Advanced Healthcare Systems

Rohit Tanwar, PhD (Kurukshetra University, Kurukshetra, India) is an assistant professor in the School of Computer Science at UPES Dehradun, India. S. Balamurugan, PhD, SMIEEE, ACM Distinguished Speaker, received his PhD from Anna University, India. He has published 57 books, 300+ international journals/conferences, and 100 patents. He is the Director of the Albert Einstein Engineering and Research Labs. He is also the Vice-Chairman of the Renewable Energy Society of India (RESI). He is serving as a research consultant to many companies, startups, SMEs, and MSMEs. He has received numerous awards for research at national and international levels. R. K. Saini, PhD (DIT University, Dehradun, India) is an assistant professor in the Department of Computer Science & Applications at DIT University, Dehradun (Uttarakhand). Vishal Bharti, PhD is a professor in the Department of Computer Science and Engineering, Chandigarh University, India. He has published more than 75 research papers in both national & international journals. Premkumar Chithaluru, PhD is an assistant professor in the Department of SCS at the University of Petroleum and Energy Studies (UPES), Dehradun, India.

• Preface xvii1 Internet of Medical Things—State-of-the-Art 1Kishor Joshi and Ruchi Mehrotra1.1 Introduction 21.2 Historical Evolution of IoT to IoMT 21.2.1 IoT and IoMT—Market Size 41.3 Smart Wearable Technology 41.3.1 Consumer Fitness Smart Wearables 41.3.2 Clinical-Grade Wearables 51.4 Smart Pills 71.5 Reduction of Hospital-Acquired Infections 81.5.1 Navigation Apps for Hospitals 81.6 In-Home Segment 81.7 Community Segment 91.8 Telehealth and Remote Patient Monitoring 91.9 IoMT in Healthcare Logistics and Asset Management 121.10 IoMT Use in Monitoring During COVID-19 131.11 Conclusion 14References 152 Issues and Challenges Related to Privacy and Security in Healthcare Using IoT, Fog, and Cloud Computing 21Hritu Raj, Mohit Kumar, Prashant Kumar, Amritpal Singh and Om Prakash Verma2.1 Introduction 222.2 Related Works 232.3 Architecture 252.3.1 Device Layer 252.3.2 Fog Layer 262.3.3 Cloud Layer 262.4 Issues and Challenges 262.5 Conclusion 29References 303 Study of Thyroid Disease Using Machine Learning 33Shanu Verma, Rashmi Popli and Harish Kumar3.1 Introduction 343.2 Related Works 343.3 Thyroid Functioning 353.4 Category of Thyroid Cancer 363.5 Machine Learning Approach Toward the Detection of Thyroid Cancer 373.5.1 Decision Tree Algorithm 383.5.2 Support Vector Machines 393.5.3 Random Forest 393.5.4 Logistic Regression 393.5.5 Naïve Bayes 403.6 Conclusion 41References 414 A Review of Various Security and Privacy Innovations for IoT Applications in Healthcare 43Abhishek Raghuvanshi, Umesh Kumar Singh and Chirag Joshi4.1 Introduction 444.1.1 Introduction to IoT 444.1.2 Introduction to Vulnerability, Attack, and Threat 454.2 IoT in Healthcare 464.2.1 Confidentiality 464.2.2 Integrity 464.2.3 Authorization 464.2.4 Availability 474.3 Review of Security and Privacy Innovations for IoT Applications in Healthcare, Smart Cities, and Smart Homes 484.4 Conclusion 54References 545 Methods of Lung Segmentation Based on CT Images 59Amit Verma and Thipendra P. Singh5.1 Introduction 595.2 Semi-Automated Algorithm for Lung Segmentation 605.2.1 Algorithm for Tracking to Lung Edge 605.2.2 Outlining the Region of Interest in CT Images 625.2.2.1 Locating the Region of Interest 625.2.2.2 Seed Pixels and Searching