-
Browse Book Series
- Adhesion and Adhesives: Fundamental and Applied Aspects
- Advances in Additive Manufacturing Technologies
- Advances in Antenna, Microwave and Communication Engineering
- Advances in Biofeedstocks and Biofuels
- Advances in Cyber Security
- Advances in Data Engineering and Machine Learning
- Advances in Disease Diagnosis, Drug Delivery and Treatment
- Advances in E-Mobility
- Advances in Hydrogen Production and Storage
- Advances in Intelligent and Scientific Computing (AISC)
- Advances in Learning Analytics for Intelligent Cloud-IoT Systems
- Advances in Membrane Processes
- Advances in Nanotechnology and Applications
- Advances in Natural Gas Engineering
- Advances in Pipes and Pipelines
- Advances in Production Engineering
- Advances in Solar Cell Materials and Storage
- Advances in Surface Engineering and Materials Processing
- Applied Functional Materials
- Artificial Intelligence and Soft Computing for Industrial Transformation
- Astrobiology Perspectives on Life in the Universe
- Bioprocessing in Food Science
- Computational Intelligence and Biomedical Engineering
- Computational Intelligence in Industrial Mathematics
- Concise Introductions to AI and Data Science
- Cyber Systems and Quantum Engineering
- Decentralized Systems and Next-Generation Internet
- Diatoms: Biology and Applications
- Digital Convergence in Engineering Systems
- Emerging Trends in Medicinal and Pharmaceutical Chemistry
- Engineering Systems Design for Sustainable Development
- Fintech in a Sustainable Digital Society
- Human Centric Sustainability and Next Generation Technology
- Industry 5.0 Transformation Applications
- Infectious and Rare Diseases
- Innovations in Materials and Manufacturing
- Leading-Edge Breakthroughs in Artificial Intelligence
- Lifeline Molecules: Exploring Antioxidants and Their Impact
- Machine Learning in Biomedical Science and Healthcare Informatics
- Marine Nanoscience and Nanotechnology
- Materials Degradation and Failure
- Mathematics and Computer Science
- Next-Generation Computing and Communication Engineering
- Performability Engineering Series
- Robotics and Automation for Modern Applications
- Rotating Machinery Fundamentals and Advances
- Semiconductor Devices and Their Applications
- Separation Science
- Studies in Computational Intelligence and Smart Technologies
- Sustainable Biopolymer Technologies and Applications
- Sustainable Computing and Optimization
- Thermoplastic Bionanocomposites Series
- Transformative Innovations in Materials Science
Browse Subject Areas
For Authors
Submit a ProposalData Driven Modeling
One Line Description
Equip yourself with the essentials of informed decision-making with this practical guide to mastering data-driven modeling and extracting actionable, meaningful patterns from the vast sea of modern data.
Audience
Data scientists and analysts, researchers, academics, engineers, and professionals involved with AI, machine learning, and process optimization.
Data scientists and analysts, researchers, academics, engineers, and professionals involved with AI, machine learning, and process optimization.
Description
In an era defined by data, the ability to transform raw information into actionable insights is a skill set that transcends industries and disciplines. This book is a comprehensive guide designed to unravel the intricacies of extracting meaningful patterns from the vast sea of data that surrounds us. It explores the significance of data-driven modelling, comparing it to traditional approaches and setting the stage for understanding the transformative power and diverse applications of data-driven techniques. This comprehensive resource empowers readers to leverage data for informed decision-making. Whether you are a novice looking to grasp the fundamentals or an experienced professional seeking advanced techniques, this book serves as a practical guide through the dynamic landscape of data-driven modelling. Through clear explanations, hands-on examples, and real-world applications, readers will gain the skills needed to navigate the complexities of modern data analysis.
Back to Top
In an era defined by data, the ability to transform raw information into actionable insights is a skill set that transcends industries and disciplines. This book is a comprehensive guide designed to unravel the intricacies of extracting meaningful patterns from the vast sea of data that surrounds us. It explores the significance of data-driven modelling, comparing it to traditional approaches and setting the stage for understanding the transformative power and diverse applications of data-driven techniques. This comprehensive resource empowers readers to leverage data for informed decision-making. Whether you are a novice looking to grasp the fundamentals or an experienced professional seeking advanced techniques, this book serves as a practical guide through the dynamic landscape of data-driven modelling. Through clear explanations, hands-on examples, and real-world applications, readers will gain the skills needed to navigate the complexities of modern data analysis.
