Investigation on Blind Source Separation for Under-determined Mixtures Based on Time-frequency Analysis and Weak Feature Extraction

2014 ◽  
Vol 50 (18) ◽  
pp. 14 ◽  
Author(s):  
Hongkun LI
Keyword(s):  
Feature Extraction ◽  
Blind Source Separation ◽  
Frequency Analysis ◽  
Source Separation ◽  
Time Frequency Analysis ◽  
Time Frequency

Application of the Blind Source Separation Based on Time-Frequency Analysis in Mechanical Fault Diagnosis

2014 ◽  
Vol 945-949 ◽  
pp. 1054-1062 ◽  
Author(s):  
Zhi Nong Li ◽  
Fen Zhang ◽  
Xu Ping He ◽  
Yao Xian Xiao
Keyword(s):  
Fault Diagnosis ◽  
Blind Source Separation ◽  
Frequency Analysis ◽  
Source Separation ◽  
Spectral Feature ◽  
Frequency Domain Analysis ◽  
Mechanical Equipment ◽  
Time Frequency Analysis ◽  
Time Frequency ◽  
Non Stationary Signal

Blind source separation provides a new method for the separation of mechanical sources under high level background noise, as well as the diagnosis of the compound fault. At present, the blind source separation has been successfully applied to the mecanical fault diagnosis. But the traditional mechanical source separation methods are restricted to non-gauss, stationary and mutually independent source signals. However, the mechanical fault signals do not suffice to these conditions, and generally exhibit non-stationarity and non-independence. For the non-stationary signal, its spectral feature is time-varying. Thus only the time-domain or frequency-domain analysis is not sufficient to describe the characteristics of non-stationary signal. The time-frequency analysis, which can provide the information about that the spectrum of the signal varies with the time, is a useful tool for non-stationary signal analysis. In this paper, combined time-frequency analysis with blind source separation, a blind source separation method for the non-stationary signal of the mechanical equipment based on time-frequency analysis is proposed and studied. The simulation and experimental results show that the proposed approach is feasible and effective.

Blind Source Separation for Under-Determined Mixtures Based on Time-Frequency Analysis

2016 ◽  
Vol 693 ◽  
pp. 1350-1356 ◽  
Author(s):  
Hong Kun Li ◽  
Hong Yi Liu ◽  
Chang Bo He
Keyword(s):  
Blind Source Separation ◽  
Frequency Analysis ◽  
Source Separation ◽  
Vibration Signal ◽  
Time Frequency Analysis ◽  
Time Frequency ◽  
Mode Decomposition ◽  
Diagnosis And Classification ◽  
Source Signals

Blind source separation (BSS) is an effective method for the fault diagnosis and classification of mixture signals with multiple vibration sources. The traditional BSS algorithm is applicable to the number of observed signals is no less to the source signals. But BSS performance is limit for the under-determined condition that the number of observed signals is less than source signals. In this research, we provide an under-determined BSS method based on the advantage of time-frequency analysis and empirical mode decomposition (EMD). It is suitable for weak feature extraction and pattern recognition. Firstly, vibration signal is decomposed by using EMD. The number of source signals are estimated and the optimal observed signals are selected according to the EMD. Then, the vibration signal and the optimal observed signals are used to construct the multi-channel observed signals. In the end, BSS based on time-frequency analysis are used to the constructed signals. Gearbox signals are used to verify the effectiveness of this method.

Blind source separation of spatio-temporal mixed signals using time-frequency analysis

2009 ◽  
Vol 88 (3) ◽  
pp. 425-456 ◽  
Author(s):  
Ryuichi Ashino ◽  
Takeshi Mandai ◽  
Akira Morimoto ◽  
Fumio Sasaki
Keyword(s):  
Blind Source Separation ◽  
Frequency Analysis ◽  
Source Separation ◽  
Time Frequency Analysis ◽  
Time Frequency ◽  
Spatio Temporal

scholarly journals SEMG Feature Extraction Based on Stockwell Transform Improves Hand Movement Recognition Accuracy

Sensors ◽  
2019 ◽  
Vol 19 (20) ◽  
pp. 4457 ◽  
Author(s):  
She ◽  
Zhu ◽  
Tian ◽  
Wang ◽  
Yokoi ◽  
...  
Keyword(s):  
Feature Extraction ◽  
Frequency Analysis ◽  
Recognition Accuracy ◽  
Hand Movement ◽  
Analysis Method ◽  
Time Frequency Analysis ◽  
Time Frequency ◽  
Analysis Methods ◽  
Movement Recognition ◽  
S Transform

Feature extraction, as an important method for extracting useful information from surfaceelectromyography (SEMG), can significantly improve pattern recognition accuracy. Time andfrequency analysis methods have been widely used for feature extraction, but these methods analyzeSEMG signals only from the time or frequency domain. Recent studies have shown that featureextraction based on time-frequency analysis methods can extract more useful information fromSEMG signals. This paper proposes a novel time-frequency analysis method based on the Stockwelltransform (S-transform) to improve hand movement recognition accuracy from forearm SEMGsignals. First, the time-frequency analysis method, S-transform, is used for extracting a feature vectorfrom forearm SEMG signals. Second, to reduce the amount of calculations and improve the runningspeed of the classifier, principal component analysis (PCA) is used for dimensionality reduction of thefeature vector. Finally, an artificial neural network (ANN)-based multilayer perceptron (MLP) is usedfor recognizing hand movements. Experimental results show that the proposed feature extractionbased on the S-transform analysis method can improve the class separability and hand movementrecognition accuracy compared with wavelet transform and power spectral density methods.

Sign in / Sign up

Export Citation Format

Share Document