificial Intelligence
5.4.1 Need Identification/Awareness Creation
5.4.1.1 Use of Social Media in Awareness Creation
5.4.2 Consideration/Searching Suitable Options
5.4.3 Purchase Decision
5.4.4 Retention/In-Life Support
5.4.5 Loyalty
5.5 Conclusion
5.6 Future of AI
5.6.1 Future of AI in Customer Experience
5.6.2 Future of AI across Verticals
References
6. Artificial Intelligence in Radiotherapy
Objectives
6.1 Introduction
6.2 Importance of Artificial Intelligence (AI) in Radiotherapy
6.3 AI Tools for Automated Treatment Planning (ATP)
6.3.1 Present ATP Techniques
6.3.2 AI Applications, Advancements, and Research Guidance in ATP
6.3.3 AI Challenges in ATP
6.4 AI in Intensity Modulated Radiotherapy (IMRT)
6.4.1 AI for IMRT Dose Estimation
6.4.2 AI for IMRT Planning Support
6.4.3 AI for Modeling IMRT Outcome and Plan Deliverability
6.4.4 AI for Auto-Segmentation of OAR in IMRT
6.4.5 Future Directions
6.5 AI in Brachytherapy
6.6 AI in Radiotherapy Quality Assurance
6.6.1 Developments in ML towards Quality Assurance
6.6.2 Applications of ML Models for Quality Assurance in Radiotherapy
6.6.3 Quality Assurance of ML Algorithms in Radiotherapy
6.6.4 Challenges Associated with AI for Quality Assurance in RT
6.6.5 Future Directions to Improve AI-Based Quality Assurance in RT
6.7 AI in Radiation Biology
6.8 AI in Radiation Protection/Safety
6.8.1 Motivations to Develop AI-Based Systems for Radiation Protection
6.8.2 Problems Associated with AI-Based Systems for Radiation Protection
6.8.3 Benefits and Future Directions
6.9 Radiomics in Radiotherapy
6.9.1 Radiomics Objectives and Workflow
6.9.2 Influence of Radiomics in RT
6.9.3 Challenges for Medical Physicists
6.9.4 Future Directions
6.10 AI Considerations for RT Curriculum Development
References
7. Artificial Intelligence in Systems Biology: Opportunities in Agriculture, Biomedicine, and Healthcare
Objectives
7.1 Introduction to Artificial Intelligence (AI)
7.2 AI Methodologies and Algorithm for Systems Biology
7.2.1 Machine Learning (ML)
7.2.2 ML Algorithm Applied in Systems Biology
7.2.3 Computational Neural Networks
7.2.4 Pros and Cons of Artificial Neural Network (ANN)
7.3 Applications of Artificial Intelligence (AI) in Agriculture, Biomedicine, and Healthcare
7.3.1 AI in Agriculture
7.3.2 AI in Biomedicine
7.3.3 AI in DNA Expression Profiling
7.3.4 AI for Identifying Exonic Regions
7.3.5 AI in Identifying Variants/Mutations from Genetic Data
7.3.6 AI Workflow Method for Genomic Analysis
7.3.7 AI in Structure Prediction
7.3.8 AI in Phylogeny
7.3.9 AI in Healthcare
7.4 Case Studies on AI in Systems Biology
7.4.1 AI Technologies in Systems Biology towards Pharmacogenomics
7.4.2 AI in Systems Biology for Cancer Cure
7.4.3 Applications of AI for COVID-19 Pandemic
7.5 Future Challenges in Artificial Intelligence
Acknowledgments
References
8. Artificial Intelligence Applications in Genetic Disease/Syndrome Diagnosis
Objectives
8.1 Introduction
8.2 Milestones
8.3 Algorithms
8.4 Artificial Intelligence in the Diagnosis of Genetic Diseases
8.4.1 Cancer
8.4.2 Diabetes
8.5 Artificial Intelligence in the Diagnosis of Syndromes
8.6 Artificial Intelligence in the Diagnosis of Psychiatric Disorders
8.6.1 Depression
8.6.2 Alzheimer's Disease
8.6.3 Autism Spectrum Disorder
8.6.4 Anxiety
8.6.5 Parkinson's Disease
8.7 Artificial Intelligence in Other Disease Diagnosis
8.7.1 Infectious Disease
8.7.2 Lung and Brain Disease
8.8 Food and Drug Administration Approval and Guidelines
8.9 Conclusion
References
