Utilizing a Hybrid Deep Learning Model for Automated Arrhythmia Classification & Detection with the Integration of the AI-ML based Farmland Fertility Algorithm for accurate segregations of ECG Signals

Abstract

In this research article, the utilizing of a hybrid deep learning model for the automation based arrhythmia classifications with the Integration of the Farmland Fertility Algorithm for accurate segregations is presented along with the simulation results. The present study introduces an innovative approach, Automated Arrhythmia Classifications utilizing the Farmland based Fertility type of Algo with Hybridized Deep Learnings (AACFFAHDL), within the Internet of Things (IoT) framework. This novel system employs a hyperparameter-tuned Deep Learning (DL) model for the analysis of Electrocardiogram (ECG) signals, leading to the accurate diagnosis of arrhythmia. The AACFFAHDL techniques begins with data’s preprocessing’s, ensuring standardized input signal scaling. Subsequently, the Hybrid Deep Learning [HDL] approaches are utilized for arrhythmia detection & the classifications. To enhance the HDLs performance in classification and detection, the AAC-FFAHDL incorporates a hyperparameter tuning process based on the Farmland Fertility Algorithm (FFA). Simulation-based validation using a benchmark ECG database demonstrates the efficacy of the proposed AAC-FFAHDL approach. Comparative experimental analyses affirm its superior performance across various evaluation metrics in comparison to alternative models.