Search

Snoring is an important characteristic of obstructive sleep apnea-hypopnea syndrome (OSAHS). Snoring sound can be used to develop a non-invasive approach for automatically screening OSAHS. In this paper, a snoring detection algorithm based on acoustic features and the XGBoost was proposed. The Fisher Ratio (FR) method was used for feature selection and the 23-dimensional feature set was extracted from the original 58-dimensional feature to reduce computational complexity. A variety of training and test data split methods were used to evaluate the performance of the proposed model. In addition, the proposed method was compared with the deep learning method on the independent subjects training set and test set. The accuracy of the reduced feature set by the proposed model was 87.22% and the deep learning model 87.26% on independent subjects training set and test set, the prediction time of the deep learning model on the test set was around 238 ms, the prediction time of XGBoost was around 58 ms, and the computing efficiency of XGBoost is higher than that of the deep learning model. The results show that the proposed method achieves a good balance between computational cost and performance. These results provide an important method for fast and real-time classification and evaluation of snoring for OSAHS. [ABSTRACT FROM AUTHOR]

Currently, traditional feature extraction algorithms have poor data expression and noise robustness. Moreover, traditional recognition methods are gradually falling behind the demand for increasing data, and struggle to extract deep features in targets. By considering the preceding issues, an integrated neural network has been created in this paper for underwater acoustic target recognition via feature fusion learning. Firstly, the short time Fourier transform (STFT) amplitude spectrum, STFT phase spectrum, and bispectrum feature of underwater acoustic signals are extracted and form the input for the network. They not only contain rich information about the target, but also have strong noise robustness. Secondly, an integrated neural network has been designed, which is trained with different features and contains three neural networks. Finally, in the softmax layer of the network, the shuffled frog leaping algorithm (SFLA) is utilized to train the weight coefficients of different networks. Experimental results of the measured data show that the integrated neural network method based on feature fusion has a higher recognition accuracy and stronger noise robustness. [ABSTRACT FROM AUTHOR]