Faculty Publications

Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736

Publications by NITK Faculty

Browse

Filters

2023 - 20252

Settings

Subject: search.filters.subject.2D-CNN

Search Results

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Detection of atrial fibrillation based on Stockwell transformation using convolutional neural networks
    (Springer Science and Business Media B.V., 2023) Mohan Rao, B.M.; Kumar, A.; Bachwani, N.; Marwaha, P.
    Atrial Fibrillation (AF) is a pervasive cardiac cantering rhythm that is harmful and causes heart-related complications. AF causes an irregular heartbeat, which may show up at intervals known as proximal AF or for a long duration known as persistent AF. Such irregularities lead to the unhealthy functioning of the heart and cause various cardiac problems. So, the early detection of AF can help in planning efficient treatment, though automatic and early detection of AF is a challenging task. In this study presents a novel approach to detecting AF signals from electrocardiogram (ECG) signals that is based on the combination of a Stockwell Transformation (ST) technique with a 2-D convolutional neural network (CNN). These traditional AF detection methods are used for the isolation of ventricular and atrial activities. The proposed method uses the MIT-BIH database of AF and normal sinus rhythm (NSR) for training and testing. However, the proposed method analyses the time–frequency features of the ECG, and to improve the prior AF detection, a 2D-CNN model is trained and tested for the overall accuracy (Acc), sensitivity (Se), specificity (Sp), and positive predictive value (PPV) performance measures. The results indicated that the proposed method improved the overall performance significantly, providing better accuracy and precision compared to other existing models. The experimental results performed on the proposed approach provide significant improvements in Acc, Se, Sp, and PPV of 99.543%, 99.50%, 99.58%, and 99.57%, respectively. The proposed method can be used in the emergency healthcare department, and it helps cardiologists in the accurate detection of heart problems. © 2023, The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of Computer Applications and Management.
  • No Thumbnail Available
    Item
    Detection of Heart Abnormality with Stethoscope Sounds
    (Springer, 2025) Jat, T.; Bhat, P.; Patil, N.
    Cardiac rhythm assessment is a critical step in the early diagnosis of cardiac arrhythmia, which has been identified as a kind of cardiovascular disease (CVD) that affects millions of individuals worldwide. Although electrocardiography is the right test to confirm cardiovascular diseases, due to the time and cost involved in the test, an alternate solution like heart abnormality detection using a stethoscope test is needed. A stethoscope test is a facility that is relatively easily available in rural parts of the country and can aid in the early diagnosis of heart abnormalities. The central aim of this work is to build a deep learning model for classifying heartbeat sounds which are captured with the help of iStethoscope Pro iPhone app or using a digital stethoscope. The proposed methodology is implemented using the Heart Sounds Classification Challenge dataset from PASCAL and the 2016 Physionet Challenge dataset. To extract features from the recorded heart sounds, we employ Mel spectrograms, Mel-frequency cepstral coefficients (MFCC), and Chroma short-time Fourier transform (STFT). A key novelty of our approach lies in the use of the stacked Bidirectional and Unidirectional Long Short Term Memory (SBU-LSTM) and deep BiLSTM architectures, which, combined with the three feature types (Mel spectrograms, Chroma STFT, and MFCC), enhances model performance for the classification task. Additionally, we introduce the use of Mel spectrograms and Chroma STFT with the 2D Convolutional Neural Network (CNN) architecture, which, as far as we know, has not been investigated in prior research. Experimental results show that the best accuracy achieved is 72% for PASCAL’s Dataset-A, 66% for Dataset-B, 83% for Dataset A + B, and 89% for Physionet’s Dataset-C. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.