Multi-variable Discretization Based on Extended Maximum Information Coefficient

Feature selection is an essential process in the identification task because the irrelevant and redundant features contained in the unselected feature set can reduce both the performance and efficiency of recognition. However, when identifying the underwater targets based on their radiated noise, the diversity of targets, and the complexity of underwater acoustic channels introduce various complex relationships among the extracted acoustic features. For this problem, this paper employs the normalized maximum information coefficient (NMIC) to measure the correlations between features and categories and the redundancy among different features and further proposes an NMIC based feature selection method (NMIC-FS). Then, on the real-world dataset, the average classification accuracy estimated by models such as random forest and support vector machine is used to evaluate the performance of the NMIC-FS. The analysis results show that the feature subset obtained by NMIC-FS can achieve higher classification accuracy in a shorter time than that without selection. Compared with correlation-based feature selection, laplacian score, and lasso methods, the NMIC-FS improves the classification accuracy faster in the process of feature selection and requires the least acoustic features to obtain classification accuracy comparable to that of the full feature set.

Download Full-text

Functional Linear and Nonlinear Brain–Heart Interplay during Emotional Video Elicitation: A Maximum Information Coefficient Study

Entropy ◽

10.3390/e21090892 ◽

2019 ◽

Vol 21 (9) ◽

pp. 892 ◽

Cited By ~ 3

Author(s):

Vincenzo Catrambone ◽

Alberto Greco ◽

Enzo Pasquale Scilingo ◽

Gaetano Valenza

Keyword(s):

Emotional Processing ◽

Right Hemisphere ◽

Power Spectra ◽

Low Frequency ◽

Emotional Valence ◽

Brain Regions ◽

Time Varying ◽

Maximum Information ◽

Information Coefficient ◽

Linear And Nonlinear

Brain and heart continuously interact through anatomical and biochemical connections. Although several brain regions are known to be involved in the autonomic control, the functional brain–heart interplay (BHI) during emotional processing is not fully characterized yet. To this aim, we investigate BHI during emotional elicitation in healthy subjects. The functional linear and nonlinear couplings are quantified using the maximum information coefficient calculated between time-varying electroencephalography (EEG) power spectra within the canonical bands ( δ , θ , α , β and γ ), and time-varying low-frequency and high-frequency powers from heartbeat dynamics. Experimental data were gathered from 30 healthy volunteers whose emotions were elicited through pleasant and unpleasant high-arousing videos. Results demonstrate that functional BHI increases during videos with respect to a resting state through EEG oscillations not including the γ band (>30 Hz). Functional linear coupling seems associated with a high-arousing positive elicitation, with preferred EEG oscillations in the θ band ( [ 4 , 8 ) Hz) especially over the left-temporal and parietal cortices. Differential functional nonlinear coupling between emotional valence seems to mainly occur through EEG oscillations in the δ , θ , α bands and sympathovagal dynamics, as well as through δ , α , β oscillations and parasympathetic activity mainly over the right hemisphere. Functional BHI through δ and α oscillations over the prefrontal region seems primarily nonlinear. This study provides novel insights on synchronous heartbeat and cortical dynamics during emotional video elicitation, also suggesting that a nonlinear analysis is needed to fully characterize functional BHI.

Download Full-text

Evaluation on Light Sources for Electric Power Emergency Recovery System Based on Grille Method and Maximum Information Coefficient Method

Energy Procedia ◽

10.1016/j.egypro.2018.04.031 ◽

2018 ◽

Vol 145 ◽

pp. 181-186

Author(s):

Cui Jisheng ◽

Wu Yunxin ◽

Gang Hong ◽

Wang Tao ◽

Qiu Peng

Keyword(s):

Electric Power ◽

Light Sources ◽

Maximum Information ◽

Recovery System ◽

Information Coefficient ◽

Coefficient Method

Download Full-text

Improving Bearing Fault Diagnosis Using Maximum Information Coefficient Based Feature Selection

Applied Sciences ◽

10.3390/app8112143 ◽

2018 ◽

Vol 8 (11) ◽

pp. 2143 ◽

Cited By ~ 7

Author(s):

Xianghong Tang ◽

Jiachen Wang ◽

Jianguang Lu ◽

Guokai Liu ◽

Jiadui Chen

Keyword(s):

Feature Selection ◽

Fault Diagnosis ◽

Feature Selection Method ◽

Selection Method ◽

Diagnostic Feature ◽

Feature Subset ◽

Maximum Information ◽

Bearing Fault ◽

Bearing Fault Diagnosis ◽

Information Coefficient

Effective feature selection can help improve the classification performance in bearing fault diagnosis. This paper proposes a novel feature selection method based on bearing fault diagnosis called Feature-to-Feature and Feature-to-Category- Maximum Information Coefficient (FF-FC-MIC), which considers the relevance among features and relevance between features and fault categories by exploiting the nonlinearity capturing capability of maximum information coefficient. In this method, a weak correlation feature subset obtained by a Feature-to-Feature-Maximum Information Coefficient (FF-MIC) matrix and a strong correlation feature subset obtained by a Feature-to-Category-Maximum Information Coefficient (FC-MIC) matrix are merged into a final diagnostic feature set by an intersection operation. To evaluate the proposed FF-FC-MIC method, vibration data collected from two bearing fault experiment platforms (CWRU dataset and CUT-2 dataset) were employed. Experimental results showed that accuracy of FF-FC-MIC can achieve 97.50%, and 98.75% on the CWRU dataset at the motor speeds of 1750 rpm, and 1772 rpm, respectively, and reach 91.75%, 94.69%, and 99.07% on CUT-2 dataset at the motor speeds of 2000 rpm, 2500 rpm, 3000 rpm, respectively. A significant improvement of FF-FC-MIC has been confirmed, since the p-values between FF-FC-MIC and the other methods are 1.166 × 10 − 3 , 2.509 × 10 − 5 , and 3.576 × 10 − 2 , respectively. Through comparison with other methods, FF-FC-MIC not only exceeds each of the baseline feature selection method in diagnosis accuracy, but also reduces the number of features.

Download Full-text