Back to Top
Author / Editor Details
Arindam Mondal, PhD is a Professor at Dr. B.C. Roy Engineering College with more than 20 years of experience. He has published more than 35 papers for scientific and technical journals and conferences. He has eighteen patents to his credit and has won several awards for his scholarship.
Arindam Mondal, PhD is a Professor at Dr. B.C. Roy Engineering College with more than 20 years of experience. He has published more than 35 papers for scientific and technical journals and conferences. He has eighteen patents to his credit and has won several awards for his scholarship.
Souvik Ganguli, PhD is an Assistant Professor at the Thapar Institute of Engineering and Technology with more than 19 years of teaching experience. He has published more than 50 papers in leading journals, conferences, and book chapters. He has 15 granted patents to his credit and has won several awards for his scholarly activities.
Back to Top
Table of Contents
Preface
1. Fundamentals of Data Analysis and Preprocessing
Sudipta Hazra and Arindam Mondal
1.1 Introduction
1.2 Data Preprocessing
1.2.1 Issues with Data
1.2.1.1 Excessive Data
1.2.1.2 Too Little Data
1.2.1.3 Splintered Data
1.2.2 Setting Up for DA
1.2.2.1 Recognizing the Types of Data
1.2.2.2 Preparing Data for Detailed DA
1.3 Strategies for Preparing Data
1.3.1 Transforming Data
1.3.1.1 Filtering Data
1.3.1.2 Data Arranging
1.3.1.3 Editing Data
1.3.1.4 Modeling Noise
1.3.2 Information Compilation
1.3.2.1 Data Visualization
1.3.2.2 Data Elimination
1.3.2.3 Data Selection
1.3.2.4 Analysis of Principal Components
1.3.2.5 Data Sampling
1.3.3 Production of Novel Information
1.3.3.1 Including Extra Features
1.3.3.2 Data Fusion
1.3.3.3 Time–Series Analysis
1.3.3.4 Information Modeling
1.3.3.5 Dimensional Analysis
1.4 Real-World Applications
1.4.1 Machine Learning and Predictive Analytics
1.4.2 Healthcare and Biomedical Research
1.4.3 Financial Analysis and Risk Management
1.4.4 Marketing and Customer Analytics
1.4.5 Supply Chain Management and Logistics
1.4.6 Environmental Monitoring and Sustainability
1.5 Conclusion
References
2. Advanced Data Control Methods for Data-Driven Modeling: Techniques, Challenges, and Future Directions
Aarushi Chatterjee and Souvik Ganguli
2.1 Introduction
2.2 Related Works
2.2.1 Data Quality and Preprocessing
2.2.2 Data Governance and Control in Distributed Systems
2.2.3 Data Privacy and Security
2.2.4 Model Predictive Control and Data-Driven Approaches
2.2.5 Data Drift and Adaptive Control
2.3 Data Control Architecture in Modeling
2.3.1 Centralized versus Decentralized Data Control
2.3.1.1 Centralized Data Control
2.3.1.2 Decentralized Data Control
2.3.2 Automated Data Governance
2.3.2.1 Metadata Management
2.3.2.2 Data Provenance and Lineage
2.3.2.3 Policy Enforcement Engines
2.3.3 Real-Time Data Control in Streaming and Dynamic Systems
2.3.3.1 Windowing and Stream Processing
2.3.3.2 Adaptive Sampling and Real-Time Data Filtering
2.3.3.3 Real-Time Model Retraining
2.3.4 Emerging Trends in Data Control Architecture
2.3.4.1 Federated Learning for Data Control
2.3.4.2 Blockchain for Data Integrity and Control
2.4 Advanced Techniques for Data Control
2.4.1 Data-Driven Control Strategies
2.4.1.1 Model Predictive Control
2.4.1.2 RL for Data-Driven Control
2.4.1.3 Adaptive Control Systems
2.4.2 Control of Streaming Data
2.4.2.1 Sliding Windows and Stream Processing Frameworks
2.4.2.2 Approximate Query Processing
2.4.2.3 Online Learning for Streaming Data
2.4.3 Handling Dynamic and Evolving Data Environments
2.4.3.1 Adaptive Learning Models
2.4.3.2 Handling Data Drift and Concept Drift
2.4.4 Advanced Real-Time Data Governance
2.4.4.1 Automated Policy Enforcement
2.4.4.2 Dynamic Access Control
2.5 Challenges in Data Control for Modeling
2.5.1 Scalability Issues
2.5.1.1 Data Volume and Velocity
2.5.1.2 Horizontal versus Vertical Scaling
2.5.2 Data Drift and Concept Drift
2.5.2.1 Types of Drift
2.5.2.2 Challenges in Detecting Drift
2.5.2.3 Model Adaptation
2.5.3 Real-Time Data Control
2.5.3.1 Latency Issues
2.5.3.2 Synchronization and Consistency
