7/31/2019 ACCAS2011 Paper

1/2

The 7th Asian Conference on Computer Aided Surgery (ACCAS 2011)

Improving of sEMG Signal Feature Combination for Gait

Phase Detection

Jirapong Manit Prakarnkiat Youngkong

King Mongkut's University of Technology, Thonburi King Mongkut's University of Technology, Thonburi52432302@study.fibo.kmutt.ac.th youngkong@fibo.kmutt.ac.th

1. IntroductionSurface electromyography (sEMG) signal is widely

used in many studies as the intelligent prosthetic control

input. While using the raw sEMG signal is difficult toclassify subject movements or activities, various type of

domains extracted from raw signal such as time domain,

frequency domain and time-scale domain were introducedto make the sEMG pattern classification more reliable [1,

2]. But the only one domain feature able to show limited

signal information [3]. {Explain some more} In this study,we present the combination of multiple domain feature setfor improving gait phase recognition performance which is

used in the variable damper above-knee prostheses [].{Explain some more}

2. MethodsA. Data Acquisition

The data was collected with sampling rate of 2000 Hzfrom three muscles; Rectus femoris, Vastus medialis and

Biceps femoris, on both legs. ZeroWire electrodes were

attached on a single leg as shown in figure 1. Five healthy

males subjects between 22 to 34 years old were instructedto walk in a comfortable pace on a 10 meters length hardfloor repeatedly 8 times. Three force plates were placed on

the floor, and used to identify the interval of swing phaseand stance phase. All collected data was labeled its class

number manually; 0 for stance phase and 1 for swingphase.

Figure 1. sEMG electrode location : (1) Rectus femoris(2) Vastus medialis and (3) Biceps femoris

B. Feature Extraction

Two kinds of feature domain, time and frequencydomain, were applied to raw sEMG signal for creating

single and multiple domain feature combination. Time

domain features include Mean Absolute Value (MAV),Variance (VAR), Waveform Length (WL), log-Detector

(logDet) and Willison Amplitude (wAmp). And, frequencydomain features consist of Mean Frequency (MNF) and

Median Frequency (MDF). Data from each channel wasfirst segmented into a 256-sample window, extracted to

seven features from the window data. Next, the windowwas shifted by 64 samples until reaching the end of data.

The combinations of two different domain features were

made by selectively choosing one feature from timedomain and another one from frequency domain.

Therefore, a total number of features for testing is fifteen.

C. Dimensional Reduction

This section is very important for sEMG pattern

classification to obtain an optimal computational time.Hence, the dimensional reduction technique helps making

the input data size smaller. Principle component analysis

(PCA) was proved to be as a good dimensional reductiontechnique for applying with sEMG signal data [ ]. It is a

simple linear projection technique that is fast and easy toimplement. So, it was implemented in this study. At the

end of the part, the dimension of the input feature wasreduced from three to two.

2.4 Pattern Classification

Support Vector Machine (SVM) had been shown to bethe best classifier. Fast computational time and ability to

handle with non-linearity of SVM are advantages whichare suitable for sEMG signal classification [ ]. Radial

basis function (RBF) was used as the kernel function inSVM in this study. The feature with reduced dimension

was divided into two sets, equally. The first set was usedfor training the classifier model and the second set was

used for testing. Output of the classifier is the numberthat associates to the gait phase.

3. ResultsAccuracy is used to show the performance, e.g. the

best feature set shall give the highest accuracy. Table 1 to

4 display accuracies in percent of gait phase detection foreach feature. The average values of accuracy in the time

domain features and in the combination between timedomain and frequency domain are 89.97% and 96.15%,

respectively. The result emphasizes that the combinationbetween two domains feature give higher detection

accuracy. give detection accuracy higher than a single

time domain feature.

7/31/2019 ACCAS2011 Paper

2/2

The 7th Asian Conference on Computer Aided Surgery (ACCAS 2011)

Table 1 Detection accuracy of time domain features.

Feature MAV VAR WL wAmp logDet

% Acc

Table 2 Detection accuracy of frequency domain

features.

Feature MDF MND

% Acc

Table 3 Detection accuracy of combination betweentime domain features and Median Frequency.

Feature MAV+

MDF

VAR+

MDF

WL+

MDF

wAmp+

MDF

logDet

+MDF

% Acc

Table 4 Detection accuracy of combination betweentime domain features and Mean Frequency.

Feature MAV+

MNF

VAR+

MNF

WL+

MNF

wAmp+

MNF

logDet

+MNF

% Acc

4. Conclusions

As shown in the result, the combinations between time

domain feature and frequency domain feature improve the

accuracy of gait phase classification and the bestcombination feature is {wait'n for the result} which shallbe applied in the variable damper above-knee prostheses.

AcknowledgementsThis research was financially supported by National

Science and Technology Development Agency (NSTDA),

the Higher Education Research Promotion and NationalResearch University Project of Thailand, Office of the

Higher Education Commission and King MongkutsUniversity of Technology Thonburi, Thailand, and

medically supported by Sirindhorn National Medical

Rehabilitation Centre (SNMRC).

References

[1] Dennis T, He H, Tood A K. Journal of Nuero-

Engineering and Rehabilitation, 2010, 7:21[2] Zeeshan O K, Zhen G X, Carlo Menon. BioMedical

Engineering Online, 2010, 9:41[3] Mahammadreza A O, Housheng H. Biomedical

Signal Processing and Control 2,- 2007: 275-294[4]

[5][6]

[7]

[8]