부산대학교 도서관

Surface EMG is being used as a control source for myoelectric control of upper-limb prosthetics. There has been a concern whether there exists any difference in the EMG of males and females and the features that are proposed in research have been used generally for both males and females. This study aimed to evaluate any difference in EMG and compare the performance of different features for both male and female subjects. The EMG of 11 healthy males and females was recorded using BIOPAC by performing 11 basic hand movements with their dominant hand. The classification was performed using Artificial Neural Networks (ANN) and performing ANOVA tests for 13 basic features. Also, the graphical analysis of comparison of mean RMS values across each channel of each movement and the ANOVA tests for RMS values of males and females were performed. From classification results, it was found that there was no significant difference existed ($\mathrm{p} > 0.05$) except for WL feature where classification accuracies of male subjects ($96.29\pm 3.33$) were significantly higher ($\mathrm{p} < 0.05$) than females subjects ($87.91\pm 11.73$). The feature Mean Frequency achieved the highest classification accuracy for males and females ($97.63\pm 1.76$ and $96.99 \pm 1.57$) followed by AR as the second highest ($97.48\pm 1.82$ and $96.96 \pm 1.65$). Based on RMS of EMG signals, there was no significant difference found between the male and female subjects.