Title: Diabetic prediction framework using optimisation strategy via optimal weighted score-based deep ensemble network to support diabetic patients

Authors: Santosh Kumar Bejugam; Jyothi Vankara

Addresses: Department of Electrical Electronics and Communication Engineering, GITAM (Deemed to be University), India ' Department of Electrical Electronics and Communication Engineering, GITAM (Deemed to be University), India

Abstract: Diabetes is one of the dangerous diseases that increase blood glucose levels, and it affects the patient's life. Next, in the deep feature extraction stage, the collected data is employed as the input. Here, the deep features are extracted using one-dimensional convolutional neural network (1DCNN). Then, the acquired optimal features are offered as the input to intelligent deep ensemble network (IDENet) that holds the networks such as long short-term memory (LSTM), 1DCNN, deep temporal context networks (DTCN) and extreme learning (EL). The parameters of IDENet are tuned by enhanced light spectrum with horse herd optimisation (ELS-HHO). Further, the attained predicted values from the IDENet are fed as the input to the weighted fusion of predicted values. Then, their weights are tuned by ELS-HHO to attain the effective glucose prediction outcome. Finally, the suggested glucose prediction model secured a better prediction rate than the classical glucose prediction models in experimental observation.

Keywords: diabetics prediction framework; ELS-HHO; optimal weighted predicted scores; intelligent deep ensemble network; IDENet.

DOI: 10.1504/IJBRA.2023.139119

International Journal of Bioinformatics Research and Applications, 2023 Vol.19 No.5/6, pp.343 - 369

Received: 02 Aug 2023
Accepted: 09 Oct 2023
Published online: 14 Jun 2024 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article