AI-Centric Modeling and Analytics; Concepts, Technologies, and Applications

Cover
Half Title
Title
Copyright
Contents
Preface
Acknowledgments
Editors
Contributors
Chapter 1 Artificial Intelligence-Based Model and Applications in Business Decision-Making
	1.1 Introduction
	1.2 Literature Survey
	1.3 Artificial Intelligence-Centric Business Models
	1.4 Tools for Supporting Business Decision-Making
		1.4.1 Artificial Intelligence-Centric Tools for Supporting Business Decision-Making
		1.4.2 ChatGPT for Business Decision-Making
		1.4.3 Example (Case Study) for Business Decision-Making
	1.5 Conclusion
	References
Chapter 2 Exploration of Machine Learning Models for Business Ecosystem
	2.1 Introduction
	2.2 Machine Learning in Industry 4.0
		2.2.1 Machine Learning Models
		2.2.2 Technology Features of Machine Learning for Industry 4.0
		2.2.3 Challenges in Industry 4.0 Using Machine Learning
	2.3 Literature Survey
	2.4 Machine Learning Framework for Business Ecosystem
	2.5 Performance Analysis of Machine Learning Models
	2.6 Conclusion
	References
Chapter 3 The Role of Big Data and Data Analysis Tools in Business and Production
	3.1 Introduction
	3.2 Definition of Big Data
		3.2.1 Managing Big Data
		3.2.2 Data Use Cases
	3.3 Big Data Process Life Cycle
		3.3.1 Data Ingestion
		3.3.2 Data Storage
		3.3.3 Data Processing
		3.3.4 Data Analysis
		3.3.5 Big Data Analytics
		3.3.6 Data Visualization
	3.4 Conclusion
	References
Chapter 4 Revolutionized Teaching by Incorporating Artificial Intelligence Chatbot for Higher Education Ecosystem
	4.1 Introduction
	4.2 Related Work
		4.2.1 Student Engagement
		4.2.2 Chatbots and Language Learning
	4.3 Methods
	4.4 Results and Discussion
		4.4.1 Student Engagement in Incorporating Artificial Intelligence Chatbots
		4.4.2 Discussion
	4.5 Conclusion
	References
Chapter 5 Application of Artificial Intelligence in AgroWeb
	5.1 Introduction
	5.2 Related Work
	5.3 Pre-Harvesting
		5.3.1 Crop Prediction
		5.3.2 Model Selection for Crop Prediction
		5.3.3 Seed Prediction
		5.3.4 Crop Disease Prediction
		5.3.5 Irrigation System
		5.3.6 Irrigation System Model
	5.4 Conclusion
	5.5 Recommendation
	References
Chapter 6 Natural Language Processing: A Study of State of the Art
	6.1 Introduction
	6.2 Text Pre-Processing and Vector-Based Models
	6.3 Text Pre-Processing Techniques
		6.3.1 Term Frequency–Inverse Document Frequency
		6.3.2 Term Frequency Matrix
	6.4 Natural Language Processing: Text Similarity and Semantic Analysis
		6.4.1 Euclidian Distance
		6.4.2 Dot Product
		6.4.3 Cosine Similarity
	6.5 Semantic Analysis
	6.6 Probability Models in Natural Language Processing
		6.6.1 Hidden Markov Model
		6.6.2 Language Models
	6.7 Machine Learning Methods for Natural Language Processing
		6.7.1 Spam Detection–Naive Bayes
		6.7.2 Sentiment Analysis–Logistic Regression
		6.7.3 Latent Semantic Analysis–Singular Value Decomposition
		6.7.4 Topic Modeling–Latent Dirichlet Allocation
	6.8 Deep Learning Methods
		6.8.1 Multilayer Perceptron
		6.8.2 Convolutional Neural Network
		6.8.3 Recurrent Neural Network
	6.9 Conclusion
	References
