Machine Learning for Intelligent Decision Science (Algorithms for Intelligent Systems)

✍ Scribed by Jitendra Kumar Rout (editor), Minakhi Rout (editor), Himansu Das (editor)

• Publisher: Springer
• Year: 2020
• Tongue: English
• Leaves: 219
• Category: Library

✦ Synopsis

The book discusses machine learning-based decision-making models, and presents intelligent, hybrid and adaptive methods and tools for solving complex learning and decision-making problems under conditions of uncertainty. Featuring contributions from data scientists, practitioners and educators, the book covers a range of topics relating to intelligent systems for decision science, and examines recent innovations, trends, and practical challenges in the field. The book is a valuable resource for academics, students, researchers and professionals wanting to gain insights into decision-making.

✦ Table of Contents

Preface
Contents
About the Editors
1 Development of Different Machine Learning Ensemble Classifier for Gully Erosion Susceptibility in Gandheswari Watershed of West Bengal, India
1 Introduction
2 Study Area
3 Database and Methodology
3.1 Used Dataset
3.2 Orientation of the Data
4 Materials and Methodology
4.1 Geo-Environmental Factors
4.2 Gully Erosion Inventory Map
4.3 Description of Methodology
4.4 Evaluation of Models
5 Results and Discussion
5.1 Gully Erosion Susceptibility Assessment Using MLPC, Bagging-MLPC, Dagging-MLPC and Decorate-MLPC
5.2 Validation
6 Conclusion
References
2 Classification of ECG Heartbeat Using Deep Convolutional Neural Network
1 Introduction
1.1 State of the Art
1.2 Contribution
2 Database Used
3 Methodology
3.1 Arrhythmia Database Normalization
3.2 Heartbeat Segmentation
3.3 Class Imbalance to Balance by Artificial Data Generation
3.4 Convolutional Neural Network (CNN)
4 Experimental Results
5 Conclusion
References
3 Breast Cancer Identification and Diagnosis Techniques
1 Introduction
1.1 Clinical Decision Support Systems
2 Imaging Techniques
3 Pre-processing Techniques
3.1 Mean Filter
3.2 Median Filtering
3.3 AMF Technique
3.4 Wiener Filter
3.5 CLAHE Technique
3.6 HM-LCE Technique
4 Feature Extraction Techniques
4.1 Gray-Map
4.2 Sobel
4.3 SGLDM
4.4 AFUM
4.5 SFUM
5 Machine Learning Approaches
5.1 Support Vector Machine
5.2 Biclustering and Adaboost Techniques
5.3 CNN Classifier
5.4 RCNN
5.5 BI-RADS
5.6 Hierarchical Attention Bidirectional Recurrent Neural Networks (HA-BiRNN)
6 ICD-9 Diagnosis Codes from an Existing EHR Data Repository
7 Outlier Detection
8 Conclusions
References
4 Energy-Efficient Resource Allocation in Data Centers Using a Hybrid Evolutionary Algorithm
1 Introduction
2 Related Work
3 Interactive PSO-GA
3.1 Particle Swarm Optimization (PSO)
3.2 Genetic Algorithm (GA)
3.3 Modeling Energy-Aware VM Allocation
3.4 Interactive PSO-GA (IPSOGA)
4 Experiments and Performance Evaluation
4.1 Performance Analysis in Terms of Energy Consumption
4.2 Performance Analysis in Terms of Convergence
4.3 Performance Analysis in Terms of Speedup and Parallel Efficiency
4.4 Validation Against Benchmark Test Problems
5 Conclusion
References
5 Root-Cause Analysis Using Ensemble Model for Intelligent Decision-Making
1 Introduction
2 Literature Review
2.1 Unsupervised Approaches
2.2 Semi-supervised Approaches
2.3 Supervised Approaches
2.4 Rule-Based Approaches
3 Proposed Work
3.1 Pre-processing of Reviews
3.2 Aspect Categorization Ontology
3.3 Prediction-Based Word Embedding Model
3.4 Variegated Ensemble-Based Weighted Voting (VEWV) Model for Prediction
3.5 Aspect Ranking and Ontology Reinforcement
4 Results and Discussion
5 Conclusion
References
6 Spider Monkey Optimization Algorithm in Data Science: A Quantifiable Objective Study
1 Spider Monkey Inspired Technique
1.1 Introduction to Spider Monkey Optimization Algorithm (SMO)
1.2 Case Study: SMO to Optimize Golestan and Voshmgir Dam Operations in Iran
2 Introduction to Mathematical Modeling and Implementation of Spider Monkey Optimization Algorithm (SMO)
2.1 Population Initialization
2.2 Local Leader Phase
2.3 Global Leader Phase
2.4 Global Leader Learning Phase
2.5 Local Leader Learning Phase
2.6 Local Leader Decision (LLD) Phase
2.7 Global Leader Decision (GLD) Phase
3 Implementation of the Mathematical Model via Algorithms (Local Leader)
4 Implementation of Mathematical Model via Algorithms (Global Leader)
5 Variants of Spider Monkey Applied to Data Science
5.1 Constrained Spider Monkey Optimization (SMO) Algorithm
5.2 Ageist Spider Monkey Optimization
5.3 Self-adaptive Spider Monkey Optimization (SaSMO)
5.4 Chaotic Spider Monkey Optimization
5.5 Hybridization of Genetic Algorithm and Spider Monkey Optimization
6 Thinning of Circular Concentric Antenna Arrays (CCAA)
6.1 Antenna Array Optimization
6.2 Binary Spider Monkey Optimization (BinSMO)
6.3 Geometry and Fitness Function of CCAA
6.4 Experimental Analysis
7 Application of Spider Monkey Optimization in Solving the Traveling Salesman Problem
7.1 Brief Introduction to the Traveling Salesman Problem
7.2 Applying Spider Monkey Optimization to Solve TSP
7.3 Algorithm Definition and Worked Example
8 Research Trends and Conclusion
References
7 Multi-agent-Based Systems in Machine Learning and Its Practical Case Studies
1 Intelligent Agents and Its Interacting Environment
1.1 Illustrating the Example of a Predator–Prey Model
1.2 Agent Function
1.3 Discussing the Environments of the Agents
2 The Paradigm of Multi-Agent Systems
2.1 Characteristics of Multi-Agent Systems
2.2 Parameters Associated with Multi-Agent Systems
2.3 Quick Introduction to Netlogo—A Multi-agent Programmable Modeling Environment
2.4 Demonstrating Agents and Their Environment Using Netlogo
3 Types of Agents
3.1 Simplex-Reflex Agents
3.2 Model-Based Reflex Agents
3.3 Goal-Based Agents
3.4 Utility-Based Agents
4 Multi-Agents in Reinforcement Learning (MARL)
4.1 Learning Agents
4.2 Combination of Learning Agents and Reinforcement Learning—Origin of MARL
4.3 Demonstrating Learning Agents and Reinforcement Learning Using Netlogo
4.4 MARL and Game Theory
4.5 Challenges of MARL
4.6 Benefits of MARL
5 Equilibrium Algorithms for Multi-Agent Reinforcement Learning (MARL)
5.1 Q-Learning
5.2 Minimax Q-Learning—A Popular Q-Learning Variant
5.3 Nash Q-Learning
5.4 Policy Hill-Climbing
6 Optimization of Multi-Agent Systems
6.1 Issues that MAS Developers Deal With
6.2 Distributed Constraint Optimization (DCOP)
6.3 Coalition Formation Algorithms
7 Applications of Multi-agents—Case Studies
7.1 Multi-agents to Build an Optimal Supply Chain Management
7.2 Optimization Technique Using Ant Colony Based Multi-agents for Traveling Salesman Problem
8 Conclusion and Research Trends
References
8 Computer Vision and Machine Learning Approach for Malaria Diagnosis in Thin Blood Smears from Microscopic Blood Images
1 Introduction
2 Related Works
3 Computer Vision and Machine Learning Methods
3.1 Dataset Collection
3.2 Image Denoising
3.3 Cell Segmentation
3.4 Blood Image Feature Extraction
4 Feature Selection Through ExtraTreesClassifier
4.1 Feature Selection
5 Malaria Life Stages Classification Using Machine Learning Approaches
5.1 Extremely Randomized Trees
6 Experimentations and Results
7 Conclusions
References