WAVELET-BASED DENOISING ALGORITHM FOR ROBUST EMG PATTERN RECOGNITION

2011 ◽  
Vol 10 (02) ◽  
pp. 157-167 ◽  
Author(s):  
ANGKOON PHINYOMARK ◽  
PORNCHAI PHUKPATTARANONT ◽  
CHUSAK LIMSAKUL
Keyword(s):  
Recognition Accuracy ◽  
Signal To Noise Ratio ◽  
Wavelet Denoising ◽  
Hand Movements ◽  
Signal Recognition ◽  
Signal To Noise ◽  
Processing Stage ◽  
Emg Signal ◽  
Baseline System ◽  
Emg Pattern Recognition

A successful pre-processing stage based on wavelet denoising algorithm for electromyography (EMG) signal recognition is proposed. From the limitation of traditional universal wavelet denoising, the optimal weighted parameter is assigned for universal thresholding method. The optimal weight for increasing EMG recognition accuracy is 50–60% of traditional universal threshold with hard transformation. Experimental results show that it improved approximately from 2 to 50% of recognition accuracy for EMG with signal-to-noise ratio (SNR) in the range of 20 to 0 dB compared to a baseline system (without pre-processing stage) and traditional universal wavelet denoising. The results are evaluated through a large EMG dataset with seven kinds of hand movements and eight types of muscle positions.

scholarly journals EMG Based Gesture Recognition Using the Unbiased Difference Power

2021 ◽  
Vol 11 (4) ◽  
pp. 1526
Author(s):  
Kimoon Kang ◽  
Hyun-Chool Shin
Keyword(s):  
Gesture Recognition ◽  
Recognition Accuracy ◽  
Signal To Noise Ratio ◽  
Noise Power ◽  
Signal To Noise ◽  
Emg Signal ◽  
Power Equation ◽  
Average Accuracy ◽  
The Difference ◽  
Resting Period

In this paper, we propose an unbiased difference power that is robust against noise as a feature for electromyography (EMG)-based gesture recognition. The proposed unbiased difference power is obtained by subtracting the noise-biased part from the difference power. We derive the difference power equation and discover that the difference power is biased by twice the noise power. For noise power estimation, we utilized the characteristics of the EMG signal and estimated the noise power from the resting period. For performance evaluation, we used EMG signals provided by the open source Ninapro project database. We used the recognition accuracy as an evaluation index. We compare the recognition accuracy of the case using the proposed unbiased feature with those of two conventional cases. Experimental results show that the proposed unbiased difference power improves the accuracy compared with conventional ones. As the noise level increases, cases where the proposed unbiased difference power is used show a clear improvement in accuracy compared with the two conventional cases. For the signal-to-noise ratio (SNR) of 0 dB, the proposed unbiased difference power improves the average accuracy by more than 12%.

Signal-to-Noise Ratio Estimation in Electromyography Signals Contaminated with Electrocardiography Signals

2020 ◽  
Vol 19 (03) ◽  
pp. 2050027
Author(s):  
Thandar Oo ◽  
Pornchai Phukpattaranont
Keyword(s):  
Signal To Noise Ratio ◽  
Training Data ◽  
Signal To Noise ◽  
Zero Crossing ◽  
Ecg Signals ◽  
Average Value ◽  
Emg Signal ◽  
Recognition Systems ◽  
Noise Ratio ◽  
Electromyography Signals

When electromyography (EMG) signals are collected from muscles in the torso, they can be perturbed by the electrocardiography (ECG) signals from heart activity. In this paper, we present a novel signal-to-noise ratio (SNR) estimate for an EMG signal contaminated by an ECG signal. We use six features that are popular in assessing EMG signals, namely skewness, kurtosis, mean average value, waveform length, zero crossing and mean frequency. The features were calculated from the raw EMG signals and the detail coefficients of the discrete stationary wavelet transform. Then, these features are used as inputs to a neural network that outputs the estimate of SNR. While we used simulated EMG signals artificially contaminated with simulated ECG signals as the training data, the testing was done with simulated EMG signals artificially contaminated with real ECG signals. The results showed that the waveform length determined with raw EMG signals was the best feature for estimating SNR. It gave the highest average correlation coefficient of 0.9663. These results suggest that the waveform length could be deployed not only in EMG recognition systems but also in EMG signal quality measurements when the EMG signals are contaminated by ECG interference.