Outline 625.3 Automated Method for Lung Segmentation 635.3.1 Knowledge-Based Automatic Model for Segmentation 635.3.2 Automatic Method for Segmenting the Lung CT Image 645.4 Advantages of Automatic Lung Segmentation Over Manual and Semi-Automatic Methods 645.5 Conclusion 65References 656 Handling Unbalanced Data in Clinical Images 69Amit Verma6.1 Introduction 706.2 Handling Imbalance Data 716.2.1 Cluster-Based Under-Sampling Technique 726.2.2 Bootstrap Aggregation (Bagging) 756.3 Conclusion 76References 767 IoT-Based Health Monitoring System for Speech-Impaired People Using Assistive Wearable Accelerometer 81Ishita Banerjee and Madhumathy P.7.1 Introduction 827.2 Literature Survey 847.3 Procedure 867.4 Results 937.5 Conclusion 97References 978 Smart IoT Devices for the Elderly and People with Disabilities 101K. N. D. Saile and Kolisetti Navatha8.1 Introduction 1018.2 Need for IoT Devices 1028.3 Where Are the IoT Devices Used? 1038.3.1 Home Automation 1038.3.2 Smart Appliances 1048.3.3 Healthcare 1048.4 Devices in Home Automation 1048.4.1 Automatic Lights Control 1048.4.2 Automated Home Safety and Security 1048.5 Smart Appliances 1058.5.1 Smart Oven 1058.5.2 Smart Assistant 1058.5.3 Smart Washers and Dryers 1068.5.4 Smart Coffee Machines 1068.5.5 Smart Refrigerator 1068.6 Healthcare 1068.6.1 Smart Watches 1078.6.2 Smart Thermometer 1078.6.3 Smart Blood Pressure Monitor 1078.6.4 Smart Glucose Monitors 1078.6.5 Smart Insulin Pump 1088.6.6 Smart Wearable Asthma Monitor 1088.6.7 Assisted Vision Smart Glasses 1098.6.8 Finger Reader 1098.6.9 Braille Smart Watch 1098.6.10 Smart Wand 1098.6.11 Taptilo Braille Device 1108.6.12 Smart Hearing Aid 1108.6.13 E-Alarm 1108.6.14 Spoon Feeding Robot 1108.6.15 Automated Wheel Chair 1108.7 Conclusion 112References 1129 IoT-Based Health Monitoring and Tracking System for Soldiers 115Kavitha N. and Madhumathy P.9.1 Introduction 1169.2 Literature Survey 1179.3 System Requirements 1189.3.1 Software Requirement Specification 1199.3.2 Functional Requirements 1199.4 System Design 1199.4.1 Features 1219.4.1.1 On-Chip Flash Memory 1229.4.1.2 On-Chip Static RAM 1229.4.2 Pin Control Block 1229.4.3 UARTs 1239.4.3.1 Features 1239.4.4 System Control 1239.4.4.1 Crystal Oscillator 1239.4.4.2 Phase-Locked Loop 1249.4.4.3 Reset and Wake-Up Timer 1249.4.4.4 Brown Out Detector 1259.4.4.5 Code Security 1259.4.4.6 External Interrupt Inputs 1259.4.4.7 Memory Mapping Control 1259.4.4.8 Power Control 1269.4.5 Real Monitor 1269.4.5.1 GPS Module 1269.4.6 Temperature Sensor 1279.4.7 Power Supply 1289.4.8 Regulator 1289.4.9 LCD 1289.4.10 Heart Rate Sensor 1299.5 Implementation 1299.5.1 Algorithm 1309.5.2 Hardware Implementation 1309.5.3 Software Implementation 1319.6 Results and Discussions 1339.6.1 Heart Rate 1339.6.2 Temperature Sensor 1359.6.3 Panic Button 1359.6.4 GPS Receiver 1359.7 Conclusion 136References 13610 Cloud-IoT Secured Prediction System for Processing and Analysis of Healthcare Data Using Machine Learning Techniques 137G. K. Kamalam and S. Anitha10.1 Introduction 13810.2 Literature Survey 13910.3 Medical Data Classification 14110.3.1 Structured Data 14210.3.2 Semi-Structured Data 14210.4 Data Analysis 14210.4.1 Descriptive Analysis 14210.4.2 Diagnostic Analysis 14310.4.3 Predictive Analysis 14310.4.4 Prescriptive Analysis 14310.5 ML Methods Used in Healthcare 14410.5.1 Supervised Learning Technique 14410.5.2 Unsupervised Learning 14510.5.3 Semi-Supervised Learning 