2.5.4 Data Privacy and Security
2.5.4.1 Data Anonymization and Differential Privacy
2.5.4.2 Data Encryption and Secure Computation
2.5.5 Collaborative Data Control
2.5.5.1 Data Sharing Across Organizations
2.5.5.2 Version Control and Auditing
2.6 Best Practices for Data Control in Data-Driven Modeling
2.6.1 Data Versioning and Auditing
2.6.1.1 Data Versioning
2.6.1.2 Auditing
2.6.2 Collaborative Data Control
2.6.2.1 Role-Based Access Control
2.6.2.2 Data Sharing and Federation
2.6.3 Metadata Management for Governance and Provenance
2.6.3.1 Automated Metadata Generation
2.6.3.2 Data Provenance and Lineage Tracking
2.6.4 Automation in Data Governance
2.6.4.1 Automated Policy Enforcement
2.6.4.2 Automated Compliance Monitoring
2.7 Case Studies in Data Control Methods
2.7.1 Real-Time Data Control in AVs
2.7.2 Data Governance and Privacy in Healthcare
2.7.3 Collaborative Data Sharing in Financial Services
2.7.4 Data Control in Smart Energy Grids
2.7.5 Big Data Control in E-Commerce
2.8 Future Directions in Data Control
2.8.1 Decentralized and Distributed Data Control
2.8.1.1 Edge Computing and Data Control at the Edge
2.8.1.2 Blockchain for Decentralized Data Control
2.8.2 Privacy-Preserving Data Control
2.8.2.1 Differential Privacy
2.8.2.2 Homomorphic Encryption and Secure Computation
2.8.3 Real-Time Adaptive Data Control
2.8.3.1 AI-Driven Data Control
2.8.3.2 Context-Aware Data Control
2.8.4 Federated Learning and Collaborative Data Control
2.8.4.1 Federated Learning at Scale
2.8.4.2 Federated Governance and Data Control
2.8.5 Quantum Computing and Its Impact on Data Control
2.8.5.1 Quantum Cryptography for Data Security
2.8.5.2 Quantum Machine Learning for Data Control
2.9 Concluding Remarks
References
3. Machine Learning Algorithms for Data-Driven Modeling
Souryadip Ghosh, Indrani Mukherjee and Suparna Biswas
3.1 Introduction
3.2 What is Machine Learning?
3.3 Classification of Machine Learning Methods
3.3.1 Supervised Learning
3.3.2 Unsupervised Learning
3.3.3 Reinforcement Learning
3.4 Supervised Machine Learning
3.4.1 Decision Tree for Classification
3.4.2 C4.5
3.4.3 CART
3.4.4 CHAID
3.4.5 Iterative Dichotomizer 3
3.5 Support Vector Machine
3.5.1 SVM for Linear Classification
3.5.2 SVM for Nonlinear Classification
3.5.3 Kernel
3.5.4 Unsupervised Machine Learning
3.5.5 Clustering
3.5.6 K-Means
3.6 Hierarchical Clustering
3.6.1 Methodologies for Determining the Optimal Number of Clusters
3.6.2 Dimensionality Reduction
3.6.3 t-Distributed Stochastic Neighbor Embedding
3.6.4 Multidimensional Scaling
3.7 Principal Component Analysis
3.8 Conclusion
Bibliography
4. Neural Networks and Deep Learning in Data-Driven Modeling
Tanishka Chakraborty, Indrani Mukherjee and Suparna Biswas
4.1 Introduction
4.2 Basic Concept of Neural Network and Deep Learning
4.2.1 Characteristics of Neural Network
4.2.2 Characteristics of Deep Learning
4.3 Applications of Neural Networks and Deep Learning in Data-Driven Modeling
4.3.1 Image Recognition
4.3.2 Natural Language Processing
4.3.3 Time–Series Prediction
4.3.4 Recommender Systems
4.3.5 Anomaly Detection
4.3.6 Generative Adversarial Networks
4.3.7 Autonomous Driving
4.3.8 Health Monitoring Using Wearable Devices
4.3.9 Attention Mechanisms in NLP
4.3.10 Brain–Computer Interface
4.3.11 Fault Diagnosis in Industrial Systems
4.3.12 Speech Recognition
4.3.13 Cybersecurity Applications
4.3.14 Energy Consumption Forecasting
4.3.15 Human Activity Recognition
4.4 Techniques of Neural Networks and Deep Learning in Data-Driven Modeling
4.4.1 Convolutional Neural Networks
4.4.2 Recurrent Neural Networks
4.4.3 Long Short-Term Memory Networks
4.4.4 Autoencoders
4.4.5 Generative Adversarial Networks
4.4.6 Deep Reinforcement Learning
4.4.7 Transfer Learning
4.4.8 Data Augmentation
4.5 Methods of Neural Networks and Deep Learning in Data-Driven Modeling
4.5.1 Backpropagation
4.5.2 Data Augmentation
4.5.3 Hyperparameter Optimization
4.5.4 Ensemble Learning
4.5.5 Attention Mechanisms
4.5.6 Capsule Networks
4.5.7 Neuroevolution
4.6 Conclusion
Bibliography
5. Advances in Time-Series Analysis: Techniques and Applications for Predictive Forecasting