scholarly journals Signal Recognition for English Speech Translation Based on Improved Wavelet Denoising Method

2021 ◽  
Vol 2021 ◽  
pp. 1-9
Author(s):  
Zhuo Chen
Keyword(s):  
Speech Recognition ◽  
Recognition Accuracy ◽  
Wavelet Denoising ◽  
Simulation Software ◽  
Signal Recognition ◽  
Denoising Method ◽  
Speech Translation ◽  
Time Frequency ◽  
Traditional Algorithm ◽  
Translation Signals

The signal corresponding to English speech contains a lot of redundant information and environmental interference information, which will produce a lot of distortion in the process of English speech translation signal recognition. Based on this, a large number of studies focus on encoding and processing English speech, so as to achieve high-precision speech recognition. The traditional wavelet denoising algorithm plays an obvious role in the recognition of English speech translation signals, which mainly depends on the excellent local time-frequency domain characteristics of the wavelet signal algorithm, but the traditional wavelet signal algorithm is still difficult to select the recognition threshold, and the recognition accuracy is easy to be affected. Based on this, this paper will improve the traditional wavelet denoising algorithm, abandon the single-threshold judgment of the original traditional algorithm, innovatively adopt the combination of soft threshold and hard threshold, further solve the distortion problem of the denoising algorithm in the process of English speech translation signal recognition, improve the signal-to-noise ratio of English speech recognition, and further reduce the root mean square error of the signal. Good noise reduction effect is realized, and the accuracy of speech recognition is improved. In the experiment, the algorithm is compared with the traditional algorithm based on MATLAB simulation software. The simulation results are consistent with the actual theoretical results. At the same time, the algorithm proposed in this paper has obvious advantages in the recognition accuracy of English speech translation signals, which reflects the superiority and practical value of the algorithm.

scholarly journals A Radar Signal Recognition Approach via IIF-Net Deep Learning Models

2020 ◽  
Vol 2020 ◽  
pp. 1-8
Author(s):  
Ji Li ◽  
Huiqiang Zhang ◽  
Jianping Ou ◽  
Wei Wang
Keyword(s):  
Recognition Accuracy ◽  
Signal To Noise Ratio ◽  
Recognition Rate ◽  
Software Radio ◽  
Radar Signal ◽  
Signal Recognition ◽  
Electromagnetic Environment ◽  
Time Frequency ◽  
Low Snr ◽  
Radar Signals

In the increasingly complex electromagnetic environment of modern battlefields, how to quickly and accurately identify radar signals is a hotspot in the field of electronic countermeasures. In this paper, USRP N210, USRP-LW N210, and other general software radio peripherals are used to simulate the transmitting and receiving process of radar signals, and a total of 8 radar signals, namely, Barker, Frank, chaotic, P1, P2, P3, P4, and OFDM, are produced. The signal obtains time-frequency images (TFIs) through the Choi–Williams distribution function (CWD). According to the characteristics of the radar signal TFI, a global feature balance extraction module (GFBE) is designed. Then, a new IIF-Net convolutional neural network with fewer network parameters and less computation cost has been proposed. The signal-to-noise ratio (SNR) range is −10 to 6 dB in the experiments. The experiments show that when the SNR is higher than −2 dB, the signal recognition rate of IIF-Net is as high as 99.74%, and the signal recognition accuracy is still 92.36% when the SNR is −10 dB. Compared with other methods, IIF-Net has higher recognition rate and better robustness under low SNR.

