Artificial Intelligence, Machine Learning, and Data Science Technologies: Future Impact and Well-Being for Society 5.0

Cover
Half Title
Series Information
Title Page
Copyright Page
Table of Contents
Preface
Editor Biographies
1 Breast Cancer Diagnosis Using Machine Learning and Fractal Analysis of Malignancy-Associated Changes in Buccal Epithelium
	1.1 Introduction
	1.2 Malignant-Associated Changes in Buccal Epithelium
	1.3 Materials and Methods of Morphometric Research and Image Analysis
	1.4 Fractal Analysis of Chromatin
		1.4.1 The Overall Algorithm for the Screening of Breast Cancer
	1.5 Results and Discussion
	1.6 Conclusion and Future Scope
	References
2 Artificial Intelligence for Sustainable Health Care Advancements
	2.1 Introduction
	2.2 Health Care Data
		2.2.1 Electronic Health Records
		2.2.2 Disease Registries
		2.2.3 Health Surveys
	2.3 Major AI Technologies Relevant to Health Care
		2.3.1 Machine Learning
		2.3.2 Deep Learning
		2.3.3 Natural Language Processing
		2.3.4 Robotics
	2.4 AI for Diagnosis and Treatment
		2.4.1 Recent Applications of AI in Medical Diagnostics
		2.4.2 Chatbots
		2.4.3 Oncology
		2.4.4 Pathology
		2.4.5 Radiology
	2.5 AI for Reducing Diagnostic Errors
		2.5.1 Buoy Health
		2.5.2 PathAI
		2.5.3 Enlitic
	2.6 AI for Drug Discovery
		2.6.1 BioXcel Therapeutics
		2.6.2 BERG Health
	2.7 AI for Medical Transcription
	2.8 AI for COVID-19 Diagnosis
	2.9 The Role of Corporations in AI in Health Care
	2.10 Benefits and Challenges of AI Services in Health Care
	2.11 Looking Ahead—Future of AI in Health Care
	References
3 Identification of Lung Cancer Malignancy Using Artificial Intelligence
	3.1 Introduction
	3.2 Background and Related Work
	3.3 Proposed Model
		3.3.1 Dataset (LIDC-IDRI)
		3.3.2 Image Acquisition
		3.3.3 Image Enhancement
	3.4 Image Segmentation
		3.4.1 Watershed Segmentation
		3.4.2 Otsu’s Thresholding
	3.5 Feature Extraction
		3.5.1 Distances
		3.5.2 Area
		3.5.3 Convex Area
		3.5.4 Perimeter
		3.5.5 Convex Perimeter
		3.5.6 Axis Length
			3.5.6.1 Major Axis Length
			3.5.6.2 Minor Axis Length
		3.5.7 Compactness
		3.5.8 Eccentricity
		3.5.9 Standard Deviation
		3.5.10 Skewness
		3.5.11 Kurtosis
		3.5.12 Entropy
		3.5.13 Circularity Or Roundness
		3.5.14 Convexity
		3.5.15 Solidity
		3.5.16 Bounding Box
		3.5.17 Mean Intensity
	3.6 Machine and Deep Learning Algorithms
	3.7 Metrics of Performance Evaluation
		3.7.1 Precision / Positive Predictive Value (PPV)
		3.7.2 Negative Predictive Value (NPV)
		3.7.3 Recall / Sensitivity / Probability of Detection / Hit Rate / True Positive Rate (TPR)
		3.7.4 Specificity / Selectivity / True Negative Rate (TNR)
		3.7.5 Fall Out / False Positive Rate (FPR)
		3.7.6 Mis Rate / False Negative Rate (FNR)
		3.7.7 False Discovery Rate (FDR)
		3.7.8 False Omission Rate (FOR)
		3.7.9 F1-Score / F-Measure/ Sørensen–Dice Coefficient / Dice Similarity Coefficient (DSC)
		3.7.10 Accuracy
		3.7.11 Confusion Matrix
		3.7.12 ROC-AUC Score
	3.8 Classification
		3.8.1 Bidirectional Long Short-Term Memory Networks (BLSTM)
	3.9 Experiments and Results
	3.10 Future Enhancement
	3.11 Conclusion
	References
4 Deep Learning in Content-Based Medical Image Retrieval
	4.1 Introduction
	4.2 Related Work
		4.2.1 Image Retrieval Based On Content (CBIR)
		4.2.2 Medical Image Recovery Based On Content (CBMIR)
