Оглавление
Группа авторов. Machine Learning for Healthcare Applications
Table of Contents
List of Tables
List of Illustrations
Guide
Pages
Machine Learning for Healthcare Applications
Preface
1. Innovation on Machine Learning in Healthcare Services—An Introduction
1.1 Introduction
1.2 Need for Change in Healthcare
1.3 Opportunities of Machine Learning in Healthcare
1.4 Healthcare Fraud
1.4.1 Sorts of Fraud in Healthcare
1.4.2 Clinical Service Providers
1.4.3 Clinical Resource Providers
1.4.4 Protection Policy Holders
1.4.5 Protection Policy Providers
1.5 Fraud Detection and Data Mining in Healthcare
1.5.1 Data Mining Supervised Methods
1.5.2 Data Mining Unsupervised Methods
1.6 Common Machine Learning Applications in Healthcare
1.6.1 Multimodal Machine Learning for Data Fusion in Medical Imaging
1.6.2 Machine Learning in Patient Risk Stratification
1.6.3 Machine Learning in Telemedicine
1.6.4 AI (ML) Application in Sedate Revelation
1.6.5 Neuroscience and Image Computing
1.6.6 Cloud Figuring Systems in Building AI-Based Healthcare
1.6.7 Applying Internet of Things and Machine Learning for Personalized Healthcare
1.6.8 Machine Learning in Outbreak Prediction
1.7 Conclusion
References
2. A Framework for Health Status Estimation Based on Daily Life Activities Data Using Machine Learning Techniques
2.1 Introduction. 2.1.1 Health Status of an Individual
2.1.2 Activities and Measures of an Individual
2.1.3 Traditional Approach to Predict Health Status
2.2 Background
2.3 Problem Statement
2.4 Proposed Architecture
2.4.1 Pre-Processing
2.4.2 Phase-I
2.4.3 Phase-II
2.4.4 Dataset Generation
2.4.4.1 Rules Collection
2.4.4.2Feature Selection
2.4.4.3 Feature Reduction
2.4.4.4 Dataset Generation From Rules
2.4.4.5 Example
2.4.5 Pre-Processing
2.5 Experimental Results
2.5.1 Performance Metrics
2.5.1.1 Accuracy
2.5.1.2 Precision
2.5.1.3 Recall
2.5.1.4 F1-Score
2.6 Conclusion
References
3. Study of Neuromarketing With EEG Signals and Machine Learning Techniques
3.1 Introduction
3.1.1 Why BCI
3.1.2 Human–Computer Interfaces
3.1.3 What is EEG
3.1.4 History of EEG
3.1.5 About Neuromarketing
3.1.6 About Machine Learning
3.2 Literature Survey
3.3 Methodology. 3.3.1 Bagging Decision Tree Classifier
3.3.2 Gaussian Naïve Bayes Classifier
3.3.3 Kernel Support Vector Machine (Sigmoid)
3.3.4 Random Decision Forest Classifier
3.4 System Setup & Design
3.4.1 Pre-Processing & Feature Extraction
3.4.1.1 Savitzky–Golay Filter
3.4.1.2 Discrete Wavelet Transform
3.4.2 Dataset Description
3.5 Result. 3.5.1 Individual Result Analysis
3.5.2 Comparative Results Analysis
3.6 Conclusion
References
4. An Expert System-Based Clinical Decision Support System for Hepatitis-B Prediction & Diagnosis
4.1 Introduction
4.2 Outline of Clinical DSS
4.2.1 Preliminaries
4.2.2 Types of Clinical DSS
4.2.3 Non-Knowledge-Based Decision Support System (NK-DSS)
4.2.4 Knowledge-Based Decision Support System (K-DSS)
4.2.5 Hybrid Decision Support System (H-DSS)
4.2.6 DSS Architecture
4.3 Background
4.4 Proposed Expert System-Based CDSS
4.4.1 Problem Description
4.4.2 Rules Set & Knowledge Base
4.4.3 Inference Engine
4.5 Implementation & Testing
4.6 Conclusion
References
5. Deep Learning on Symptoms in Disease Prediction
5.1 Introduction
5.2 Literature Review
5.3 Mathematical Models
5.3.1 Graphs and Related Terms
5.3.2 Deep Learning in Graph
5.3.3 Network Embedding
5.3.4 Graph Neural Network
5.3.5 Graph Convolution Network
5.4 Learning Representation From DSN
5.4.1 Description of the Proposed Model
5.4.2 Objective Function
5.5 Results and Discussion
5.5.1 Description of the Dataset
5.5.2 Training Progress
5.5.3 Performance Comparisons
5.6 Conclusions and Future Scope
References
6. Intelligent Vision-Based Systems for Public Safety and Protection via Machine Learning Techniques
