Comparative study of feature extraction and classification based on dispersion Lempel‐Ziv complexity

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.

A Comparative Study of Four Nonlinear Dynamic Characteristics in Feature Extraction of Bearing Fault Diagnosis

“…Normalized LZC (NLZC) and weight LZC (WLZC) were proposed and applied to the analysis of biosequence and piecewise smooth systems of switching converters in 2009 and 2012 [5,6]. By introducing the permutation mode of permutation entropy and the mapping mode of DE, permutation LZC (PLZC) and dispersion LZC (DLZC) were proposed in 2015 and 2020 [7][8][9][10]. In 2022, dispersion entropy-based LZC (DELZC) was presented by introducing the dispersion mode of dispersion entropy [11].…”

Information flow between global financial market stress and African equity markets: An EEMD-based transfer entropy analysis

“…Other quantile regression approaches [ [78] , [79] , [80] , [81] ], could be considered. Importantly, given that Rényi effective entropy has been proposed relatively early, we recommend for future studies the application of new entropy features, such as dispersion entropy-based Lempel-Ziv complexity [ 82 ], particle swarm optimisation fractional slope entropy [ 83 ], and dispersion entropy-based Lempel-Ziv complexity [ 84 ] that may have a better distinguishing ability.…”

Comparative Study on Feature Extraction of Marine Background Noise Based on Nonlinear Dynamic Features

“…For this reason, Bai et al [ 25 ] first combined LZC with entropy theory and proposed the permutation LZC (PLZC) by replacing the binary mapping with the permutation pattern in PE, which inherits the strong anti-noise ability of PE and improves the ability of LZC to characterize signals [ 26 ]. In 2020, Mao et al [ 27 ] were inspired by the advantages of DE to effectively reflect amplitude information and integrated it into LZC to launch dispersion LZC (DLZC); the application of DLZC in various fields showed high stability and separability [ 28 ]. Dispersion entropy-based Lempel–Ziv complexity (DELZC) is a newly proposed complexity measure [ 29 ], which makes full use of the more effective dispersion pattern in DE to reflect more pattern information and further boosts the ability to capture the dynamic changes of signal.…”