		4.2.3 Deep Learning
	4.3 Methodology
		4.3.1 Phase
			4.3.1.1 The DCNN Model Architecture
			4.3.1.2 Details of Training
		4.3.2 Phase
		4.3.3 Phase 3: Optimization
			4.3.3.1 Spotted Hyena Optimizer (SHO)
	4.4 Dataset
	4.5 Experimental Results
	4.6 Performance Metrics
	4.7 Conclusion
	References
5 Implication of Image Pre-Processing in Object Detection Using Machine Learning Techniques
	5.1 Introduction
	5.2 Literature Review
	5.3 Preprocessing Methods
		5.3.1 Contrast Adjustment
		5.3.2 Intensity Adjustment
		5.3.3 Histogram Equalization
		5.3.4 Morphological Operation
	5.4 Image Enhancement Techniques
		5.4.1 Intensity Enhancement (IE)
		5.4.2 Histogram Equalization (HE)
		5.4.3 Adaptive Histogram Equalization (AHE)
		5.4.4 Contrast Limited Adaptive Histogram Equalization (CLAHE)
		5.4.5 Brightness Preserving Bi-Histogram Equalization (BBHE)
		5.4.6 Dualistic Sub-Image Histogram Equalization (DSHIE)
		5.4.7 Minimum Mean Brightness Error Bi-Histogram Equalization (MMBEBHE)
		5.4.8 Background Brightness Preserving Histogram Equalization (BBPHE)
	5.5 Performance Metrics for Image Enhancement Techniques
		5.5.1 Mean Squared Error (MSE)
		5.5.2 Peak Signal to Noise Ratio (PSNR)
		5.5.3 Absolute Mean Brightness Error (AMBE)
		5.5.4 Contrast
		5.5.5 Entropy
		5.5.6 Normalized Absolute Error (NAE)
		5.5.7 Measure of Enhancement (EME)
		5.5.8 Measure of Enhancement By Entropy (EMEE)
		5.5.9 Contrast Improvement Index (CII)
		5.5.10 Tenegrad Measurement (TM)
	5.6 Image Segmentation Techniques
		5.6.1 Thresholding
			5.6.1.1 Global Thresholding
			5.6.1.2 Variable Thresholding
			5.6.1.3 Multiple Thresholding
		5.6.2 Edge Detection Based Techniques
		5.6.3 Region Based Techniques
			5.6.3.1 Region Growing Methods
			5.6.3.2 Region Splitting and Merging Methods
		5.6.4 Clustering Based Techniques
		5.6.5 Watershed Based Techniques
		5.6.6 Partial Differential Equation Based Techniques
		5.6.7 Artificial Neural Network Based Techniques
		5.6.8 Fuzzy Logic Based Techniques
		5.6.9 Genetic Algorithm Based Techniques
		5.6.10 Saliency Based Technique
	5.7 Experimental Results
	5.8 Conclusion
	References
6 Forecasting Time Series Data Using Artificial Neural Network: A Review
	6.1 Introduction
	6.2 Historical Developments in the Field of ANN
	6.3 Methodology
	6.4 Classification of ANN
		6.4.1 Feed-Forward Neural Networks
		6.4.2 Recurrent Neural Networks
		6.4.3 Elman Back Propagation Neural Networks
		6.4.4 Time-Delay Feed-Forward Neural Network
	6.5 Structural Design of ANN
	6.6 Review of Applications, Results and Discussions
		6.6.1 River Flow Forecasting
		6.6.2 Environmental Pollution Forecasting
		6.6.3 Stock Market Forecasting
		6.6.4 Agriculture Related Forecasting
	6.7 Conclusions
	References
7 Internet of Things: An Emerging Paradigm for Social Safety and Security
	7.1 Introduction
	7.2 The IoT System: Tools and Technologies
		7.2.1 Sensors
			7.2.1.1 Temperature Sensor
			7.2.1.2 Thermistor
			7.2.1.3 Thermocouples
			7.2.1.4 Hair Tension Moisture Sensor
			7.2.1.5 Light Sensors
			7.2.1.6 Smart Acoustic Sensors
			7.2.1.7 Hydrophone
			7.2.1.8 Geophone
			7.2.1.9 Hydro-Pressure Sensor
			7.2.1.10 Optical Sensor
			7.2.1.11 Motion Sensor
			7.2.1.12 Passive Infrared Sensor (PIR)
			7.2.1.13 Gyroscope Sensors
			7.2.1.14 Electrochemical Breathalyzer
