Details

<p>Preface xvii</p> <p><b>1 Internet of Medical Things—State-of-the-Art 1<br /></b><i>Kishor Joshi and Ruchi Mehrotra</i></p> <p>1.1 Introduction 2</p> <p>1.2 Historical Evolution of IoT to IoMT 2</p> <p>1.2.1 IoT and IoMT—Market Size 4</p> <p>1.3 Smart Wearable Technology 4</p> <p>1.3.1 Consumer Fitness Smart Wearables 4</p> <p>1.3.2 Clinical-Grade Wearables 5</p> <p>1.4 Smart Pills 7</p> <p>1.5 Reduction of Hospital-Acquired Infections 8</p> <p>1.5.1 Navigation Apps for Hospitals 8</p> <p>1.6 In-Home Segment 8</p> <p>1.7 Community Segment 9</p> <p>1.8 Telehealth and Remote Patient Monitoring 9</p> <p>1.9 IoMT in Healthcare Logistics and Asset Management 12</p> <p>1.10 IoMT Use in Monitoring During COVID-19 13</p> <p>1.11 Conclusion 14</p> <p>References 15</p> <p><b>2 Issues and Challenges Related to Privacy and Security in Healthcare Using IoT, Fog, and Cloud Computing 21<br /></b><i>Hritu Raj, Mohit Kumar, Prashant Kumar, Amritpal Singh and Om Prakash Verma</i></p> <p>2.1 Introduction 22</p> <p>2.2 Related Works 23</p> <p>2.3 Architecture 25</p> <p>2.3.1 Device Layer 25</p> <p>2.3.2 Fog Layer 26</p> <p>2.3.3 Cloud Layer 26</p> <p>2.4 Issues and Challenges 26</p> <p>2.5 Conclusion 29</p> <p>References 30</p> <p><b>3 Study of Thyroid Disease Using Machine Learning 33<br /></b><i>Shanu Verma, Rashmi Popli and Harish Kumar</i></p> <p>3.1 Introduction 34</p> <p>3.2 Related Works 34</p> <p>3.3 Thyroid Functioning 35</p> <p>3.4 Category of Thyroid Cancer 36</p> <p>3.5 Machine Learning Approach Toward the Detection of Thyroid Cancer 37</p> <p>3.5.1 Decision Tree Algorithm 38</p> <p>3.5.2 Support Vector Machines 39</p> <p>3.5.3 Random Forest 39</p> <p>3.5.4 Logistic Regression 39</p> <p>3.5.5 Naïve Bayes 40</p> <p>3.6 Conclusion 41</p> <p>References 41</p> <p><b>4 A Review of Various Security and Privacy Innovations for IoT Applications in Healthcare 43<br /></b><i>Abhishek Raghuvanshi, Umesh Kumar Singh and Chirag Joshi</i></p> <p>4.1 Introduction 44</p> <p>4.1.1 Introduction to IoT 44</p> <p>4.1.2 Introduction to Vulnerability, Attack, and Threat 45</p> <p>4.2 IoT in Healthcare 46</p> <p>4.2.1 Confidentiality 46</p> <p>4.2.2 Integrity 46</p> <p>4.2.3 Authorization 46</p> <p>4.2.4 Availability 47</p> <p>4.3 Review of Security and Privacy Innovations for IoT Applications in Healthcare, Smart Cities, and Smart Homes 48</p> <p>4.4 Conclusion 54</p> <p>References 54</p> <p><b>5 Methods of Lung Segmentation Based on CT Images 59<br /></b><i>Amit Verma and Thipendra P. Singh</i></p> <p>5.1 Introduction 59</p> <p>5.2 Semi-Automated Algorithm for Lung Segmentation 60</p> <p>5.2.1 Algorithm for Tracking to Lung Edge 60</p> <p>5.2.2 Outlining the Region of Interest in CT Images 62</p> <p>5.2.2.1 Locating the Region of Interest 62</p> <p>5.2.2.2 Seed Pixels and Searching Outline 62</p> <p>5.3 Automated Method for Lung Segmentation 63</p> <p>5.3.1 Knowledge-Based Automatic Model for Segmentation 63</p> <p>5.3.2 Automatic Method for Segmenting the Lung