Comparative study of feature extraction and classification based on dispersion Lempel‐Ziv complexity. (31st August 2021)

• Record Type: Journal Article
• Authors: Jiao, Shangbin; Geng, Bo; Li, Yuxing; Zhang, Qing; Wang, Qing; Li, Yujun; Wang, Wenqing
• Is Part Of: International journal of numerical modelling. Volume 35:Number 2(2022)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2021-08-31
• Subjects: acoustic signals -- classification -- dispersion Lempel‐Ziv complexity -- feature extraction -- fluctuation‐based dispersion entropy -- nonlinear dynamics; Electric networks -- Mathematical models -- Periodicals; Electronics -- Mathematical models -- Periodicals; 621.3011
• DOI: 10.1002/jnm.2949
• Languages: English
• ISSNs: 0894-3370

Abstract

Abstract: As an important complexity feature of signal, Lempel‐Ziv complexity (LZC) has the advantage of simple‐to‐calculate, but it ignores amplitude information, and has low sensitivity at low amplitude. Dispersion Lempel‐Ziv complexity (DLZC) is a recently proposed nonlinear dynamic method, it has the advantage of immunity to noise even at relatively large proportion of noise and has been used to describe different pathological states. In view of its good performance in the field of biomedicine, we introduce DLZC into the field of underwater acoustic and fault diagnosis, and propose a feature extraction method for ship and gear fault signals based on DLZC, then an intelligent classification method was proposed by combining DLZC with K‐Nearest Neighbor (KNN) to further verify the effectiveness of the proposed feature extraction method, termed DLZC‐KNN. We conducted comparative experiments on feature extraction and classification, respectively: for the feature extraction comparison experiment, we compared the proposed feature extraction method with other feature extraction methods, which are based on Lempel‐Ziv complexity (LZC), permutation entropy (PE), dispersion entropy (DE), and fluctuation‐based dispersion entropy (FDE); for the classification comparison experiment, we compare the impact of different features and different classifiers on the recognition rate and also discussed the influence of different parameters on the experiment. The results show that DLZC has a better representation of signal complexity, and the DLZC‐KNN classification method gets a higher recognition rate than other comparative methods both in the field of fault diagnosis and underwater acoustic.