Data Science and Innovations for Intelligent Systems: Computational Excellence and Society 5.0 (Demystifying Technologies for Computational Excellence)

✍ Scribed by Kavita Taneja (editor), Harmunish Taneja (editor), Kuldeep Kumar (editor), Arvind Selwal (editor), Eng Lieh Ouh (editor)

• Publisher: CRC Press
• Year: 2021
• Tongue: English
• Leaves: 385
• Edition: 1
• Category: Library

✦ Synopsis

Data science is an emerging field and innovations in it need to be explored for the success of society 5.0. This book not only focuses on the practical applications of data science to achieve computational excellence, but also digs deep into the issues and implications of intelligent systems.

This book highlights innovations in data science to achieve computational excellence that can optimize performance of smart applications. The book focuses on methodologies, framework, design issues, tools, architectures, and technologies necessary to develop and understand data science and its emerging applications in the present era.

This book will be useful for the research community, start-up entrepreneurs, academicians, and data centered industries and professors that are interested in exploring innovations in varied applications and areas of data science.

✦ Table of Contents

Cover
Half Title
Series Page
Title Page
Copyright Page
Contents
Editors
Contributors
1. Quantum Computing: Computational Excellence for Society 5.0
1.1 Introduction
1.2 Quantum Computing Fundamentals
1.2.1 Key Concepts
1.2.2 Hardware, Software, Alorithms, and Workflow
1.3 Quantum Computing Needs and Service Industry Applications
1.3.1 Business Needs and Concerns
1.3.2 Decision Problem Framing and Computation
1.3.3 The Range of Business Problem Areas That Can Be Addressed
1.3.4 The Unique Role of Quantum Computing in Financial Services Applications
1.4 Application Framework
1.4.1 Algorithm Design
1.4.2 Software Development
1.4.3 Hardware for Quantum Computing
1.4.4 Integration with Other IT Systems in the Firm
1.5 Case: Implementing a Quantum Neural Network for Credit Risk
1.5.1 Credit Risk Assessment
1.5.2 Algorithm Design for a Quantum Neural Network (QNN)
1.5.3 Software Design for QNN
1.5.4 Hardware for Quantum Credit Scoring
1.5.5 Issues for Moving from a Stand-Alone to an Integrated System
1.6 Conclusion
Acknowledgments
Notes
References
Appendix A: Glossary of Terms
2. Prediction Models for Accurate Data Analysis: Innovations in Data Science
2.1 Introduction
2.1.1 Overview of Chapter
2.2 Multi Classifier System
2.2.1 Philosophy
2.2.2 History
2.2.3 Need for Multi Classifier System
2.2.4 Distinctive Features of Multi Classifier System
2.2.5 Working of Multi Classifier System
2.3 Ensemble Methods
2.3.1 Comparison Among Ensemble Methods
2.4 Design of Multi Classifier System
2.5 Combination Techniques
2.6 The Topologies for Multi Classifier System
2.7 Ensemble Diversity
2.8 Advantages and Disadvantages of MCS
2.9 Applications of Ensemble
2.10 Emerging Areas
2.11 Challenges in Building Multi Classifier System
2.12 Issues and Challenges Related to Society 5.0
2.13 Conclusion and Future Work
References
3. Software Engineering Paradigm for Real-Time Accurate Decision Making for Code Smell Prioritization
3.1 Introduction
3.2 Literature Survey
3.3 Proposed Methodology
3.3.1 Code Smells Detection
3.1.1.1 Feature Envy Code Smell
3.1.1.2 GOD Class Code Smell
3.1.1.3 Long Method Code Smell
3.1.1.4 Long Parameter List Code Smell
3.1.1.5 Refused Bequest Code Smell
3.1.1.6 Shotgun Surgery Code Smell
3.1.1.7 Duplicated Code Smell
3.3.2 Code Smells Prioritization
3.3.3 Refactoring and Quality Improvement
3.4 Experimentation and Results
3.4.1 Experimental Planning and Setup
3.4.2 Research Questions and Evaluation Method
3.4.3 Results Analysis and Interpretations
3.5 Conclusion and Future Work
References
4. Evaluating Machine Learning Capabilities for Predicting Joining Behavior of Freshmen Students Enrolled at Institutes of Higher Education: Case Study from a Novel Problem Domain
4.1 Introduction
4.2 Methods and Materials
4.2.1 Demography of the Subjects Used
4.2.2 Novelty and Modifications in Preparing the Data Set
4.2.3 Experiments Designed
4.2.4 Classification Algorithms and Performance Evaluation
4.2.5 Interpretability Techniques
