![heartbeat sound heartbeat sound](https://img.staticdj.com/7a0806d17de93ab33c5331a7b506e9d3.jpeg)
The support vector machine, a Bayesian method, the k -nearest neighbour method, and a two-layer neural network showed very good separation abilities and successfully classified different walking patterns only in the case when the effect of face mask wearing was not included in the classification process. The results indicate that face mask use has a minimal effect on blood oxygen concentration and heart rate, with the average mean changes of these parameters being less than 2 %.
![heartbeat sound heartbeat sound](https://i.ytimg.com/vi/A9BMAd_aMoQ/maxresdefault.jpg)
The proposed methodology is based on signal analysis in both the time and frequency domains.
![heartbeat sound heartbeat sound](https://i.ytimg.com/vi/Kx4pFGo-sZ0/hqdefault.jpg)
The experimental dataset includes 86 signal segments acquired under different conditions. This paper presents the possibility of using oximetric, heart rate (HR), accelerometric, and global navigation satellite systems (GNSSs) to analyse signals recorded during uphill and downhill walking without and with a face mask to find its influence on physiological functions during selected walking patterns.
![heartbeat sound heartbeat sound](https://d16qt3wv6xm098.cloudfront.net/4G4SeUiBTUuFxhHenefTMYeSS7OdAmF2/_.jpg)
Gait analysis and the assessment of rehabilitation exercises are important processes that occur during fitness level monitoring and the treatment of neurological disorders. Thus, care should be taken to ensure clinically appropriate forms of data augmentation to avoid negatively impacting model performance. For example, methods like noise injection have found success in other areas of automated sound classification, but in the context of cardiac sound analysis, noise injection can mimic the presence of murmurs and worsen model performance. However, data augmentation is necessarily domain specific. Concatenating the best performing data augmentation technique (horizontal flip) with PCA and SV perturbations improved model performance.ĭata augmentation can improve classification accuracy by expanding and diversifying the dataset, which protects against overfitting to random variance. Pitch shifting, time stretching and compressing, noise injection, vertical flipping, and applying random color filters negatively impacted model performance. Time and frequency masking resulted in a PR AUC of 0.772 ± 0.050. Principal component analysis color augmentation (PCA) and perturbations of saturation-value (SV) of the hue-saturation-value (HSV) color scale achieved a PR AUC of 0.779 ± 045 and 0.784 ± 0.037, respectively. Among the single data augmentation techniques explored, horizontal flipping of the spectrogram image improved the model performance the most, with a PR AUC of 0.819 ± 0.044. The baseline control model achieved a PR AUC of 0.763 ± 0.047. We built a standard CNN model to classify cardiac sound recordings as either normal or abnormal. To that end, we examined a CNN model’s performance on automated heart sound classification, before and after various forms of data augmentation, and aimed to identify the most optimal augmentation methods for cardiac spectrogram analysis. However, the relative paucity of patient data remains a significant barrier to creating models that can adapt to a wide range of potential variability. The use of convolutional neural networks (CNN) on heart sound spectrograms in particular has defined state-of-the-art performance. The application of machine learning to cardiac auscultation has the potential to improve the accuracy and efficiency of both routine and point-of-care screenings.