It is challenging to extract weak impulse features from vibration signals corrupted by strong noise in mechanical fault diagnosis. Due to its simple calculation, fast convergence and easy implementation, K-singular value decomposition (K-SVD) has been widely used in rolling bearing
fault diagnosis. However, it fails to consider the influence of noise and harmonics on atoms learning from impulse characteristics, which results in many irrelevant atoms, and then increases the difficulty of extracting the impulse features in bearing fault signals. Therefore, a clustering
K-SVD-based sparse representation method is proposed in this paper and it is combined with the particle swarm optimisation (PSO)-based time-varying filter empirical mode decomposition (TVF-EMD) for rolling bearing fault diagnosis. The PSO-based TVF-EMD is developed to automatically decompose
the original signal to eliminate the impact of noise and harmonics on the impulses in the signal. Then, the clustering K-SVD method is applied to perform dictionary learning on the sensitive component containing impulses to obtain a redundant dictionary of atoms with obvious impulse patterns.
Finally, the orthogonal matching pursuit (OMP) algorithm is introduced to extract the fault features from rolling bearing vibration signals. The experimental results show that the proposed method can improve the robustness of the dictionary atoms to noise and achieve the extraction of rolling
bearing fault features.
With the work of magnetoencephalography (MEG) classification in brain-computer interface (BCI), a feature extraction method of frequency band power and statistical characteristics was proposed. On the basis of spectrum analysis for the two subjects' experimental MEG data, frequency band powers of 0.5~6Hz for S1 and 10~25Hz for S2 were extracted as features for the two subjects, together with the statistical characteristics of mean for S1/S2 and standard deviation for S1, finally, the features were classified with linear discriminate analysis function directly and secondly, the results showed that the average classification accuracy was 54.38% which was higher than the achievement of BCI competition winner. Therefore, the frequency band power and statistical characteristics are effective features for MEG signals and the research of this paper gives MEG-based BCIs a beneficial complement.
Abstract.A new face recognition method is proposed by using total variation minimization and Log-Gabor filter. First of all, facial images are transformed by total variation minimization model. Secondly, the facial feature is extracted by Log-Gabor filter from the result of the former transformation. Then, dimensionality reduction is realized by using principle component analysis. Finally, classification is achieved by using nearest neighbor classifier. This method is a kind of combination of advantage between total variation minimization and Log-Gabor filter which holds edge feature and describes textural feature of facial image reasonably. The experiment is conducted on Yale Face database. Compared with the methods such as Gabor filter based feature extraction, et al., the face recognition method we presented has better recognition performance. The correct recognition rate reaches to 86.36%.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.