IMAGE IMPROVEMENT IN THE WAVELET DOMAIN FOR OPTICAL COHERENCE TOMOGRAMS

2011 ◽  
Vol 04 (01) ◽  
pp. 73-78 ◽  
Author(s):  
YINGLI WANG ◽  
YANMEI LIANG ◽  
JINGYI WANG ◽  
SHU ZHANG
Keyword(s):  
Signal To Noise Ratio ◽  
Wavelet Denoising ◽  
Processing Method ◽  
Optical Coherence ◽  
Context Modeling ◽  
Wavelet Domain ◽  
Signal To Noise ◽  
Contrast Measure ◽  
Image Improvement

In this paper, an image processing method for improving the quality of optical coherence tomography (OCT) images is proposed. Wavelet denoising based on context modeling and contrast enhancement by means of the contrast measure in the wavelet domain is carried out on the OCT images in succession. Three parameters are selected to assess the effectiveness of the method. It is shown from the results that the proposed method can not only enhance the contrast of images, but also improve signal-to-noise ratio. Compared with two other typical algorithms, it has the best visual effect.

scholarly journals Increasing reliability of forensic analysis while research on destroyed relief marking with magneto-optical devices

2021 ◽  
Vol 23 (1) ◽  
pp. 148-166
Author(s):  
Yu. Agalidi ◽  
O. Koshel
Keyword(s):  
Optical Imaging ◽  
Signal To Noise Ratio ◽  
Forensic Analysis ◽  
Imaging Method ◽  
Signal Recognition ◽  
Visualization Method ◽  
Signal To Noise ◽  
Instrumental Data ◽  
Noise Ratio ◽  
Correct Signal

While research on destroyed relief marking of metal objects using the magneto-optical method, visualization of (invisible) fields of internal stress in the VIN plate area is performed and then a forensic analysis of obtained instrumental data is carried out (indirect organoleptic observation of the visualization results); thus, forensic analysis reliability of results directly depends on sensitivity of instruments and informativeness of instrumental data. The main quantitative characteristic in this case is probability of correct signal recognition  (contours of marking signs) against the background of noise (structural noise of investigated surface and the noise of the visualization method itself) determined by the signal-to-noise ratio. This article presents results of a comparative experimental assessment of signal-to-noise ratio and probability of correct signal recognition while restoringthe destroyed relief markings for two complexes of magneto-optical imaging – models of 2006 and 2018. This article purpose is a quantitative and qualitative comparative assessment of results of visualization of internal stresses in areas of completely removed relief marking of metal objects. The results of successful practical research obtained by forensic experts from different countries make it possible to assess effectiveness and prospects of using the magneto-optical imaging method. In a new modification of the magneto-optical complex: signal level is 4.35 dB higher (contrast of reconstructed marking signs); 2.71 dB lower noise level (surface relief/texture and magnetic copying noise);• probability of correct character recognition is P> 0.995 (increased by 14.9%). Technical improvements in implementation of magneto-optical visualization method made it possible to expand the range of materials for research objects(magnetic and electrically conductive materials were investigated). The high efficiency of method for restoring marking is illustrated by results of forensic examinations for materials with a low level of residual stresses (aluminum alloy, low-carbon steel) which  chemical etching method did not give results for. The use of new modification allows examining the rust layer, up to cases of corrosion to the entire depth of marks. Considering non-destructive nature of magneto-optical researches, possibility of their repeated repetition without losing  object properties, this method (in accordance with the order of application of types of studies) deserves more attention for application.

Application of Wavelet Method on Preprocessing of Voltage Signals

2010 ◽  
Vol 40-41 ◽  
pp. 272-276
Author(s):  
Li Di Wang ◽  
Nan Zhu ◽  
Jin Kai Li
Keyword(s):  
Mean Squared Error ◽  
Signal To Noise Ratio ◽  
Electrical Parameter ◽  
Wavelet Denoising ◽  
Signal To Noise ◽  
Denoising Method ◽  
Wavelet Method ◽  
Squared Error ◽  
Noise Ratio

Wavelet denoising method is applied in the measurement voltage signals in this paper. Noise reduction is important for signal preprocessing in order to achieve many objects such as the improvement of accuracy of modal analysis and electrical parameter identification, the effective extraction of features and auto-matic classification of different kinds of signals. The voltage signals measured from one 35Kv bus are used for the preprocessing research. The denoising effect is evaluated by three parameters, i.e. signal to noise ratio, mean squared error, and capture ability of step points. Compared with the traditional methods including mean filtering and medial filtering, wavelet method is superior in signal to noise ratio and mean squared error.

