Emerging Technologies for Healthcare

Monika Mangla, received her PhD from Thapar Institute of Engineering & Technology, Patiala, Punjab, in 2019. Currently, she is working as an assistant professor in the Department of Computer Engineering at Lokmanya Tilak College of Engineering (LTCoE), Navi Mumbai.Nonita Sharma is working as assistant professor, National Institute of Technology, Jalandhar. She received the B. Tech degree in Computer Science Engineering in 2002, the M. Tech degree in Computer Science engineering in 2004, and her PhD degree in Wireless Sensor Network from the National Institute of Technology, Jalandhar, India in 2017. Poonam Mittal received her PhD from J.C Bose University of Science and Technology YMCA, Faridabad, India, in 2019. Currently, she is working as an assistant professor in the Department of Computer Engineering at J.C Bose University of Science and Technology YMCA, Faridabad, India. Vaishali Mehta Wadhwa obtained her PhD in Facility Location Problems from Thapar University. Her research interests include approximation algorithms, location modeling, IoT, cloud computing and machine learning. She has multiple articles and 2 patents to her name. Thirunavakkarasu K. is a distinguished academician with over twenty-two years of experience in teaching and working in the software industry. Curently, he is heading the Department of BCA and Specialization at Galgotias University. He has done Bachelor in computer science from the University of Madras in 1994 and received 3 master’s degrees in computer science. Shahnawaz Khan is an assistant professor and serving as Secretary-General of Scientific Research Council at University College of Bahrain. He holds a PhD (Computer Science) from the Indian Institute of Technology (BHU), India.

• Preface xviiPart I: Basics of Smart Healthcare 11 An Overview of IoT in Health Sectors 3Sheeba P. S.1.1 Introduction 31.2 Influence of IoT in Healthcare Systems 61.2.1 Health Monitoring 61.2.2 Smart Hospitals 71.2.3 Tracking Patients 71.2.4 Transparent Insurance Claims 81.2.5 Healthier Cities 81.2.6 Research in Health Sector 81.3 Popular IoT Healthcare Devices 91.3.1 Hearables 91.3.2 Moodables 91.3.3 Ingestible Sensors 91.3.4 Computer Vision 101.3.5 Charting in Healthcare 101.4 Benefits of IoT 101.4.1 Reduction in Cost 101.4.2 Quick Diagnosis and Improved Treatment 101.4.3 Management of Equipment and Medicines 111.4.4 Error Reduction 111.4.5 Data Assortment and Analysis 111.4.6 Tracking and Alerts 111.4.7 Remote Medical Assistance 111.5 Challenges of IoT 121.5.1 Privacy and Data Security 121.5.2 Multiple Devices and Protocols Integration 121.5.3 Huge Data and Accuracy 121.5.4 Underdeveloped 121.5.5 Updating the Software Regularly 121.5.6 Global Healthcare Regulations 131.5.7 Cost 131.6 Disadvantages of IoT 131.6.1 Privacy 131.6.2 Access by Unauthorized Persons 131.7 Applications of IoT 131.7.1 Monitoring of Patients Remotely 131.7.2 Management of Hospital Operations 141.7.3 Monitoring of Glucose 141.7.4 Sensor Connected Inhaler 151.7.5 Interoperability 151.7.6 Connected Contact Lens 151.7.7 Hearing Aid 161.7.8 Coagulation of Blood 161.7.9 Depression Detection 161.7.10 Detection of Cancer 171.7.11 Monitoring Parkinson Patient 171.7.12 Ingestible Sensors 181.7.13 Surgery by Robotic Devices 181.7.14 Hand Sanitizing 181.7.15 Efficient Drug Management 191.7.16 Smart Sole 191.7.17 Body Scanning 191.7.18 Medical Waste Management 201.7.19 Monitoring the Heart Rate 201.7.20 Robot Nurse 201.8 Global Smart Healthcare Market 211.9 Recent Trends and Discussions 221.10 Conclusion 23References 232 IoT-Based Solutions for Smart Healthcare 25Pankaj Jain, Sonia F Panesar, Bableen Flora Talwar and Mahesh Kumar Sah2.1 Introduction 262.1.1 Process Flow of Smart Healthcare System 262.1.1.1 Data Source 262.1.1.2 Data Acquisition 272.1.1.3 Data Pre-Processing 272.1.1.4 Data Segmentation 282.1.1.5 Feature Extraction 282.1.1.6 Data Analytics 282.2 IoT