Next Generation Healthcare Systems Using Soft Computing Techniques (Artificial Intelligence in Smart Healthcare Systems)

Description

This book presents soft computing techniques and applications used in healthcare systems, along with the latest advancements. Written as a guide for assessing the roles that these techniques play, the book also highlights implementation strategies, lists problem-solving solutions, and paves the way for future research endeavors in smart and next-generation healthcare systems. This book provides applications of soft computing techniques related to healthcare systems and can be used as a reference guide for assessing the roles that various techniques, such as machine learning, fuzzy logic, and statical mathematics, play in the advancements of smart healthcare systems. The book presents the basics as well as the advanced concepts to help beginners, as well as industry professionals, get up to speed on the latest developments in healthcare systems. The book examines descriptive, predictive, and social network techniques and discusses analytical tools and the important role they play in finding solutions to problems in healthcare systems. A framework of robust and novel healthcare techniques is highlighted, as well as implementation strategies and a setup for future research endeavors. Healthcare Systems Using Soft Computing Techniques is a valuable resource for researchers and postgraduate students in healthcare systems engineering, computer science, information technology, and applied mathematics. The book introduces beginners to―and at the same time brings industry professionals up to speed with―the important role soft computing techniques play in smart healthcare systems. Cover Half Title Series Page Title Page Copyright Page Contents Preface Editors Contributors 1. Computational Intelligence for Healthcare 1.1 Introduction 1.1.1 Artificial Neural Network 1.1.2 Restricted Boltzman Machines 1.1.3 Support Vector Machines 1.1.4 Evolutionary Algorithms 1.1.5 Fuzzy Systems 1.1.6 Swarm Intelligence 1.2 Issues and Challenges 1.2.1 Data Inconsistency, Inaccuracy, and Missing Values 1.2.2 Imbalanced Data 1.2.3 Data Collection Cost 1.2.4 Huge Data Volume 1.2.5 Ethical and Privacy Issues 1.3 Feature Engineering 1.3.1 Feature Extraction 1.3.2 Feature Selection 1.3.2.1 Filter Method 1.3.2.2 Wrapper Method 1.3.2.3 Embedded Method 1.3.3 Feature Weighting 1.3.4 Introduction to Gene Expression Dataset 1.3.5 Challenges in Gene Expression Data 1.3.6 Feature Selection and Classification of Gene Expression Data Using Binary Jaya Algorithm 1.3.6.1 Binary Jaya Algorithm 1.3.6.2 Use of Feature Selection with Binary Jaya Algorithm 1.3.6.3 Result and Discussion 1.4 Available Resources 1.5 Conclusion References 2. Analysis of Recurrent Neural Network and Convolution Neural Network Techniques in Blood Cell Classification 2.1 Introduction 2.1.1 Deep Learning Techniques 2.1.2 Medical Imaging/White Blood Cell Classification 2.2 Dataset 2.3 Analysis of Deep Learning Techniques 2.3.1 Recurrent Neural Network 2.3.2 Convolution Neural Network 2.3.3 Convolution Neural Network Experiment Design and Results 2.3.3.1 Case # 1 2.3.3.2 Case # 2 2.3.3.3 Case # 3 2.4 Conclusions References 3. Evaluating the Effectiveness of the Convolution Neural Network in Detecting Brain Tumors 3.1 Introduction 3.1.1 Deep Learning and Convolution Neural Network 3.1.2 Medical Imagery/Brain Tumor Detection 3.2 Related Work 3.3 Dataset 3.4 Evaluation of Convolution