9. Artificial Intelligence in Disease Diagnosis via Smartphone Applications
9.1 Introduction
9.2 Smartphone Applications and ML Algorithms in Disease Diagnosis
9.2.1 Diagnosis of Diseases by Using Smartphone Applications
9.2.1.1 Smartphone App for Noninvasive Detection of Anemia
9.2.1.2 Mobile Touch Screen Typing in the Detection of Motor Impairment of Parkinson's Disease
9.2.1.3 Screening Services for Cancer on Android Smartphones
9.2.1.4 Detection of Cardiovascular Disease Using Smartphone Mechanocardiography
9.2.1.5 Mobile-Enabled Expert System for Diagnosis of Tuberculosis in Real Time
9.2.1.6 Smartphone-Based Pathogen Detection of Urinary Sepsis
9.2.1.7 Detecting Acute Otitis Media Using a Mobile App
9.2.1.8 Diagnosis of Covert Hepatic Encephalopathy via Encephal App, a Smartphone-Based Stroop Test
9.2.1.9 Mobile-Based Nutrition and Child Health Monitoring
9.2.1.9.1 Other Mobile Apps in Healthcare
9.2.2 Machine Learning Technology in the Diagnosis of Various Diseases
9.2.2.1 Heart Disease
9.2.2.2 Diabetes Disease
9.2.2.3 Liver Disease
9.2.2.4 Dengue Disease
9.2.2.5 Hepatitis Disease
9.2.2.6 Genetic Disorders (Acromegaly) from Facial Photographs
9.3 Conclusion
Acknowledgment
References
10. Artificial Intelligence in Agriculture
10.1 Introduction to Artificial Intelligence
10.2 Agriculture - Never Die Business Until Humans Exist
10.3 Need for AI in Agriculture
10.4 Emerging Agricultural Technologies
10.4.1 Soil and Water Sensors
10.4.2 Weather Tracking
10.4.3 Satellite Imaging Agriculture
10.4.4 Automation Systems
10.4.5 RFID Technology
10.5 Potential Agricultural Domains for Modernization
10.5.1 AI in Crop Monitoring
10.5.2 AI in Seed Germination
10.5.3 AI in Soil Management
10.5.4 AI in Crop Productivity
10.5.5 AI in Price Forecasting of Agricultural Products
10.5.6 AI in Pest and Weed Management
10.5.7 AI in Agricultural Land Utilization
10.5.8 AI in Fertilizer Optimization
10.5.9 AI in Irrigation Management
10.6 Can AI Transform Agricultural Scenario?
10.7 Summary
References
11. Artificial Intelligence-Based Ubiquitous Smart Learning Educational Environments
11.1 Introduction
11.2 Need and Considering the Foundations
11.3 Framework for Ubiquitous Smart Learning
11.4 Role and Advantage of Using Artificial Intelligence
11.4.1 Advantage of Artificial Intelligence
11.5 Conclusion
References
12. Artificial Intelligence in Assessment and Evaluation of Program Outcomes/Program Specific Outcomes
12.1 Introduction
12.2 Assessment and Evaluation
12.3 Data Set Attributes and Implementation Platform
12.4 Evaluation Using Machine Learning Models
12.4.1 Statistical Summary
12.4.2 Data Visualization
12.4.3 Model Creation and Estimation
12.4.4 Build Models
12.4.5 Select Best Model
12.4.6 Make Predictions
12.4.7 Evaluate Predictions
12.5 Observations
12.6 Conclusion
References
13. Artificial Intelligence-Based Assistive Technology
13.1 Introduction
13.2 Overview of AI on AT
13.2.1 What Is Artificial Intelligence?
13.2.2 How AI Is Changing the World
13.2.3 How Can Artificial Intelligence Be Used in AT?
13.3 A Transformative Impact of AI on AT
13.4 Extensive AT Applications Based on AI
13.5 AI Experience and AT for Disabled People in India
13.6 AI-Powered Technology for an Inclusive World
13.6.1 Applications Based on Vision Areas
13.6.2 Applications Based on Voice Areas
13.7 Research Perceptive Over AI Influence on AT
13.7.1 Vision-Based Applications
13.7.2 Voice-Based Applications
13.8 AI Implementation on Assistive Technologies - Pragmatic Approach
13.9 Conclusion
References
14. Machine Learning