Smart Healthcare System 292.2.1 System Architecture 302.2.1.1 Stage 1: Perception Layer 302.2.1.2 Stage 2: Network Layer 322.2.1.3 Stage 3: Data Processing Layer 322.2.1.4 Stage 4: Application Layer 332.3 Locally and Cloud-Based IoT Architecture 332.3.1 System Architecture 332.3.1.1 Body Area Network (BAN) 342.3.1.2 Smart Server 342.3.1.3 Care Unit 352.4 Cloud Computing 352.4.1 Infrastructure as a Service (IaaS) 372.4.2 Platform as a Service (PaaS) 372.4.3 Software as a Service (SaaS) 372.4.4 Types of Cloud Computing 372.4.4.1 Public Cloud 372.4.4.2 Private Cloud 382.4.4.3 Hybrid Cloud 382.4.4.4 Community Cloud 382.5 Outbreak of Arduino Board 382.6 Applications of Smart Healthcare System 392.6.1 Disease Diagnosis and Treatment 412.6.2 Health Risk Monitoring 422.6.3 Voice Assistants 422.6.4 Smart Hospital 422.6.5 Assist in Research and Development 432.7 Smart Wearables and Apps 432.8 Deep Learning in Biomedical 442.8.1 Deep Learning 462.8.2 Deep Neural Network Architecture 472.8.3 Deep Learning in Bioinformatic 492.8.4 Deep Learning in Bioimaging 492.8.5 Deep Learning in Medical Imaging 502.8.6 Deep Learning in Human-Machine Interface 532.8.7 Deep Learning in Health Service Management 532.9 Conclusion 55References 553 QLattice Environment and Feyn QGraph Models—A New Perspective Toward Deep Learning 69Vinayak Bharadi3.1 Introduction 703.1.1 Machine Learning Models 703.2 Machine Learning Model Lifecycle 713.2.1 Steps in Machine Learning Lifecycle 713.2.1.1 Data Preparation 723.2.1.2 Building the Machine Learning Model 723.2.1.3 Model Training 723.2.1.4 Parameter Selection 723.2.1.5 Transfer Learning 733.2.1.6 Model Verification 733.2.1.7 Model Deployment 743.2.1.8 Monitoring 743.3 A Model Deployment in Keras 753.3.1 Pima Indian Diabetes Dataset 753.3.2 Multi-Layered Perceptron Implementation in Keras 763.3.3 Multi-Layered Perceptron Implementation With Dropout and Added Noise 773.4 QLattice Environment 803.4.1 Feyn Models 803.4.1.1 Semantic Types 823.4.1.2 Interactions 833.4.1.3 Generating QLattice 833.4.2 QLattice Workflow 833.4.2.1 Preparing the Data 843.4.2.2 Connecting to QLattice 843.4.2.3 Generating QGraphs 843.4.2.4 Fitting, Sorting, and Updating QGraphs 853.4.2.5 Model Evaluation 863.5 Using QLattice Environment and QGraph Models for COVID-19 Impact Prediction 87References 914 Sensitive Healthcare Data: Privacy and Security Issues and Proposed Solutions 93Abhishek Vyas, Satheesh Abimannan and Ren-Hung Hwang4.1 Introduction 944.1.1 Types of Technologies Used in Healthcare Industry 944.1.2 Technical Differences Between Security and Privacy 954.1.3 HIPAA Compliance 954.2 Medical Sensor Networks/Medical Internet of Things/Body Area Networks/WBANs 974.2.1 Security and Privacy Issues in WBANs/WMSNs/WMIOTs 1014.3 Cloud Storage and Computing on Sensitive Healthcare Data 1124.3.1 Security and Privacy in Cloud Computing and Storage for Sensitive Healthcare Data 1144.4 Blockchain for Security and Privacy Enhancement in Sensitive Healthcare Data 1194.5 Artificial Intelligence, Machine Learning, and Big Data in Healthcare and Its Efficacy in Security and Privacy of Sensitive Healthcare Data 1224.5.1 Differential Privacy for Preserving Privacy of Big Medical Healthcare Data and for Its Analytics 1244.6 Conclusion 124References 125Part II: Employment of Machine Learning in Disease Detection 1295 Diabetes Prediction Model Based on Machine Learning 131Ayush Kumar Gupta, Sourabh Yadav, Priyanka Bhartiya and Divesh Gupta5.1 Introduction 1315.2 Literature Review 1335.3 Proposed Methodology 1355.3.1 Data Accommodation 1355.3.1.1 Data Collection 1355.3.1.2 Data Preparation 1365.3.2 Model Training 1385.3.2.1 K Nearest Neighbor Classification Technique 1395.3.2.2 Support Vector Machine 1405.3.2.3 Random Forest Algorithm 1425.3.2.4 Logistic Regression 1445.3.3 Model Evaluation 1455.3.4 User Interaction 1455.3.4.1 User Inputs 1465.3.4.2 Validation Using Classifier Model 1465.3.4.3 Truth Probability 