Computational Intelligence and Machine Learning Approaches in Biomedical Engineering and Health Care Systems

Description

Computational Intelligence and Machine Learning Approaches in Biomedical Engineering and Health Care Systems explains the emerging technology that currently drives computer-aided diagnosis, medical analysis and other electronic healthcare systems. 11 book chapters cover advances in biomedical engineering fields achieved through deep learning and soft-computing techniques. Readers are given a fresh perspective of how intelligent systems impact patient outcomes for healthcare professionals who are assisted by advanced computing algorithms. Key Features: - Covers emerging technologies in biomedical engineering and healthcare that assist physicians in diagnosis, treatment, and surgical planning in a multidisciplinary context - Provides examples of technical use cases for artificial intelligence, machine learning and deep learning in medicine, with examples of different algorithms - Introduces readers to the concept of telemedicine and electronic healthcare systems - Provides implementations of disease prediction models for different diseases including cardiovascular diseases, diabetes and Alzheimer’s disease - Summarizes key information for learners - Includes references for advanced readers The book serves as an essential reference for academic readers, as well as computer science enthusiasts who want to familiarize themselves with the practical computing techniques in the field of biomedical engineering (with a focus on medical imaging) and medical informatics. Cover Title Copyright End User License Agreement Contents Foreword Preface List of Contributors Convolutional Neural Network for Denoising Left Ventricle Magnetic Resonance Images Zakarya Farea Shaaf1, Muhammad Mahadi Abdul Jamil1,*, Radzi Ambar1 and Mohd Helmy Abd Wahab1 INTRODUCTION DENOISING MRI IMAGES USING CONVOLUTIONAL NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORK FOR DENOISING Building Blocks of Convolutional Neural Network Network Architecture Implementation Platform Data Description RESULT AND DISCUSSION Quantitative Measurements Confusion Matrix CONCLUSION CONSENT FOR PUBLICATION CONFLICT OF INTEREST ACKNOWLEDGEMENTS REFERENCES Early Diabetic Retinopathy Detection Using Elevated Continuous Particle Swarm Optimization Clustering With Raspberry PI Bhimavarapu Usharani1,* INTRODUCTION Heart Kidney Eye BACKGROUND Particle Swarm Optimization Clustering Particle Swarm Optimization Clustering Algorithm Raspberry PI LITERATURE REVIEW PROPOSED MODEL Pre-processing Segmentation Elevated Continuous Particle Swarm Optimization Clustering Fitness Measures Feature Extraction RESULTS AND DISCUSSION Results CONCLUSION CONSENT FOR PUBLICATION CONFLICT OF INTEREST ACKNOWLEDGEMENTS REFERENCES E-Health System and Telemedicine: An Overview and its Applications in Health Care and Medicine Ranjitha Vijay Anand1, Harshavardhini Parthiban1, Karthikeyan Subbiahanadar Chelladurai1, Jackson Durairaj Selvan Christyraj1,* and Johnson Retnaraj Samuel Selvan Christyraj1,* INTRODUCTION E-HEALTH ELECTRONIC HEALTH SYSTEM Health Care Informatics or Health Information Technology (HIT) Electronic Health Records (EHR) Medical Information System Biomedical Informatics COMPONENCE OF E-HEALTH Telehealth Real-Time Audio And Video Consultation Mobile- Health Digital Medical Imaging Remote Patient Monitoring (RPM) Electro-Cardiogram Telemonitoring Blood Pressure Telemonitoring Glucose Level Telemonitoring Body Temperature Telemonitoring Stored And Forward TELEMEDICINE Types Of Telemedicine Services Tele- Consultancy Tele-Emergency Tele-Diagnosis Tele-Psychiatry Tele -Dentistry Robotic Surgery OTHER FUNCTIONAL SYSTEMS OF E-HEALTH SYSTEM [Clinical ICT System] Clinical ICT System Integrated Healthcare System Health IT Support System Online Health Information System Public Health Data Collection and Analysis Consumer Health Informatics Applications Telemedicine in Developing Countries CONCLUSION CONSENT FOR PUBLICATION CONFLICT OF INTEREST ACKNOWLEDGEMENTS REFERENCES Fuzzy Logic Implementation in Patient Monitoring System for Lymphatic Treatment of Leg Pain Fauziah Abdul Wahid1, Noor Anita Khairi2, Siti Aishah Muhammed Suzuki1,*, Rafidah Hanim Mokhtar1, Norita Md Norwawi1 and Roesnita Ismail1 INTRODUCTION LITERATURE REVIEW Definition of Computational Intelligence Definition of Lymphatic System Lymphatic Treatment for Leg Pain Health Information Management System Security Issues Related to Data Breach Introduction to Double-Loop Learning Characteristics of Double-Loop Learning The Approach of Double-Loop in Patient Monitoring System Fuzzy Logic Application of Fuzzy Logic in Patient Monitoring System THE PROPOSED APPROACH Agile Model Agile SDLC Implementation in Double-Loop Patient Monitoring System