A. UmaDevi, Jagendra Singh, Shrinwantu Raha, Nazeer Shaik, Anil V. Turukmane and Ishaan Singh
5.1 Introduction
5.1.1 Definition and Conceptual Framework
5.1.2 Importance and Applications
5.2 Foundational Techniques in TSA
5.2.1 AR Models
5.2.2 MA Models
5.2.3 ARIMA Models
5.2.4 Exponential Smoothing Methods
5.2.5 Seasonal Decomposition of Time Series
5.2.6 State Space Models and Kalman Filtering
5.2.7 Spectral Analysis and Fourier Transform
5.2.8 ML Techniques
5.3 Applications of TSA
5.3.1 Economic and Financial Forecasting
5.3.2 Healthcare and Epidemiology
5.4 Future Directions and Emerging Trends
5.4.1 Deep Learning and Neural Networks
5.4.2 Probabilistic Forecasting
5.4.3 Anomaly Detection and Outlier Analysis
5.4.4 Interpretable and Explainable Models
5.4.5 Multivariate and High-Dimensional TSA
5.4.6 Integration with Domain-Specific Knowledge
5.4.7 Ethical and Fair TSA
5.4.8 Automated ML for Time Series
5.4.9 Continuous Learning and Model Adaptation
5.5 Conclusion
References
6. Ensemble Methods for Data-Driven Modeling in Agriculture and Applications
Khalil Ahmed, Mithilesh Kumar Dubey, Kajal and Devendra Kumar Pandey
6.1 Introduction
6.1.1 Data Analysis Solutions for Data Modeling in Agriculture
6.2 Data-Driven Agriculture Cycle
6.3 Cloud-Based Event and Data Management in Data-Driven Modeling
6.4 Ensemble Methods for Data-Driven Modeling in Agriculture
6.4.1 Random Forest
6.4.2 Gradient-Boosting Machines
6.4.2.1 Loss Function
6.4.2.2 Weak Learners
6.4.2.3 Additive Model
6.4.3 AdaBoost
6.4.3.1 XGBoost
6.4.4 Bagging
6.4.5 Boosting
6.5 Applications of Data Modeling in Agriculture
6.5.1 Field and Resource Management
6.5.2 Environmental Sustainability and Food Safety
6.5.3 Crop Yield Prediction
6.5.4 Agriculture Market and Associated Risk Management
6.6 Conclusion and Future Directions
References
7. Artificial Intelligence–Enabled Ensemble Machine Learning Approaches for Solanaceae Crops
Kajal, Mithilesh Kumar Dubey, Khalil Ahmed and Devendra Kumar Pandey
7.1 Introduction
7.2 Overview of Solanaceae Crops
7.3 Data Modeling in Agriculture
7.3.1 Life Cycle of Data Modeling
7.3.1.1 Conceptual Data Model
7.3.1.2 Logical Data Model
7.4 Ensemble Machine Learning Methods in Sustainable Farming
7.4.1 Basic Ensemble Learning Techniques
7.4.1.1 Max Voting
7.4.1.2 Averaging
7.4.1.3 Weighted Average
7.4.2 Advanced Ensemble Learning Techniques
7.4.2.1 Stacking
7.4.2.2 Blending
7.4.2.3 Boosting
7.5 Application of Data Modeling and Ensemble Learning in Solanaceae Crops
7.5.1 Disease Detection and Diagnosis
7.5.2 Yield Prediction and Optimization
7.5.3 Supply Chain Optimization
7.6 Conclusion and Future Directions
References
8. Dynamic Multitask Transfer Learning with Adaptive Feature Sharing for Heterogeneous Data and Continual Learning
Toufique Ahammad Gazi
Introduction
Methodology
Conclusion
References
9. Forecasting Solar Power Generation in the Future by ARIMA Approach and Stationary Transformation
Sudeep Samanta
Introduction
Conclusion
References
10. Prognosticating Plays: ANN-Enabled Score Projection with the Help of FIS
Susmit Chakraborty and Sourish Harh
10.1 Introduction
10.2 System Model
10.3 ANFIS Controller
10.3.1 Layer 1
10.3.2 Layer 2
10.3.3 Layer 3
10.3.4 Layer 4
10.3.5 Layer 5
10.4 Results and Analysis
10.4.1 Data Preprocessing in Jupyter Notebook
10.4.2 ANFIS Model Building in MATLAB 2020A
10.4.3 Score Predictor Model Evaluation
10.5 Conclusion
References
11. Designing a PID Controller for the Two-Area LFC Problem Using Gradient Descent–Based Linear Regression
Susmit Chakraborty and Arindam Mondal
11.1 Introduction
11.2 Plant Model
11.3 PID Controller
11.4 LR Model
11.5 Result Analysis
11.5.1 ML Phase in Jupyter Notebook
11.5.2 Simulation Phase in MATLAB
11.6 Conclusion
Appendix
References
12. Implementing PID Controllers for Data‑Driven Recognizing for a Nonlinear System
Susmit Chakraborty and Sagnik Agasti
12.1 Introduction
12.2 System Model
12.3 Nonlinear System
12.4 ML Engine
12.5 Result Analysis
12.6 Conclusion
References
13. Temporal Resilience Redux: BiLSTM for Short-Term Load Forecasting in Deep Learning Domain
Ritu K. R.
