5G IoT and Edge Computing for Smart Healthcare (Intelligent Data-Centric Systems)

Description

5G IoT and Edge Computing for Smart Healthcare addresses the importance of a 5G IoT and Edge-Cognitive-Computing-based system for the successful implementation and realization of a smart-healthcare system. The book provides insights on 5G technologies, along with intelligent processing algorithms/processors that have been adopted for processing the medical data that would assist in addressing the challenges in computer-aided diagnosis and clinical risk analysis on a real-time basis. Each chapter is self-sufficient, solving real-time problems through novel approaches that help the audience acquire the right knowledge. With the progressive development of medical and communication - computer technologies, the healthcare system has seen a tremendous opportunity to support the demand of today's new requirements. Front Cover 5G IoT and Edge Computing for Smart Healthcare Copyright Page Contents List of contributors 1 Edge-IoMT-based enabled architecture for smart healthcare system 1.1 Introduction 1.2 Applications of an IoMT-based system in the healthcare industry 1.3 Application of edge computing in smart healthcare systems 1.4 Challenges of using edge computing with IoMT-based system in smart healthcare system 1.5 The framework for edge-IoMT-based smart healthcare system 1.6 Case study for the application of edge-IoMT-based systems enabled for the diagnosis of diabetes mellitus 1.6.1 Experimental results 1.7 Future prospects of edge computing for internet of medical things 1.8 Conclusions and future research directions References 2 Physical layer architecture of 5G enabled IoT/IoMT system 2.1 Architecture of IoT/IoMT system 2.1.1 Sensor layer 2.1.2 Gateway layer 2.1.3 Network layer 2.1.4 Visualization layer 2.2 Consideration of uplink healthcare IoT system relying on NOMA 2.2.1 Introduction 2.2.2 System model 2.2.3 Outage probability for UL NOMA 2.2.3.1 Outage probability of x1 2.2.3.2 Outage probability of X2 2.2.3.3 Asymptotic 2.2.4 Ergodic capacity of UL NOMA 2.2.5 Numerical results and discussions 2.3 Conclusions References 3 HetNet/M2M/D2D communication in 5G technologies 3.1 Introduction 3.2 Heterogenous networks in the era of 5G 3.2.1 5G mobile communication standards and enhanced features 3.2.2 5G heterogeneous network architecture 3.2.3 Intelligent software defined network framework of 5G HetNets 3.2.4 Next-Gen 5G wireless network 3.2.5 Internet of Things toward 5G and heterogenous wireless networks 3.2.6 5G-HetNet H-CRAN fronthaul and TWDM-PON backhaul: QoS-aware virtualization for resource management 3.2.7 Spectrum allocation and user association in 5G HetNet mmWave communication: a coordinated framework 3.2.8 Diverse service provisioning in 5G and beyond: an intelligent self-sustained radio access network slicing framework 3.3 Device-to-Device communication in 5G HetNets 3.4 Machine-to-Machine communication in 5G HetNets 3.4.1 Machine-to-Machine communication in 5G: state of the art architecture, recent advances and challenges 3.4.2 Recent advancement in the Internet of Things related standard: oneM2M perspective 3.4.2.1 Advantages of oneM2M 3.4.2.2 OneM2M protocols 3.4.2.3 OneM2M standard platform: a unified common service-oriented communication framework 3.4.3 M2M traffic in 5G HetNets 3.4.4 Distributed gateway selection for M2M communication cognitive 5G5G networks 3.4.5 Algorithm for clusterization, aggregation, and prioritization of M2M devices in 5G5G HetNets 3.5 Heterogeneity and interoperability 3.5.1 User interoperability 3.5.1.1 Locating the device through identification and classification 3.5.1.2 Syntactic and semantic interoperability for interconnecting devices 3.5.2 Device interoperability 3.6 Research issues and challenges 3.6.1 Resource