Neural Network Architectures 3.4.1 Test Case # 1 3.4.2 Test Case # 2 3.4.3 Test Case # 3 3.5 Conclusions References 4. Implementation of Machine Learning in Color Perception and Psychology: A Review 4.1 Introduction 4.1.1 Motivation 4.1.2 Related Works 4.1.3 Contribution 4.2 Application Areas 4.2.1 Food and Breed Hunting for Animals 4.2.2 Application in Color Constancy 4.2.3 Color Blindness Detection 4.2.4 Sentiment Analysis Based on Color Attributes 4.2.5 Application in Agriculture Using Color Classification 4.3 Deep Learning Methods Used in Color Psychology Analysis 4.3.1 Conditional GAN 4.3.2 Convolution Neural Network 4.3.3 Bidirectional Long Short Term Memory 4.3.4 Probabilistic Neural Network 4.3.5 VGG-16 4.3.6 DenseNet 4.4 Conclusion References 5. Early Recognition of Dynamic Sleeping Patterns Associated with Rapid Eyeball Movement Sleep Behavior Disorder of Apnea Patients Using Neural Network Techniques 5.1 Introduction 5.2 Methodologies 5.3 Data Collection 5.4 Preprocessing of Data and Feature Extraction Using Wavelet Packet Decomposition (WPD) 5.5 Feature Classification by Deep Neural Network (DNN) Classifier 5.6 Long Short Term Memory (LSTM) Technique 5.7 Results and Discussions 5.8 Conclusion References 6. Smart Attendance cum Health Check-up Machine for Students/Villagers/Company Employees 6.1 Introduction 6.2 Overview of Various Possible Smart Attendance Systems 6.2.1 Proposed Solution 6.2.2 Face Recognition System 6.2.2.1 Face Detection 6.2.2.2 Face Recognition 6.3 Health Parameters and Stress Detection 6.3.1 Eye Blink Detection 6.3.2 Emotion Detection 6.4 Physiological Parameters and Sensors Description 6.4.1 Body Temperature 6.4.2 Blood SpO2 Level 6.4.3 Heart Rate 6.5 Hardware and Sensors Used 6.5.1 MLX 90614 Temperature Sensor 6.5.2 MAX 30100 Heart Rate and Blood SpO2 Sensor 6.5.3 Arduino UNO 6.6 Software Tools 6.6.1 Arduino IDE 6.6.2 Tkinter 6.7 Outcomes and Result 6.7.1 Face Recognition 6.7.2 Emotion Recognition and Eye-Blink Rate Detection 6.7.3 Data from Sensors 6.8 Conclusion Acknowledgement References 7. Oral Histopathological Photomicrograph Classification Using Deep Learning 7.1 Introduction 7.2 Related Work 7.3 Present Diagnosing Method for Oral Cancer 7.4 Materials and Methods 7.4.1 Deep-Learning Combined with SVM Approach 7.4.2 Transfer Learning of the Deep-Learning Model's Approach 7.4.3 Fusion of the Results Obtained from Transfer Learning and SVM Process 7.5 Results and Discussions 7.5.1 Comparison of the Results with Other Related Works 7.6 Conclusion References 8. Prediction of Stage of Alzheimer's Disease DenseNet Deep Learning Model 8.1 Introduction 8.2 Literature Survey 8.3 Methodology 8.3.1 Deep Learning Techniques 8.3.2 Dataset 8.3.3 Data Preprocessing 8.3.4 Network Architecture 8.3.5 DenseNet 8.4 Experiment and Result Discussion 8.4.1 Using Machine Learning 8.4.2 Using Deep Learning 8.5 Conclusion References 9. An Insight of Deep Learning Applications in the Healthcare Industry 9.1 Introduction 9.2 Drug Discovery 9.3 Medical Image and Diagnostics 9.4 Clinical Trials 9.5 Patient Monitoring and Personalized Treatment 9.6 Chatbot Using NLP 9.7 Health Insurance and Fraud Detection 9.8 Medical Diagnosis 9.9 Future Development References 10. Expand Patient Care with AWS Cloud for Remote Medical Monitoring 10.1 Introduction 10.2 Literature Review 10.3 Cloud Healthcare Management 10.3.1 Cloud Computing Models 10.3.1.1 Infrastructure as a Service (IaaS) 10.3.1.2 Platform as a Service (PaaS) 10.3.1.3 