A computationally efficient learning model to classify audio signal attributes

<p>The era of machine learning has opened up groundbreaking realities and opportunities in the field medical diagnosis. However, it is also observed that faster proper diagnosis any diseases/medical conditions require analysis classification digital signal data. It indicates identification tumors brain. Brain magnetic resonance imaging (MRI) data to be appropriately classified, similarly, pulse required evaluate human heart operating condition. Several studies have used (ML) modeling classify speech signals, but very few explored audio attributes context intelligent healthcare monitoring. The study thereby aims introduce novel mathematical analyze synthetic with cost-effective computation. numerical composed several functional blocks where deep neural network-based (DNNL) plays a crucial role during training phase, further combined recurrent structure long-short term memory (R-LSTM) feedback connections (FCs). design approaches experiment computing environment terms accuracy computational aspects. outcome proposed approach shows attains approximately 85% accuracy, which comparable baseline execution time.</p>