论文信息 - Frequency Features Selection Using Decision Tree for Classification of Sleep Breathing Sound

Frequency Features Selection Using Decision Tree for Classification of Sleep Breathing Sound

Sleep snoring has recently been one of the important topics in healthcare and sleep study. Most methods currently focus on spectral analysis in frequency domain that requires high computation for Fourier transform and further processes. Moreover, for full analysis in frequency domain, it is necessary to obtain a high-resolution power spectrum which can lead to difficulties in big data processing and classification. In this paper, the Decision Tree (DT) algorithm was applied to the raw data set of 4,000 ~ 8,000 feature points in order to obtain less than 100 feature points. With the benefits of this feature selection technique, the computational burden was dramatically reduced and its effectiveness in classification was demonstrated by multilayer perceptron neural network (MLP) and support vector machine (SVM).

Yonggwan Won | Tan Loc Nguyen | Yonggwan Won | T. Nguyen

[1] Charu C. Aggarwal,et al. Feature Selection for Classification: A Review , 2014, Data Classification: Algorithms and Applications.

[2] Kwang Suk Park,et al. Polyvinylidene fluoride sensor-based method for unconstrained snoring detection , 2015, Physiological measurement.

[3] Ron Kohavi,et al. Scaling Up the Accuracy of Naive-Bayes Classifiers: A Decision-Tree Hybrid , 1996, KDD.

[4] F. Dalmasso,et al. Snoring: analysis, measurement, clinical implications and applications. , 1996, The European respiratory journal.

[5] David G. Stork,et al. Pattern Classification (2nd ed.) , 1999 .

[6] Yonggwan Won,et al. Sleep snoring detection using multi-layer neural networks. , 2015, Bio-medical materials and engineering.

[7] Zhiyong Wang,et al. Unsupervised snore detection from respiratory sound signals , 2015, 2015 IEEE International Conference on Digital Signal Processing (DSP).

[8] M Cavusoglu,et al. An efficient method for snore/nonsnore classification of sleep sounds , 2007, Physiological measurement.

[9] David G. Stork,et al. Pattern Classification , 1973 .

[10] Yu-Lun Lo,et al. Energy Types of Snoring Sounds in Patients with Obstructive Sleep Apnea Syndrome: A Preliminary Observation , 2012, PloS one.

[11] Yonggwan Won,et al. Efficient snoring and breathing detection based on sub-band spectral statistics. , 2015, Bio-medical materials and engineering.