Class-specific mutual information variation for feature selection

Gao, Wanfu; Hu, Liang; Zhang, Ping

doi:10.1016/j.patcog.2018.02.020

Cited by 122 publications

(35 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The dependency between the original signal and the subsignal obtained by VMD can be characterized by MI. MI is used to reflect the degree of correlation between two random variables and its ability of distinguish correlation is higher than the correlation coefficient method [52]. The mutual information of two discrete random variables is defined as:…”

Section: B Mutual Information Variational Mode Decompositionmentioning

confidence: 99%

A New Denoising Method for Underwater Acoustic Signal

Yang

2020

IEEE Access

View full text Add to dashboard Cite

In recent years, the rapid development of marine science has put forward higher and higher requirements for the processing of ship-radiated noise signal. Ship-radiated noise is the noise signal generated by the vibration of various mechanical equipment or the movement of the hull and radiated into the sea when the ship is traveling. Ship-radiated noise signal contains a large number of time-varying, nonlinear and non-stationary components. The denoising processing of ship-radiated noise is the most critical part of underwater acoustic signal processing. In order to more effective reduce the noise of the ship-radiated noise signal, a new denoising method for underwater acoustic signal based on mutual information variational mode decomposition (MIVMD), multivariate multiscale dispersion entropy (mvMDE), and lift wavelet threshold (LWTD) and Savitzky Golay filter (S-G filter), named MIVMD-mvMDE-LWTD-SG, is proposed. Firstly, MIVMD is used to decompose the original signal into n subsignals. Secondly, the mvMDE value of each sub-signal is calculated, and the n sub-signals are divided into high-frequency components and low-frequency components according to the threshold. Then, S-G filter and LWTD method are used to reduce the noise of low-frequency components and high-frequency components respectively. Finally, the low-frequency components and high-frequency components after the denoising processing are reconstructed to obtain the denoising signal. In order to verify the effectiveness of the proposed method, the proposed method is used to reduce the noise of chaotic signal under different signalto-noise ratios (SNR), and compared with the EMD-mvMDE-LWTD and MIVMD-mvMDE-LWTD method. The results show that the proposed method can effective remove the noise in the chaotic signal, better distinguish the adjacent trajectories in the phase space, approximate the real chaotic attractor trajectory, and better retain the useful information in the chaotic signal. The proposed method is further applied to the actual ship-radiated noise signal, and the experimental analysis shows its effectiveness, which lays a solid foundation for further prediction and detection. INDEX TERMS Mutual information variational mode decomposition; multivariate multiscale dispersion entropy; lift wavelet threshold; chaotic signal; denoising

show abstract

Section: B Mutual Information Variational Mode Decompositionmentioning

confidence: 99%

A New Denoising Method for Underwater Acoustic Signal

Yang

2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The filter approach is computationally efficient but usually yields lower prediction accuracy than the wrapper approach. Recent studies on this approach have focused on maximizing variable relevancy while minimizing variable redundancy based on information theory [28][29][30]. The wrapper approach evaluates variable subsets by building prediction models directly on the subsets using a learning algorithm [31].…”

Section: Related Workmentioning

confidence: 99%

Effect of Irrelevant Variables on Faulty Wafer Detection in Semiconductor Manufacturing

Kim

Kang

2019

Energies

View full text Add to dashboard Cite

Machine learning has been applied successfully for faulty wafer detection tasks in semiconductor manufacturing. For the tasks, prediction models are built with prior data to predict the quality of future wafers as a function of their precedent process parameters and measurements. In real-world problems, it is common for the data to have a portion of input variables that are irrelevant to the prediction of an output variable. The inclusion of many irrelevant variables negatively affects the performance of prediction models. Typically, prediction models learned by different learning algorithms exhibit different sensitivities with regard to irrelevant variables. Algorithms with low sensitivities are preferred as a first trial for building prediction models, whereas a variable selection procedure is necessarily considered for highly sensitive algorithms. In this study, we investigate the effect of irrelevant variables on three well-known representative learning algorithms that can be applied to both classification and regression tasks: artificial neural network, decision tree (DT), and k-nearest neighbors (k-NN). We analyze the characteristics of these learning algorithms in the presence of irrelevant variables with different model complexity settings. An empirical analysis is performed using real-world datasets collected from a semiconductor manufacturer to examine how the number of irrelevant variables affects the behavior of prediction models trained with different learning algorithms and model complexity settings. The results indicate that the prediction accuracy of k-NN is highly degraded, whereas DT demonstrates the highest robustness in the presence of many irrelevant variables. In addition, a higher model complexity of learning algorithms leads to a higher sensitivity to irrelevant variables.

show abstract

“…The high-dimensional multi-label data set often contains a large number of irrelevant and redundant features that bring many disadvantages to the multi-label learning such as the computational burden and over-fitting [ 10 , 11 , 12 ]. To address this problem, many multi-label feature selection techniques have been proposed to select the informative feature subset from the original feature set and to discard irrelevant and redundant features [ 13 , 14 , 15 ].…”

Section: Introductionmentioning

confidence: 99%

Multi-Label Feature Selection Based on High-Order Label Correlation Assumption

Zhang

Gao

et al. 2020

Entropy

Self Cite

View full text Add to dashboard Cite

Multi-label data often involve features with high dimensionality and complicated label correlations, resulting in a great challenge for multi-label learning. Feature selection plays an important role in multi-label learning to address multi-label data. Exploring label correlations is crucial for multi-label feature selection. Previous information-theoretical-based methods employ the strategy of cumulative summation approximation to evaluate candidate features, which merely considers low-order label correlations. In fact, there exist high-order label correlations in label set, labels naturally cluster into several groups, similar labels intend to cluster into the same group, different labels belong to different groups. However, the strategy of cumulative summation approximation tends to select the features related to the groups containing more labels while ignoring the classification information of groups containing less labels. Therefore, many features related to similar labels are selected, which leads to poor classification performance. To this end, Max-Correlation term considering high-order label correlations is proposed. Additionally, we combine the Max-Correlation term with feature redundancy term to ensure that selected features are relevant to different label groups. Finally, a new method named Multi-label Feature Selection considering Max-Correlation (MCMFS) is proposed. Experimental results demonstrate the classification superiority of MCMFS in comparison to eight state-of-the-art multi-label feature selection methods.

show abstract

Class-specific mutual information variation for feature selection

Cited by 122 publications

References 25 publications

A New Denoising Method for Underwater Acoustic Signal

A New Denoising Method for Underwater Acoustic Signal

Effect of Irrelevant Variables on Faulty Wafer Detection in Semiconductor Manufacturing

Multi-Label Feature Selection Based on High-Order Label Correlation Assumption

Contact Info

Product

Resources

About