Title: Recurrent Shephard convolutional neural network for heart disease prediction in spark framework

Authors: Jayasri Kotti; Jamal Mohammed Saira Banu; Ramanathan Lakshmanan

Addresses: Department of Information Technology, GMR Institute of Technology, Rajam, Andhra Pradesh, India ' School of Computer Science and Engineering, Vellore Institute of Technology, Vellore-632014, India ' School of Computer Science and Engineering, Vellore Institute of Technology, Vellore-632014, India

Abstract: The heart is the most essential organ in the human body, and so, heart disease should be predicted more accurately, even a minute mistake in prediction leads to death. To deal with the issue, this paper introduced a new technique, named recurrent Shephard convolutional neural network (R_ShCNN) for heart disease prediction. Initially, big data is considered as input and it is passed to data partitioning, which is carried out by utilising deep embedded clustering (DEC). Here, pre-processing is executed by missing data imputation and linear normalisation, whereas feature fusion is performed using the Harmonic mean measure with deep Q network (DQN). Lastly, heart disease is predicted by utilising the proposed R_ShCNN, which is attained by fusing the Shephard convolutional neural network (ShCNN) and deep recurrent neural network (DRNN). The experimental result shows that R_ShCNN accomplished the specificity of 92.3%, accuracy of 89.5%, and sensitivity of 90.9%.

Keywords: heart disease; deep embedded clustering; DEC; deep Q network; DQN; Shephard convolutional neural network; ShCNN; deep recurrent neural network; DRNN.

DOI: 10.1504/IJAHUC.2024.140443

International Journal of Ad Hoc and Ubiquitous Computing, 2024 Vol.46 No.4, pp.216 - 230

Received: 13 Nov 2023
Accepted: 20 Mar 2024
Published online: 09 Aug 2024 *

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