CT Image 64</p> <p>5.4 Advantages of Automatic Lung Segmentation Over Manual and Semi-Automatic Methods 64</p> <p>5.5 Conclusion 65</p> <p>References 65</p> <p><b>6 Handling Unbalanced Data in Clinical Images 69<br /></b><i>Amit Verma</i></p> <p>6.1 Introduction 70</p> <p>6.2 Handling Imbalance Data 71</p> <p>6.2.1 Cluster-Based Under-Sampling Technique 72</p> <p>6.2.2 Bootstrap Aggregation (Bagging) 75</p> <p>6.3 Conclusion 76</p> <p>References 76</p> <p><b>7 IoT-Based Health Monitoring System for Speech-Impaired People Using Assistive Wearable Accelerometer 81<br /></b><i>Ishita Banerjee and Madhumathy P.</i></p> <p>7.1 Introduction 82</p> <p>7.2 Literature Survey 84</p> <p>7.3 Procedure 86</p> <p>7.4 Results 93</p> <p>7.5 Conclusion 97</p> <p>References 97</p> <p><b>8 Smart IoT Devices for the Elderly and People with Disabilities 101<br /></b><i>K. N. D. Saile and Kolisetti Navatha</i></p> <p>8.1 Introduction 101</p> <p>8.2 Need for IoT Devices 102</p> <p>8.3 Where Are the IoT Devices Used? 103</p> <p>8.3.1 Home Automation 103</p> <p>8.3.2 Smart Appliances 104</p> <p>8.3.3 Healthcare 104</p> <p>8.4 Devices in Home Automation 104</p> <p>8.4.1 Automatic Lights Control 104</p> <p>8.4.2 Automated Home Safety and Security 104</p> <p>8.5 Smart Appliances 105</p> <p>8.5.1 Smart Oven 105</p> <p>8.5.2 Smart Assistant 105</p> <p>8.5.3 Smart Washers and Dryers 106</p> <p>8.5.4 Smart Coffee Machines 106</p> <p>8.5.5 Smart Refrigerator 106</p> <p>8.6 Healthcare 106</p> <p>8.6.1 Smart Watches 107</p> <p>8.6.2 Smart Thermometer 107</p> <p>8.6.3 Smart Blood Pressure Monitor 107</p> <p>8.6.4 Smart Glucose Monitors 107</p> <p>8.6.5 Smart Insulin Pump 108</p> <p>8.6.6 Smart Wearable Asthma Monitor 108</p> <p>8.6.7 Assisted Vision Smart Glasses 109</p> <p>8.6.8 Finger Reader 109</p> <p>8.6.9 Braille Smart Watch 109</p> <p>8.6.10 Smart Wand 109</p> <p>8.6.11 Taptilo Braille Device 110</p> <p>8.6.12 Smart Hearing Aid 110</p> <p>8.6.13 E-Alarm 110</p> <p>8.6.14 Spoon Feeding Robot 110</p> <p>8.6.15 Automated Wheel Chair 110</p> <p>8.7 Conclusion 112</p> <p>References 112</p> <p><b>9 IoT-Based Health Monitoring and Tracking System for Soldiers 115<br /></b><i>Kavitha N. and Madhumathy P.</i></p> <p>9.1 Introduction 116</p> <p>9.2 Literature Survey 117</p> <p>9.3 System Requirements 118</p> <p>9.3.1 Software Requirement Specification 119</p> <p>9.3.2 Functional Requirements 119</p> <p>9.4 System Design 119</p> <p>9.4.1 Features 121</p> <p>9.4.1.1 On-Chip Flash Memory 122</p> <p>9.4.1.2 On-Chip Static RAM 122</p> <p>9.4.2 Pin Control Block 122</p> <p>9.4.3 UARTs 123</p> <p>9.4.3.1 Features 123</p> <p>9.4.4 System Control 123</p> <p>9.4.4.1 Crystal Oscillator 123</p> <p>9.4.4.2 Phase-Locked Loop 124</p> <p>9.4.4.3 Reset and Wake-Up Timer 124</p> <p>9.4.4.4 Brown Out Detector 125</p> <p>9.4.4.5 Code Security 125</p> <p>9.4.4.6 External Interrupt Inputs 125</p> <p>9.4.4.7 Memory Mapping Control 125</p> <p>9.4.4.8 Power Control 126</p> <p>9.4.5 Real Monitor 126</p> <p>9.4.5.1 GPS Module 126</p> <p>9.4.6 Temperature Sensor 127</p> <p>9.4.7 Power Supply 128</p> <p>9.4.8 Regulator 128</p> <p>9.4.9 LCD 128</p> <p>9.4.10 Heart Rate Sensor 129</p> <p>9.5 Implementation 129</p> <p>9.5.1 Algorithm 130</p> <p>9.5.2 Hardware Implementation 130</p> <p>9.5.3 Software Implementation 131</p> <p>9.6 Results and Discussions 133</p> <p>9.6.1 Heart Rate 133</p> <p>9.6.2 Temperature Sensor 135</p> <p>9.6.3 Panic Button 135</p> <p>9.6.4 GPS Receiver 135</p> <p>9.7 Conclusion 136</p> <p>References 136</p> <p><b>10 Cloud-IoT Secured Prediction System for Processing and Analysis of Healthcare Data Using Machine Learning Techniques 137<br /></b><i>G. K. Kamalam and S. Anitha</i></p> <p>10.1 Introduction 138</p> <p>10.2 Literature Survey 139</p> <p>10.3 Medical Data Classification 141</p> <p>10.3.1 Structured Data 142</p> <p>10.3.2 Semi-Structured Data 142</p> <p>10.4 Data Analysis 142</p> <p>10.4.1 Descriptive Analysis 142</p> <p>10.4.2 Diagnostic Analysis 143</p> <p>10.4.3 Predictive Analysis 143</p> <p>10.4.4 Prescriptive Analysis 143</p> <p>10.5 ML Methods Used in Healthcare 144</p> <p>10.5.1 Supervised Learning Technique 144</p> <p>10.5.2 Unsupervised Learning 145</p> <p>10.5.3 Semi-Supervised Learning 145</p> <p>10.5.4 Reinforcement Learning 145</p> <p>10.6 Probability Distributions 145</p> <p>10.6.1 Discrete Probability Distributions 146</p> <p>10.6.1.1 Bernoulli Distribution 146</p> <p>10.6.1.2 Uniform Distribution 147</p> <p>10.6.1.3 Binomial Distribution 147</p> <p>10.6.1.4 Normal Distribution 148</p> <p>10.6.1.5 Poisson Distribution 148</p> <p>10.6.1.6 Exponential Distribution 149</p> <p>10.7 Evaluation Metrics 150</p> <p>10.7.1 Classification Accuracy 150</p> <p>10.7.2 Confusion Matrix 150</p> <p>10.7.3 Logarithmic Loss 151</p> <p>10.7.4 Receiver Operating Characteristic Curve, or ROC Curve 152</p> <p>10.7.5 Area Under Curve (AUC) 152</p> <p>10.7.6 Precision 153</p> <p>10.7.7 Recall 153</p> <p>10.7.8 F1 Score 153</p> <p>10.7.9 Mean Absolute Error 154</p> <p>10.7.10 Mean Squared Error 154</p> <p>10.7.11 Root Mean Squared Error 155</p> <p>10.7.12 Root Mean Squared Logarithmic Error 155</p> <p>10.7.13 R-Squared/Adjusted R-Squared 156</p> <p>10.7.14 Adjusted R-Squared 156</p> <p>10.8 Proposed Methodology 156</p> <p>10.8.1 Neural Network 158</p> <p>10.8.2 Triangular Membership Function 158</p> <p>10.8.3 Data Collection 159</p> <p>10.8.4 Secured Data Storage 159</p> <p>10.8.5 Data Retrieval and Merging 161</p> <p>10.8.6 Data Aggregation 162</p> <p>10.8.7 Data Partition 162</p> <p>10.8.8 Fuzzy Rules for Prediction of Heart Disease 163</p> <p>10.8.9 Fuzzy Rules for Prediction of Diabetes 164</p> <p>10.8.10 Disease Prediction With Severity and Diagnosis 165</p> <p>10.9 Experimental Results 166</p> <p>10.10 Conclusion 169</p> <p>References 169</p> <p><b>11 CloudIoT-Driven Healthcare: Review, Architecture, Security Implications, and Open Research Issues 173<br /></b><i>Junaid Latief Shah, Heena Farooq Bhat and Asif Iqbal