scholarly journals A Modified MFCC for Improved Wavelet-Based Denoising on Robust Speech Recognition

2021 ◽  
Vol 14 (1) ◽  
pp. 12-21
Author(s):  
Risanuri Hidayat ◽  
◽  
Anggun Winursito ◽  
Keyword(s):  
Speech Recognition ◽  
Signal To Noise Ratio ◽  
Process Analysis ◽  
Recognition System ◽  
Wavelet Denoising ◽  
Robust Speech Recognition ◽  
Speech Recognition System ◽  
Signal To Noise ◽  
Mel Frequency Cepstral Coefficients ◽  
Noise Ratio

Research on the current speech recognition system leads to the creation of a noise-resistant system. The Mel Frequency Cepstral Coefficients (MFCC) extraction method becomes a popular method in the speech recognition system. In this paper, the MFCC's weakness of noise interference is the main reason underlies the accomplishment of a robust speech recognition system. Development was carried out by improving the denoising performance using a wavelet transform. Modifications were carried out by analyzing the weakness of the wavelet denoising process on the recognition system using the MFCC method. The analysis was conducted at one of the MFCC stages, the Fast Fourier Transform (FFT) stage. The proposed method was conducted by performing the denoising process using Wavelet only on the noise-related data based on the FFT process' analysis results. The study utilized speech data in the form of eleven isolated words in English added with noise with several different characteristics. Results showed that the proposed method was capable of generating a better accuracy than conventional wavelet denoising methods on the signal to noise ratio (SNR) of 10dB, 15dB, and 20dB using a Fejer Korovkin 6 wavelet type. The highest accuracy increase of the proposed method was in signal to noise ratio (SNR) of 15dB with a rise of 4.63%, followed by a 3.96% increase at 20dB intensity, and 2.3% at 10dB intensity. The performance of the proposed method is then compared with other methods. The results show that the proposed method has the best performance on clean speech and noisy speech at SNR intensities of 10dB, 15dB, and 20dB.

Age and Information Processing

1982 ◽  
Vol 26 (2) ◽  
pp. 184-188 ◽  
Author(s):  
Jan Moraal
Keyword(s):  
Information Processing ◽  
Signal To Noise Ratio ◽  
The Other ◽  
General Nature ◽  
Sense Organs ◽  
Signal To Noise ◽  
Processing Stage ◽  
Research Findings ◽  
Stage Analysis ◽  
The Brain

The question is raised whether the slowing of behavior with age is of a general nature, affecting all subprocesses or stages of information processing, or whether it can be ‘localized’ in one or more specific stages. Based upon studies on the stage analysis of the reaction process, it is concluded that there is no converging empirical evidence to answer this question in favor of one of the alternatives. The research findings seem to fit very well in the assumption of a lowering of the signal-to-noise ratio with increasing age, i.e. a lowering of the strength of the signals coming from the sense organs to the brain and from one processing stage to the other.

scholarly journals Denoising and Analysis of EMG Signal using Wavelet Transform

2020 ◽  
pp. 13-19
Author(s):  
Iffat Ara
Keyword(s):  
Feature Extraction ◽  
Wavelet Transform ◽  
Time Domain ◽  
Spectrum Analysis ◽  
Surface Electromyography ◽  
Additive Noise ◽  
Signal To Noise Ratio ◽  
Signal To Noise ◽  
Emg Signal ◽  
Classification Time

EMG is the recording of the electrical activity produced within the muscle fibers. Measurement of EMG signal is corrupted by additive noise whose signal-to-noise ratio (SNR) varies. Feature extraction is an important step for EMG classification. Time domain and frequency domain parameters were chosen as representative features for EMG signals. In this thesis, the Wavelet transform and wavelet coefficients have adopted to represent the EMG signals. Wavelet transform (WT) has been applied also in this research for the analysis of the surface electromyography signal (SEMG). The properties of wavelet transform turned out to be suitable for nonstationary EMG signals. Also Spectrum analysis has been applied to various types of EMG signal.

Sign in / Sign up

Export Citation Format

Share Document