13.1 Introduction
13.2 Literature Review
13.3 Recurrent Neural Networks and LSTM
13.3.1 Architecture and Functioning of LSTM
13.3.2 LTSM versus RNN
13.4 Bidirectional LSTM
13.4.1 Bidirectional, Multilayer Stacked LSTM NN
13.4.2 Multilayer Stacked LSTM Bidirectional NN for Short-Term Load Forecasting
13.4.3 Multilayer BiLSTM Stacked NN
13.4.4 Load Forecasting of Multilayer Stacked BiLSTM
13.5 Experimental Settings
13.6 Conclusion
References
Index
Back to Top
Preface
1. Fundamentals of Data Analysis and Preprocessing
Sudipta Hazra and Arindam Mondal
1.1 Introduction
1.2 Data Preprocessing
1.2.1 Issues with Data
1.2.1.1 Excessive Data
1.2.1.2 Too Little Data
1.2.1.3 Splintered Data
1.2.2 Setting Up for DA
1.2.2.1 Recognizing the Types of Data
1.2.2.2 Preparing Data for Detailed DA
1.3 Strategies for Preparing Data
1.3.1 Transforming Data
1.3.1.1 Filtering Data
1.3.1.2 Data Arranging
1.3.1.3 Editing Data
1.3.1.4 Modeling Noise
1.3.2 Information Compilation
1.3.2.1 Data Visualization
1.3.2.2 Data Elimination
1.3.2.3 Data Selection
1.3.2.4 Analysis of Principal Components
1.3.2.5 Data Sampling
1.3.3 Production of Novel Information
1.3.3.1 Including Extra Features
1.3.3.2 Data Fusion
1.3.3.3 Time–Series Analysis
1.3.3.4 Information Modeling
1.3.3.5 Dimensional Analysis
1.4 Real-World Applications
1.4.1 Machine Learning and Predictive Analytics
1.4.2 Healthcare and Biomedical Research
1.4.3 Financial Analysis and Risk Management
1.4.4 Marketing and Customer Analytics
1.4.5 Supply Chain Management and Logistics
1.4.6 Environmental Monitoring and Sustainability
1.5 Conclusion
References
2. Advanced Data Control Methods for Data-Driven Modeling: Techniques, Challenges, and Future Directions
Aarushi Chatterjee and Souvik Ganguli
2.1 Introduction
2.2 Related Works
2.2.1 Data Quality and Preprocessing
2.2.2 Data Governance and Control in Distributed Systems
2.2.3 Data Privacy and Security
2.2.4 Model Predictive Control and Data-Driven Approaches
2.2.5 Data Drift and Adaptive Control
2.3 Data Control Architecture in Modeling
2.3.1 Centralized versus Decentralized Data Control
2.3.1.1 Centralized Data Control
2.3.1.2 Decentralized Data Control
2.3.2 Automated Data Governance
2.3.2.1 Metadata Management
2.3.2.2 Data Provenance and Lineage
2.3.2.3 Policy Enforcement Engines
2.3.3 Real-Time Data Control in Streaming and Dynamic Systems
2.3.3.1 Windowing and Stream Processing
2.3.3.2 Adaptive Sampling and Real-Time Data Filtering
2.3.3.3 Real-Time Model Retraining
2.3.4 Emerging Trends in Data Control Architecture
2.3.4.1 Federated Learning for Data Control
2.3.4.2 Blockchain for Data Integrity and Control
2.4 Advanced Techniques for Data Control
2.4.1 Data-Driven Control Strategies
2.4.1.1 Model Predictive Control
2.4.1.2 RL for Data-Driven Control
2.4.1.3 Adaptive Control Systems
2.4.2 Control of Streaming Data
2.4.2.1 Sliding Windows and Stream Processing Frameworks
2.4.2.2 Approximate Query Processing
2.4.2.3 Online Learning for Streaming Data
2.4.3 Handling Dynamic and Evolving Data Environments
2.4.3.1 Adaptive Learning Models
