Two-level coarse-to-fine classification algorithm for asthma wheezing recognition in children's respiratory sounds. (August 2015)

• Record Type: Journal Article
• Authors: Mazić, Igor; Bonković, Mirjana; Džaja, Barbara
• Is Part Of: Biomedical signal processing and control. Volume 21(2015)
• Page Start: 105
• Page End: 118
• Publication Date: 2015-08
• Subjects: Asthma wheeze recognition -- Support vector machines -- Mel frequency cepstral coefficients; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2015.05.002
• Languages: English
• ISSNs: 1746-8094

Abstract

Abstract : Highlights: The respiratory sounds in children should be considered separately from adults. Two layer pattern recognition system for wheezing recognition is introduced and its functionality is justified. The special structure of SVM classifier stacked in parallel improves the ordinary SVM classifier. The system is efficient in negative samples classification which is important for avoiding false asthma alarm and possibility to get used to medications. The difference between central frequencies of tested wheeze and its closest neighbor from training set is important for classification efficiency. Abstract: The paper proposes a two-layer pattern recognition system architecture for asthma wheezing detection in recorded children's respiratory sounds. The first layer consists of two SVM classifiers specifically designed as a cascade stacked in parallel to emphasize the differences among signals with similar acoustic properties, such as wheezes and inspiratory stridors. The second layer is realized using a digital detection threshold, which further upgrades the proposed structure with the aim of improving the process of wheezing detection. The results were experimentally evaluated on the data acquired from the General Hospital of Dubrovnik, Croatia. Classification results obtained on the test data sets revealed that the central frequency of wheezes included in the training data is important for the success of classification.