Advances in Machine Learning for Big Data Analysis

✍ Scribed by Satchidananda Dehuri (editor), Yen-Wei Chen (editor)

• Publisher: Springer
• Year: 2022
• Tongue: English
• Leaves: 254
• Series: Intelligent Systems Reference Library 218
• Edition: 1st ed. 2022
• Category: Library

✦ Synopsis

This book focuses on research aspects of ensemble approaches of machine learning techniques that can be applied to address the big data problems.

In this book, various advancements of machine learning algorithms to extract data-driven decisions from big data in diverse domains such as the banking sector, healthcare, social media, and video surveillance are presented in several chapters. Each of them has separate functionalities, which can be leveraged to solve a specific set of big data applications. This book is a potential resource for various advances in the field of machine learning and data science to solve big data problems with many objectives. It has been observed from the literature that several works have been focused on the advancement of machine learning in various fields like biomedical, stock prediction, sentiment analysis, etc. However, limited discussions have been carried out on application of advanced machine learning techniques in solving big data problems.

✦ Table of Contents

Preface
Contents
Editors and Contributors
About the Editors
Contributors
1 Multi-objective Ant Colony Optimization: An Updated Review of Approaches and Applications
1.1 Introduction
1.2 Ant Colony Optimization
1.3 Basic Concepts of Multi-objective Optimization
1.4 The ACO Metaheuristic for MOPs in the Literature
1.5 ACO Variants for MOP: A Refined Taxonomy
1.6 Real-World Applications
1.7 Promising Research Areas
1.8 Conclusions
References
2 Cost-Effective Detection of Cyber Physical System Attacks
2.1 Introduction
2.1.1 Motivation
2.1.2 Contribution
2.1.3 Organization
2.2 Background
2.2.1 CPS and Its Vulnerability Issues
2.2.2 Machine Learning Approaches
2.2.3 Some Popular Supervised Learners
2.3 Problem Formulation
2.4 Proposed Detection Framework: CPSAD
2.4.1 FSRA: Optimal Feature Selection Using Rank Aggregation
2.5 Datasets Used and Results
2.5.1 Results
2.6 Conclusion
References
3 A Prognostic Approach to Crime Analysis
3.1 Introduction
3.1.1 Inspiration from Modern Criminology
3.2 Geometry of Crime and Pattern Theory in Modern Crime Analysis
3.2.1 A Criminological Justification for Predictive Policing
3.2.2 Smart Policing
3.3 Collaborating Technologies
3.4 Approaches to Smart Policing
3.4.1 Place-Based Predictive Policing
3.4.2 Person-Based Predictive Policing
3.5 Data Flow in Crime Analysis
3.6 Crime Analysis
3.7 Clustering
3.7.1 Partitioning-Based clustering
3.7.2 Hierarchical-Based Clustering
3.7.3 Density-Based Clustering
3.7.4 Grid-Based Clustering
3.7.5 Model-Based Clustering
3.8 Models Used with Real-Time Data
3.8.1 Time Series Forecasting
3.8.2 Machine Learning Model
3.8.3 Deep Learning Model
3.9 Role of Big Data in Crime Analysis and Prediction
3.9.1 Addressing Real-time Issues
3.9.2 Crime Prediction
3.10 Discussions on Performance Metric
3.10.1 Evaluation Metric on Machine Learning and Deep Learning Model
3.10.2 Evaluation Metric on Statistical Model
3.11 Open Research Areas of Crime Prediction
3.12 Conclusion
References
4 A Counter-Based Profiling Scheme for Improving Locality Through Data and Reducer Placement
4.1 Introduction
4.2 Related Works
4.3 Proof of Concept
4.3.1 Hadoop Native Strategy
4.3.2 Improved Data Locality with CPS
4.4 Algorithm for Proposed Counter based Profiling Scheme (CPS)
4.5 Experimental Evaluation and Results Discussion
4.5.1 Testbed Setup
4.5.2 Experiments Performed
4.5.3 Results and Discussion
4.6 Conclusion
References
5 Hybridization of the Higher Order Neural Networks with the Evolutionary Optimization Algorithms—An Application to Financial Time Series Forecasting
5.1 Introduction
5.2 HONN
5.2.1 Pi-Sigma Neural Network
5.2.2 Sigma-Pi Neural Network
5.2.3 Functional Link Artificial Neural Network
5.3 Evolutionary Optimization Algorithm
5.3.1 Genetic Algorithm
5.3.2 Particle Swarm Optimization
5.3.3 Chemical Reaction Optimization
5.4 HONN-Based Forecasting
5.4.1 Data Collection and Description
5.4.2 Experimental Setup
5.4.3 Experimental Results and Analysis
5.5 Conclusions
References
6 Supply Chain Management (SCM): Employing Various Big Data and Metaheuristic Strategies
6.1 Background Study
6.2 Introducing Big Data
6.2.1 Defining Big Data
6.2.2 Data Sources
6.2.3 Data Analytics and Data Processing
6.3 Big Data and Supply Chain Management (SCM)
6.3.1 Big Data Security in Agricultural SCM
6.4 SCM and Big Data Analytics
6.5 Supply Chain Analytics Phases
6.5.1 Planning of Revenues, Supplies and Activities
6.6 Crucial Ultimatums for Big Data in Supply Chain Management
6.6.1 Hierarchical Challenges
6.6.2 Moral Challenges
6.6.3 Technical Ultimatums
6.6.4 Cultural Ultimatums
6.6.5 Procedural Ultimatums
6.6.6 Strategic Challenges
6.6.7 Functional Challenges
6.7 Advantages of Using Big Data for Supply Chain
6.8 Usage of Big Data Framework in Dynamic Supply Chain System (DSCM)
6.9 Summary
References
7 Value of Random Vector Functional Link Neural Networks in Software Development Effort Estimation
7.1 Introduction
7.2 Background and Related Work
7.2.1 FLANN
7.2.2 RVFL Neural Nets
7.3 Related Work
7.4 Proposed Methodology
7.5 Experimental Setup
7.5.1 Performance Metrics
7.5.2 Characteristics of the Datasets
7.5.3 Environment, Parameter Settings, and RVFL Configuration
7.5.4 SDEE Techniques
7.6 Result Analysis
7.7 Threats to Validity
7.8 Conclusion and Future Work
References
8 Hybrid Approach to Prevent Accidents at Railway: An Assimilation of Big Data, IoT and Cloud
8.1 Introduction
8.2 Related Work
8.3 Proposed Framework
8.3.1 Stage 1: Internet of Things (IoT)
8.3.2 Stage 2: Big Data & Edge IT
8.3.3 Stage 3: Cloud Computing with Data Analytics
8.4 Railway Accidents and Prevention
8.4.1 Types of Railway Accidents
8.5 Big Data and Meta-Heuristics for Railway Engineering
8.5.1 Big Data
8.5.2 Meta-Heuristics
8.6 Conclusion
References
9 Hybrid Decision Tree for Machine Learning: A Big Data Perspective
9.1 Introduction
9.2 Preliminaries
9.2.1 Machine Learning
9.2.2 Decision Tree
9.2.3 Big Data Analysis
9.3 Hybrid Decision Tree
9.3.1 Hybridization of Decision tree with Support Vector Machine
9.3.2 Hybridization of Decision tree with Neural network
9.3.3 Hybridization of Decision Tree with Genetic Algorithm
9.4 Big Data Analysis using Hybrid Decision Tree
9.5 Conclusion and Future works
References