This book aims to provide a detailed understanding of IoMT-supported applications while engaging premium smart computing methods and improved algorithms in the field of computer science. It contains thirteen chapters discussing various applications under the umbrella of the Internet of Medical Things. These applications geared towards IoMT cloud analysis, machine learning, computer vision and deep learning have enabled the evaluation of the proposed solutions.
Author(s): Aboul Ella Hassanien, Aditya Khamparia, Deepak Gupta, K. Shankar, Adam Slowik
Series: Studies in Systems, Decision and Control, 311
Publisher: Springer
Year: 2020
Language: English
Pages: 227
City: Cham
Preface
Contents
About the Editors
A Review of Applications, Security and Challenges of Internet of Medical Things
1 Introduction
2 Applications of IoT in Healthcare
2.1 Smart-Medical Technology
2.2 Ingestible Cameras
2.3 Real-Time Patient Monitoring (RTPM)
2.4 Cardiovascular Health Monitoring Systems
2.5 Skin Condition Monitoring Systems
2.6 IoMT Device as a Movement Detector
3 IoT Healthcare Security and Privacy
3.1 Perception Layer Issues
3.2 Network Layer Issues
3.3 Middleware Layer Issues
3.4 Applicatsion Layer Issues
3.5 Business Layer Issues
4 Security Measures
5 IoMT Design
5.1 Model-Based Development
5.2 Service Layer Based IoMT Design
6 Role of Cloud in IoT Healthcare Systems
6.1 Cloud for Healthcare
6.2 Big Data Management
6.3 Data Processing and Analytics
7 Sensors and Wearable Hardware
8 Concerns, Challenges and Risks
9 Conclusion
References
IoT Enabled Technology in Secured Healthcare: Applications, Challenges and Future Directions
1 Introduction
2 IoT Enabled Technology in Healthcare
2.1 Introduction to IoHT
2.2 A Prototype for Forthcoming Systems of IoHT
2.3 Wearable Healthcare Systems
3 Classes and Challenges of IoHT
3.1 Four Basis Classes of IoHT
3.2 Challenges of IoHT
4 Security Requirements and Challenges in IoHT
4.1 Security Requirements in IoHT
4.2 Security Challenges in IoHT
4.3 Various Technologies to Revolutionize the Services of Healthcare in IoT
5 Future Research Direction
6 Conclusion
References
A Comparative Analysis of Image Denoising Problem: Noise Models, Denoising Filters and Applications
1 Introduction
2 Related Works
3 Overview of the Working Process
4 Types of Image Noise
4.1 Gaussian Noise
4.2 Speckle Noise
4.3 Uniform Noise
4.4 Salt and Pepper Noise
5 Image Denoising Filters
5.1 Median Filter
5.2 Gaussian Filter
5.3 Mean Filter
5.4 Wiener Filter
6 Experimental Results
6.1 Mean Square Error (MSE)
6.2 Peak Signal to Noise Ratio (PSNR)
6.3 Average Difference Value (AD)
6.4 Maximum Difference (MD) Value
7 Conclusion
References
Applications and Challenges of Cloud Integrated IoMT
1 Introduction
2 A Gap Analysis of Internet of Things in Healthcare Environment
3 Cloud Computing in Healthcare Systems
4 Obstacles in Cloud Computing in IoMT Driven Applications
5 The IoT Healthcare Network Platform
6 IoT Healthcare Services and Applications
7 Classification of Healthcare Apps by Category
8 Conclusion
References
Optimal SVM Based Brain Tumor MRI Image Classification in Cloud Internet of Medical Things
1 Introduction
2 Background Information
2.1 Challenges and Advantages of IoMT
2.2 Technologies Enduing IoMT Implementation
3 Proposed Model
3.1 IGSAGA Based Feature Selection
3.2 Optimal SVM Based Classification
4 Experimental Analysis
4.1 Dataset Used
4.2 Results Analysis
5 Conclusion
References
An Effective Fuzzy Logic Based Clustering Scheme for Edge-Computing Based Internet of Medical Things Systems
1 Introduction
2 The Proposed FC-IoMT Model
2.1 Network Model
2.2 Energy Consumption Model
2.3 System Model and Assumptions
2.4 Cluster Head (CH) Selection Process
3 Experimental Validation
4 Conclusion
References
Automated Internet of Medical Things (IoMT) Based Healthcare Monitoring System
1 Introduction
2 Literature Survey
3 Proposed Methodology
3.1 Wireless Sensor Networks
3.2 CHAID Algorithm
4 Result and Discussion
5 Conclusion
References
Deep Belief Network Based Healthcare Monitoring System in IoMT
1 Introduction
2 Literature Survey
3 Proposed Methodology
3.1 ECG Sensor (Module AD8232)
3.2 Raspberry Pi 3 Model B
3.3 Preprocessing
3.4 Feature Extraction
4 Result and Discussion
5 Conclusions
References
An IoMT Assisted Heart Disease Diagnostic System Using Machine Learning Techniques
1 Introduction
2 Related Work
3 Proposed Methodology
3.1 Dataset Description
3.2 Proposed System
4 Classification Techniques
4.1 Naïve Bayes
4.2 Majority Voting
4.3 Logistic Regression
4.4 SVM (Support Vector Machine)
4.5 Random Forest
4.6 Cart
5 Result Analysis
6 Conclusion
References
QoS Optimization in Internet of Medical Things for Sustainable Management
1 Introduction
1.1 MANET-IoT Based Smart Healthcare Networks
1.2 Assaults in WSN and IoT Based Networks
2 QoS for WMN Based Smart Infrastructure
3 WSN—MANET Based Routing Protocols
4 Simulation Results
5 Discussions and Conclusion
6 Future Developments
References
An Intelligent Internet of Medical Things with Deep Learning Based Automated Breast Cancer Detection and Classification Model
1 Introduction
2 The Proposed LBP-DNN Model
2.1 K-means Clustering Based Segmentation
2.2 LBP Based Feature Extraction
2.3 DNN Based Classification
3 Experimental Evaluation
4 Conclusion
References
Internet of Medical Things (IoMT) Enabled Skin Lesion Detection and Classification Using Optimal Segmentation and Restricted Boltzmann Machines
1 Introduction
2 The Proposed OS-RBM Model
2.1 Preprocessing
2.2 ABC-KT Based Segmentation
2.3 Feature Extraction
2.4 RBM Based Classification
3 Performance Validation
4 Conclusion
References
An IOT Based Medical Tracking System (IMTS) and Prediction with Probability of Infection
1 Introduction
1.1 Introduction to the Work
1.2 Literature Survey
1.3 Medical Appliances and Its Uses at Domestic Level
2 Requirement of IoT Based Medical Tracking Systems
2.1 IoT and Medical Science
2.2 Architecture of IoT Based Medical Appliances
3 Proposed Medical Tracking System
3.1 Basic Model Using Integration of Available Appliances
3.2 Feature Selection
3.3 Methodology and Experimental Design of Proposed System
3.4 Rule Based Classifiers to Predict the Probability of Infection
4 Inference
4.1 Results and Conclusion
4.2 Discussion and Future Work
References