Abstract:
Today, various mobile applications and wearable devices support the management of diabetes by offering early and remote monitoring facilities. However, most of the availa...Show MoreMetadata
Abstract:
Today, various mobile applications and wearable devices support the management of diabetes by offering early and remote monitoring facilities. However, most of the available products recommend the activity/exercise level for patients based on standard data about the impact of exercise on calories burnt and blood Glucose levels. There is a risk associated with such products due to lack of customization to the individual patients. In this paper, we propose to use an Internet of Medical Things (IoMT) architecture to predict the level of activity required each day by the patient to maintain the recommended level of blood Glucose. We compare the performance of Artificial Neural Network (ANN) and Support Vector Machine (SVM) for their prediction accuracy. The proposed model takes pre-exercise Glucose level as input parameter and recommends the duration and intensity of the physical activity required by the patient each day. ANN has been observed to perform better for its classification accuracy.
Date of Conference: 28 June 2021 - 02 July 2021
Date Added to IEEE Xplore: 09 August 2021
ISBN Information: