Information Distances versus Entropy Metric

Hu, Bo; Bi, Lvqing; Dai, Songsong

doi:10.3390/e19060260

Cited by 7 publications

(4 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Kolmogorov complexity distance (KD) has become an important tool in a wide variety of applications [ 25 ]. It has also been applied in hydrology in scaling problems, since the heterogeneity of catchments and the variability of hydrological processes make scaling (which is performed either in a deterministic or a stochastic framework) so difficult [ 26 ].…”

Section: Methodsmentioning

confidence: 99%

The Choice of an Appropriate Information Dissimilarity Measure for Hierarchical Clustering of River Streamflow Time Series, Based on Calculated Lyapunov Exponent and Kolmogorov Measures

Mihailoviĉ

Nikolić-Đorić

Malinović-Milićević

et al. 2019

Entropy

View full text Add to dashboard Cite

The purpose of this paper was to choose an appropriate information dissimilarity measure for hierarchical clustering of daily streamflow discharge data, from twelve gauging stations on the Brazos River in Texas (USA), for the period 1989–2016. For that purpose, we selected and compared the average-linkage clustering hierarchical algorithm based on the compression-based dissimilarity measure (NCD), permutation distribution dissimilarity measure (PDDM), and Kolmogorov distance (KD). The algorithm was also compared with K-means clustering based on Kolmogorov complexity (KC), the highest value of Kolmogorov complexity spectrum (KCM), and the largest Lyapunov exponent (LLE). Using a dissimilarity matrix based on NCD, PDDM, and KD for daily streamflow, the agglomerative average-linkage hierarchical algorithm was applied. The key findings of this study are that: (i) The KD clustering algorithm is the most suitable among others; (ii) ANOVA analysis shows that there exist highly significant differences between mean values of four clusters, confirming that the choice of the number of clusters was suitably done; and (iii) from the clustering we found that the predictability of streamflow data of the Brazos River given by the Lyapunov time (LT), corrected for randomness by Kolmogorov time (KT) in days, lies in the interval from two to five days.

show abstract

Section: Methodsmentioning

confidence: 99%

The Choice of an Appropriate Information Dissimilarity Measure for Hierarchical Clustering of River Streamflow Time Series, Based on Calculated Lyapunov Exponent and Kolmogorov Measures

Mihailoviĉ

Nikolić-Đorić

Malinović-Milićević

et al. 2019

Entropy

View full text Add to dashboard Cite

show abstract

“…Entropy can reflect the state of a system, and IE can quantifies the noise amount in reconstruction signal. The higher the entropy value of a signal, the sparser and more uncertain it is, indicating more noise in the signal and a lower signal-to-noise ratio (SNR) (and vice versa) [27]. In this paper, the IE of the reconstructed signal is used as part of the fitness evaluation function.…”

Section: ) Fitness Evaluation Function Based On Information Entropymentioning

confidence: 99%

Research on Noise Reduction Method for Leakage Signal of Water Supply Pipeline

Jiang,

Wang,

Yang

et al. 2024

IEEE Access

View full text Add to dashboard Cite

The negative pressure wave (NPW) signal caused by leakage of water supply pipeline contains a lot of noise due to the influence of water flow state and circuit noise, which will adversely affect the accuracy of leakage detection and leak location. To solve this problem, a novel pipeline pressure signal denoising method based on variational mode decomposition (VMD) is proposed in the paper. Firstly, the key parameters which affect the performance of VMD method: IMFs K and penalty factor α are optimized by genetic algorithm (GA) without prior knowledge. At the same time, different parameters are combined to form different reconstructed signals based on the correlation coefficient (CC). Secondly, the optimal combination of parameters is adaptively determined by using a fitness evaluation function based on the information entropy (IE). Thirdly, based on the optimal parameter combination, reconstruct the signal to achieve noise reduction. Finally, the denoised signal will be used for leak detection and leak location calculation. In order to verify the effectiveness of the proposed method, simulation analysis and laboratory experiments are carried out. Simulation analysis results show that the noise suppression effect of our method is better than that of wavelet, empirical mode decomposition (EMD) and VMD. The highest SNR obtained by our method is 16.187. The laboratory experiment results showed that the NPW signal denoised by proposed method had less error and more stable results in location, with an average relative error of 2.97%.

show abstract

“…The number of feature subspaces ( ) . The mutual information entropy (MIE) [16,17] between samples () i a…”

Section: B Fluctuating Features Division Based On the Proposed Entrop...mentioning

confidence: 99%

An entropy clustering method for blades biofouling detection of marine current turbine under variable marine current speeds

Xu,

Wang,

Xie

et al. 2023

2023 CAA Symposium on Fault Detection, Supervision and Safety for Technical Processes (SAFEPROCESS)

View full text Add to dashboard Cite

Marine current turbine (MCT) attracts extensive attention as a renewable energy power generation equipment. However, accurate and reliable blades biofouling detection for MCT remains a significant challenge, especially under variable marine current speed. This paper proposes an entropy clustering method to improve the detection accuracy of blades biofouling for MCT under variable marine current speed. Firstly, the stator current signal is decomposed based on variational mode decomposition (VMD) to enlarge the feature of blades biofouling. Secondly, to eliminate the influence of swell effect, fluctuating features caused by swell effect are divided into each subspace based on the proposed entropy clustering method. At the last stage, principal component analysis models (PCA) are established in each feature subspace to detect blades biofouling. To verify the effectiveness of the proposed method, experiments are carried out on a 230W MCT platform. The results show that the proposed method has satisfactory performance for blades biofouling detection under variable marine current speed.

show abstract

Information Distances versus Entropy Metric

Cited by 7 publications

References 33 publications

The Choice of an Appropriate Information Dissimilarity Measure for Hierarchical Clustering of River Streamflow Time Series, Based on Calculated Lyapunov Exponent and Kolmogorov Measures

The Choice of an Appropriate Information Dissimilarity Measure for Hierarchical Clustering of River Streamflow Time Series, Based on Calculated Lyapunov Exponent and Kolmogorov Measures

Research on Noise Reduction Method for Leakage Signal of Water Supply Pipeline

An entropy clustering method for blades biofouling detection of marine current turbine under variable marine current speeds

Contact Info

Product

Resources

About