allocation 3.6.2 Interference management 3.6.3 Power allocation 3.6.4 User association 3.6.5 Computational complexity and multiaccess edge computing 3.6.6 Current research in HetNet based on various technologies 3.7 Smart healthcare using 5G5G Inter of Things: a case-study 3.7.1 Mobile cellular network architecture: 5th generation 3.7.1.1 5G5G system architecture 3.7.1.2 Master core technology 3.7.2 ZigBee IP 3.7.3 Healthcare system architecture using wireless sensor network and mobile cellular network 3.7.3.1 System protocol 3.7.3.2 Data transmission by 5G terminal in ZigBee network 3.7.3.3 Data transmission through 5G terminal by ZigBee network 3.8 Conclusions References 4 An overview of low power hardware architecture for edge computing devices 4.1 Introduction 4.2 Basic concepts of cloud, fog and edge computing infrastructure 4.2.1 Role of edge computing in Internet of Things 4.2.2 Edge intelligence and 5G in Internet of Things based smart healthcare system 4.3 Low power hardware architecture for edge computing devices 4.3.1 Objectives of hardware development in edge computing 4.3.2 System architecture 4.3.3 Central processing unit architecture 4.3.4 Input–output architecture 4.3.5 Power consumption 4.3.6 Data processing and algorithmic optimization 4.4 Examples of edge computing devices 4.5 Edge computing for intelligent healthcare applications 4.5.1 Edge computing for healthcare applications 4.5.2 Advantages of edge computing for healthcare applications 4.5.3 Implementation challenges of edge computing in healthcare systems 4.5.4 Applications of edge computing based healthcare system 4.5.5 Patient data security in edge computing 4.6 Impact of edge computing, Internet of Things and 5G on smart healthcare systems 4.7 Conclusion and future scope of research References 5 Convergent network architecture of 5G and MEC 5.1 Introduction 5.2 Technical overview on 5G network with MEC 5.2.1 5G with multi-access edge computing (MEC): a technology enabler 5.2.2 Application splitting in MEC 5.2.3 Layered service oriented architecture for 5G MEC 5.3 Convergent network architecture for 5G with MEC 5.4 Current research in 5G with MEC 5.5 Challenges and issues in implementation of MEC 5.5.1 Communication and computation perspective 5.5.1.1 MEC service orchestration and programmability 5.5.1.2 MEC service continuity and mobility and service enhancements 5.5.1.3 MEC security and privacy 5.5.1.4 Standardization of protocols 5.5.1.5 MEC service monetization 5.5.1.6 Edge cloud infrastructure and resource management 5.5.1.7 Mobile data offloading 5.5.2 Application perspective 5.5.2.1 Industrial IoT application in 5G 5.5.2.2 Large scale healthcare and big data management 5.5.2.3 Integration of AI and 5G for MEC enabled healthcare application 5.6 Conclusions References 6 An efficient lightweight speck technique for edge-IoT-based smart healthcare systems 6.1 Introduction 6.2 The Internet of Things in smart healthcare system 6.2.1 Support for diagnosis treatment 6.2.2 Management of diseases 6.2.3 Risk monitoring and prevention of disease 6.2.4 Virtual support 6.2.5 Smart healthcare hospitals support 6.3 Application of edge computing in smart healthcare system 6.4 Application of encryptions algorithm in smart healthcare system 6.4.1 Speck encryption 6.5 Results and discussion 6.6 Conclusions and future research directions References 7 Deep learning approaches for the cardiovascular disease diagnosis using smartphone 7.1 Introduction 7.2 Disease diagnosis and treatment 7.3 Deep learning approaches for the disease diagnosis and treatment 7.3.1 Artificial neural networks 7.3.2 Deep learning 7.3.3 Convolutional Neural Networks 7.4 Case study of a smartphone-based Atrial Fibrillation Detection 7.4.1 Smartphone data acquisition 7.4.2 Biomedical signal processing 7.4.3 Prediction and