Chapter 7 Application of Artificial Intelligence in Healthcare System Management with Dynamic Modeling of COVID-19 Diagnosis
	7.1 Introduction
	7.2 Nomenclature
	7.3 Mathematical Assumptions
	7.4 Mathematical Model (SEIQR)
		7.4.1 Model Analysis for Boundedness and Positivity
		7.4.2 Calculation of Basic Reproduction Number
	7.5 Existence of Equilibrium Points of the System of Equations
		7.5.1 Coronavirus-Free Equilibrium Point
		7.5.2 Stability Analysis of the Endemic Equilibrium
		7.5.3 Global Stability of the Endemic Equilibrium
	7.6 Results and Discussion
	7.7 Conclusion
	References
Chapter 8 Breast Cancer Prediction Using Voting Classifier Model
	8.1 Introduction
		8.1.1 Problem
		8.1.2 Requirement for Our System
	8.2 Literature Review
	8.3 Methodology
		8.3.1 Implementing Environment
		8.3.2 Dataset Analysis and Pre-Processing
	8.4 Proposed Work
	8.5 Analysis and Comparison
	8.6 Conclusion
	References
Chapter 9 Privacy Protection for Internet of Medical Things Data Using Effective Outsourced Support Vector Machine Approach
	9.1 Introduction
		9.1.1 Big Data
		9.1.2 Privacy-Preserving Data
		9.1.3 Internet of Medical Things
		9.1.4 Machine Learning in Internet of Medical Things
	9.2 Literature Review
		9.2.1 Data Mining
		9.2.2 Machine Learning
	9.3 System Design
	9.4 Results and Discussion
	9.5 Conclusion
	References
Chapter 10 Robotics in Real-Time Applications Using Bayesian Hyper-Tuned Artificial Neural Network
	10.1 Introduction
	10.2 Problem Statement
	10.3 Proposed Work
		10.3.1 Data Collection
		10.3.2 Pre-Processing Using Min-Max Normalization
		10.3.3 Feature Extraction Using Kernel Linear Discriminant Analysis
		10.3.4 Feature Detection Using Bayesian Hyper-Tuned Artificial Neural Network
	10.4 Performance Evaluation
		10.4.1 Security
		10.4.2 Sensing Level
		10.4.3 Robustness
		10.4.4 Implementation Cost
	10.5 Conclusion
	References
Chapter 11 Quantitative Study on Variation of Glaucoma Eye Images Using Various EfficientNetV2 Models
	11.1 Introduction
	11.2 Literature Survey
	11.3 Technical Approach
		11.3.1 Dataset Description
		11.3.2 EfficientNetV2 Models
	11.4 Why EfficientNetV2?
		11.4.1 EfficientNetV2B0
		11.4.2 EfficientNetV2B1
		11.4.3 EfficientNetV2B2
		11.4.4 EfficientNetV2B3
		11.4.5 EfficientNetV2S
		11.4.6 EfficientNetV2M
		11.4.7 EfficientNetV2L
		11.4.8 EfficientNetV2XL
	11.5 Hyper-Parameters Used
		11.5.1 Adam (Optimizer)
		11.5.2 Sigmoid (Activation Function)
	11.6 Proposed Methodology
	11.7 Implementation and Results
		11.7.1 Evaluation of a Model Using Classification Metrics
		11.7.2 Evaluation of Models Using Confusion Matrix
	11.8 Conclusion
	References
Chapter 12 Disaster Management System for Forest Fire Prediction: Fog and Cloud Data-Driven Analytical Compatible Model
	12.1 Introduction
	12.2 Related Work
	12.3 Discussion and Results
		12.3.1 Data Acquisition Layer
		12.3.2 Fog Layer
		12.3.3 Cloud Layer
	12.4 Performance Analysis and Results
	12.5 Implementation
	12.6 Conclusion
	References
Chapter 13 Hybrid Particle Swarm Optimization with Random Forest Algorithm Used in Job Scheduling to Improve Business and Production
