• Journal of the Ergonomics Society of Korea
• /
• v.29 no.4
• /
• pp.667-671
• /
• 2010

Runs test is a mathematical tool to test the stationarity of electromyographic (EMG) signals. The purpose of this study is to investigate the effects of segmentation size on the stationarity of EMG signals in runs test. Six subjects participated in this experiment and performed isometric trunk exertions for twenty seconds at the load level of 25% and 50% MVC. The signals extracted from the erector spinae muscles were divided into the intervals of 1000ms and the stationarity of the signal in each interval was tested by the runs test. In this test, seven segmentation sizes such as 1.0, 2.0, 3.9, 7.8, 15.6, 31.3 and 62.5ms were applied. Additionally, two stationarity tests of reverse arrangements test and modified reverse arrangements test were used to verify the results of the runs test. In results, the segmentation size of 62.5ms showed the similar results with the other stationarity tests. However, the stationarity values among there tests were different each other when segmentation sizes other than 62.5ms were used. These results indicated the effect of segmentation size in runs test that needs to be considered to have consistent and sensitive result in stationarity test.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.63 no.2
• /
• pp.291-296
• /
• 2014

Most of the statistical signal analysis processed in the time domain and the frequency domain are based on the assumption that the signal is weakly stationary(wide sense stationary). Therefore, it is necessary to know whether the surface EMG signals processed in the statistical basis satisfy the condition of weak stationarity. The purpose of this study is to analyze the accuracy of the Run-test, modified Run-test, RA(reverse arrangement)-test, and modified RA-test for assessing surface EMG signal stationarity. Six stationary and three non-stationary signals were simulated by using sine wave, AR(autoregressive) modeling, and real surface EMG. The simulated signals were tested for stationarity using nine different methods of Run-test and RA-test. The results showed that the modified Run-test method2 (mRT2) classified exactly the surface EMG signals by stationarity with 100% accuracy. This finding indicates that the mRT2 may be the best way for assessing stationarity in surface EMG signals.

• Journal of the Korean Statistical Society
• /
• v.30 no.1
• /
• pp.115-125
• /
• 2001

We consider the threshold autoregressive moving average(TARMA) process and find a sufficient condition for strict stationarity of the proces. Given region for stationarity of TARMA(p,q) model is the same as that of TAR(p) model given by Chan and Tong(1985), which shows that the moving average part of TARMA(p,q) process does not affect the stationarity of the process. We find also a sufficient condition for the existence of kth moments(k$\geq$1) of the process with respect to the stationary distribution.

• Journal of the Ergonomics Society of Korea
• /
• v.29 no.2
• /
• pp.183-188
• /
• 2010

The purpose of this study is to investigate the stationarity of the electromyographic signal in various flexion angles, loads, and window sizes, which influence the result of the mean power frequency (MPF) and median frequency (MNF) analysis. Six healthy subjects participated in the experiment. They were tested in the combination of 3-level flexion angles (0 degree, 22.5 degree, 45 degree) and 3-level loads (0Nm, 30Nm, 60Nm). Electromyographic data were collected for 20 seconds during isometric contraction. The stationarity of collected data were analyzed with four different window sizes including 250, 500, 1000 and 2000ms. Two test methods for stationarity such as Reverse Arrangements Test and Modified Reverse Arrangements Test were used. In order to show the effect of nonstationarity, the increasing/decreasing trend of MPF and MNF trend were discussed. In results, the stationarity of the electromyographic signal decreased as flexion angle increased and load decreased while window size decreased based on Reverse Arrangements Test. The highest stationarity was shown at 500 ms window in Modified Reverse Arrangements Test. The inclination of MNF and MPF indicated 3.6-6.3%, 3.8-5.1% discrepancy compared to the result from stationary data.

• Bulletin of the Korean Mathematical Society
• /
• v.38 no.3
• /
• pp.495-504
• /
• 2001

In this paper we consider the (generalized) autoregressive model with conditional heteroscedasticity (ARCH/GARCH models). We willing give conditions under which strict stationarity, ergodicity and the functional central limit theorem hold for the corresponding models.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.63 no.8
• /
• pp.1128-1133
• /
• 2014

Most of the statistical signal analysis processed in the time domain and the frequency domain are based on the assumption that the signal is weakly stationary(wide sense stationary). Therefore, it is necessary to know whether the surface EMG signals processed in the statistical basis satisfy the condition of the weak stationarity. The purpose of this study is to find optimal segment length of surface EMG signal for assessing stationarity with the modified Run-test and RA-test. Ten stationary surface EMG signals were simulated by AR(autoregressive) modeling, and ten real surface EMG signals were recorded from biceps brachii muscle and then modified to have non-stationary structures. In condition of varying segment length from 20ms to 100ms, stationarity of the signals was tested by using six different methods of modified Run-test and RA-test. The results indicate that the optimal segment length for the surface EMG is 30ms~35ms, and the best way for assessing surface EMG signal stationarity is the modified Run-test (Run2) method using this optimal length.

• Journal of Korean Association for Spatial Structures
• /
• v.7 no.2 s.24
• /
• pp.5-9
• /
• 2007

• Journal of the Korean Data and Information Science Society
• /
• v.18 no.1
• /
• pp.211-218
• /
• 2007

Nonlinear ARMA model $X_n\;=\;h(X_{n-1},{\cdots},X_{n-p},e_{n-1},{\cdots},e_{n-p})+e_n$ is considered and easy-to-check sufficient condition for strict stationarity of {$X_n$} without some irreducibility or continuity assumption is given. Threshold ARMA(p, q) and momentum threshold ARMA(p, q) models are examined as special cases.

• Journal of the Korean Data and Information Science Society
• /
• v.18 no.1
• /
• pp.237-245
• /
• 2007

Nonlinear asymmetric time series models have the growing interest in econometrics and finance. Threshold model is one of the successful asymmetric model. We consider a smooth transition ARMA model which converges a.s. to a threshold ARMA model and show that the smooth transition ARMA model admits a stationary measure, provided a suitable condition on the coefficients of the autoregressive parts of the different regimes is satisfied. Stationarity of a smooth transition GARCH model is also obtained.

• Bulletin of the Korean Mathematical Society
• /
• v.43 no.4
• /
• pp.813-820
• /
• 2006

We consider a MAR model with ARCH type conditional heteroscedasticity. MAR-ARCH model can be derived as a smoothed version of the double threshold AR-ARCH model by adding a random error to the threshold parameters. Easy to check sufficient conditions for strict stationarity, ${\beta}-mixing$ property and existence of moments of the model are given via Markovian representation technique.