Heart disease diagnosis using optimized features of hybridized ALCSOGA algorithm and LSTM classifier

Abstract

Background: Cardiac Disease is the predominant cause of global death mainly due to its hidden symptoms and late diagnosis. People with CVD along with other diseases like hypertension, hyperlipidemia require very early detection for appropriate treatment. Hence this research proposed a hybrid technique for heart disease diagnosis. OBJECTIVE The main contribution of the study is to overcome the existing limitations of Antlion, Crow search, and improved genetic algorithm and to hybridize the algorithm for the effective feature selection thereby improving the classification performance of the LSTM classifier. The motivation of this research is to improve the feature selection method with the optimization of features for effective heart disease prediction. Methodology: The proposed architecture uses the Ant lion algorithm with the effective determination of the elite position. The crow search Algorithm utilizes the phenomenon of position and memory of each crow for the evaluation of objective function. The inputs were processed by the improved genetic algorithm for effective feature selection. Now the hybridized proposed system successfully extracts the optimized features. These features are classified by the LSTM classifier. Results:The performance analysis was performed with two datasets. The dataset 1 had been used for the determination of the efficiency of the proposed system and the dataset 2 is utilized for the estimation of the proposed system followed by a detailed comparative analysis with the existing system. Further cross-validation of the sample with a varied range of testing percentage has also been accomplished. Apart from the intercombination performance of feature selection among the three utilized algorithms was also compared. From this comparative analysis, the proposed method had the highest accuracy of 99.7% compared to existing methods.

A Meta heuristic based deep learning classifier for effective dengue disease prediction in IoT‐Fog system

“…One of the major drawbacks of using traditional LSTM is difficulty to capture longer‐range dependencies. Furthermore, it inefficiently manages the information obtained from different time steps with‐in the sequences (Bai et al, 2022; Kalaivani et al, 2022). Therefore, an attention mechanism is incorporated with the conventional LSTM model to improve the capability of this model in capturing contextual and complex patterns.…”