Application of Advanced Optimization Techniques for Healthcare Analytics

Description:

Application of Advanced Optimization Techniques for Healthcare Analytics, 1st Edition, is an excellent compilation of current and advanced optimization techniques which can readily be applied to solve different hospital management problems. The healthcare system is currently a topic of significant investigation to make life easier for those who are disabled, old, or sick, as well as for young children. The emphasis of the healthcare system has evolved throughout time due to several emerging beneficial technologies, such as personal digital assistants (PDAs), data mining, the internet of things, metaheuristics, fog computing, and cloud computing.

Metaheuristics are strong technology for tackling several optimization problems in various fields, especially healthcare systems. The primary advantage of metaheuristic algorithms is their ability to find a better solution to a healthcare problem and their ability to consume as little time as possible. In addition, metaheuristics are more flexible compared to several other optimization techniques. These algorithms are not related to a specific optimization problem but could be applied to any optimization problem by making some small adaptations to become suitable to tackle it.

The successful outcome of this book will enable a decision-maker or practitioner to pick a suitable optimization approach when making decisions to schedule patients under crowding environments with minimized human errors.

See more ebooks for you at here:

Dose Optimization in Digital Radiography and Computed Tomography

Quantum Care: A Deep Dive into AI for Health Delivery and Research

Electronic Health Record Optimization for Artificial Intelligence

The Internet of things enabling technologies, platforms, and use cases

Opportunities and Challenges with Artificial Intelligence in Genomics

Table of contents :

