Ultra high speed deterministic algorithm for transmission lines disturbance identification based on principal component analysis and Euclidean norm

Research on "man-machine interface" has increased in many fields of engineering and its application to facial expressions recognition is expected. The eigenface method by using the principal component analysis (PCA) is popular in this research field. However, it is not easy to compute eigenvectors with a large matrix if the cost of calculation when applying it for time-varying processing is taken into consideration. In this paper, in order to achieve high-speed PCA, the simple principal component analysis (SPCA) is applied to compress the dimensionality of portions that constitute a face. A value of cos θ is calculated using an eigenvector by SPCA as well as a gray-scale image vector of each picture pattern. By using neural networks (NNs), the difference in the value of cos θ between the true and the false (plastic) smiles is clarified and the true smile is discriminated. Finally, in order to show the effectiveness of the proposed face classification method for true or false smiles, computer simulations are done with real images. Furthermore, an experiment using the self-organisation map (SOM) is also conducted as a comparison.

Download Full-text

Comparison between Principal Component Analysis and Wavelet Transform ‘Filtering Methods for Lightning Stroke Classification on Transmission Lines

Electric Power Systems Research ◽

10.1016/j.epsr.2014.05.018 ◽

2015 ◽

Vol 118 ◽

pp. 37-46 ◽

Cited By ~ 6

Author(s):

John A. Morales ◽

E. Orduña ◽

C. Rehtanz ◽

R.J. Cabral ◽

A.S. Bretas

Keyword(s):

Principal Component Analysis ◽

Wavelet Transform ◽

Transmission Lines ◽

Principal Component ◽

Component Analysis ◽

Lightning Stroke ◽

Stroke Classification

Download Full-text

Multiple Measures are Needed to Quantify Training Loads in Professional Rugby League

International Journal of Sports Medicine ◽

10.1055/s-0043-114007 ◽

2017 ◽

Vol 38 (10) ◽

pp. 735-740 ◽

Cited By ~ 25

Author(s):

Daniel Weaving ◽

Ben Jones ◽

Phil Marshall ◽

Kevin Till ◽

Grant Abt

Keyword(s):

Principal Component Analysis ◽

Principal Components ◽

High Speed ◽

Perceived Exertion ◽

Principal Component ◽

Component Analysis ◽

Rugby League ◽

Training Load ◽

Rating Of Perceived Exertion ◽

Training Mode

AbstractThis study aims to investigate the effect of training mode (conditioning and skills) on multivariate training load relationships in professional rugby league via principal component analysis. Four measures of training load (internal: heart rate exertion index, session rating of perceived exertion; external: PlayerLoad™, individualised high-speed distance) were collected from 23 professional male rugby league players over the course of one 12 wk preseason period. Training was categorised by mode (skills or conditioning) and then subjected to a principal component analysis. Extraction criteria were set at an eigenvalue of greater than 1. Modes that extracted more than 1 principal component were subject to a varimax rotation. Skills extracted 1 principal component, explaining 57% of the variance. Conditioning extracted 2 principal components (1st: internal; 2nd: external), explaining 85% of the variance. The presence of multiple training load dimensions (principal components) during conditioning training provides further evidence of the influence of training mode on the ability of individual measures of external or internal training load to capture training variance. Consequently, a combination of internal and external training-load measures is required during certain training modes.

Download Full-text