Improved Bat Algorithm with Deep Learning-Based Biomedical ECG Signal Classification Model

With new developments experienced in Internet of Things (IoT), wearable, and sensing technology, the value healthcare services has enhanced. This evolution brought significant changes from conventional medicine-based to real-time observation-based healthcare. Bio-medical Electrocardiogram (ECG) signals are generally utilized examination diagnosis Cardiovascular Diseases (CVDs) since it is quick non-invasive nature. Due increasing number patients recent years, classifier efficiency gets reduced due high variances observed ECG signal patterns obtained patients. In such scenario computer-assisted automated diagnostic tools important for classification signals. The current study devises an Improved Bat Algorithm with Deep Learning Based Biomedical Signal Classification (IBADL-BECGC) approach. To accomplish this, proposed IBADL-BECGC model initially pre-processes input Besides, applies NasNet derive features test addition, (IBA) employed optimally fine-tune hyperparameters related Finally, Extreme Machine (ELM) algorithm executed perform method. presented was experimentally validated utilizing benchmark dataset. comparison outcomes established improved performance over other existing methodologies former achieved a maximum accuracy 97.49%.