			7.2.1.15 Electronic Nose
			7.2.1.16 Image Sensors
		7.2.2 Actuators
			7.2.2.1 Linear Actuators
			7.2.2.2 Motors
			7.2.2.3 Relays
			7.2.2.4 Solenoids
	7.3 Connectivity
		7.3.1 LPWANs
		7.3.2 Cellular (3G/4G/5G)
		7.3.3 Zigbee
		7.3.4 Bluetooth
		7.3.5 Wi-Fi
		7.3.6 RFID
	7.4 IoT Applications
		7.4.1 Smart Homes
		7.4.2 Smart Cities
		7.4.3 Wearables
		7.4.4 Agriculture
		7.4.5 Smart Supply Chain
		7.4.6 Smart Retail
		7.4.7 Transportation
		7.4.8 Smart Grid
		7.4.9 Healthcare
		7.4.10 Industry
	7.5 IOT Applications for Social Safety and Security
		7.5.1 Urban Data Privacy
		7.5.2 Personal Safety
		7.5.3 Crime Detection and Indicators
		7.5.4 Emergency Services Coordination
		7.5.5 Firefighting
		7.5.6 Crowdsourcing and Crowdsensing
		7.5.7 Smart Grid Security
		7.5.8 Smart Street Lighting
		7.5.9 Counter-Terrorism
		7.5.10 Traffic Safety and Incident Management
	7.6 Case Study (Intrusion Detection and Tackling System for Agricultural Fields)
		7.6.1 Animal Intrusion and Handling
		7.6.2 Development of IDTS
		7.6.3 Deployment and Discussion
	7.7 Privacy and Security Issues With IoT
		7.7.1 Insufficient Testing and Updating
		7.7.2 Default Passwords and Credentials
		7.7.3 Malware and Ransomware
		7.7.4 Data Security and Privacy Concerns (Mobile, Web, Cloud)
		7.7.5 Small IoT Incursions That Bypass Detection
		7.7.6 Data Handling and Security
		7.7.7 Home Seizures
		7.7.8 Remote Vehicle Access
		7.7.9 Unreliable Communications
	7.8 Conclusion
	References
8 Artificial Intelligence: Encouraging Students in Higher Education to Seize Its Potential
	8.1 Introduction
	8.2 Ethos for Higher Education
	8.3 Some Bio-Inspired and Human Fuzzy Techniques in AI
		8.3.1 Fuzzy Logic Types 1 and
		8.3.2 Genetic Algorithm
		8.3.3 Artificial Neural Network
		8.3.4 Particle Swarm Optimization
		8.3.5 Invasive Weed Optimization
		8.3.6 Gray Wolf Optimization
		8.3.7 Lion Optimization Algorithm
		8.3.8 Mine Blast Optimization
		8.3.9 Whale Optimization Algorithm
	8.4 Application of Artificial Intelligence in Real World Problems
		8.4.1 E-Commerce Marketing
		8.4.2 Control Engineering
		8.4.3 Surgery and Operations in Medical Science
		8.4.4 AI in Agriculture
		8.4.5 In Aviation and Space Organizations
	8.5 Conclusion
	References
9 Thermal Performance of Natural Insulation Materials for Energy Efficient Buildings
	9.1 Introduction
	9.2 Insulation for Thermal Comfort, Thermal Performance of Insulation and Sustainable Insulation Materials
		9.2.1 Insulation for Thermal Comfort
		9.2.2 Thermal Performance
		9.2.3 Sustainable Insulation Materials
	9.3 Natural Insulation Materials, Their Thermal Properties, Environmental Impact and Sustainable Aspects
		9.3.1 Natural Insulation Materials
		9.3.2 Sustainability of Natural Insulation Materials
		9.3.3 Environmental Impact of Natural Insulation Materials
		9.3.4 Thermal Performance of Natural Insulation Materials
		9.3.5 Reduction in Cooling Load
		9.3.6 Reduction in Energy Consumption
	9.4 Conclusion
	References
10 Maximum Power Point Tracking Techniques for PV Framework Under Partial Shaded Conditions: Towards Green Energy ...
	10.1 Introduction
	10.2 Perturb & Observe MPPT Technique
	10.3 Incremental Conductance MPPT Techniques
	10.4 Simulation Model of Proposed System
	10.5 Results and Discussion
	10.6 Conclusions
