Artificial Intelligence for the Internet of Health Things

Cover
Half Title
Series Page
Title Page
Copyright Page
Contents
Author Biographies
Preface
Chapter 1: Artificial Intelligence (AI) for IoHT – An Introduction
	1.1. Artificial Intelligence (AI) in the Healthcare Domain
	1.2. Evolution of AI in the Medical Sector
	1.3. Use of AI Devices for Clinical Data Generation
	1.4. Types of AI of Relevance to Healthcare
		1.4.1. Machine Learning – Neural Networks and Deep
Learning
		1.4.2. Natural Language Processing
		1.4.3. Rule-Based Expert Systems
		1.4.4. Physical Robots
		1.4.5. Robotic Process Automation
	1.5. AI-Based Applications in Healthcare
		1.5.1. Patient Engagement and Adherence
Applications
		1.5.2. Administrative Applications
		1.5.3. Implications for the Healthcare Workforce
		1.5.4. Ethical Implications
	1.6. Conclusion
	References
Chapter 2: Role of Internet of Things and Cloud Computing Technologies
in the Healthcare Sector
	2.1. Introduction
	2.2. IoT-Based Healthcare Framework
	2.3. Cloud Computing for Healthcare
	2.4. IoT-Based Healthcare Services and Applications
		2.4.1. IoT Healthcare Services
			2.4.1.1. The Internet of m-Health Things
			2.4.1.2. Adverse Drug Reactions
			2.4.1.3. Community Healthcare
			2.4.1.4. Children’s Health Information
		2.4.2. IoT Healthcare Applications
			2.4.2.1. Glucose Level Sensing
			2.4.2.2. Electrocardiogram Monitoring
			2.4.2.3. Blood Pressure Monitoring
			2.4.2.4. Body Temperature Monitoring
		2.4.3. IoT Healthcare: Current Issues and
Challenges
			2.4.3.1. Cost Analysis
			2.4.3.2. Continuous Monitoring
			2.4.3.3. Identification
			2.4.3.4. Mobility
	2.5. Components in IoT-Based Healthcare Services
		2.5.1. IoT Devices
		2.5.2. Wireless Technologies for IoT
		2.5.3. Web Technologies for IoT
	2.6. Conclusion
	References
Chapter 3: An Extensive Overview of Wearable Technologies in the Healthcare Sector
	3.1. Introduction
	3.2. Background Information
		3.2.1. Quantified Self
		3.2.2. Wearable Technology
		3.2.3. Advantages of Wearable Technology
	3.3. Challenges
		3.3.1. Sustainability
		3.3.2. Digital Divide
		3.3.3. Failure Rates
		3.3.4. Lack of Predictive Comparability
		3.3.5. Privacy and Security
	3.4. Typical Wearable Devices With Applications
		3.4.1. Wearable Devices Used for General Health Management
		3.4.2. Wearable Biosensors Revolutionizing In-Clinic/Hospital Care
		3.4.3. Wearable Biosensors Revolutionizing Specific Fields of Healthcare Outside of the Hospital and 
Clinic
		3.4.4. Regulatory Oversight and Economic Impact
	3.5. Conclusion
	References
Chapter 4: IoHT and Cloud-Based Disease Diagnosis Model Using Particle Swarm Optimization with Artificial Neural Networks
	4.1. Introduction
	4.2. The Proposed Model
		4.2.1. Data Collection
		4.2.2. PSO-ANN Model
			4.2.2.1. ANN Model
			4.2.2.2. Parameter Optimization of ANN Using PSO
		4.2.3. Proposed Diagnostic Model
	4.3. Performance Validation
	4.4. Conclusion
	References
Chapter 5: IoHT-Based Improved Grey Optimization with Support Vector Machine for Gastrointestinal Hemorrhage Detection and Diagnosis Model
	5.1. Introduction
	5.2. Proposed Method
		5.2.1. Preprocessing
		5.2.2. Feature Extraction Process Using NGLCM
		5.2.3. NGLCM-IGWO-SVM–Based Classification
	5.3. Experimental Validation
		5.3.1. Data Set Used
		5.3.2. Results Analysis
	5.4. Conclusion
	References
Chapter 6: An Effective-Based Personalized Medicine Recommendation System Using an Ensemble of Extreme Learning Machine Model
	6.1. Introduction
	6.2. The Proposed Medical Recommender System
		6.2.1. Database System Module
		6.2.2. Data Preparation Module
		6.2.3. Recommendation Model Module
		6.2.4. Model Evaluation Module
		6.2.5. Proposed Recommendation Model
			6.2.5.1. Extreme Learning Machine (ELM)
			6.2.5.2. b-ELM Classifier
	6.3. Experimental Results and Discussion
	6.4. Conclusion
	References
Chapter 7: A Novel MapReduce-Based Hybrid Decision Tree with TFIDF Algorithm for Public Sentiment Mining of Diabetes Mellitus
	7.1. Introduction
	7.2. The Proposed Model
		7.2.1. Data Collection
		7.2.2. Data Preprocessing and Integration
			7.2.2.1. Data Tokenization
			7.2.2.2. Generating and Removing Stop Words