Objectives
14.1 Introduction
14.1.1 Why Should Machines Learn?
14.1.2 The Importance of Machine Learning
14.2 What Is Machine Learning?
14.2.1 The Simple Side of ML
14.2.2 The Technical Side of ML
14.2.2.1 Gathering Data
14.2.2.2 Data Preparation
14.2.2.3 Choose a Model
14.2.2.4 Training
14.2.2.5 Evaluation
14.2.2.6 Parameter Tuning
14.2.2.7 Using the Model
14.2.3 Summing Up
14.3 Types of Machine Learning
14.3.1 Supervised Learning
14.3.2 Unsupervised Learning
14.3.3 Reinforcement Learning
14.4 Machine Learning Algorithms
14.4.1 Linear Regression
14.4.2 Logistic Regression
14.4.3 Decision Tree
14.4.4 Support Vector Machine (SVM)
14.4.5 Naïve Bayes
14.4.6 K-Nearest Neighbor (K-NN)
14.4.7 K-Means
14.4.8 Random Forest
14.4.9 Dimensionality Reduction Algorithms
14.4.10 Gradient Boosting Algorithms
14.5 Tools Available for Machine Learning
14.5.1 Programming Languages
14.5.1.1 Python
14.5.1.2 R
14.5.1.3 Scala
14.5.1.4 Julia
14.5.1.5 Java
14.5.2 Frameworks
14.5.2.1 Tensor Flow
14.5.2.2 PyTorch
14.5.2.3 Spark ML Library
14.5.2.4 CAFFE (Convolutional Architecture for Fast Feature Embedding)
14.5.2.5 scikit-learn
14.5.2.6 Amazon Machine Learning
14.5.3 Databases
14.5.3.1 MySQL
14.5.3.2 PostgreSQL
14.5.3.3 MongoDB
14.5.3.4 MLDB
14.5.3.5 Spark with Hadoop HDFS
14.5.3.6 Apache Cassandra
14.5.3.7 Microsoft SQL Server
14.5.4 Deployment Tools
14.5.4.1 Github
14.5.4.2 PyCharm Community Edition
14.5.4.3 Pytest
14.5.4.4 CircleCi
14.5.4.5 Heroku
14.5.4.6 MLFlow
14.6 Application Areas of Machine Learning
14.6.1 Everyday Life
14.6.1.1 Virtual Personal Assistants
14.6.1.2 Personalized Shopping
14.6.1.3 Weather Forecasts
14.6.1.4 Google Services
14.6.1.5 Spam Detection
14.6.1.6 Credit Card Fraud Detection
14.6.2 Healthcare
14.6.2.1 Personalized Medicine/Treatment
14.6.2.2 Medical Imaging and Diagnostics
14.6.2.3 Identification of Diseases and Diagnosis
14.6.2.4 Drug Discovery and Development
14.6.2.5 Smart Health Records
14.6.2.6 Treatment and Prediction of Disease
14.6.3 Agriculture
14.6.3.1 Crop Management
14.6.3.2 Livestock Management
14.6.3.3 Plant Breeding
14.6.3.4 Soil Management
14.6.3.5 Agriculture Robot
14.6.4 Transportation
14.6.4.1 Driverless Cars
14.6.4.2 Predictions While Commuting
14.6.4.3 Video Surveillance
14.6.4.4 Transportation Services
14.6.4.5 Interactive Journey
14.6.5 Education
14.6.5.1 Customized Learning Experience
14.6.5.2 Increasing Efficiency of Education
14.6.5.3 Predictive Analytics
14.6.5.4 Personalized Learning
14.6.6 Urbanization
14.6.6.1 Automatic Classification of Buildings and Structures
14.6.6.2 Urban Population Modeling
14.6.6.3 Other Applications
14.6.7 Social Media Services
14.6.7.1 Personalized Feeds
14.6.7.2 Email Spam and Malware Filtering
14.6.7.3 Online Customer Support
14.6.7.4 Search Engine Result Refining
14.6.8 Financial World
14.6.8.1 Online Fraud Detection
14.6.8.2 Robo-Advisory
14.6.8.3 Customer Service
14.6.8.4 Risk Management
14.6.8.5 Marketing Strategy
14.6.8.6 Network Security
14.7 Conclusion
References
15. Machine Learning in Human Resource Management
Objectives
15.1 Introduction
15.2 How Machine Learning Helps Human Resource Management
15.3 Machine Learning Concepts
15.3.1 Supervised Learning
15.3.1.1 Naïve Bayes Classifier (Generative Learning Model)
15.3.1.2 K-Nearest Neighbor
15.3.1.3 Support Vector Machine (SVM)
15.3.1.4 Logistic Regression (Predictive Learning Model)
15.3.1.5 Decision Trees
15.3.1.6 Random Forest
15.3.2 Unsupervised Learning
15.3.2.1 Exclusive (Partitioning)
15.3.2.2 Overlapping