2.4.3.2 Handling Data Drift and Concept Drift
2.4.4 Advanced Real-Time Data Governance
2.4.4.1 Automated Policy Enforcement
2.4.4.2 Dynamic Access Control
2.5 Challenges in Data Control for Modeling
2.5.1 Scalability Issues
2.5.1.1 Data Volume and Velocity
2.5.1.2 Horizontal versus Vertical Scaling
2.5.2 Data Drift and Concept Drift
2.5.2.1 Types of Drift
2.5.2.2 Challenges in Detecting Drift
2.5.2.3 Model Adaptation
2.5.3 Real-Time Data Control
2.5.3.1 Latency Issues
2.5.3.2 Synchronization and Consistency
2.5.4 Data Privacy and Security
2.5.4.1 Data Anonymization and Differential Privacy
2.5.4.2 Data Encryption and Secure Computation
2.5.5 Collaborative Data Control
2.5.5.1 Data Sharing Across Organizations
2.5.5.2 Version Control and Auditing
2.6 Best Practices for Data Control in Data-Driven Modeling
2.6.1 Data Versioning and Auditing
2.6.1.1 Data Versioning
2.6.1.2 Auditing
2.6.2 Collaborative Data Control
2.6.2.1 Role-Based Access Control
2.6.2.2 Data Sharing and Federation
2.6.3 Metadata Management for Governance and Provenance
2.6.3.1 Automated Metadata Generation
2.6.3.2 Data Provenance and Lineage Tracking
2.6.4 Automation in Data Governance
2.6.4.1 Automated Policy Enforcement
2.6.4.2 Automated Compliance Monitoring
2.7 Case Studies in Data Control Methods
2.7.1 Real-Time Data Control in AVs
2.7.2 Data Governance and Privacy in Healthcare
2.7.3 Collaborative Data Sharing in Financial Services
2.7.4 Data Control in Smart Energy Grids
2.7.5 Big Data Control in E-Commerce
2.8 Future Directions in Data Control
2.8.1 Decentralized and Distributed Data Control
2.8.1.1 Edge Computing and Data Control at the Edge
2.8.1.2 Blockchain for Decentralized Data Control
2.8.2 Privacy-Preserving Data Control
2.8.2.1 Differential Privacy
2.8.2.2 Homomorphic Encryption and Secure Computation
2.8.3 Real-Time Adaptive Data Control
2.8.3.1 AI-Driven Data Control
2.8.3.2 Context-Aware Data Control
2.8.4 Federated Learning and Collaborative Data Control
2.8.4.1 Federated Learning at Scale
2.8.4.2 Federated Governance and Data Control
2.8.5 Quantum Computing and Its Impact on Data Control
2.8.5.1 Quantum Cryptography for Data Security
2.8.5.2 Quantum Machine Learning for Data Control
2.9 Concluding Remarks
References
3. Machine Learning Algorithms for Data-Driven Modeling
Souryadip Ghosh, Indrani Mukherjee and Suparna Biswas
3.1 Introduction
3.2 What is Machine Learning?
3.3 Classification of Machine Learning Methods
3.3.1 Supervised Learning
3.3.2 Unsupervised Learning
3.3.3 Reinforcement Learning
3.4 Supervised Machine Learning
3.4.1 Decision Tree for Classification
3.4.2 C4.5
3.4.3 CART
3.4.4 CHAID
3.4.5 Iterative Dichotomizer 3
3.5 Support Vector Machine
3.5.1 SVM for Linear Classification
3.5.2 SVM for Nonlinear Classification
3.5.3 Kernel
3.5.4 Unsupervised Machine Learning
3.5.5 Clustering
3.5.6 K-Means
3.6 Hierarchical Clustering
3.6.1 Methodologies for Determining the Optimal Number of Clusters
3.6.2 Dimensionality Reduction
3.6.3 t-Distributed Stochastic Neighbor Embedding
3.6.4 Multidimensional Scaling