	References
11 Forecasting Energy Consumption Using Deep Echo State Networks Optimized With Genetic Algorithm
	11.1 Introduction
	11.2 Related Work
	11.3 Deep Echo State Network Optimized With Genetic Algorithm
	11.4 Description of Datasets and Preprocessing
	11.5 Experimental Analysis of Data Center Power Consumption Dataset
	11.6 Experimental Analysis of Individual Household Power Consumption Dataset
	11.7 Performance Evaluation
	11.8 Conclusion
	Acknowledgements
	References
12 State-Of-The-Art Natural Language Processing Techniques
	12.1 Introduction
		12.1.1 Syntax
		12.1.2 Semantics
	12.2 Related Work
		12.2.1 NLP – Language Modelling
		12.2.2 NLP – Word, Sentence and Document Embedding
		12.2.3 NLP-Machine Reading
		12.2.4 NLP-Machine Translation
		12.2.5 NLP – Dialogue System (Open-Domain, Generative)
		12.2.6 NLP – Dialogue System
		12.2.7 NLP – Dialogue System (Task-Oriented)
		12.2.8 NLP – Text Generation
		12.2.9 NLP – Text Summarization
		12.2.10 NLP – Text Classification
		12.2.11 NLP – Sentiment Analysis
		12.2.12 NLP – Lexicon and Datasets
	12.3 Applications of NLP
	12.4 NLP Datasets
		12.4.1 NLP Datasets for Sentiment Analysis
		12.4.2 Text Datasets
		12.4.3 Audio Speech Datasets for NLP
	12.5 Conclusion
	References
13 Modern Approaches in HR Analytics Towards Predictive Decision-Making for Competitive Advantage
	13.1 Introduction
	13.2 Review of Literature
		13.2.1 HR Analytics: A Modern HR Decision-Making Tool
			13.2.1.1 Concept of HR Analytics
			13.2.1.2 Analytical Methods for HR
			13.2.1.3 IT Technology and Central Storage of Data
			13.2.1.4 Make Insightful Judgment
			13.2.1.5 Problems of Data Governance in HR Analytics
			13.2.1.6 Strategic Study
	13.3 Measuring the Business Advantage Through HR Predictive Analytics
		13.3.1 Employee Acquisition Opportunities of Predictive Analytics
		13.3.2 Effects of Workforce Performance Predictive Analytics
		13.3.3 Effects of Employee Retention Predictive Analytics
	13.4 HR Analytics and Predictive Decision-Making Model
	13.5 Findings and Conclusion
	13.6 Limitation and Scope
	References
14 Digital Transformation: Utilization of Analytics and Machine Learning in Smart Manufacturing
	14.1 Introduction
	14.2 Digital Transformation, Analytics, and Machine Learning
	14.3 Digital Transformation in Smart Manufacturing
	14.4 Analytics and Smart Manufacturing
	14.5 Machine Learning and Smart Manufacturing
	14.6 Conclusion
	References
15 A Robust Cyber Security: Challenges and Opportunities
	15.1 Introduction
	15.2 Literature Survey
	15.3 Getting Familiar With Hacking
		15.3.1 How Do Hackers Think?
		15.3.2 Types of Hackers
		15.3.3 What Path Does a Hacker/Attacker Follow?
	15.4 Development of Cyber Security Management Model
		15.4.1 Mistakes in Cyber Security
	15.5 Challenges in Cyber Security
		15.5.1 Large Number of IoT Devices
		15.5.2 NFV-SDN Integrated Edge Cloud Platform
		15.5.3 Data Privacy and Security
		15.5.4 Offloading and Interaction Between Edge and IoT Devices
	15.6 Opportunities in Cyber Security
		15.6.1 Blockchain and Zero-Trust Security
		15.6.2 Artificial Intelligence (AI) and Machine Learning (ML)
		15.6.3 Weak/Lightweight IOT Security
		15.6.4 Cyber Defense Based in Deception
		15.6.5 Isolated Identity of the Devices Under the Internet of Things
	15.7 Conclusion
	References
Index