15.3.3 Reinforcement Learning
15.4 Applications of Machine Learning in HRM
15.4.1 Recruitment
15.4.2 Applicant Tracking and Assessment
15.4.3 Attracting Talent
15.4.4 Attrition Detection
15.4.5 Machine Learning Technologies to Optimize Staffing
15.4.6 Talent Management
15.4.7 Individual Skill Management
15.4.8 Chatbox for FAQs of Employees
15.4.9 Clustering for Strategic Management of HRM
15.5 Case Studies
15.5.1 Case Study 1: Competency-Based Recruitment Process
15.5.1.1 True Positive
15.5.1.2 True Negative
15.5.1.3 False Positive
15.5.1.4 False Negative
15.5.1.5 Recall
15.5.1.6 Precision
15.5.1.7 F1-Measure
15.5.1.8 Accuracy
15.5.2 Case Study 2: Prediction of Employee Attrition
15.5.3 Case Study 3: Performance Assessment for Educational Institution
15.6 Summary
References
16. Machine Learning Models in Product Development and Its Statistical Evaluation
16.1 Introduction
16.2 Methodology for Model Buildings
16.2.1 Prepare the Data
16.2.2 Perform Data Analysis
16.3 Product Development
16.4 Smart Manufacturing
16.5 Quality Control Aspects
16.6 Machine Learning Methods
16.6.1 Regression Analysis
16.6.2 Classification
16.6.3 Clustering
16.6.3.1 Supervised Clustering
16.6.3.2 Unsupervised Clustering
16.6.3.3 Semi-Supervised Clustering
16.7 Statistical Measures
16.8 Algorithm for Data Analytics
16.9 Real-Time Applications
16.10 Results
16.11 Conclusion
Acknowledgments
References
17. Influence of Artificial Intelligence in Clinical and Genomic Diagnostics
17.1 Artificial Intelligence
17.1.1 Branches of Computer Science
17.1.2 Applications of Artificial Intelligence
17.2 Machine Learning
17.2.1 Approaches of Machine Learning
17.3 Influence of Artificial Intelligence in Machine Learning
17.3.1 Classification of AI
17.3.2 Utilization of AI
17.4 Medical Machine Learning
17.4.1 Computer Techniques Used in Medical ML
17.4.2 Methods for Calculating Biological Sequence Patterns
17.5 Influence of AI and ML in Clinical and Genomic Diagnostics
17.5.1 Classification of AI Used in Medical Data
17.5.1.1 Computer Vision
17.5.1.2 Time Series Analysis
17.5.1.3 Automatic Speech Recognition
17.5.1.4 Natural Language Processing
17.5.2 AI in Clinical Genomics
17.5.2.1 Variant Calling
17.5.2.2 Genome Annotation and Variant Classification
17.5.2.3 Coding Variants Classification
17.5.2.4 Non-Coding Variants Classification
17.5.2.5 Phenotype-Genotype Mapping
17.5.2.6 Genetic Diagnosis
17.5.2.7 Electronic Health Record (EHR) to Genetic Diagnosis
17.5.2.8 Genotype-Phenotype Predictions
17.6 Conclusion
References
18. Applications of Machine Learning in Economic Data Analysis and Policy Management
18.1 Goals of Economic Policies
18.1.1 Areas under Consideration for Economic Policy Creation
18.2 Current Methods and Thought Process to Analyze, Measure, and Modify Policies
18.3 Overview of Common Machine Learning Algorithms, Tools, and Frameworks
18.4 Applicability of Advanced Machine Learning Methods in Economics
18.4.1 Broad Areas for ML Adoption
18.4.2 Challenges in Economic Analysis and Advantages of Machine Learning
18.4.3 Major Areas of Concern for Leveraging ML in Economics
18.5 Machine Learning Studies Undertaken by Economists, Institutions, and Regulators
18.6 Conclusion
References
19. Industry 4.0: Machine Learning in Video Indexing
19.1 Introduction
19.2 Importance of Video Indexing
19.3 Video Structure Analysis
19.4 How Data Mining and Machine Learning Help Video Indexing
19.5 Analysis of Machine Learning Concepts for Video Indexing
19.5.1 Supervised Learning
19.5.1.1 Naive Bayes Model
