Classification of power disturbances using feature extraction in time-frequency plane

2002 ◽  
Vol 38 (15) ◽  
pp. 833 ◽  
Author(s):  
J.Y. Lee ◽  
Y.J. Won ◽  
J.-M. Jeong ◽  
S.W. Nam
Keyword(s):  
Feature Extraction ◽  
Time Frequency ◽  
Power Disturbances

Voice Recognition from Spectrograms: A Wavelet Based Approach

Fractals ◽  
1997 ◽  
Vol 05 (supp01) ◽  
pp. 165-172 ◽  
Author(s):  
G. van de Wouwer ◽  
P. Scheunders ◽  
D. van Dyck ◽  
M. de Bodt ◽  
F. Wuyts ◽  
...  
Keyword(s):  
Pattern Recognition ◽  
Feature Extraction ◽  
Recognition Accuracy ◽  
Voice Recognition ◽  
Original Signal ◽  
Pattern Recognition Technique ◽  
Time Frequency ◽  
Novel Method ◽  
Recognition Technique

The performance of a pattern recognition technique is usually determined by the ability of extracting useful features from the available data so as to effectively characterize and discriminate between patterns. We describe a novel method for feature extraction from speech signals. For this purpose, we generate spectrograms, which are time-frequency representations of the original signal. We show that, by considering this spectrogram as a textured image, a wavelet transform can be applied to generate useful features for recognizing the speech signal. This method is used for the classification of voice dysphonia. Its performance is compared with another technique taken from the literature. A recognition accuracy of 98% is achieved for the classification between normal an dysphonic voices.

scholarly journals Classification of Aggressive Behaviors Based on sEMG Feature Extraction and Machine Learning Algorithm

2020 ◽  
Vol 4 (Supplement_1) ◽  
pp. 656-656
Author(s):  
Youngjun Kim ◽  
Uchechukuwu David ◽  
Yeonsik Noh
Keyword(s):  
Machine Learning ◽  
Feature Extraction ◽  
Classification Accuracy ◽  
Learning Algorithm ◽  
Machine Learning Algorithm ◽  
Intrinsic Mode Functions ◽  
Time Frequency ◽  
Mode Decomposition ◽  
Learning Machine

Abstract New surface electromyography (sEMG) feature extraction approach combined with Empirical Mode Decomposition (EMD) and Dispersion Entropy (DisEn) is proposed for classifying aggressive and normal behaviors from sEMG data. In this study, we used the sEMG physical action dataset from the UC Irvine Machine Learning repository. The raw sEMG was decomposed with EMD to obtain a set of Intrinsic Mode Functions (IMF). The IMF, which includes the most discriminant feature for each action, was selected based on the analysis by Hibert Transform (HT) in the time-frequency domain. Next, the DisEn of the selected IMF was calculated as a corresponding feature. Finally, the DisEn value was tested using five different classifiers, such as LDA, Quadratic DA, k-NN, SVM, and Extreme Learning Machine (ELM) for the classification task. Among these ML algorithms, we achieved classification accuracy, sensitivity, and specificity with ELM as 98.44%, 100%, and 96.72%, respectively.

Fracture Images Classification Based on Fractional Cosine Transform and Markov Mode

2011 ◽  
Vol 311-313 ◽  
pp. 970-973
Author(s):  
Yong Liang Zhang ◽  
Li Xin Gao ◽  
Ling Li
Keyword(s):  
Feature Extraction ◽  
Recognition Rate ◽  
Analysis Method ◽  
Cosine Transform ◽  
Time Frequency ◽  
Fracture Failure ◽  
Metal Fracture ◽  
Correct Recognition Rate ◽  
Better Than

Fracture images automatic classification and recognition is an important one of fracture failure intelligent diagnosis, and in which feature extraction is a key issue. In this paper, fractional cosine transform, which is a useful time-frequency analysis method, is used in feature extraction of fracture images, and then the classification of fatigue, dimples, intergranular and cleavage is performed by Hidden markov model (HMM). For metal fracture images classification, experiment shows that fractional cosine transform is better than the cosine transform in fracture images feature description, and the correct recognition rate can be achieved 98.8% based on HMM classification mode

Sign in / Sign up

Export Citation Format

Share Document