Healthcare monitoring using cloud-based IoT environment ppt.pptx

Health care monitoring using cloud

1. Healthcare monitoring using cloud-based IoT environment PRESENTED BY : Ravichandran. M B.E CSE Madhan babu. G B.E CSE s

2. The Internet of Things (IoT) and smart medical devices have revolutionized healthcare by enabling continuous remote patient monitoring, especially during the COVID-19 pandemic. However, securing the vast amounts of sensitive health data remains a challenge. This paper proposes a remote health monitoring model using a lightweight block encryption method to protect patient data in cloud-based IoT environments. Experimental results show that the K-star classification method outperforms others, achieving 95% accuracy, making the model effective for secure, remote health monitoring. abstract 2

3. Patients with COVID-19face a high risk of cardiovascular disease (CVD) and myocardial injury, particularly in critical cases. Early diagnosis of chronic conditions like diabetes, hypertension, and hypercholesterolemia is crucial for reducing treatment burdens, especially in vulnerable populations. Cloud-based IoT platforms, which enhance remote health monitoring through data collection, storage, and analysis, offer significant benefits. However, these systems require robust security measures, such as lightweight encryption, to protect sensitive medical data. This paper proposes a secure, cloud-IoT-based remote health monitoring model using advanced data mining techniques for early disease diagnosis. Introduction

4. COVID-19 patients are at high risk for cardiovascular complications, making early diagnosis of chronic conditions like diabetes and hypertension vital. Cloud-based IoT platforms enhance remote health monitoring but require strong security measures. This paper proposes a secure, IoT-cloud-based health monitoring model using data mining for early disease diagnosis. Data mining in disease prediction

5. data acquiring : *Based on 1st year projections 6 In the proposed secure health monitoring model, various medical data are collected, including patient identification and past clinical data from IoT devices, as well as sensor data such as blood cholesterol, blood pressure, heart rate, and other vital signs from IoT sensors on the patient's body. This data is then stored in distributed cloud storage for further processing and analysis.

6. 8 Algorithms used in disease Lightweight Block Encryption K-star Classification Method Random Forest (RF) Multilayer Perceptron (MLP) Support Vector Machine (SVM) J48 Classifier Deep Convolutional Neural Network (DCNN ) Prediction

7. 4 9

8. Security : 10 The surveyed papers mostly overlook security issues, unlike our proposed cloud-based IoT remote health monitoring model, which emphasizes confidentiality through a lightweight block encryption method suitable for constrained medical IoT resources. where we compare frameworks, technologies, and security approaches, demonstrating that our model uniquely addresses these concerns.

9. 11

10. 12 Real-Time Monitoring Early Disease Detection Remote Accessibility Scalability Data Security Improved Patient Engagement Cost-Effectiveness

11. 13 Dependence on Internet Connectivity Data Accuracy and Reliability Data Privacy and Security Risks High Initial Costs Data Overload

12. 14 REfernces 1. Clerkin KJ, Fried JA, Raikhelkar J, Sayer G, Griffin JM, Masoumi A, Jain SS, Burkhoff D, Kumaraiah D, Rabbani LR, Schwartz A, Uriel N (2020) COVID-19 and cardiovascular disease. 2. Bansal M (2020) “Cardiovascular disease and COVID-19,” Diabetes & Metabolic Syndrome: Clin Res Rev. 3.Liaw A, Wiener M (2002) Classification and regression by randomForest.

13. THANKs FOR THIS OPPORTUNITY..