1465.4 System Implementation 1475.5 Conclusion 153References 1536 Lung Cancer Detection Using 3D CNN Based on Deep Learning 157Siddhant Panda, Vasudha Chhetri, Vikas Kumar Jaiswal and Sourabh Yadav6.1 Introduction 1576.2 Literature Review 1596.3 Proposed Methodology 1616.3.1 Data Handling 1616.3.1.1 Data Gathering 1616.3.1.2 Data Pre-Processing 1626.3.2 Data Visualization and Data Split 1626.3.2.1 Data Visualization 1626.3.2.2 Data Split 1626.3.3 Model Training 1636.3.3.1 Training Neural Network 1636.3.3.2 Model Optimization 1666.4 Results and Discussion 1686.4.1 Gathering and Pre-Processing of Data 1696.4.1.1 Gathering and Handling Data 1696.4.1.2 Pre-Processing of Data 1706.4.2 Data Visualization 1716.4.2.1 Resampling 1736.4.2.2 3D Plotting Scan 1736.4.2.3 Lung Segmentation 1736.4.3 Training and Testing of Data in 3D Architecture 1756.5 Conclusion 178References 1787 Pneumonia Detection Using CNN and ANN Based on Deep Learning Approach 181Priyanka Bhartiya, Sourabh Yadav, Ayush Gupta and Divesh Gupta7.1 Introduction 1827.2 Literature Review 1837.3 Proposed Methodology 1857.3.1 Data Gathering 1857.3.1.1 Data Collection 1857.3.1.2 Data Pre-Processing 1867.3.1.3 Data Split 1867.3.2 Model Training 1877.3.2.1 Training of Convolutional Neural Network 1897.3.2.2 Training of Artificial Neural Network 1917.3.3 Model Fitting 1937.3.3.1 Fit Generator 1937.3.3.2 Validation of Accuracy and Loss Plot 1937.3.3.3 Testing and Prediction 1937.4 System Implementation 1947.4.1 Data Gathering, Pre-Processing, and Split 1947.4.1.1 Data Gathering 1947.4.1.2 Data Pre-Processing 1957.4.1.3 Data Split 1967.4.2 Model Building 1967.4.3 Model Fitting 1977.4.3.1 Fit Generator 1977.4.3.2 Validation of Accuracy and Loss Plot 1977.4.3.3 Testing and Prediction 1987.5 Conclusion 199References 1998 Personality Prediction and Handwriting Recognition Using Machine Learning 203Vishal Patil and Harsh Mathur8.1 Introduction to the System 2048.1.1 Assumptions and Limitations 2068.1.1.1 Assumptions 2068.1.1.2 Limitations 2068.1.2 Practical Needs 2068.1.3 Non-Functional Needs 2068.1.4 Specifications for Hardware 2078.1.5 Specifications for Applications 2078.1.6 Targets 2078.1.7 Outcomes 2078.2 Literature Survey 2088.2.1 Computerized Human Behavior Identification Through Handwriting Samples 2088.2.2 Behavior Prediction Through Handwriting Analysis 2098.2.3 Handwriting Sample Analysis for a Finding of Personality Using Machine Learning Algorithms 2098.2.4 Personality Detection Using Handwriting Analysis 2108.2.5 Automatic Predict Personality Based on Structure of Handwriting 2108.2.6 Personality Identification Through Handwriting Analysis: A Review 2108.2.7 Text Independent Writer Identification Using Convolutional Neural Network 2108.2.8 Writer Identification Using Machine Learning Approaches 2118.2.9 Writer Identification from HandwrittenText Lines 2118.3 Theory 2128.3.1 Pre-Processing 2128.3.2 Personality Analysis 2158.3.3 Personality Characteristics 2168.3.4 Writer Identification 2178.3.5 Features Used 2198.4 Algorithm To Be Used 2208.5 Proposed Methodology 2248.5.1 System Flow 2258.6 Algorithms vs. Accuracy 2268.6.1 Implementation 2288.7 Experimental Results 2318.8 Conclusion 2328.9 Conclusion and Future Scope 232Acknowledgment 232References 2339 Risk Mitigation in Children With Autism Spectrum Disorder Using Brain Source Localization 237Joy Karan Singh, Deepti Kakkar and Tanu Wadhera9.1 Introduction 2389.2 Risk Factors Related to Autism 2399.2.1 Assistive Technologies for Autism 2409.2.2 Functional Connectivity as a Biomarker for Autism 2419.2.3 Early Intervention and Diagnosis 2429.3 Materials and Methodology 2439.3.1 Subjects 2439.3.2 Methods 2439.3.3 Data Acquisition and Processing 2439.3.4 sLORETA as a Diagnostic Tool 2449.4 Results and Discussion 2459.5 Conclusion and Future Scope 247References 24710 Predicting Chronic Kidney Disease Using Machine Learning 251Monika Gupta and Parul Gupta10.1 Introduction 25210.2 