3.7 Principal Component Analysis
3.8 Conclusion
Bibliography
4. Neural Networks and Deep Learning in Data-Driven Modeling
Tanishka Chakraborty, Indrani Mukherjee and Suparna Biswas
4.1 Introduction
4.2 Basic Concept of Neural Network and Deep Learning
4.2.1 Characteristics of Neural Network
4.2.2 Characteristics of Deep Learning
4.3 Applications of Neural Networks and Deep Learning in Data-Driven Modeling
4.3.1 Image Recognition
4.3.2 Natural Language Processing
4.3.3 Time–Series Prediction
4.3.4 Recommender Systems
4.3.5 Anomaly Detection
4.3.6 Generative Adversarial Networks
4.3.7 Autonomous Driving
4.3.8 Health Monitoring Using Wearable Devices
4.3.9 Attention Mechanisms in NLP
4.3.10 Brain–Computer Interface
4.3.11 Fault Diagnosis in Industrial Systems
4.3.12 Speech Recognition
4.3.13 Cybersecurity Applications
4.3.14 Energy Consumption Forecasting
4.3.15 Human Activity Recognition
4.4 Techniques of Neural Networks and Deep Learning in Data-Driven Modeling
4.4.1 Convolutional Neural Networks
4.4.2 Recurrent Neural Networks
4.4.3 Long Short-Term Memory Networks
4.4.4 Autoencoders
4.4.5 Generative Adversarial Networks
4.4.6 Deep Reinforcement Learning
4.4.7 Transfer Learning
4.4.8 Data Augmentation
4.5 Methods of Neural Networks and Deep Learning in Data-Driven Modeling
4.5.1 Backpropagation
4.5.2 Data Augmentation
4.5.3 Hyperparameter Optimization
4.5.4 Ensemble Learning
4.5.5 Attention Mechanisms
4.5.6 Capsule Networks
4.5.7 Neuroevolution
4.6 Conclusion
Bibliography
5. Advances in Time-Series Analysis: Techniques and Applications for Predictive Forecasting
A. UmaDevi, Jagendra Singh, Shrinwantu Raha, Nazeer Shaik, Anil V. Turukmane and Ishaan Singh
5.1 Introduction
5.1.1 Definition and Conceptual Framework
5.1.2 Importance and Applications
5.2 Foundational Techniques in TSA
5.2.1 AR Models
5.2.2 MA Models
5.2.3 ARIMA Models
5.2.4 Exponential Smoothing Methods
5.2.5 Seasonal Decomposition of Time Series
5.2.6 State Space Models and Kalman Filtering
5.2.7 Spectral Analysis and Fourier Transform
5.2.8 ML Techniques
5.3 Applications of TSA
5.3.1 Economic and Financial Forecasting
5.3.2 Healthcare and Epidemiology
5.4 Future Directions and Emerging Trends
5.4.1 Deep Learning and Neural Networks
5.4.2 Probabilistic Forecasting
5.4.3 Anomaly Detection and Outlier Analysis
5.4.4 Interpretable and Explainable Models
5.4.5 Multivariate and High-Dimensional TSA
5.4.6 Integration with Domain-Specific Knowledge
5.4.7 Ethical and Fair TSA
5.4.8 Automated ML for Time Series
5.4.9 Continuous Learning and Model Adaptation
5.5 Conclusion
References
6. Ensemble Methods for Data-Driven Modeling in Agriculture and Applications
Khalil Ahmed, Mithilesh Kumar Dubey, Kajal and Devendra Kumar Pandey
6.1 Introduction
6.1.1 Data Analysis Solutions for Data Modeling in Agriculture
6.2 Data-Driven Agriculture Cycle
6.3 Cloud-Based Event and Data Management in Data-Driven Modeling
6.4 Ensemble Methods for Data-Driven Modeling in Agriculture
6.4.1 Random Forest
6.4.2 Gradient-Boosting Machines
6.4.2.1 Loss Function
6.4.2.2 Weak Learners
6.4.2.3 Additive Model
