FPGA-enhanced IoT methods for disease pre-screening and prediction: An energy optimization approach

Abstract

The research paper has introduced a system based on the Internet of Things (IoT) that has the potential to contribute to the creation of a Consumer Electronics (CE) product. In the event that any health-related measure deviates from the normal range, this system, which is based on IoT technology, will send a notification to the user. The data collected by this system is sent to an analysis system based on a Field Programmable Gate Array (FPGA) through a mobile application, and then transferred to the cloud for storage. To display this raw data, a wearable IoT device can be utilized, and the system will process the data accordingly. The major innovation of this proposed project lies in the development of a fuzzy classifier that can accurately predict the pathological condition of an illness. By implementing a fuzzy classifier using FPGA, the execution time is greatly reduced i.e. 57.7μs compared to other algorithms. Ans also the accuracy of the proposed model is 98.8 %, which higher then other machine learning model such as 97 %, 96.5 %, 93.2 % respectively for SVM, KNN and DT models.previous models like KNN, DT, SVM, and NB (Naive Bayes).

Keywords

• IoT
• Healthcare system
• Energy optimization
• FPGA
• Machine learning