4.3 Proposed Mathematical Framework
4.4 Results and Discussion
4.4.1 Comparison of Models Using Performance Metrics
4.4.2 Interpreting Model Behavior
4.4.3 Year-wise Significant Features
4.5 Conclusion
References
5. Image Processing for Knowledge Management and Effective Information Extraction for Improved Cervical Cancer Diagnosis
5.1 Introduction
5.1.1 Digital Image Processing
5.1.2 Fundamental Key Stages in Digital Image Processing
5.2 Literature Review
5.3 Proposed Methodology
5.3.1 Data Collections
5.3.2 Preprocessing - Image Enhancement
5.3.3 Intensity Transformation Function
5.3.4 Segmentation
5.3.5 Feature Extraction
5.4 Role of Knowledge Management and Effective Information Extraction in Image Processing
5.5 Knowledge Management in Case-Based Reasoning Methodology on Healthcare Handling
5.6 OBIA (Object-Based Image Analysis)
5.7 Results and Discussion
5.7.1 Image Segmentation
5.7.2 Feature Extraction
5.8 Conclusion
References
6. Recreating Efficient Framework for Resource-Constrained Environment: HR Analytics and Its Trends for Society 5.0
6.1 Introduction
6.2 Literature Review
6.3 Conceptualizing HR Analytics
6.3.1 Relevance of HR Analytics
6.3.2 Benefits of Using HR Analytics
6.4 Applications of HR Analytics for Industry 5.0
6.4.1 Managing the HR Through Analytics: A Case Study of Google
6.4.2 Employee Recruitment: A Case Study of JP Morgan and Rentokil Initial
6.4.3 Employee Retention: A Case Study of HP, IBM, and WIPRO
6.4.4 Employee Engagement: A Case Study of Clarks and Shell
6.4.5 Compensation and Benefits: A Case Study of Clarks
6.4.6 Employee Training
6.5 Recent Trends in HR Analytics
6.5.1 R Programming Language
6.5.2 Python
6.5.3 Business Intelligence
6.6 Challenges of Implementing Human Resource Analytics
6.7 HR Analytics Framework: The Way Forward
6.7.1 Developing Leaders
6.7.2 Ensuring Requisite Skill Sets
6.7.3 Focussing on Clarity of Vision and Mission of Adopting HR Analytics
6.7.4 Understanding and Connecting with the Business Strategy
6.7.5 Collaborating with Stakeholders
6.8 Discussion
6.9 Conclusion
References
7. Integration of Internet of Things (IoT) in Health Care Industry: An Overview of Benefits, Challenges, and Applications
7.1 Introduction
7.1.1 Elements of IoT
7.1.2 Characteristics of IoT
7.2 Architecture of IoT in Healthcare
7.3 Advantages of IoT in Healthcare
7.4 IoT Healthcare Security Challenges
7.5 Design Considerations
7.6 Applications of IoT in Healthcare
7.7 IoT Use Cases
7.8 Conclusion
References
8. Cloud, Edge, and Fog Computing: Trends and Case Studies
8.1 Introduction
8.2 Overview of the Multi-Tenancy Cloud Service Models
8.3 Engineering of Cloud Services
8.3.1 Static Binding Variation Techniques
8.3.2 Dynamic Binding Variation Techniques
8.4 Packaging of Cloud Services
8.4.1 Service Level
8.4.2 Tenant Level
8.5 Hosting Cloud Services
8.5.1 Shared Instance
8.5.2 Dedicated Instance
8.6 Discussion on Architecture Choices
8.6.1 Cloud Service Variability
8.6.2 Costs and Benefits of Designing Service Variability
8.6.3 Cloud Service Architecture Models
8.7 Variability Scenarios - Service Provider Perspective
8.7.1 Cost Considerations
8.7.2 Revenue Considerations
8.7.3 Tenant Profile
8.7.4 Market Share Considerations
8.7.5 Service Isolation
8.7.6 Budget Constraints
8.8 Cloud Service Profitability Model
8.8.1 Service Tenants
8.8.2 Range of Service Variability
8.8.3 Service Costs
8.8.4 Service Revenue
8.8.5 Service Profits
8.9 Analyzing Service Profitability Based on Concept Map
8.9.1 Overview of Simulation Process
8.9.2 Simulating with Constraints
8.9.3 Tooling for the Simulation Process
8.10 Experiments and Evaluations
8.10.1 Experiments Overview
8.10.2 Performing Simulations
8.10.3 Budget Constraint Scenario
8.11 Related Works
8.12 Threats to Validity
8.13 Conclusion
References
9. A Paradigm Shift for Computational Excellence from Traditional Machine Learning to Modern Deep Learning-Based Image Steganalysis
9.1 Introduction
9.1.1 Motivation
9.1.2 Key Contributions
9.2 Universal Image Steganalysis Preliminaries
9.2.1 The Conceptualization
9.2.2 Rationale for Using CNN Models
9.2.2.1 Image Pre-Processing Layer
9.2.2.2 Convolutional Layer
9.2.2.3 Non Linear Mapping Layer
9.2.2.4 Pooling Layer
9.2.2.5 Batch Normalization
9.2.2.6 Classification Layer
