Publication: Design algorithm of smart detection pressure sensors for diabetic patient using artificial neural networks (ANN) model
Loading...
Date
2023-08
Authors
Isaiah, Ong Wei Sheng
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
This research suggests an Artificial Neural Network (ANN) model-based approach for smart pressure sensors for diabetic patients. Walking has been demonstrated to improve health in people with diabetes and peripheral arterial disease. However, for a diabetic individual, continuous walking can produce repeated stress on the plantar foot which increases the likelihood to get foot ulcers, in which when left untreated, might lead to amputation. Having shoes with pressure sensors can identify pressure variations aids in the prevention of emergence of foot ulcers. However, because of several variables, including variations in foot shapes and motions, it might be difficult to identify these changes precisely. In addition, when the smart monitoring device is used, the device will be notifying the user each time when the plantar pressure exceeds the unhealthy threshold set by the designer. This constant notification is not necessary where it is a distraction to the user receiving alerts consistently from both the foot. Hence, having an ANN that intelligently learns the static and dynamic condition of the user, then notify the user the potential occurrence of foot ulcer accordingly. The ANN model generally consists of three main parts which are the data eprocessing, model design and training, then the metric evaluation. The results of the model showed that 86% accuracy was achieved on determining whether the user is walking or standing. To summarise, having this smart detection algorithm will be able to intelligently notify users with diabetic condition regarding the plantar foot condition intelligently.