Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{193725,
        author = {Dr. C. Siva Balaji Yadav and Muddangala Nandini and Malepati Vijay Sai and Gurijala Raghunatha Reddy and Elakaturu Vinay},
        title = {MACHINE LEARNING AND DEEP LEARNING BASED APPROACH FOR ANALYZING HEARTBEAT SOUNDS},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {10},
        pages = {1605-1612},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=193725},
        abstract = {Machine learning and Deep learning have been increasing at a fast rate in various areas particularly the health care sector. Heart diseases are still among the major causes of death in the world, and timely and correct diagnosis of them is vital to enhance better patient outcomes. This paper is on automatic categorization of heartbeat sounds with machine learning and deep learning-based methods. The various feature extraction methods are examined to determine their effects on classification. To this end, three categories of features will be looked into: traditional audio signal processing features, deep learning features purported by pre-trained models, and a composite grouping of the two audio and deep learning features. The features obtained are then classified into Support Vector Machine (SVM), Random Forest and XGBoost classifier. The use of Principal Component Analysis (PCA) to reduce dimensions is used in order to manage the large dimensional feature space. Moreover, there are feature concatenation and majority voting methods used that enhance the accuracy and robustness of classification. The results of the experiments prove the effectiveness of the hybrid feature approach, since it is better than the separate sets of features, which provides the evidence of the efficiency of combining machine learning with deep learning methods in analyzing the sound of the heartbeat.},
        keywords = {Heart Sound Classification, Spectrogram Analysis, Machine Learning, Feature Engineering, Support Vector Machine, Deep Learning, Transfer Learning.},
        month = {March},
        }