6.1 Introduction
6.1.1 Problems Intended in Video Surveillance Systems
6.1.2 Current Developments in This Area
6.1.3 Role of AI in Video Surveillance Systems
6.2 Public Safety and Video Surveillance Systems
6.2.1 Offline Crime Prevention
6.2.2 Crime Prevention and Identification via Apps
6.2.3 Crime Prevention and Identification via CCTV
6.3 Machine Learning for Public Safety
6.3.1 Abnormality Behavior Detection via Deep Learning
6.3.2 Video Analytics Methods for Accident Classification/Detection
6.3.3 Feature Selection and Fusion Methods
6.4 Securing the CCTV Data. 6.4.1 Image/Video Security Challenges
6.4.2 Blockchain for Image/Video Security
6.5 Conclusion
References
7. Semantic Framework in Healthcare
7.1 Introduction
7.2 Semantic Web Ontology
7.3 Multi-Agent System in a Semantic Framework
7.3.1 Existing Healthcare Semantic Frameworks. 7.3.1.1 AOIS
7.3.1.2 SCKE
7.3.1.3 MASE
7.3.1.4 MET4
7.3.2 Proposed Multi-Agent-Based Semantic Framework for Healthcare Instance Data
7.3.2.1 Data Dictionary
7.3.2.2 Mapping Database
7.3.2.3 Decision Making Ontology
7.3.2.4 STTL and SPARQL-Based RDF Transformation
7.3.2.5 Query Optimizer Agent
7.3.2.6 Semantic Web Services Ontology
7.3.2.7 Web Application User Interface and Customer Agent
7.3.2.8 Translation Agent
7.3.2.9 RDF Translator
7.4 Conclusion
References
8. Detection, Prediction & Intervention of Attention Deficiency in the Brain Using tDCS
8.1 Introduction
8.2 Materials & Methods. 8.2.1 Subjects and Experimental Design
8.2.2 Data Preprocessing & Statistical Analysis
8.2.3 Extracting Singularity Spectrum from EEG
8.3 Results & Discussion
8.4 Conclusion
Acknowledgement
References
9. Detection of Onset and Progression of Osteoporosis Using Machine Learning
9.1 Introduction
9.1.1 Measurement Techniques of BMD
9.1.2 Machine Learning Algorithms in Healthcare
9.1.3 Organization of Chapter
9.2 Microwave Characterization of Human Osseous Tissue
9.2.1 Frequency-Domain Analysis of Human Wrist Sample
9.2.2 Data Collection and Analysis
9.3 Prediction Model of Osteoporosis Using Machine Learning Algorithms
9.3.1 K-Nearest Neighbor (KNN)
9.3.2 Decision Tree
9.3.3 Random Forest
9.4 Conclusion
Acknowledgment
References
10. Applications of Machine Learning in Biomedical Text Processing and Food Industry
10.1 Introduction
10.2 Use Cases of AI and ML in Healthcare
10.2.1 Speech Recognition (SR)
10.2.2 Pharmacovigilance and Adverse Drug Effects (ADE)
10.2.3 Clinical Imaging and Diagnostics
10.2.4 Conversational AI in Healthcare
10.3 Use Cases of AI and ML in Food Technology
10.3.1 Assortment of Vegetables and Fruits
10.3.2 Personal Hygiene
10.3.3 Developing New Products
10.3.4 Plant Leaf Disease Detection
10.3.5 Face Recognition Systems for Domestic Cattle
10.3.6 Cleaning Processing Equipment
10.4 A Case Study: Sentiment Analysis of Drug Reviews
10.4.1 Dataset
10.4.2 Approaches for Sentiment Analysis on Drug Reviews
10.4.3 BoW and TF-IDF Model
10.4.4 Bi-LSTM Model
10.4.4.1 Word Embedding
10.4.5 Deep Learning Model
10.5 Results and Analysis
10.6 Conclusion
References
11. Comparison of MobileNet and ResNet CNN Architectures in the CNN-Based Skin Cancer Classifier Model
11.1 Introduction
11.2 Our Skin Cancer Classifier Model
11.3 Skin Cancer Classifier Model Results
11.4 Hyperparameter Tuning and Performance
11.4.1 Hyperparameter Tuning of MobileNet-Based CNN Model
11.4.2 Hyperparameter Tuning of ResNet50-Based CNN Model
11.4.3 Table Summary of Hyperparameter Tuning Results
11.5 Comparative Analysis and Results
11.5.1 Training and Validation Loss. 11.5.1.1 MobileNet
11.5.1.2 ResNet50
11.5.1.3 Inferences
11.5.2 Training and Validation Categorical Accuracy. 11.5.2.1 MobileNet
11.5.2.2 ResNet50
11.5.2.3 Inferences