6.4.3 AdaBoost
6.4.3.1 XGBoost
6.4.4 Bagging
6.4.5 Boosting
6.5 Applications of Data Modeling in Agriculture
6.5.1 Field and Resource Management
6.5.2 Environmental Sustainability and Food Safety
6.5.3 Crop Yield Prediction
6.5.4 Agriculture Market and Associated Risk Management
6.6 Conclusion and Future Directions
References
7. Artificial Intelligence–Enabled Ensemble Machine Learning Approaches for Solanaceae Crops
Kajal, Mithilesh Kumar Dubey, Khalil Ahmed and Devendra Kumar Pandey
7.1 Introduction
7.2 Overview of Solanaceae Crops
7.3 Data Modeling in Agriculture
7.3.1 Life Cycle of Data Modeling
7.3.1.1 Conceptual Data Model
7.3.1.2 Logical Data Model
7.4 Ensemble Machine Learning Methods in Sustainable Farming
7.4.1 Basic Ensemble Learning Techniques
7.4.1.1 Max Voting
7.4.1.2 Averaging
7.4.1.3 Weighted Average
7.4.2 Advanced Ensemble Learning Techniques
7.4.2.1 Stacking
7.4.2.2 Blending
7.4.2.3 Boosting
7.5 Application of Data Modeling and Ensemble Learning in Solanaceae Crops
7.5.1 Disease Detection and Diagnosis
7.5.2 Yield Prediction and Optimization
7.5.3 Supply Chain Optimization
7.6 Conclusion and Future Directions
References
8. Dynamic Multitask Transfer Learning with Adaptive Feature Sharing for Heterogeneous Data and Continual Learning
Toufique Ahammad Gazi
Introduction
Methodology
Conclusion
References
9. Forecasting Solar Power Generation in the Future by ARIMA Approach and Stationary Transformation
Sudeep Samanta
Introduction
Conclusion
References
10. Prognosticating Plays: ANN-Enabled Score Projection with the Help of FIS
Susmit Chakraborty and Sourish Harh
10.1 Introduction
10.2 System Model
10.3 ANFIS Controller
10.3.1 Layer 1
10.3.2 Layer 2
10.3.3 Layer 3
10.3.4 Layer 4
10.3.5 Layer 5
10.4 Results and Analysis
10.4.1 Data Preprocessing in Jupyter Notebook
10.4.2 ANFIS Model Building in MATLAB 2020A
10.4.3 Score Predictor Model Evaluation
10.5 Conclusion
References
11. Designing a PID Controller for the Two-Area LFC Problem Using Gradient Descent–Based Linear Regression
Susmit Chakraborty and Arindam Mondal
11.1 Introduction
11.2 Plant Model
11.3 PID Controller
11.4 LR Model
11.5 Result Analysis
11.5.1 ML Phase in Jupyter Notebook
11.5.2 Simulation Phase in MATLAB
11.6 Conclusion
Appendix
References
12. Implementing PID Controllers for Data‑Driven Recognizing for a Nonlinear System
Susmit Chakraborty and Sagnik Agasti
12.1 Introduction
12.2 System Model
12.3 Nonlinear System
12.4 ML Engine
12.5 Result Analysis
12.6 Conclusion
References
13. Temporal Resilience Redux: BiLSTM for Short-Term Load Forecasting in Deep Learning Domain
Ritu K. R.
13.1 Introduction
13.2 Literature Review
13.3 Recurrent Neural Networks and LSTM
13.3.1 Architecture and Functioning of LSTM
13.3.2 LTSM versus RNN
13.4 Bidirectional LSTM
13.4.1 Bidirectional, Multilayer Stacked LSTM NN
13.4.2 Multilayer Stacked LSTM Bidirectional NN for Short-Term Load Forecasting
13.4.3 Multilayer BiLSTM Stacked NN
13.4.4 Load Forecasting of Multilayer Stacked BiLSTM
13.5 Experimental Settings
13.6 Conclusion
References
Index
Back to Top