classification 7.4.4 Experimental data 7.4.5 Performance evaluation measures 7.4.6 Experimental results 7.5 Discussion 7.6 Conclusion References 8 Advanced pattern recognition tools for disease diagnosis 8.1 Introduction 8.2 Disease diagnosis 8.3 Pattern recognition tools for the disease diagnosis 8.3.1 Artificial neural networks 8.3.2 K-nearest neighbor 8.3.3 Support vector machines 8.3.4 Random forests 8.3.5 Bagging 8.3.6 AdaBoost 8.3.7 XGBoost 8.3.8 Deep learning 8.3.9 Convolutional neural network 8.3.10 Transfer learning 8.4 Case study of COVID-19 detection 8.4.1 Experimental data 8.4.2 Performance evaluation measures 8.4.3 Feature extraction using transfer learning 8.4.4 Experimental results 8.5 Discussion 8.6 Conclusions References 9 Brain-computer interface in Internet of Things environment 9.1 Introduction 9.1.1 Components of BCI 9.1.2 Types of BCI 9.1.3 How does BCI work? 9.1.4 Key features of BCI 9.1.5 Applications 9.2 Brain-computer interface classification 9.2.1 Noninvasive BCI 9.2.2 Semiinvasive or partially invasive BCI 9.2.3 Invasive BCI 9.3 Key elements of BCI 9.3.1 Signal acquisition 9.3.2 Preprocessing or signal enhancement 9.3.3 Feature extraction 9.3.4 Classification stage 9.3.5 Feature translation or control interface stage 9.3.6 Device output or feedback stage 9.4 Modalities of BCI 9.4.1 Electrical and magnetic signals 9.4.1.1 Intracortical electrode array 9.4.1.2 Electrocorticography 9.4.1.3 Electroencephalography 9.4.1.4 Magnetoencephalography 9.4.2 Metabolic signals 9.4.2.1 Positron emission tomography 9.4.2.2 Functional magnetic resonance imaging 9.4.2.3 Functional near-infrared spectroscopy 9.5 Computational intelligence methods in BCI/BMI 9.5.1 State of the prior art 9.5.1.1 Preprocessing 9.5.1.2 Feature extraction 9.5.1.3 Feature classification 9.5.1.4 Performance evaluation of BCI systems 9.6 Online and offline BCI applications 9.7 BCI for the Internet of Things 9.8 Secure brain-brain communication 9.8.1 Edge computing for brain–to–things 9.9 Summary and conclusion 9.10 Future research directions and challenges Abbreviations References 10 Early detection of COVID-19 pneumonia based on ground-glass opacity (GGO) features of computerized tomography (CT) angio... 10.1 Introduction 10.2 Background 10.2.1 Ground-glass opacity (GGO) 10.2.2 Support vector machine (SVM) 10.2.3 Histogram of oriented gradients (HOG) algorithm 10.2.4 Convolutional neural network (CNN) 10.2.4.1 Rectified Linear Unit (ReLU) activation function 10.2.5 Literature 10.3 Materials and methods 10.3.1 Dataset description 10.3.2 Methodology 10.3.2.1 Data preprocessing 10.3.2.2 The development of convolution neural network (CNN) model 10.3.2.3 The development of cascade classifier model 10.4 Results and analysis 10.4.1 Test results of the COVID-19 pneumonia detection system 10.4.2 Analysis of the test results 10.5 Conclusion References 11 Applications of wearable technologies in healthcare: an analytical study 11.1 Introduction 11.2 Application of wearable devices 11.3 The importance of wearable technology in healthcare 11.3.1 Personalization 11.3.2 Remote patient monitoring 11.3.3 Early diagnosis 11.3.4 Medication adherence 11.3.5 Complete information 11.3.6 Cost savings 11.4 Current scenario of wearable computing 11.5 The wearable working procedure 11.6 Wearables in healthcare 11.6.1 Weight loss 11.6.2 Medication tracking 11.6.3 Virtual doctor consultations 11.6.4 Geiger counter for illnesses 11.6.5 Hydration tool 11.6.6 Pregnancy and fertility tracking 11.7 State-of-the-art implementation of wearables 11.7.1 Detection of soft fall in disabled or elderly people 11.7.2 The third case study is based on the detection of stress using a smart wearable band 11.7.3 Use of wearables to reduce cardiovascular risk 11.8 Future scope and conclusion References Index Back Cover