Please use this identifier to cite or link to this item:
http://10.1.7.192:80/jspui/handle/123456789/12479
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Panchal, Barkha | - |
dc.date.accessioned | 2024-08-29T06:16:56Z | - |
dc.date.available | 2024-08-29T06:16:56Z | - |
dc.date.issued | 2024-06-01 | - |
dc.identifier.uri | http://10.1.7.192:80/jspui/handle/123456789/12479 | - |
dc.description.abstract | With its incredible efficiency, the Internet of Things (IoT) in particular is transforming care for patients and healthcare operations. The medical industry has seen firsthand how this state-of-the-art equipment can change things. The incorporation of sensing into IoT devices facilitates seamless connectivity and the gathering of essential data required for patient monitoring and treatment optimization. Numerous medical devices, including wheelchairs, nebulizers, and oxygen pumps, can be monitored in real time using connected sensors. The gathering of vital signs, prescription data, diagnoses for patients, and medical history may be made possible by this integration. Strong security measures are required to guarantee privacy and confidentiality of patients as worries about the safety of this private health information have surfaced. This research proposes a blockchain, software defined networking (SDN) and artificial intelligence(AI) for offering security measures for medical IoT data. Medical IoT data is classified into two classes: attack (1) and normal (0), using a variety of machine learning (ML) classifiers, such as support vector machine (SVM), random forest (RF), and K-Nearest neighbor (KNN). We discuss the solution of our literature is based on the security mechanism for the IoMT framework. This research work tackle these challenges and proposed a solution for healthcare IoT. Furthermore, other performance measures are taken into consideration evaluation, including accuracy, precision, recall and F1 score. The detection model using SVM obtained 75.3%, RF is 75.9%andK-NN is 84.3%. The K-NN gets the greatest accuracy among all ML classifiers. | en_US |
dc.publisher | Institute of Technology | en_US |
dc.relation.ispartofseries | 22MCES07; | - |
dc.subject | Computer 2022 | en_US |
dc.subject | Project Report | en_US |
dc.subject | Project Report 2022 | en_US |
dc.subject | Computer Project Report | en_US |
dc.subject | 22MCE | en_US |
dc.subject | 22MCES | en_US |
dc.subject | 22MCES07 | en_US |
dc.subject | CE (CCS) | en_US |
dc.subject | CCS 2022 | en_US |
dc.subject | Cyber Security | en_US |
dc.title | Blockchain Enabled Secure IoMT Framework | en_US |
dc.type | Dissertation | en_US |
Appears in Collections: | Dissertation, CE (CCS) |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
22MCES07.pdf | 22MCES07 | 876.41 kB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.