Combining a recursive approach via non-negative matrix factorization and Gini index sparsity to improve reliable detection of wheezing sounds
作者：
Highlights：
• We propose a method to locate time intervals in which wheeze sounds are active.
• A recursive orthogonal NMF and spectral sparsity provided by Gini index.
• The spectral sparsity attempts to model the periodic nature shown by wheeze sounds.
• The proposed method provides reliable and promising wheezing detection results.
• The proposed method does not depend on any training dataset (unsupervised approach).
摘要
•We propose a method to locate time intervals in which wheeze sounds are active.•A recursive orthogonal NMF and spectral sparsity provided by Gini index.•The spectral sparsity attempts to model the periodic nature shown by wheeze sounds.•The proposed method provides reliable and promising wheezing detection results.•The proposed method does not depend on any training dataset (unsupervised approach).
论文关键词：Wheezing,Detection,Non-negative matrix factorization,Gini index,Sparsity,Clustering
论文评审过程：Received 25 April 2019, Revised 15 January 2020, Accepted 16 January 2020, Available online 16 January 2020, Version of Record 23 January 2020.
论文官网地址：https://doi.org/10.1016/j.eswa.2020.113212
