Work

Early Risk Identification of Cardiac Disease Prediction using Data Mining and Deep Learning Technique

Year: 2024
Type: article
Abstract: Data Mining (DM) in cardiovascular data prediction is a rapidly growing field of research. As the amount of cardiovascular data available continues to grow, new and more sophisticated data mining. Most peoples affected by the disease without knowing the feature dependencies to make proper treatment leads more deaths. Artificial intelligence techniques make intelligence feature analysis to predict the disease earlier to support treatment. But most of the prevailing techniques are failed to analyses the disease margins and feature release related to disease factor affects the precision rate, so the prediction accuracy is low and to make improper suggestion. To resolve tis properly a novel optimization is need to improve the prediction accuracy based on the deep learning techniques. DM is utilized to extract valuable information from cardiovascular dataset. In this paper, to propose an enhanced deep featured neural network is designed to analyses the cardiac risk to make efficient prediction and recommendation. The Cross Layer Leap Gated Convolution Neural Network (CLLG-CNN) using Recursive Random Forest Feature Selection (RRFFS) for early risk identification is attained for efficient prediction. The Sparse augmentation disease rate (SADR) finds the ideal margins the feature deficiency factor weight and features are selected using Recursive random forest feature selection (RRFFS). The selected feature are trained with cross layer Leap gated convolution neural network (CLLG-CNN) to find the disease risk factor. The proposed system produce high performance compared to the other system by identifying disease efficiently. This improve the detection rate as well precision recall rate to support from early treatment to avoid the cardiac risks.
Language: English
Open Access status: diamond
OpenAlex ID: W7217346080
FWCI: 0.169
Cites: 35
Cited by: 1
Related to: 10