Software as a Service (SaaS) 10.3.2 Deployment Models 10.3.2.1 Cloud 10.3.2.2 Hybrid 10.3.2.3 On-Premises 10.3.3 Advantages of Cloud Computation 10.4 Amazon Web Services 10.4.1 Compute 10.4.1.1 Amazon Elastic Compute Cloud 10.4.1.2 AWS Elastic Beanstalk 10.4.2 Storage 10.4.2.1 Amazon Elastic Block Store (EBS Volumes) 10.4.2.2 Amazon Elastic File System (Amazon EFS) 10.4.3 Amazon Machine Learning 10.4.4 Big Data Analysis in AWS 10.5 Cloud Pricing Strategy 10.6 AWS - Healthcare Solutions 10.7 Conclusion References 11. Privacy and Security Solution in Wireless Sensor Network for IoT in Healthcare System 11.1 Introduction 11.2 Classification of WSNs Protocols 11.2.1 Data-Centric Routing Protocol 11.2.2 Multiple Path Routing Protocol 11.2.2.1 Disjoint Path Routing Protocol 11.2.2.2 Braided Path Routing Protocol 11.2.2.3 N to 1 Multipath Discovery Routing Protocol 11.2.3 Hierarchical Routing Protocol 11.2.3.1 Initial Phase 11.2.3.2 Neighbor Discovery Phase 11.2.3.3 Clustering Phase 11.2.3.4 Data Message Exchange Phase 11.2.4 Routing Protocol Based on Location 11.2.5 Mobility-Based Routing Protocol 11.2.6 Quality of Service-Based Routing Protocol 11.2.6.1 Sequential Assignment Outing (SAR) Protocol 11.2.6.2 SPEED Protocol 11.2.6.3 Quality of Service - Aware and Heterogeneously Clustered Routing Protocol (QHCR) 11.3 Privacy and Security Issues in WSN 11.3.1 Security and Privacy Issues 11.3.1.1 Denial of Service Attack 11.3.1.2 Manipulating Routing Information 11.3.1.3 Sybil Attack 11.3.1.4 Sinkhole Attack 11.3.2 Clone Attack 11.3.3 Selective Forwarding Attack 11.3.3.1 HELLO Flood Attack 11.4 Security and Privacy Solutions 11.4.1 Use of Effective Key Management 11.4.2 Use of Efficient Public Key Infrastructure 11.4.3 Effective Use of Multiclass Nodes 11.4.4 Efficient Clustering of Modules to Increase Safety of WSN 11.4.5 Point-to-Point Protection Approach 11.4.6 Registration and Key Management Phase 11.4.7 Secure Data Exchange Phase 11.4.8 Generating Perturb Phase 11.4.9 Signature and Perturbation Phase 11.4.10 Authentication Phase 11.4.11 Decryption and Authentication 11.5 Conclusion References 12. An Epileptic Seizure Detection and Classification Based on Machine Learning Techniques 12.1 Introduction 12.2 Related Work 12.3 Proposed Methodology 12.3.1 Database Description - BONN University EEG Dataset 12.3.1.1 Data Pre-processing 12.3.1.2 Statistical Features of the Dataset 12.3.1.2.1 Common EEG Artifacts 12.3.1.2.2 Features Extraction 12.3.2 Evaluation Assessment Method 12.3.3 Classification Techniques 12.3.3.1 Support Vector Machines (SVMs) 12.3.3.2 Random Forests 12.3.3.3 Extreme Learning Machine 12.3.3.4 K-Nearest Neighbors 12.3.3.5 Logistic Regression 12.3.3.6 Decision Trees 12.3.3.7 Multilayer Perceptron 12.3.3.8 Ensemble Classifiers 12.4 Experimental Results 12.5 Discussion 12.6 Conclusion References 13. Analysis of Coronary Artery Disease Using Various Machine Learning Techniques 13.1 Introduction 13.2 Literature Survey 13.3 Material and Methods 13.3.1 Dataset Description 13.4 Methodology 13.4.1 Data Normalization 13.4.1.1 Data Splitting 13.4.1.2 Classification Models 13.4.1.3 Support Vector Machine 13.4.1.4 Decision Tree 13.4.1.5 Random Forest 13.4.1.6 K‑Nearest Neighbor (K‑NN) 13.4.2 Logistic Regression 13.4.3 Types of Logistic Regression 13.4.3.1 Logistic Regression Assumptions 13.4.3.2 Naïve Bayes 13.4.3.3 XG-Boost 13.5 Result Analysis 13.5.1 Performance Comparison of Algorithms 13.6 Discussion 13.7 Conclusion References Index