Khan</i></p> <p>11.1 Introduction 174</p> <p>11.2 Background Elements 180</p> <p>11.2.1 Security Comparison Between Traditional and IoT Networks 185</p> <p>11.3 Secure Protocols and Enabling Technologies for CloudIoT Healthcare Applications 187</p> <p>11.3.1 Security Protocols 187</p> <p>11.3.2 Enabling Technologies 188</p> <p>11.4 CloudIoT Health System Framework 191</p> <p>11.4.1 Data Perception/Acquisition 192</p> <p>11.4.2 Data Transmission/Communication 193</p> <p>11.4.3 Cloud Storage and Warehouse 194</p> <p>11.4.4 Data Flow in Healthcare Architecture - A Conceptual Framework 194</p> <p>11.4.5 Design Considerations 197</p> <p>11.5 Security Challenges and Vulnerabilities 199</p> <p>11.5.1 Security Characteristics and Objectives 200</p> <p>11.5.1.1 Confidentiality 202</p> <p>11.5.1.2 Integrity 202</p> <p>11.5.1.3 Availability 202</p> <p>11.5.1.4 Identification and Authentication 202</p> <p>11.5.1.5 Privacy 203</p> <p>11.5.1.6 Light Weight Solutions 203</p> <p>11.5.1.7 Heterogeneity 203</p> <p>11.5.1.8 Policies 203</p> <p>11.5.2 Security Vulnerabilities 203</p> <p>11.5.2.1 IoT Threats and Vulnerabilities 205</p> <p>11.5.2.2 Cloud-Based Threats 208</p> <p>11.6 Security Countermeasures and Considerations 214</p> <p>11.6.1 Security Countermeasures 214</p> <p>11.6.1.1 Security Awareness and Survey 214</p> <p>11.6.1.2 Security Architecture and Framework 215</p> <p>11.6.1.3 Key Management 216</p> <p>11.6.1.4 Authentication 217</p> <p>11.6.1.5 Trust 218</p> <p>11.6.1.6 Cryptography 219</p> <p>11.6.1.7 Device Security 219</p> <p>11.6.1.8 Identity Management 220</p> <p>11.6.1.9 Risk-Based Security/Risk Assessment 220</p> <p>11.6.1.10 Block Chain–Based Security 220</p> <p>11.6.1.11 Automata-Based Security 220</p> <p>11.6.2 Security Considerations 234</p> <p>11.7 Open Research Issues and Security Challenges 237</p> <p>11.7.1 Security Architecture 237</p> <p>11.7.2 Resource Constraints 238</p> <p>11.7.3 Heterogeneous Data and Devices 238</p> <p>11.7.4 Protocol Interoperability 238</p> <p>11.7.5 Trust Management and Governance 239</p> <p>11.7.6 Fault Tolerance 239</p> <p>11.7.7 Next-Generation 5G Protocol 240</p> <p>11.8 Discussion and Analysis 240</p> <p>11.9 Conclusion 241</p> <p>References 242</p> <p><b>12 A Novel Usage of Artificial Intelligence and Internet of Things in Remote-Based Healthcare Applications 255<br /></b><i>V. Arulkumar, D. Mansoor Hussain, S. Sridhar and P. Vivekanandan</i></p> <p>12.1 Introduction Machine Learning 256</p> <p>12.2 Importance of Machine Learning 256</p> <p>12.2.1 ML vs. Classical Algorithms 258</p> <p>12.2.2 Learning Supervised 259</p> <p>12.2.3 Unsupervised Learning 261</p> <p>12.2.4 Network for Neuralism 263</p> <p>12.2.4.1 Definition of the Neural Network 263</p> <p>12.2.4.2 Neural Network Elements 263</p> <p>12.3 Procedure 265</p> <p>12.3.1 Dataset and Seizure Identification 265</p> <p>12.3.2 System 265</p> <p>12.4 Feature Extraction 266</p> <p>12.5 Experimental Methods 266</p> <p>12.5.1 Stepwise Feature Optimization 