Metaheuristic optimized electrocardiography time-series anomaly classification with recurrent and long-short term neural networks

Abstract

This study explores the realm of time series forecasting, focusing on the utilization of Recurrent Neural Networks (RNN) to detect abnormal cardiovascular rhythms in Electrocardiogram (ECG) signals. The principal objective is to optimize RNN performance by finely tuning hyperparameters, a complex task with known NP-hard complexity. To address this challenge, the study employs metaheuristic algorithms, specialized problem-solving techniques crafted for navigating intricate and non-deterministic optimization landscapes. Additionally, a refined algorithm is introduced to overcome limitations inherent in the original approach. This modified algorithm exhibits significant improvements, surpassing its predecessor in identifying anomalous cardiovascular rhythms within ECG signals. The most successful optimized model achieves an accuracy of 99.26%, outperforming models optimized by other contemporary metaheuristics assessed in the study. Further experimentation extends the initial inquiry by exploring the capabilities of Long Short-Term Memory (LSTM) models augmented by attention layers. In this extension, the best models demonstrate an accuracy of 99.83%, surpassing the original RNN models. These findings underscore the crucial importance of refining machine learning models and emphasize the potential for substantial advancements in healthcare through innovative algorithmic approaches.