9.2.2.7 Optimization of Gradient Descent
9.3 Recent Advancements
9.4 Open Research Issues and Opportunities
9.5 Conclusion
References
10. Feature Engineering for Presentation Attack Detection in Face Recognition: A Paradigm Shift from Conventional to Contemporary Data-Driven Approaches
10.1 Introduction
10.2 Feature Engineering for Secured and Intelligent Face Biometric Systems
10.2.1 Facial Features
10.3 Computational Image Features for Face PAD Mechanisms
10.3.1 Handcrafted Features
10.3.1.1 Local Binary Patterns
10.3.1.2 Binarized Statistical Image Features
10.3.1.3 Local Phase Quantization
10.3.1.4 Speed Up Robust Features
10.3.2 Deep Features Engineering for Face PAD Mechanisms
10.4 Security Evaluation Using Face Anti-Spoofing Data Sets
10.5 Open Research Issues and Opportunities
10.6 Conclusion
References
11. Reconfigurable Binary Neural Networks Hardware Accelerator for Accurate Data Analysis in Intelligent Systems
11.1 Introduction
11.2 Related Works
11.3 Binary Neural Network Fundamentals
11.3.1 BNN Representation
11.4 Research Considerations
11.4.1 Data sets
11.4.2 Topologies
11.4.3 Accuracy
11.4.4 Hardware Implementation
11.5 Proposed BNN Architecture
11.6 Results and Discussions
11.7 Conclusion
References
12. Recommender System: Techniques for Better Decision Making for Society 5.0
12.1 Introduction
12.2 Literature Survey
12.2.1 Recommendation Techniques: Collaborative Filtering Based
12.2.2 Recommendation Techniques: Content-Based
12.2.3 Recommendation Techniques: Hybrid
12.2.4 Recommendation Techniques: Knowledge-Based
12.2.5 Recommendation Techniques: Context Awareness-Based
12.3 Recommendation Systems and Related Issues
12.3.1 User Preferences
12.3.2 Sparsity in Ratings
12.3.3 Cold-Start Problem (User and Item Point of View)
12.3.4 Overspecialization
12.3.5 Novelty and Diversity of Recommendation
12.3.6 Scalability
12.3.7 Context-Awareness
12.3.8 Prediction Accuracy
12.3.9 Privacy
12.3.10 Adaptivity
12.4 Trends in Recommendation System to Support Decision Making for Society 5.0
12.5 Merits and Limitations of Recommendation Systems in Light of Society 5.0
12.6 Design Guidelines for Attenuating the Challenging Issues in Recommendation System
12.7 Conclusion and Future Scope
References
13. Implementation of Smart Irrigation System Using Intelligent Systems and Machine Learning Approaches
13.1 Introduction
13.2 Related Work
13.3 Data Analysis
13.4 Proposed System
13.4.1 Setting Up Soil Moisture Threshold Value
13.4.2 Materials and Methods
13.4.2.1 Hardware Requirements
13.4.2.2 Software Requirements
13.4.2.3 Supporting Materials
13.5 Implementation and Working
13.6 Results and Discussion
13.6.1 Simulation Results
13.7 Conclusion
13.8 Future Research Directions
References
14. Lightweight Cryptography Using a Trust-Based System for Internet of Things (IoT)
14.1 Introduction
14.1.1 Challenges In Internet of Things
14.1.2 Destination-Oriented Directed Acyclic Graph
14.1.3 IPv6 Low Power and Lossy Networks Routing Protocol (RPL)
14.1.4 Version Number Attack
14.1.5 Trust and Reputation
14.2 Literature Review
14.2.1 Related Work
14.2.2 Research Challenges
14.3 Research Methodology
14.3.1 Proposed Algorithm
14.4 Result and Discussion
14.4.1 Network Deployment
14.4.2 Version Number Attack
14.4.3 Analysis of Packet Loss and Thoughput
14.5 Conclusion
References
15. Innovation in Healthcare for Improved Pneumonia Diagnosis with Gradient-Weighted Class Activation Map Visualization
15.1 Introduction
15.1.1 Deep Learning and Convolutional Neural Networks
15.1.2 Image Preprocessing and Visualization
15.1.3 Relevance and Contributions
15.2 Background and Motivation
15.3 Literature Survey
15.4 Data Analysis
15.4.1 Exploratory Data Analysis
15.5 Framework and Methodology Used
15.5.1 Convolutional Neural Network
15.5.2 Data Preprocessing and Augmentation
15.5.3 Transfer Learning: Pretrained Architecture
15.5.3.1 ResNet-50
15.5.3.2 EfficientNet
15.5.3.3 VGG-16
15.5.3.4 MobileNetV2
15.5.3.5 DenseNet
15.6 Design and Architecture
15.6.1 Data Flow Analysis
15.6.2 Architecture Details
15.7 Experimental Setup
15.7.1 Evaluation
15.7.2 Implementation Details
15.8 Results and Discussion
15.8.1 Results
15.8.2 Discussion
15.9 Future Research Directions
15.10 Conclusion
Glossary
References
Index