266</p> <p>12.5.2 Post-Classification Validation 268</p> <p>12.5.3 Fusion of Classification Methods 268</p> <p>12.6 Experiments 269</p> <p>12.7 Framework for EEG Signal Classification 269</p> <p>12.8 Detection of the Preictal State 270</p> <p>12.9 Determination of the Seizure Prediction Horizon 271</p> <p>12.10 Dynamic Classification Over Time 272</p> <p>12.11 Conclusion 273</p> <p>References 273</p> <p><b>13 Use of Machine Learning in Healthcare 275<br /></b><i>V. Lakshman Narayana, R. S. M. Lakshmi Patibandla, B. Tarakeswara Rao and Arepalli Peda Gopi</i></p> <p>13.1 Introduction 276</p> <p>13.2 Uses of Machine Learning in Pharma and Medicine 276</p> <p>13.2.1 Distinguish Illnesses and Examination 277</p> <p>13.2.2 Drug Discovery and Manufacturing 277</p> <p>13.2.3 Scientific Imaging Analysis 278</p> <p>13.2.4 Twisted Therapy 278</p> <p>13.2.5 AI to Know-Based Social Change 278</p> <p>13.2.6 Perception Wellness Realisms 279</p> <p>13.2.7 Logical Preliminary and Exploration 279</p> <p>13.2.8 Publicly Supported Perceptions Collection 279</p> <p>13.2.9 Better Radiotherapy 280</p> <p>13.2.10 Incidence Forecast 280</p> <p>13.3 The Ongoing Preferences of ML in Human Services 281</p> <p>13.4 The Morals of the Use of Calculations in Medicinal Services 284</p> <p>13.5 Opportunities in Healthcare Quality Improvement 288</p> <p>13.5.1 Variation in Care 288</p> <p>13.5.2 Inappropriate Care 289</p> <p>13.5.3 Prevents Care–Associated Injurious and Death for Carefrontation 289</p> <p>13.5.4 The Fact That People Are Unable to do What They Know Works 289</p> <p>13.5.5 A Waste 290</p> <p>13.6 A Team-Based Care Approach Reduces Waste 290</p> <p>13.7 Conclusion 291</p> <p>References 292</p> <p><b>14 Methods of MRI Brain Tumor Segmentation 295<br /></b><i>Amit Verma</i></p> <p>14.1 Introduction 295</p> <p>14.2 Generative and Descriptive Models 296</p> <p>14.2.1 Region-Based Segmentation 300</p> <p>14.2.2 Generative Model With Weighted Aggregation 300</p> <p>14.3 Conclusion 302</p> <p>References 303</p> <p><b>15 Early Detection of Type 2 Diabetes Mellitus Using Deep Neural Network–Based Model 305<br /></b><i>Varun Sapra and Luxmi Sapra</i></p> <p>15.1 Introduction 306</p> <p>15.2 Data Set 307</p> <p>15.2.1 Data Insights 308</p> <p>15.3 Feature Engineering 310</p> <p>15.4 Framework for Early Detection of Disease 312</p> <p>15.4.1 Deep Neural Network 313</p> <p>15.5 Result 314</p> <p>15.6 Conclusion 315</p> <p>References 315</p> <p><b>16 A Comprehensive Analysis on Masked Face Detection Algorithms 319<br /></b><i>Pranjali Singh, Amitesh Garg and Amritpal Singh</i></p> <p>16.1 Introduction 320</p> <p>16.2 Literature Review 321</p> <p>16.3 Implementation Approach 325</p> <p>16.3.1 Feature Extraction 325</p> <p>16.3.2 Image Processing 325</p> <p>16.3.3 Image Acquisition 325</p> <p>16.3.4 Classification 325</p> <p>16.3.5 MobileNetV2 326</p> <p>16.3.6 Deep Learning Architecture 326</p> <p>16.3.7 LeNet-5, AlexNet, and ResNet-50 326</p> <p>16.3.8 Data Collection 