Fahim Hossain Sifat
University of Liberal Arts Bangladesh (ULAB)

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

Blockchain associated machine learning and IoT based hypoglycemia detection system with auto-injection feature Rahnuma Mahzabin; Fahim Hossain Sifat; Sadia Anjum; Al-Akhir Nayan; Muhammad Golam Kibria
Indonesian Journal of Electrical Engineering and Computer Science Vol 27, No 1: July 2022
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v27.i1.pp447-455

Abstract

Hypoglycemia is an unpleasant phenomenon caused by low blood glucose. The disease can lead a person to death or a high level of body damage. To avoid significant damage, patients need sugar. The research aims at implementing an automatic system to detect hypoglycemia and perform automatic sugar injections to save a life. Receiving the benefits of the internet of things (IoT), the sensor’s data was transferred using the hypertext transfer protocol (HTTP) protocol. To ensure the safety of health-related data, blockchain technology was utilized. The glucose sensor and smartwatch data were processed via Fog and sent to the cloud. A Random Forest algorithm was proposed and utilized to decide hypoglycemic events. When the hypoglycemic event was detected, the system sent a notification to the mobile application and auto-injection device to push the condensed sugar into the victim’s body. XGBoost, k-nearest neighbors (KNN), support vector machine (SVM), and decision tree were implemented to compare the proposed model's performance. The random forest performed 0.942 testing accuracy, better than other models in detecting hypoglycemic events. The system’s performance was measured in several conditions, and satisfactory results were achieved. The system can benefit hypoglycemia patients to survive this disease.