11.5.3 Training and Validation Top 2 Accuracy. 11.5.3.1 MobileNet
11.5.3.2 ResNet50
11.5.3.3 Inferences
11.5.4 Training and Validation Top 3 Accuracy. 11.5.4.1 MobileNet
11.5.4.2 ResNet50
11.5.4.3 Inferences
11.5.5 Confusion Matrix. 11.5.5.1 MobileNet
11.5.5.2 ResNet50
11.5.5.3 Inferences
11.5.6 Classification Report. 11.5.6.1 MobileNet
11.5.6.2 ResNet50
11.5.6.3 Inferences
11.5.7 Last Epoch Results. 11.5.7.1 MobileNet
11.5.7.2 ResNet50
11.5.7.3 Inferences
11.5.8 Best Epoch Results. 11.5.8.1 MobileNet
11.5.8.2 ResNet50
11.5.8.3 Inferences
11.5.9 Overall Comparative Analysis
11.6 Conclusion
References
12. Deep Learning-Based Image Classifier for Malaria Cell Detection
12.1 Introduction
12.2 Related Work
12.3 Proposed Work
12.3.1 Dataset Description
12.3.2 Data Pre-Processing and Augmentation
12.3.3 CNN Architecture and Implementation
12.4 Results and Evaluation
12.5 Conclusion
References
13. Prediction of Chest Diseases Using Transfer Learning
13.1 Introduction
13.2 Types of Diseases. 13.2.1 Pneumothorax
13.2.2 Pneumonia
13.2.3 Effusion
13.2.4 Atelectasis
13.2.5 Nodule and Mass
13.2.6 Cardiomegaly
13.2.7 Edema
13.2.8 Lung Consolidation
13.2.9 Pleural Thickening
13.2.10 Infiltration
13.2.11 Fibrosis
13.2.12 Emphysema
13.3 Diagnosis of Lung Diseases
13.4 Materials and Methods
13.4.1 Data Augmentation
13.4.2 CNN Architecture
13.4.3 Lung Disease Prediction Model
13.5 Results and Discussions
13.5.1 Implementation Results Using ROC Curve
13.6 Conclusion
References
14. Early Stage Detection of Leukemia Using Artificial Intelligence
14.1 Introduction
14.1.1 Classification of Leukemia
14.1.1.1 Acute Lymphocytic Leukemia
14.1.1.2 Acute Myeloid Leukemia
14.1.1.3 Chronic Lymphocytic Leukemia
14.1.1.4 Chronic Myeloid Leukemia
14.1.2 Diagnosis of Leukemia
14.1.3 Acute and Chronic Stages of Leukemia
14.1.4 The Role of AI in Leukemia Detection
14.2 Literature Review
14.3 Proposed Work
14.3.1 Modules Involved in Proposed Methodology
14.3.2 Flowchart
14.3.3 Proposed Algorithm
14.4 Conclusion and Future Aspects
References
15. IoT Application in Interconnected Hospitals
15.1 Introduction
15.2 Networking Systems Using IoT
15.3 What are Smart Hospitals?
15.3.1 Environment of a Smart Hospital
15.4 Assets. 15.4.1 Overview of Smart Hospital Assets
15.4.2 Exigency of Automated Healthcare Center Assets
15.5 Threats. 15.5.1 Emerging Vulnerabilities
15.5.2 Threat Analysis
15.6 Conclusion
References
16. Real Time Health Monitoring Using IoT With Integration of Machine Learning Approach
16.1 Introduction
16.2 Related Work
16.3 Existing Healthcare Monitoring System
16.4 Methodology and Data Analysis
16.5 Proposed System Architecture
16.6 Machine Learning Approach
16.6.1 Multiple Linear Regression Algorithm
16.6.2 Random Forest Algorithm
16.6.3 Support Vector Machine
16.7 Work Flow of the Proposed System
16.8 System Design of Health Monitoring System
16.9 Use Case Diagram
16.10 Conclusion
References
17. Semantic and NLP-Based Retrieval From Covid-19 Ontology
17.1 Introduction
17.2 Related Work
17.3 Proposed Retrieval System. 17.3.1 Why Ontology?
17.3.2 Covid Ontology
17.3.3 Information Retrieval From Ontology
17.3.4 Query Formulation
17.3.5 Retrieval From Knowledgebase
17.4 Conclusion
References
18. Semantic Behavior Analysis of COVID-19 Patients: A Collaborative Framework
18.1 Introduction
18.2 Related Work. 18.2.1 Semantic Analysis and Topic Discovery of Alcoholic Patients From Social Media Platforms
18.2.2 Sentiment Analysis of Tweets From Twitter Handles of the People of Nepal in Response to the COVID-19 Pandemic
18.2.3 Study of Sentiment Analysis and Analyzing Scientific Papers
18.2.4 Informatics and COVID-19 Research
18.2.5 COVID-19 Outbreak in the World and Twitter Sentiment Analysis
