Detection of Respiratory Sounds Based on Wavelet Coefficients and Machine Learning

Abstract

Respiratory sounds reveal important information of the lungs of patients. However, the analysis of lung sounds depends significantly on the medical skills and diagnostic experience of the physicians and is a time-consuming process. The development of an automatic respiratory sound classification system based on machine learning would, therefore, be beneficial. In this study, 705 respiratory sound signals (240 crackles, 260 rhonchi, and 205 normal respiratory sounds) were acquired from 130 patients. We found that similarities between the original and wavelet decomposed signals reflected the frequency of the signals. The Gaussian kernel function was used to evaluate the wavelet signal similarity. We combined the wavelet signal similarity with the relative wavelet energy and wavelet entropy as the feature vector. A 5-fold cross-validation was applied to assess the performance of the system. The artificial neural network model, which was applied, achieved the classification accuracy and classified the respiratory sound signals with an accuracy of 85.43%.

FrWCSO-DRN: Fractional Water Cycle Swarm Optimizer-based deep residual network for pulmonary abnormality detection from respiratory sound signal

“…In addition, the deep learning methods, namely Long Short-Term Memory (LSTM) and ResNet were not considered for enhancing the classification performance. • The machine learning method developed in [2] attained superior performance, but this method failed to incorporate the respiratory sounds with different medical parameters, like spirometry parameters for providing intellectual disease recognition model. • In [5], deep learning method was designed for categorizing the respiratory sounds.…”

“…The various comparative techniques taken for the assessment are Random Forest classifier [1], Machine Learning [2], DNN [3], CNN [4], WCSO-based HAN, and developed FrWCSO-based DRN.…”

“…Moreover, clinical respiratory sounds are complicated to get in practice, and the samples of lung sounds are small. Thus, the researchers have normally selected conventional machine learning techniques, such as hidden Markov model (HMM) [29], support vector machine (SVM) [30] artificial neural network (ANN) [28], and k-Nearest Neighbor [21], instead of a deep learning technique for categorizing the lung sounds [2].…”

“…The application of signal processing techniques to the data attained through the stethoscope enabled the analysis of lung sounds simpler, objective and also makes the non-invasive auscultation approach more valuable in the pulmonary disease analysis. Recently, numerous researchers have been conducted to acquire the parametric representations of lung sounds for creating a more objective basis for their assessment [2].…”

Empowering cyberphysical systems of systems with intelligence

“…Fingerprint [75], [76], [77], palmprint [78] and iris/gaze [79], [80] are mainly used for user's identification tasks due to their uniqueness for each person. EEG [81], [82], [83], EGG, respiratory [84], [85], [86], heart rate [87], [88], [89] are used for the user's state monitoring. Besides the fact that they can provide valuable information, their usage in real applications is difficult to be applied due to the special wearable devices that it is required for the capturing.…”