Cover
Half Title
Title Page
Copyright Page
Dedication
Table of Contents
Preface
About the Authors
1 Advanced Optimization Techniques: Introduction
1.1 Metaheuristic Optimization Algorithms
1.1.1 Classification of Optimization Algorithms
1.1.2 Evolution-Based Algorithms
1.1.3 Physics-Based Algorithms
1.1.4 Swarm-Based Algorithms
1.1.5 Human-Based Algorithms
1.2 Investigated Metaheuristic Algorithms
1.2.1 Whale Optimization Algorithm (WOA)
1.2.2 Teaching-Learning-Based Optimization
1.2.2.1 Teacher Phase
1.2.2.2 Learner Phase
1.2.3 Equilibrium Optimizer
1.2.4 Grey Wolf Optimizer
1.2.5 Slime Mould Algorithm
1.2.5.1 Searching for Food
1.2.5.2 Wrap Food
1.2.6 Differential Evolution
1.2.6.1 Mutation Operator
1.2.6.2 Crossover Operator
1.2.6.3 Selection Operator
1.2.7 Marine Predators Algorithm (MPA)
1.2.7.1 High-Velocity Ratio
1.2.7.2 Unit Velocity Ratio
1.2.7.3 Low Velocity-Ratio
1.3 Implementation
1.4 Summary
1.5 Exercises
References
2 Metaheuristic Algorithms for Healthcare: Open Issues and Challenges
2.1 Research Issues in Healthcare
2.2 Metaheuristics for Healthcare
2.2.1 Whale Optimization Algorithm
2.2.2 Grey Wolf Optimizer (GWO)
2.2.3 Genetic Algorithms
2.2.4 Ant-Colony Optimization Algorithm
2.2.5 Particle Swarm Optimization
2.2.6 Other Applied Metaheuristics in Healthcare
2.3 Summary and Future Trends
2.4 Exercises
References
3 Metaheuristic-Based Augmented Multilayer Perceptrons for Cancer and Heart Disease Predictions
3.1 Artificial Intelligence and Application in Healthcare
3.2 Feed-Forward Neural Network
3.2.1 The Problem Representation
3.2.2 Confusion Matrix
3.3 Results and Discussion
3.3.1 Breast Cancer Dataset
3.3.2 SPECT Heart Dataset
3.3.3 SPECTF Heart Dataset
3.4 Summary
3.5 Exercises
References
4 The Role of Metaheuristics in Multilevel Thresholding Image Segmentation
4.1 Multilevel Thresholding Image Segmentation
4.2 Image Segmentation Techniques
4.2.1 Objective Function: Kapur’s Entropy
4.2.2 Adaptation of Metaheuristics for Image Segmentation
4.2.3 Performance Evaluation Criteria
4.2.3.1 Standard Deviation (SD)
4.2.3.2 Peak Signal-To-Noise Ratio (PSNR)
4.2.3.3 Structural Similarity Index (SSIM)
4.2.3.4 Features Similarity Index (FSIM)
4.2.4 Experiment Settings
4.2.5 Choice of Parameters
4.3 Results and Discussion
4.3.1 Stability
4.3.2 Comparison Under Fitness Value
4.3.3 Comparison Under PSNR Values
4.3.4 Comparison Under SSIM Values
4.3.5 Comparison Under FSIM Values
4.3.6 Comparison Under Interval Plot
4.4 Summary
4.5 Exercises
References
5 Role of Advanced Metaheuristics for DNA Fragment Assembly Problem
5.1 DNA Fragment Assembly Problem
5.2 Metaheuristic-Based DNA Fragment Assembly Problem (DFAP)
5.3 Experiment Settings
5.4 Choice of Parameters
5.5 Results and Discussion
5.6 Summary
5.7 Exercises
References
6 Contribution of Metaheuristic Approaches for Feature Selection Techniques
6.1 Feature Selection Problem in Healthcare
6.2 Metaheuristic-Based Feature Selection
6.2.1 V-Shaped and S-Shaped Transfer Function
6.2.2 Evaluation Phase: Objective Function
6.3 Experiment Settings
6.4 Performance Metrics
6.4.1 Classification Accuracy Using KNN
6.4.2 Fitness Values
6.4.3 The Selected Number of Features
6.4.4 Standard Deviation (SD)
6.5 Choice of Parameters
6.6 Results and Discussion
6.6.1 Comparison of Various Transfer Functions
6.6.2 Comparison Among Algorithms Using Fitness Values
6.6.3 Comparison Using Classification Accuracy
6.6.4 Comparison Among Algorithms Using the Selected Feature-Length
6.7 Summary
6.8 Exercises
References
7 Advanced Metaheuristics for Task Scheduling in Healthcare IoT
7.1 Task Scheduling in Healthcare IoT
7.2 Problem Formulation
7.2.1 Make-Span
7.2.2 Energy Consumption
7.2.3 Carbon Dioxide Emission Rate (CDER)
7.2.4 Flow-Time (FT)
7.3 Adaptation of Metaheuristics for the Task Scheduling Problem
7.4 Experimental Settings
7.4.1 Choice of Parameters
7.5 Results and Discussion
7.5.1 Comparison Under Various Task Sizes
7.5.2 Comparison Under Various VM Lengths
7.6 Summary
7.7 Exercises
References
8 Metaheuristics for Augmenting Machine Learning Models to Process Healthcare Data
8.1 Data Mining for Healthcare Data
8.2 Overview of the SVM Approach
8.3 Adaptation of Metaheuristics for Parameter Estimation of SVM
8.4 Experiment Settings
8.5 Choice of Parameters
8.6 Results and Discussion
8.7 Summary
8.8 Exercises
References
9 Deep Learning Models to Process Healthcare Data: Introduction
9.1 Deep Learning Techniques for Healthcare
9.2 Deep Learning Techniques
9.2.1 Deep Neural Network (DNN)
9.2.2 Recurrent Neural Network
9.2.3 Long Short-Term Memory Networks
9.2.4 Convolutional Neural Network
9.3 Optimizers
9.4 Activation Functions
9.4.1 Rectified Linear Units (ReLU)
9.4.2 Scaled Exponential Linear Unit (SELU)
9.4.3 Exponential Linear Unit (ELU)
9.4.4 Hyperbolic Tangent (Tanh)
9.5 Role of Deep Learning Models in the Healthcare System
9.6 Metaheuristic Roles for Hyperparameters
9.7 Summary
9.8 Exercises
References
10 Metaheuristics to Augment DL Models Applied for Healthcare System
10.1 DL for Detecting COVID-19: Healthcare System
10.2 Adaptation of Metaheuristics for Tuning Hyperparameters of DNN
10.2.1 Initialization Process
10.2.2 Evaluation
10.2.3 Adapting Metaheuristics for DNN
10.3 Dataset Description
10.4 Normalization
10.5 Performance Metrics
10.6 Experimental Settings
10.7 Experimental Findings
10.8 Summary
10.9 Exercises
References
11 Intrusion Detection System for Healthcare System Using Deep Learning and Metaheuristics
11.1 Intrusion Detection System
11.2 Feature Scaling
11.3 One-Hot-Encoding
11.4 Implementation
11.5 Dataset Description
11.6 Performance Metrics
11.7 Experimental Settings
11.8 Experimental Findings
11.8.1 Metaheuristics-Based MLP Models
11.8.2 Metaheuristics-Based LSTM Models
11.9 Summary
11.10 Exercises
References
Index