18.2.6 LDA Topic Modeling on Twitter to Study Public Discourse and Sentiment During the Coronavirus Pandemic
18.2.7 The First Decade of Research on Sentiment Analysis
18.2.8 Detailed Survey on the Semantic Analysis Techniques for NLP
18.2.9 Understanding Text Semantics With LSA
18.2.10 Analyzing Suicidal Tendencies With Semantic Analysis Using Social Media
18.2.11 Analyzing Public Opinion on BREXIT Using Sentiment Analysis
18.2.12 Prediction of Indian Elections Using NLP and Decision Tree
18.3 Methodology
18.4 Conclusion
References
19. Comparative Study of Various Data Mining Techniques Towards Analysis and Prediction of Global COVID-19 Dataset
19.1 Introduction
19.2 Literature Review
19.3 Materials and Methods. 19.3.1 Dataset Collection
19.3.2 Support Vector Machine (SVM)
19.3.3 Decision Tree (DT)
19.3.4 K-Means Clustering
19.3.5 Back Propagation Neural Network (BPNN)
19.4 Experimental Results
19.5 Conclusion and Future Scopes
References
20. Automated Diagnosis of COVID-19 Using Reinforced Lung Segmentation and Classification Model
20.1 Introduction
20.2 Diagnosis of COVID-19
20.2.1 Pre-Processing of Lung CT Image
20.2.2 Lung CT Image Segmentation
20.2.3 ROI Extraction
20.2.4 Feature Extraction
20.2.5 Classification
20.3 Genetic Algorithm (GA)
20.3.1 Operators of GA
20.3.2 Applications of GA
20.4 Related Works
20.5 Challenges in GA
20.6 Challenges in Lung CT Segmentation
20.7 Proposed Diagnosis Framework
20.7.1 Image Pre-Processing
20.7.2 Proposed Image Segmentation Technique
20.7.3 ROI Segmentation
20.7.4 Feature Extraction
20.7.5 Modified GA Classifier
20.7.5.1 Gaussian Type—II Fuzzy in Classification
20.7.5.2 Classifier Algorithm
20.8 Result Discussion
20.9 Conclusion
References
21. Future of Telemedicine with ML: Building a Telemedicine Framework for Lung Sound Detection
21.1 Introduction
21.1.1 Monitoring the Remote Patient
21.1.2 Intelligent Assistance for Patient Diagnosis
21.1.3 Fasten Electronic Health Record Retrieval Process
21.1.4 Collaboration Increases Among Healthcare Practitioners
21.2 Related Work
21.3 Strategic Model for Telemedicine
21.4 Framework for Lung Sound Detection in Telemedicine
21.4.1 Data Collection
21.4.2 Pre-Processing of Data
21.4.3 Feature Extraction
21.4.3.1 MFCC
21.4.3.2 Lung Sounds Using Multi Resolution DWT
21.4.3.2.1 DWT
21.4.3.2.2 MRA
21.4.4 Classification
21.4.4.1 Correlation Coefficient for Feature Selection (CFS)
21.4.4.2 Symmetrical Uncertainty
21.4.4.3Gain Ratio
21.4.4.4 Modified RF Classification Architecture
21.5 Experimental Analysis
21.6 Conclusion
References
22. A Lightweight Convolutional Neural Network Model for Tuberculosis Bacilli Detection From Microscopic Sputum Smear Images
22.1 Introduction
22.2 Literature Review
22.3 Proposed Work
22.4 Experimental Results and Discussion
22.5 Conclusion
References
23. Role of Machine Learning and Texture Features for the Diagnosis of Laryngeal Cancer
23.1 Introduction
23.2 Clinically Correlated Texture Features
23.2.1 Texture-Based LBP Descriptors
23.2.2 GLCM Features
23.2.3 Statistical Features
23.3 Machine Learning Techniques
23.3.1 Support Vector Machine (SVM)
23.3.2 k-NN (k-Nearest Neighbors)
23.3.3 Random Forest (RF)
23.3.4 Naïve Bayes
23.4 Result Analysis and Discussions
23.5 Conclusions
References
24. Analysis of Machine Learning Technologies for the Detection of Diabetic Retinopathy
24.1 Introduction
24.2 Related Work
24.2.1 Pre-Processing of Image
24.2.2 Diabetic Retinopathy Detection
24.2.3 Grading of DR
24.3 Dataset Used
24.3.1 DIARETDB1
24.3.2 Diabetic Retinopathy-Detection Dataset
24.4 Methodology Used
24.4.1 Pre-Processing
24.4.2 Segmentation
24.4.3 Feature Extraction
24.4.4 Classification
24.5 Analysis of Results and Discussion
24.6 Conclusion
References
Index
WILEY END USER LICENSE AGREEMENT
