Vesicular sounds are ‘normal breathing sounds’ such as tracheal, bronchial and bronchovesicular sounds 2, and they generally occur between frequencies of 100 Hz and 1000 Hz, with a sharp drop at about 100–200 Hz 3. Lung sounds are primarily categorized into vesicular and adventitious sounds. Lung sounds are characterized by airflow resistance when they are produced within the chest cavity during the respiration cycle consisting of inspiration and expiration phases 1. ![]() Our findings show that SDC-L is a promising feature for the classification of lung sound signals. SVM, MLP and a hybrid deep learning algorithm (cNN plus LSTM) outperformed with SDC-L, and the other classifiers achieved equivalent results with all features. We found that the first 2 IMFs were enough to construct our feature. The performances of SDC-L were evaluated with three machine learning techniques (support vector machine (SVM), k-nearest neighbor ( k-NN) and random forest (RF)) and two deep learning algorithms (multilayer perceptron (MLP) and convolutional neural network (cNN)) and one hybrid deep learning algorithm combining cNN with long short term memory (LSTM) in terms of accuracy, precision, recall and F1-score. We modified EMD algorithm by adding a stopping rule to objectively select a finite number of intrinsic mode functions (IMFs). It preserves temporal dependency information of multiple frames nearby same to original SDC, and improves feature extraction by reducing the hyperspectral dimension. Therefore, we propose shifted \(\delta \)-cepstral coefficients in lower-subspace (SDC-L) as a novel feature for lung sound classification. ![]() However, they are modeled in high-dimensional hyperspectral space, and also lose temporal dependency information. ![]() Static cepstral coefficients such as Mel-frequency cepstral coefficients (MFCCs), have been used for classification of lung sound signals. Respiratory sounds are expressed as nonlinear and nonstationary signals, whose unpredictability makes it difficult to extract significant features for classification.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |