Page 164 - Control Theory in Biomedical Engineering

Modeling simple and complex handwriting based on EMG signals 147

and to use only two EMG signals of the most active forearm muscles.
Besides, this approach allows producing simple and complex writing, espe-
cially cursive Arabic letters, containing combing movements. The model
based on the interval observer mitigates the needs for parameter adjustment
for new data. According to Table 3, the interval observer approach allows
ameliorating the estimation of handwriting from EMG signals. Indeed, val-
idation results show good accuracy in both one-writer and multiwriter cases
(Table 3).

7 Conclusion

In this chapter, we presented different approaches that allow the character-
ization of handwriting from muscle activities. The developed models gen-
erate different kinds of writing: numbers, geometric forms and cursive
Arabic letters. These traces have different characteristics, like speed, com-
plexity, orientation, and so on. The proposed approaches are appropriate
for many fields and practical applications such as bio-engineering, bio-
robotics, intelligent therapy and military applications.

References

Adewuyi, A.A., Hargrove, L.J., Kuiken, T.A., 2017. Resolving the effect of wrist position on
myoelectric pattern recognition control. J. Neuroeng. Rehabil. 1, 14–39.
Alimi, M.A., Plamondon, R., 1993. Parameter analysis of handwriting strokes generation
models. In: Proc. International Conference on Handwriting, pp. 4–6.
Artemiadis, P.K., Kyriakopoulos, K.J., 2008. Assessment of muscle fatigue using a probabi-
listic framework for an EMG-based robot control scenario. In: 8th IEEE International
Conference on Bioinformatics and BioEngineering, Athens, pp. 1–6.
Artemiadis, P.K., Kyriakopoulos, K.J., 2010. An EMG-based robot control scheme robust to
time-varying EMG signal features. IEEE Trans. Inf. Technol. Biomed. 14 (3), 582–588.
Artemiadis, P.K., Kyriakopoulos, K.J.A., 2011. Switching regime model for the EMG-based
control of a robot arm. IEEE Trans. Syst. Man Cybern. B (Cybern.) 41 (1), 53–63.
Chen, X., Zhang, D., Zhu, X., 2013. Application of a self-enhancing 22 classification
method to electromyography pattern recognition for multifunctional prosthesis control.
J. Neuroeng. Rehabil. 10 (44), 1–13.
Chihi, I., Benrejeb, M., 2018. Online fault detection approach of unpredictable inputs: appli-
cation to handwriting system. Complexity 2018, 12.
Chihi, I., Abdelkrim, A., Benrejeb, M., 2015. Multi-model approach to characterize human
handwriting motion. Biol. Cybern. 110 (1), 17–30.
Chihi, I., Abdelkrim, A., Benrejeb, M., 2017. Internal model control to characterize human
handwriting motion. Arab J. Appl. Sci. 14 (6), 861–869.
Chihi, I., Sidhom, L., Maamri, O., 2018. Robust handwriting estimator from two forearm
muscles activities. Int. J. Appl. Eng. Res. 13 (23), 16213–16219.