14510.5.4 Reinforcement Learning 14510.6 Probability Distributions 14510.6.1 Discrete Probability Distributions 14610.6.1.1 Bernoulli Distribution 14610.6.1.2 Uniform Distribution 14710.6.1.3 Binomial Distribution 14710.6.1.4 Normal Distribution 14810.6.1.5 Poisson Distribution 14810.6.1.6 Exponential Distribution 14910.7 Evaluation Metrics 15010.7.1 Classification Accuracy 15010.7.2 Confusion Matrix 15010.7.3 Logarithmic Loss 15110.7.4 Receiver Operating Characteristic Curve, or ROC Curve 15210.7.5 Area Under Curve (AUC) 15210.7.6 Precision 15310.7.7 Recall 15310.7.8 F1 Score 15310.7.9 Mean Absolute Error 15410.7.10 Mean Squared Error 15410.7.11 Root Mean Squared Error 15510.7.12 Root Mean Squared Logarithmic Error 15510.7.13 R-Squared/Adjusted R-Squared 15610.7.14 Adjusted R-Squared 15610.8 Proposed Methodology 15610.8.1 Neural Network 15810.8.2 Triangular Membership Function 15810.8.3 Data Collection 15910.8.4 Secured Data Storage 15910.8.5 Data Retrieval and Merging 16110.8.6 Data Aggregation 16210.8.7 Data Partition 16210.8.8 Fuzzy Rules for Prediction of Heart Disease 16310.8.9 Fuzzy Rules for Prediction of Diabetes 16410.8.10 Disease Prediction With Severity and Diagnosis 16510.9 Experimental Results 16610.10 Conclusion 169References 16911 CloudIoT-Driven Healthcare: Review, Architecture, Security Implications, and Open Research Issues 173Junaid Latief Shah, Heena Farooq Bhat and Asif Iqbal Khan11.1 Introduction 17411.2 Background Elements 18011.2.1 Security Comparison Between Traditional and IoT Networks 18511.3 Secure Protocols and Enabling Technologies for CloudIoT Healthcare Applications 18711.3.1 Security Protocols 18711.3.2 Enabling Technologies 18811.4 CloudIoT Health System Framework 19111.4.1 Data Perception/Acquisition 19211.4.2 Data Transmission/Communication 19311.4.3 Cloud Storage and Warehouse 19411.4.4 Data Flow in Healthcare Architecture - A Conceptual Framework 19411.4.5 Design Considerations 19711.5 Security Challenges and Vulnerabilities 19911.5.1 Security Characteristics and Objectives 20011.5.1.1 Confidentiality 20211.5.1.2 Integrity 20211.5.1.3 Availability 20211.5.1.4 Identification and Authentication 20211.5.1.5 Privacy 20311.5.1.6 Light Weight Solutions 20311.5.1.7 Heterogeneity 20311.5.1.8 Policies 20311.5.2 Security Vulnerabilities 20311.5.2.1 IoT Threats and Vulnerabilities 20511.5.2.2 Cloud-Based Threats 20811.6 Security Countermeasures and Considerations 21411.6.1 Security Countermeasures 21411.6.1.1 Security Awareness and Survey 21411.6.1.2 Security Architecture and Framework 21511.6.1.3 Key Management 21611.6.1.4 Authentication 21711.6.1.5 Trust 21811.6.1.6 Cryptography 21911.6.1.7 Device Security 21911.6.1.8 Identity Management 22011.6.1.9 Risk-Based Security/Risk Assessment 22011.6.1.10 Block Chain–Based Security 22011.6.1.11 Automata-Based Security 22011.6.2 Security Considerations 23411.7 Open Research Issues and Security Challenges 23711.7.1 Security Architecture 23711.7.2 Resource Constraints 23811.7.3 Heterogeneous Data and Devices 23811.7.4 Protocol Interoperability 23811.7.5 Trust Management and Governance 23911.7.6 Fault Tolerance 23911.7.7 Next-Generation 5G Protocol 24011.8 Discussion and Analysis 24011.9 Conclusion 241References 24212 A Novel Usage of Artificial Intelligence and Internet of Things in Remote-Based Healthcare Applications 255V. Arulkumar, D. Mansoor Hussain, S. Sridhar and P. Vivekanandan12.1 Introduction Machine