Enhancing heart disease detection in IoT: optimizing long short-term memory with enhanced jellyfish optimization

• Published in: Multimedia tools and applications Vol. 83; no. 29; pp. 72411 - 72442
• Main Authors: Devi, N. G. Sree, Singh, N. Suresh
• Format: Journal Article
• Language: English
• Published: New York Springer US 10.02.2024; Springer Nature B.V
• Subjects: Algorithms; Blood pressure; Cardiovascular disease; Computer Communication Networks; Computer Science; Data Structures and Information Theory; Diagnosis; Electrocardiography; Heart; Heart diseases; Internet of Things; Multimedia Information Systems; Optimization; Optimization algorithms; Predictions; Principal components analysis; Special Purpose and Application-Based Systems; Electrocardiogram (ECG); Long Short-Term Memory Network (LSTM); Internet of Things (IoT)
• ISSN: 1573-7721; 1380-7501; 1573-7721
• DOI: 10.1007/s11042-024-18503-6

The Internet of Things (IoT) technology is currently being used in healthcare systems to collect sensor values for heart disease diagnosis and prediction. Although many researchers have focused on the diagnosis of heart disease, the accuracy of the diagnosis results is low. To address this problem, we present a novel method for predicting heart disease. This paper proposes a novel approach for heart disease detection using long short-term memory networks (LSTM) optimized with Self-improved Jellyfish Optimization. Initially, input data are gathered from the smartwatch and heart monitor device that is attached to the patient to monitor the blood pressure and electrocardiogram (ECG). Then the input data are Pre-processed using the Principal Component Analysis (PCA) algorithm. The African vulture’s optimization algorithm (AVOA) is employed for feature selection. Selected features are provided to LSTM for classifying the received sensor data into normal and abnormal. The proposed approach aims to optimize LSTM hyperparameters the Self-improved Jellyfish Optimization (SIJO) is utilized. In addition, the proposed algorithm incorporates a self-improvement mechanism. By then, the proposed approach's performance has been tested on the MATLAB platform and its results have been compared to those of other approaches. Thus, the results demonstrate the effectiveness of the Jellyfish Optimization algorithm in enhancing LSTM for heart disease detection.