326</p> <p>16.3.9 Development of Model 327</p> <p>16.3.10 Training of Model 328</p> <p>16.3.11 Model Testing 328</p> <p>16.4 Observation and Analysis 328</p> <p>16.4.1 CNN Algorithm 328</p> <p>16.4.2 SSDNETV2 Algorithm 330</p> <p>16.4.3 SVM 331</p> <p>16.5 Conclusion 332</p> <p>References 333</p> <p><b>17 IoT-Based Automated Healthcare System 335<br /></b><i>Darpan Anand and Aashish Kumar</i></p> <p>17.1 Introduction 335</p> <p>17.1.1 Software-Defined Network 336</p> <p>17.1.2 Network Function Virtualization 337</p> <p>17.1.3 Sensor Used in IoT Devices 338</p> <p>17.2 SDN-Based IoT Framework 341</p> <p>17.3 Literature Survey 343</p> <p>17.4 Architecture of SDN-IoT for Healthcare System 344</p> <p>17.5 Challenges 345</p> <p>17.6 Conclusion 347</p> <p>References 347</p> <p>Index 351</p>

<p><b> Rohit Tanwar, PhD</b> (Kurukshetra University, Kurukshetra, India) is an assistant professor in the School of Computer Science at UPES Dehradun, India. </p> <p><b> S. Balamurugan, PhD,</b> 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. <p><b> R. K. Saini, PhD</b> (DIT University, Dehradun, India) is an assistant professor in the Department of Computer Science & Applications at DIT University, Dehradun (Uttarakhand). <p><b> Vishal Bharti, PhD</b> 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. <p><b>Premkumar Chithaluru, PhD</b> is an assistant professor in the Department of SCS at the University of Petroleum and Energy Studies (UPES), Dehradun, India.

<p><b>This book offers a complete package involving the incubation of machine learning, AI, and IoT in healthcare that is beneficial for researchers, healthcare professionals, scientists, and technologists.</b></p> <p>The applications and challenges of machine learning and artificial intelligence in the Internet of Things (IoT) for healthcare applications are comprehensively covered in this book. <p>IoT generates big data of varying data quality; intelligent processing and analysis of this big data are the keys to developing smart IoT applications, thereby making space for machine learning (ML) applications. Due to its computational tools that can substitute for human intelligence in the performance of certain tasks, artificial intelligence (AI) makes it possible for machines to learn from experience, adjust to new inputs and perform human-like tasks. Since IoT platforms provide an interface to gather data from various devices, they can easily be deployed into AI/ML systems. The value of AI in this context is its ability to quickly mesh insights from data and automatically identify patterns and detect anomalies in the data that smart sensors and devices generate—information such as temperature, pressure, humidity, air quality, vibration, and sound—that can be really helpful to rapid diagnosis. <p><b>Audience</b> <p>This book will be of interest to researchers in artificial intelligence, the Internet of Things, machine learning as well as information technologists working in the healthcare sector.

US