A New Spatial–Spectral Feature Extraction Method for Hyperspectral Images Using Local Covariance Matrix Representation

2018 ◽  
Vol 56 (6) ◽  
pp. 3534-3546 ◽  
Author(s):  
Leyuan Fang ◽  
Nanjun He ◽  
Shutao Li ◽  
Antonio J. Plaza ◽  
Javier Plaza
Keyword(s):  
Feature Extraction ◽  
Covariance Matrix ◽  
Extraction Method ◽  
Matrix Representation ◽  
Spectral Feature ◽  
Hyperspectral Images ◽  
Feature Extraction Method ◽  
Local Covariance

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.

scholarly journals DIMENSIONALITY REDUCTION OF HYPERSPECTRAL IMAGES BY COMBINATION OF NON-PARAMETRIC WEIGHTED FEATURE EXTRACTION (NWFE) AND MODIFIED NEIGHBORHOOD PRESERVING EMBEDDING (NPE)

2014 ◽  
Vol XL-2/W3 ◽  
pp. 31-34
Author(s):  
T. Alipour Fard ◽  
H. Arefi
Keyword(s):  
Feature Extraction ◽  
Extraction Method ◽  
Extraction Methods ◽  
Hyperspectral Images ◽  
Scatter Matrix ◽  
Feature Extraction Method ◽  
Conventional Extraction ◽  
Supervised Feature Extraction ◽  
Number Of Classes ◽  
Selection Of

This paper combine two conventional feature extraction methods (NWFE&NPE) in a novel framework and present a new semi-supervised feature extraction method called Adjusted Semi supervised Discriminant Analysis (ASEDA). The advantage of this method is dominating the Hughes phenomena, automatic selection of unlabelled pixels, extraction of more than L-1(L: number of classes) features and avoidance of singularity or near singularity of within-class scatter matrix. Experimental results on well-known hyperspectral dataset demonstrate that compared to conventional extraction algorithms the overall accuracy of the classification increased.

Sign in / Sign up

Export Citation Format

Share Document