Machine Learning Techniques for Prediction of Kidney Failure 25310.2.1 Analysis and Empirical Learning 25410.2.2 Supervised Learning 25510.2.3 Unsupervised Learning 25610.2.3.1 Understanding and Visualization 25710.2.3.2 Odd Detection 25710.2.3.3 Object Completion 25810.2.3.4 Information Acquisition 25810.2.3.5 Data Compression 25810.2.3.6 Capital Market 25810.2.4 Classification 25910.2.4.1 Training Process 26010.2.4.2 Testing Process 26010.2.5 Decision Tree 26110.2.6 Regression Analysis 26310.2.6.1 Logistic Regression 26310.2.6.2 Ordinal Logistic Regression 26510.2.6.3 Estimating Parameters 26610.2.6.4 Multivariate Regression 26810.3 Data Sources 26910.4 Data Analysis 27210.5 Conclusion 27410.6 Future Scope 274References 274Part III: Advanced Applications of Machine Learning in Healthcare 27911 Behavioral Modeling Using Deep Neural Network Framework for ASD Diagnosis and Prognosis 281Tanu Wadhera, Deepti Kakkar and Rajneesh Rani11.1 Introduction 28211.2 Automated Diagnosis of ASD 28411.2.1 Deep Learning 28911.2.2 Deep Learning in ASD 29011.2.3 Transfer Learning Approach 29011.3 Purpose of the Chapter 29211.4 Proposed Diagnosis System 29311.5 Conclusion 294References 29512 Random Forest Application of Twitter Data Sentiment Analysis in Online Social Network Prediction 299Arnav Munshi, M. Arvindhan and Thirunavukkarasu K.12.1 Introduction 30012.1.1 Motivation 30012.1.2 Domain Introduction 30012.2 Literature Survey 30212.3 Proposed Methodology 30412.4 Implementation 31112.5 Conclusion 311References 31113 Remedy to COVID-19: Social Distancing Analyzer 315Sourabh Yadav13.1 Introduction 31513.2 Literature Review 31813.3 Proposed Methodology 32113.3.1 Person Detection 32113.3.1.1 Frame Creation 32413.3.1.2 Contour Detection 32513.3.1.3 Matching with COCO Model 32613.3.2 Distance Calculation 32613.3.2.1 Calculation of Centroid 32613.3.2.2 Distance Among Adjacent Centroids 32713.4 System Implementation 32813.5 Conclusion 333References 33414 IoT-Enabled Vehicle Assistance System of Highway Resourcing for Smart Healthcare and Sustainability 337Shubham Joshi and Radha Krishna Rambola14.1 Introduction 33814.2 Related Work 34014.2.1 Adoption of IoT in Vehicle to Ensure Driver Safety 34114.2.2 IoT in Healthcare System 34114.2.3 The Technology Used in Assistance Systems 34314.2.3.1 Adaptive Cruise Control (ACC) 34314.2.3.2 Lane Departure Warning 34314.2.3.3 Parking Assistance 34314.2.3.4 Collision Avoidance System 34314.2.3.5 Driver Drowsiness Detection 34414.2.3.6 Automotive Night Vision 34414.3 Objectives, Context, and Ethical Approval 34414.4 Technical Background 34514.4.1 IoT With Health 34514.4.2 Machine-to-Machine (M2M) Communication 34514.4.3 Device-to-Device (D2D) Communication 34514.4.4 Wireless Sensor Network 34614.4.5 Crowdsensing 34614.5 IoT Infrastructural Components for Vehicle Assistance System 34614.5.1 Communication Technology 34614.5.2 Sensor Network 34714.5.3 Infrastructural Component 34814.5.4 Human Health Detection by Sensors 34814.6 IoT-Enabled Vehicle Assistance System of Highway Resourcing for Smart Healthcare and Sustainability 34914.7 Challenges in Implementation 35314.8 Conclusion 353References 35415 Aids of Machine Learning for Additively Manufactured Bone Scaffold 359Nimisha Rahul Shirbhate and Sanjay Bokade15.1 Introduction 36015.1.1 Bone Scaffold 36015.1.2 Bone Grafting 36215.1.3 Comparison Bone Grafting and Bone Scaffold 36315.2 Research Background 36415.3 Statement of Problem 36415.4 Research Gap 36515.5 Significance of Research 36615.6 Outline of Research Methodology 36615.6.1 Customized Design of Bone Scaffold 36615.6.2 Manufacturing Methods and Biocompatible Material 36715.6.2.1 Conventional Scaffold Fabrication 36815.6.2.2 Additive Manufacturing 36915.6.2.3 Application of Additive Manufacturing/3D Printing in Healthcare 37015.6.2.4 Automated Process Monitoring in 3D Printing Using Supervised Machine Learning 37615.7 Conclusion 377References 377Index 381