			7.2.2.3. Detecting Stop Words with SentiCircles
			7.2.2.4. Stemming and Lemmatization
			7.2.2.5. Corpus Generation
			7.2.2.6. Tagging
		7.2.3. Data Analysis Stage
			7.2.3.1. MPHDT-T-Based Opinion Mining
			7.2.3.2. Decision Tree (DT)
			7.2.3.3. Term Frequency-Inverse Document Frequency (TFIDF)
	7.3. Performance Validation
	7.4. Conclusion
	References
Chapter 8: IoHT with Artificial Intelligence–Based Breast Cancer Diagnosis Model
	8.1. Introduction
	8.2. Related Works
	8.3. The Proposed Model
		8.3.1. Image Acquisition
		8.3.2. Preprocessing
		8.3.3. HFE Model
			8.3.3.1. Homogeneity
			8.3.3.2. Energy
			8.3.3.3. HOG Features
		8.3.4. GA-SVM-Based Classification
			8.3.4.1. Chromosome Design
			8.3.4.2. Fitness Function
			8.3.4.3. Hybridization of the GA-SVM Algorithm
	8.4. Performance Validation
	8.5. Conclusion
	References
Chapter 9: Artificial Intelligence with a Cloud-Based Medical Image Retrieval System Using a Deep Neural Network
	9.1. Introduction
	9.2. The Proposed DC-DNN Model
		9.2.1. DLTerQEP-Based Texture Feature Extraction
		9.2.2. Crest Line–Based Shape Feature Extraction
			9.2.2.1. Curvature Approximation
			9.2.2.2. Crest Point Classification
			9.2.2.3. Crest Lines
		9.2.3. Euclidean Distance–Based Similarity
		9.2.4. DNN-Based Classification
	9.3. Performance Validation
		9.3.1. Data Set Used
		9.3.2. Results Analysis
	9.4. Conclusion
	References
Chapter 10: IoHT with Cloud-Based Brain Tumor Detection Using Particle Swarm Optimization with Support Vector Machine
	10.1. Introduction
	10.2. The Proposed GLCM-PSO-SVM Model
		10.2.1. Preprocessing
		10.2.2. Feature Extraction
		10.2.3. PSO-SVM-Based Classification
			10.2.3.1. SVM Classifier
			10.2.3.2. Parameter Optimization of SVM Using the PSO Algorithm
	10.3. Experimental Analysis
		10.3.1. Data Set Description
		10.3.2. Evaluation Metrics
		10.3.3. Results Analysis
	10.4. Conclusion
	References
Chapter 11: Artificial Intelligence-Based Hough Transform with an Adaptive Neuro-Fuzzy Inference System for a Diabetic Retinopathy Classification Model
	11.1. Introduction
	11.2. Proposed Method
		11.2.1. Preprocessing
		11.2.2. Watershed-Based Segmentation
		11.2.3. Hough Transform–Based Feature Extraction
		11.2.4. ANFIS-Based Classification
	11.3. Performance Analysis
		11.3.1. Data Set Description
		11.3.2. Results Analysis
	11.4. Conclusion
	References
Chapter 12: An IoHT–Based Intelligent Skin Lesion Detection and Classification Model in Dermoscopic Images
	12.1. Introduction
	12.2. The SIFT-SVM
		12.2.1. Bilateral Filtering–Based Preprocessing
		12.2.2. Image Segmentation
		12.2.3. Feature Extraction
			12.2.3.1. Detect Scale-Space Extrema
			12.2.3.2. Localized Feature Points
			12.2.3.3. Assignment of Orientation
			12.2.3.4. Feature Point Descriptor
		12.2.4. Image Classification
	12.3. Performance Validation
		12.3.1. Data Set Used
		12.3.2. Results Analysis
	12.4. Conclusion
	References
Chapter 13: An IoHT-Based Image Compression Model Using Modified Cuckoo Search Algorithm with Vector Quantization
	13.1. Introduction
	13.2. Vector Quantization and LBG Algorithm
	13.3. Proposed MCS-LBG Algorithm–Based VQ
		13.3.1. CS Algorithm
		13.3.2. MCS Algorithm
		13.3.3. Working Process of MCS-LBG Algorithm
	13.4. Performance Validation
	13.5. Conclusion
	References
Chapter 14: An Effective Secure Medical Image Transmission Using Improved Particle Swarm Optimization and Wavelet Transform
	14.1. Introduction
	14.2. The IPSO-DWT Method
		14.2.1. Embedded Procedure
		14.2.2. Extraction of the Secret Message
			14.2.1.1. Representation of the Stego Key
			14.2.1.2. Embedded Process
		14.2.3. IPSO-Based Pixel Selection Process
	14.3. Performance Validation
	14.4. Conclusion
	References
Chapter 15: IoHT with Wearable Devices–Based Feature Extraction and a Deep Neural Networks Classification Model for Heart Disease Diagnosis
	15.1. Introduction
	15.2. Proposed Model
		15.2.1. IoHT-Based Patient Data Collection
		15.2.2. IoHT Medical Data Preprocessing
		15.2.3. Heart Feature Extraction
		15.2.4. DNN for Data Classification
			15.2.4.1. Training of Layers
			15.2.4.2. The Stacked Autoencoder
			15.2.4.3. The Softmax Layer
	15.3. Performance Validation
	15.4. Conclusion
	References
Index