Maximal Information Coefficient-Based Two-Stage Feature Selection Method for Railway Condition Monitoring

Wen, Tao; Dong, Deyi; Chen, Qianyu; Chen, Lei; Roberts, Clive

doi:10.1109/tits.2018.2881284

Cited by 43 publications

(15 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The MIC is an effective metric to evaluate the nonlinear dependence of two variables, which was proposed by Reshef et al [ 33 ] The MIC belongs to a class of maximal information based nonparametric exploration statistics and has been widely applied in variable relationship analysis. [ 34,35 ] For two variables x and y , the MIC is computed as follows [ 36,37 ] :

italicMIC ((), x, y) = italicmax \frac{I ((), x, y)}{\log_{2} italicmin ((),, n_{x}, n_{y})}

where

I ((), x, y)

is the mutual information between variables x and y and n x and n y are the number of bins required to partition x and y , respectively. According to Reshef et al, [ 33 ] bin numbers n x and n y should satisfy the condition of

n_{x} \times n_{y} < n^{0.6}

, where n is the sample number of the tested variable pair.…”

Section: Improved Rffa Methodsmentioning

confidence: 99%

“…The MIC is an effective metric to evaluate the nonlinear dependence of two variables, which was proposed by Reshef et al [33] The MIC belongs to a class of maximal information based nonparametric exploration statistics and has been widely applied in variable relationship analysis. [34,35] For two variables x and y, the MIC is computed as follows [36,37] :…”

Section: Two-level Localization Strategymentioning

confidence: 99%

See 1 more Smart Citation

Efficient batch process monitoring based on random nonlinear feature analysis

Deng

2021

Can J Chem Eng

View full text Add to dashboard Cite

Efficient batch process monitoring is a challenging task because of the large data scale, the strong process nonlinearity, and the complicated local behaviours. To handle this issue, this paper presents a random nonlinear feature analysis method, called two-level localized ensemble random Fourier feature analysis (TLERFFA), for effective batch process fault detection. Considering the large data scale of the nonlinear batch process, the random Fourier feature analysis (RFFA) is introduced to develop the statistical model, which is more efficient than the traditional kernel modelling method in terms of computation loads. Furthermore, for overcoming the model uncertainty resulting from the random mapping weights, the ensemble learning based on Bayesian inference is used to integrate multiply RFFA models with different weight settings. To further mine the rich local information of batch process data, a two-level localization strategy is designed from the perspectives of the variables and the statistics. At the first level, the monitored variables are divided into several subgroups according to their maximal information coefficients, while at the second level, the local monitoring statistics are constructed based on the temporal-spatial neighbour analysis. Lastly, one case study on the benchmark process is given to demonstrate the effectiveness of the proposed methods.

show abstract

italicMIC ((), x, y) = italicmax \frac{I ((), x, y)}{\log_{2} italicmin ((),, n_{x}, n_{y})}

where

I ((), x, y)

n_{x} \times n_{y} < n^{0.6}

, where n is the sample number of the tested variable pair.…”

Section: Improved Rffa Methodsmentioning

confidence: 99%

“…The MIC is an effective metric to evaluate the nonlinear dependence of two variables, which was proposed by Reshef et al [33] The MIC belongs to a class of maximal information based nonparametric exploration statistics and has been widely applied in variable relationship analysis. [34,35] For two variables x and y, the MIC is computed as follows [36,37] :…”

Section: Two-level Localization Strategymentioning

confidence: 99%

Efficient batch process monitoring based on random nonlinear feature analysis

Deng

2021

Can J Chem Eng

View full text Add to dashboard Cite

show abstract

“…The change rates of the measures which changed significantly after ctDCS for the active group with response to ctDCS but didn’t change significantly for the active group without response to ctDCS were used as the features to predict the treatment outcome of ctDCS. A two-step feature selection procedure was utilized to select the most informative features for the best prediction performance ( Wei et al, 2019 ; Wen et al, 2019 ). In the first step, we calculated the correlations between every feature and class labels using the maximal information coefficient (MIC) and the features were ranked according to their MIC values ( Reshef et al, 2011 ).…”

Section: Methodsmentioning

confidence: 99%

Functional Network Alterations as Markers for Predicting the Treatment Outcome of Cathodal Transcranial Direct Current Stimulation in Focal Epilepsy

Hao

Luo

Xie

et al. 2021

Front. Hum. Neurosci.

View full text Add to dashboard Cite

Background and PurposeTranscranial direct current stimulation (tDCS) is an emerging non-invasive neuromodulation technique for focal epilepsy. Because epilepsy is a disease affecting the brain network, our study was aimed to evaluate and predict the treatment outcome of cathodal tDCS (ctDCS) by analyzing the ctDCS-induced functional network alterations.MethodsEither the active 5-day, −1.0 mA, 20-min ctDCS or sham ctDCS targeting at the most active interictal epileptiform discharge regions was applied to 27 subjects suffering from focal epilepsy. The functional networks before and after ctDCS were compared employing graph theoretical analysis based on the functional magnetic resonance imaging (fMRI) data. A support vector machine (SVM) prediction model was built to predict the treatment outcome of ctDCS using the graph theoretical measures as markers.ResultsOur results revealed that the mean clustering coefficient and the global efficiency decreased significantly, as well as the characteristic path length and the mean shortest path length at the stimulation sites in the fMRI functional networks increased significantly after ctDCS only for the patients with response to the active ctDCS (at least 20% reduction rate of seizure frequency). Our prediction model achieved the mean prediction accuracy of 68.3% (mean sensitivity: 70.0%; mean specificity: 67.5%) after the nested cross validation. The mean area under the receiver operating curve was 0.75, which showed good prediction performance.ConclusionThe study demonstrated that the response to ctDCS was related to the topological alterations in the functional networks of epilepsy patients detected by fMRI. The graph theoretical measures were promising for clinical prediction of ctDCS treatment outcome.

show abstract

“…Maximum information coefficient (MIC) 29 is proposed by Reshef in 2011. MIC can find the correlation of various types of variables by obtaining the maximum normalized mutual information under different grid divisions, which has higher universality and fairness 30‐31 . For STLF with multiple factors and variables, MIC can accurately measure correlation between variables.…”

Section: Methodologiesmentioning

confidence: 99%