19.5.1.2 Decision Trees
19.5.1.3 Linear Regression
19.5.1.4 Random Forest
19.5.1.5 Support Vector Machine (SVM)
19.5.1.6 Ensemble Method
19.5.2 Unsupervised Learning
19.5.2.1 K-Means Clustering
19.5.2.2 Association Rules
19.5.3 Reinforcement Learning
19.6 Applications of Machine Learning Approach for Video Indexing
19.6.1 News Classification
19.6.2 Video Surveillance
19.6.3 Speech Recognition
19.6.4 Services of Social Media
19.6.5 Medical Services
19.6.6 Age/Gender Identification
19.6.7 Information Retrieval
19.6.8 Language Identification
19.6.9 Robot Control
19.7 Case Studies
19.8 Summary
References
20. A Risk-Based Ensemble Classifier for Breast Cancer Diagnosis
20.1 Introduction
20.2 Related Works
20.2.1 Problem Statement
20.3 Background
20.3.1 K-Nearest Neighbor
20.3.2 Naïve Bayes Classifier
20.3.3 Isotonic Separation
20.3.4 Random Forest
20.3.5 Support Vector Machine
20.3.6 Linear Discriminant Analysis
20.3.7 Proposed Risk-Based Ensemble Classifier
20.4 Experimental Analysis
20.4.1 Data Sets
20.4.2 Experimental Setup
20.4.3 Statistical Analysis
20.4.4 Findings
20.5 Conclusion
References
21. Linear Algebra for Machine Learning
21.1 Introduction
21.2 Linear Algebra - Basics and Motivations
21.2.1 Vectors
21.2.2 Vector Space
21.2.3 Vector Subspace
21.2.4 Span
21.2.5 Basis
21.2.6 Linear Mapping
21.2.7 Matrix
21.2.8 Matrix Representation of Linear Mappings
21.2.9 Transformation Matrix
21.2.10 Determinant
21.2.11 Eigenvalue
21.2.12 Rank
21.2.13 Diagonal Matrix
21.2.14 Diagonalizable
21.3 Matrix Decompositions
21.3.1 The LU Decomposition
21.3.2 The QR Decomposition
21.3.3 The Cholesky Decomposition
21.3.4 The Eigenvalue Decomposition
21.3.5 The Singular Value Decomposition (SVD)
21.3.5.1 Geometric Interpretation of SVD
21.3.5.2 Application: Data Compression Using SVD
21.3.5.3 Dimensionality Reduction
21.3.5.4 Principal Component Analysis (PCA)
21.4 Linear Regression
21.4.1 The Least Squares Method
21.4.2 Linear Algebra Solution to Least Squares Problem
21.5 Linear Algebra in Machine Learning
21.5.1 Shining in Machine Learning Components
21.5.2 Enhancing Machine Learning Algorithms
Acknowledgments
References
22. Identification of Lichen Plants and Butterflies Using Image Processing and Neural Networks in Cloud Computing
22.1 Introduction
22.2 Objectives of the Present Study
22.3 Background Information
22.3.1 About Lichens
22.3.2 About Butterflies
22.3.3 Image Processing Techniques in Lichen and Butterfly Identification
22.3.4 Image Processing Techniques in Cloud Computing
22.4 Methodology
22.5 Observations
22.5.1 Pre-Processing of Lichen Images
22.5.2 Segmentation of Pre-Processed Lichen and Butterfly Images
22.5.3 Classification and Prediction of Lichen and Butterfly Species
22.5.4 Identification of Lichen and Butterfly Images
22.5.5 Implementation of Artificial Neural Networks (ANNs)
22.5.6 Grayscale Sub-Images of Lichens and Butterfly Extracted from Input Images
22.5.7 Cloud Computing Techniques
22.6 Conclusion
Acknowledgments
References
23. Artificial Neural Network for Decision Making
Objectives
23.1 Introduction
23.2 Components of ANN
23.3 Structure with Explanation
23.3.1 Network Architectures
23.3.2 Feedforward Neural Networks
23.3.3 Backpropagation Training Algorithm
23.4 Types of Learning
23.4.1 Supervised Learning (SL)
23.4.2 Unsupervised Learning (UL)
23.4.3 Reinforcement Learning (RL)
23.5 Application
23.5.1 Performance Analysis Using Real Data
23.5.2 Results and Discussion
23.5.2.1 Results
23.5.2.2 Discussion
23.6 Conclusion
References
Index