with Fuzzy Logic Implementation Basic Algorithm Function (Fuzzy Logic) Fuzzy Logic Architecture A. Fuzzification Module B. Knowledge-based C. Inference Engine D. Defuzzification Module Development of Patient Monitoring System A. Define Variables B. Construct Membership Function C. Construct the Base Rules D. Fuzzification E. Defuzzification ACCURACY OF PROPOSED MODEL Software and Hardware Requirements Security Implementation in Health Monitoring System Digital Signature No Right-Click Script CONCLUSION AND FUTURE WORKS CONSENT FOR PUBLICATION CONFLICT OF INTEREST ACKNOWLEDGEMENTS REFERENCES Safe Distance and Face Mask Detection using OpenCV and MobileNetV2 B.S. Maya1,*, T. Asha1, P. Prajwal1, P.N. Revanth1, Pratik R Pailwan1 and Rahul Kumar Gupta1 INTRODUCTION LITERATURE REVIEW DATASET DESCRIPTION SYSTEM ARCHITECTURE Applying the Face Mask and Safe Distance Detector METHODOLOGY ON FACE-MASK-NET MODEL Details of Facemasknet Detection Model Convolutional Neural Network MobileNetV2 Learning Rate SOCIAL DISTANCING MONITORING Distance Measurement using OpenCV Social Distance Based on YOLO-v3 RESULTS AND DISCUSSION CONCLUSION FUTURE SCOPE CONSENT FOR PUBLICATION CONFLICT OF INTEREST ACKNOWLEDGEMENTS REFERENCES Performance Evaluation of ML Algorithms for Disease Prediction Using DWT and EMD Techniques Reddy K. Viswavardhan1,*, B. Hemapriya1, B. Roja Reddy1 and B.S. Premananda1 INTRODUCTION Datasets Preparation Pre-processing Feature Extraction Techniques Discrete Wavelet Transformation Empirical Mode Decomposition Kth-Nearest Neighbor Decision Tree Classifier Random Forest Support Vector Machine Stochastic Gradient Descent (SGD) Multi-level Perception Performance Evaluation Accuracy Precision Score Recall Score F1. Score RESULTS ML Algorithms for Disease Prediction using DWT and EMD tech, CI and ML, Approaches in the field of BM and HC 13 Feature Extraction using DWT and EMD ML Algorithms for disease prediction using DWT and EMD tech, CI and M, approaches in the field of BM and HC 15 ML Algorithms for Disease Prediction Using DWT and EMD Tech, CI and ML, Approaches in the Field of BM and HC 17 CI and ML approaches in the field of BM and HC Viswavardhan et al. ML Algorithms for Disease Prediction Using DWT and EMD Tech, CI and ML, Approaches in the Field of BM and HC 19 CONCLUDING REMARKS CONSENT FOR PUBLICATION CONFLICT OF INTEREST ACKNOWLEDGEMENTS REFERENCES Cardiovascular Disease Preventive Prediction and Medication (CVDPPM) - A Model Based on AI Techniques for Prediction and Timely Medical Assistance Y.V. Nagesh Meesala1,*, Sheik Khadar Ahmad Manoj1 and Ganapati Bhavana2 INTRODUCTION LITERATURE SURVEY IoT Based CVD Cloud Storage of Health Records CARDIOVASCULAR DISEASE PREVENTIVE PREDICTION AND MEDICATION (CVDPPM) MODEL IMPLEMENTATION OF ML ALGORITHMS FOR PREDICTION OF CVD Data Set Predictors: Information by positive and negative heart disease patients are given in Tables 3 and 4. Model 1: Logistic Regression Model 2: K-NN (K-Nearest Neighbors) Model 3: SVM (Support Vector Machine) Model 4: Naive Bayes Classifier Model 5: Decision Trees Model 6: Random Forests Model 7: XGBoost Making the Confusion Matrix Instructions to Deduce Information from the Confusion Matrix Highlight Importance CONCLUSION CONSENT FOR PUBLICATION CONFLICT OF INTEREST ACKNOWLEDGEMENTS REFERENCES Personalized Smart Diabetic System Using Hybrid Models of Neural Network Algorithms K. Abirami1, P. Deepalakshmi2,* and Shanmuk Srinivas Amiripalli3 INTRODUCTION CHALLENGES IN HEALTHCARE LITERATURE SURVEY HYBRID NEURAL NETWORK APPROACH Dataset Collection Data Processing Personalized Analysis Layer Common Users Healthcare Providers Diabetics Patients Data Sharing Layer RESULTS AND DISCUSSION CONCLUSION AND FUTURE SCOPE CONSENT FOR PUBLICATION CONFLICT OF INTEREST ACKNOWLEDGEMENTS REFERENCES A Framework of Smart Mobile Application for Vehicle Health Monitoring K. Aswarth1 and S. Vasavi1,* INTRODUCTION LITERATURE SURVEY Challenges in VMMS Architecture System Challenges in the DTC Coding System Challenges in Automotive Diagnostic Command Set Challenges in Digital Twin Model APPROACH Architecture Methodology Cloud Application Deployment Cloud Application Identity and Access Management RESULTS AND ANALYSIS DATASET DESCRIPTION SENSOR PREDICTED CONCLUSION CONSENT FOR PUBLICATION CONFLICT OF INTEREST ACKNOWLEDGEMENTS REFERENCES Progression Prediction and Classification of Alzheimer’s Disease using MRI Sruthi Mohan1,* and S. Naganandhini2 INTRODUCTION REVIEW OF THE LITERATURE METHODOLOGY OF PPC-AD-MRI Random Forest Classifier (RFC) Algorithm for Random Forest K Nearest Neighbor (KNN) Classifier Extreme Gradient Boosting (XGB) RESULTS AND DISCUSSION Dataset Description Performance Evaluation Matrices CONCLUSION CONSENT FOR PUBLICATION CONFLICT OF INTEREST ACKNOWLEDGEMENTS REFERENCES Subject Index