scholarly journals Optimal channel-based sparse time-frequency blocks common spatial pattern feature extraction method for motor imagery classification

2021 ◽  
Vol 18 (4) ◽  
pp. 4247-4263
Author(s):  
Xu Yin ◽  
◽  
Ming Meng ◽  
Qingshan She ◽  
Yunyuan Gao ◽  
...  
Keyword(s):  
Feature Extraction ◽  
Spatial Pattern ◽  
Motor Imagery ◽  
Extraction Method ◽  
Common Spatial Pattern ◽  
Feature Extraction Method ◽  
Time Frequency

Improved Common Spatial Patterns on EEG Feature Extraction

2014 ◽  
Vol 926-930 ◽  
pp. 1814-1817
Author(s):  
Yu Yu Gao
Keyword(s):  
Feature Extraction ◽  
Spatial Pattern ◽  
Spatial Patterns ◽  
Extraction Method ◽  
Common Spatial Pattern ◽  
Classification Result ◽  
Feature Extraction Method ◽  
Feature Information ◽  
Multi Class Classification ◽  
Recognition Capability

For extracting relatively stable and invariable feature from non-stationary EEG in mult-class pattern, many scholars study a feature extraction method, which is called as modified multi-classcommon spatial pattern. It adopts one-to-one strategy to expand common spatial pattern to multi-class classification. While for the solution of airspace filter, Kullback-Leibler distance defines pattern of discrimination of minimize difference within class and maximize difference between classes. And it establishes a function to measure difference within the class. The experiment verifies that the algorithm can obtain feature information with recognition capability which implys in the non-stationary EEG and acquires preferable classification result.

Research on a feature extraction method for local faults in planetary gearboxes based on improved dynamic time warping

2021 ◽  
Vol 63 (8) ◽  
pp. 465-471
Author(s):  
Shang Zhiwu ◽  
Yu Yan ◽  
Geng Rui ◽  
Gao Maosheng ◽  
Li Wanxiang
Keyword(s):  
Feature Extraction ◽  
Fault Diagnosis ◽  
Frequency Domain ◽  
Extraction Method ◽  
Dynamic Time Warping ◽  
Spectral Feature ◽  
Time Warping ◽  
Feature Extraction Method ◽  
Time Frequency ◽  
Dynamic Time

Aiming at the local fault diagnosis of planetary gearbox gears, a feature extraction method based on improved dynamic time warping (IDTW) is proposed. As a calibration matching algorithm, the dynamic time warping method can detect the differences between a set of time-domain signals. This paper applies the method to fault diagnosis. The method is simpler and more intuitive than feature extraction methods in the frequency domain and the time-frequency domain, avoiding their limitations and disadvantages. Due to the shortcomings of complex calculation, singularity and poor robustness, the paper proposes an improved method. Finally, the method is verified by envelope spectral feature analysis and the local fault diagnosis of gears is realised.

Sign in / Sign up

Export Citation Format

Share Document