	13.1 Introduction
		13.1.1 Job Scheduling
		13.1.2 Data Cleaning
		13.1.3 Machine Learning
		13.1.4 Big Data Analysis
		13.1.5 Particle Swarm Optimization
		13.1.6 Random Forest
	13.2 Literature Review
	13.3 System Design
		13.3.1 Particle Swarm Optimization for Data in Feature Selection
		13.3.2 Training Data
		13.3.3 Testing Data
		13.3.4 Verification Step
		13.3.5 Particle Swarm Optimization Algorithm
		13.3.6 RF in Classification Algorithm
	13.4 Results and Discussion
	13.5 Conclusion
	References
Chapter 14 Robotic Process Automation Applications in Data Management
	14.1 Introduction
		14.1.1 Robotic Process Automation Tools and Techniques
		14.1.2 Relation of Robotic Process Automation with Artificial Intelligence Processes
	14.2 Robotic Process Automation in Data Management
		14.2.1 Robotic Process Automation Application in Data Cleansing
		14.2.2 Robotic Process Automation Application in Data Normalization
		14.2.3 How Is Robotic Process Automation Used in Data Wrangling?
		14.2.4 Robotic Process Automation Application Management of Metadata
		14.2.5 Variations of Robotic Process Automation
	14.3 What Makes Robotic Process Automation So Special?
		14.3.1 Business Process Automation
		14.3.2 Business Process Management
		14.3.3 Business Process Outsourcing
		14.3.4 Advantages of Robotic Process Automation
	14.4 Robotic Process Automation Learning with Cloud
		14.4.1 Public Cloud
		14.4.2 Private Cloud
		14.4.3 Hybrid Cloud
	14.5 Generally Used Robotic Process Automation Tools
		14.5.1 Blue Prism
		14.5.2 UiPath
		14.5.3 Automation Anywhere
		14.5.4 Kofax Kapow
		14.5.5 Neptune Intelligence Computer Engineering
		14.5.6 Key Differences between the Best Robotic Process Automation Tools
	14.6 Robotic Process Automation in Business Data Management
	14.7 Robotic Process Automation Use Cases in Business Data Management
		14.7.1 How Customer Support Management Use Robotic Process Automation
		14.7.2 Natural Language Use in Business Data Processing with Robotic Process Automation
	14.8 Conclusion
	References
Chapter 15 Artificial Intelligence-Enabled Bibliometric Analysis in Tourism and Hospitality Using Biblioshiny and VOSviewer Software
	15.1 Introduction
	15.2 Artificial Intelligence/Machine Learning
	15.3 Methodology
	15.4 Related Work
		15.4.1 Analysis and Visualization of Data
		15.4.2 Main Information about the Study
		15.4.3 Emergence of Sources and Citation Analysis
		15.4.4 Keyword Analysis
		15.4.5 Analysis Based on Structures of Knowledge
	15.5 Results and Discussion
		15.5.1 Objective 1: To Investigate the Research Trend, Cluster Research, and the Evolution of Recent Research Domains in Tourism and the Hospitality Industry
		15.5.2 Objective 2: To Investigate the Scientific Production by Countries
		15.5.3 Objective 3: To Investigate the Scientific Production by Authors
		15.5.4 Objective 4: To Investigate the Scientific Production by Institutions
		15.5.5 Objective 5: To Investigate the Scientific Collaboration of the Countries
		15.5.6 Objective 6: To Investigate Scientific Production by Sources and Dissemination by Sources
		15.5.7 Objective 7: To Investigate the Content Based on the Author’s Keywords, KeyWords Plus, Titles, and Abstracts
		15.5.8 Objective 8: To Investigate the Content Based on Citations (Most Cited References)
		15.5.9 Objective 9: To Investigate the Less Researched Keywords Based on Centrality and Density
	15.6 Conclusion
	15.7 Limitations
	15.8 Further Research
	References
Chapter 16 Data-Centric Predictive Analytics for Solving Environmental Problems
	16.1 Introduction
	16.2 Materials and Methods
	16.3 Discussion and Results
		16.3.1. Exponential Decay and Logistic Models for Removal of Phenol
		16.3.2. Results for the Logistic Model
	16.4 Conclusion
	References
Chapter 17 Phishing Attack and Defense: An Exploratory Data Analytics of Uniform Resource Locators for Cybersecurity
	17.1 Introduction
		17.1.1 Background
		17.1.2 Methodology
		17.1.3 Chapter Organization
	17.2 Related Work
	17.3 Proposed Methodology
		17.3.1 Data Acquisition
		17.3.2 Exploratory Data Analysis
		17.3.3 Predictive Analytics of Uniform Resource Locators
	17.4 Results
	17.5 Conclusion
	17.6 Recommendation
	References
Chapter 18 Analysis of Deep Learning-Based Approaches for Spam Bots and Cyberbullying Detection in Online Social Networks
	18.1 Introduction
		18.1.1 SPAM
		18.1.2 Spam Bot Detection Methods
		18.1.3 Cyberbullying
		18.1.4 Types of Cyberbullying
		18.1.5 Cyberbullying Detection Methods
	18.2 Proposed Methodology
		18.2.1 Research Queries
		18.2.2 Search Strategy
		18.2.3 Study Choice
		18.2.4 Quality Valuation Tools
	18.3 Performance Metrics for Spam Bot and Cyberbullying Detection
		18.3.1 Accuracy and Average Accuracy
		18.3.2 Precision and Average Precision
		18.3.3 Recall and Average Recall
		18.3.4 F-Measure
		18.3.5 G-Measure
		18.3.6 Specificity and Average Specificity
	18.4 Spam Bot Detection in Online Social Network Using Deep Learning
		18.4.1 Social Media Bots
		18.4.2 Spam Bot Detection in X/Twitter Using Deep Learning
		18.4.3 Cyberbullying Detection in Online Social Network Using Deep Learning
	18.5 Research Gap Analysis
	18.6 Outcome of Literature Survey
	18.7 Conclusion
	18.8 Future Scope
	References
Index