Learning 25612.2 Importance of Machine Learning 25612.2.1 ML vs. Classical Algorithms 25812.2.2 Learning Supervised 25912.2.3 Unsupervised Learning 26112.2.4 Network for Neuralism 26312.2.4.1 Definition of the Neural Network 26312.2.4.2 Neural Network Elements 26312.3 Procedure 26512.3.1 Dataset and Seizure Identification 26512.3.2 System 26512.4 Feature Extraction 26612.5 Experimental Methods 26612.5.1 Stepwise Feature Optimization 26612.5.2 Post-Classification Validation 26812.5.3 Fusion of Classification Methods 26812.6 Experiments 26912.7 Framework for EEG Signal Classification 26912.8 Detection of the Preictal State 27012.9 Determination of the Seizure Prediction Horizon 27112.10 Dynamic Classification Over Time 27212.11 Conclusion 273References 27313 Use of Machine Learning in Healthcare 275V. Lakshman Narayana, R. S. M. Lakshmi Patibandla, B. Tarakeswara Rao and Arepalli Peda Gopi13.1 Introduction 27613.2 Uses of Machine Learning in Pharma and Medicine 27613.2.1 Distinguish Illnesses and Examination 27713.2.2 Drug Discovery and Manufacturing 27713.2.3 Scientific Imaging Analysis 27813.2.4 Twisted Therapy 27813.2.5 AI to Know-Based Social Change 27813.2.6 Perception Wellness Realisms 27913.2.7 Logical Preliminary and Exploration 27913.2.8 Publicly Supported Perceptions Collection 27913.2.9 Better Radiotherapy 28013.2.10 Incidence Forecast 28013.3 The Ongoing Preferences of ML in Human Services 28113.4 The Morals of the Use of Calculations in Medicinal Services 28413.5 Opportunities in Healthcare Quality Improvement 28813.5.1 Variation in Care 28813.5.2 Inappropriate Care 28913.5.3 Prevents Care–Associated Injurious and Death for Carefrontation 28913.5.4 The Fact That People Are Unable to do What They Know Works 28913.5.5 A Waste 29013.6 A Team-Based Care Approach Reduces Waste 29013.7 Conclusion 291References 29214 Methods of MRI Brain Tumor Segmentation 295Amit Verma14.1 Introduction 29514.2 Generative and Descriptive Models 29614.2.1 Region-Based Segmentation 30014.2.2 Generative Model With Weighted Aggregation 30014.3 Conclusion 302References 30315 Early Detection of Type 2 Diabetes Mellitus Using Deep Neural Network–Based Model 305Varun Sapra and Luxmi Sapra15.1 Introduction 30615.2 Data Set 30715.2.1 Data Insights 30815.3 Feature Engineering 31015.4 Framework for Early Detection of Disease 31215.4.1 Deep Neural Network 31315.5 Result 31415.6 Conclusion 315References 31516 A Comprehensive Analysis on Masked Face Detection Algorithms 319Pranjali Singh, Amitesh Garg and Amritpal Singh16.1 Introduction 32016.2 Literature Review 32116.3 Implementation Approach 32516.3.1 Feature Extraction 32516.3.2 Image Processing 32516.3.3 Image Acquisition 32516.3.4 Classification 32516.3.5 MobileNetV2 32616.3.6 Deep Learning Architecture 32616.3.7 LeNet-5, AlexNet, and ResNet-50 32616.3.8 Data Collection 32616.3.9 Development of Model 32716.3.10 Training of Model 32816.3.11 Model Testing 32816.4 Observation and Analysis 32816.4.1 CNN Algorithm 32816.4.2 SSDNETV2 Algorithm 33016.4.3 SVM 33116.5 Conclusion 332References 33317 IoT-Based Automated Healthcare System 335Darpan Anand and Aashish Kumar17.1 Introduction 33517.1.1 Software-Defined Network 33617.1.2 Network Function Virtualization 33717.1.3 Sensor Used in IoT Devices 33817.2 SDN-Based IoT Framework 34117.3 Literature Survey 34317.4 Architecture of SDN-IoT for Healthcare System 34417.5 Challenges 34517.6 Conclusion 347References 347Index 351