PC3: Myo, Myself and I: Utilizing Myoelectric Data in User Interfaces for Hand Prostheses and beyond


The course will make participants feel like a cyborg in controlling systems with their muscle signals. Participants will construct their own user interface which analyzes muscle signals (myoelectric signals) to infer the user’s intended command in real time. Such user interfaces become increasingly important in medical research where they promise to let amputees control prosthetic devices intuitively and rapidly: users can just think of a movement, thereby creating a muscle signal, which is interpreted by the user interface to generate the desired action of the prosthesis.

During the course, participants will be provided with the necessary basic knowledge, programming tools, and myoelectric sensors to build a myoelectric user interface. Attendees are free in their choice of software project, but a simple basic project will be provided (controlling a basic 2D video game). We kindly request that participants bring their own laptops and download the required software before the course as described at https://techfak.uni-bielefeld.de/~bpaassen/ik2018.html.

In more detail, the sessions will cover:
1. An introduction to myoelectric user interfaces, with a focus on prosthetics research, as well as some basics in signal processing and the use of machine learning approaches for such user interfaces. The session will also be used to form work groups of participants.
2. An introduction to the specific tools used in the course and some first steps in building the projects.
3. Further work on the projects.
4. Display session for the resulting user interfaces.

We are excited to give this course and are looking forward to your participation :)


The course aims at providing participants with a first glance into the engineering of myoelectric interfaces, which will require interdisciplinary knowledge in the application domain, classic engineering techniques such as signal processing, as well as machine learning. Participants will also extend their ability to work in interdisciplinary teams and produce rapid prototypes.


- Farina, D., Jiang, N., Rehbaum, H., Holobar, A., Graimann, B., Dietl, H. & Aszmann, O. (2014). The extraction of neural information from the surface emg for the control of upper-limb prostheses: Emerging avenues and challenges. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 22(4):797–809. doi: 10.1109/TNSRE.2014.2305111

- Prahm, C., Paaßen, B., Schulz, A., Hammer, B., & Aszmann, O. (2016). Transfer Learning for Rapid Re-calibration of a Myoelectric Prosthesis after Electrode Shift. In J. Ibáñez, J. Gonzáles-Vargas, J. M. Azorín, M. Akay, & J. L. Pons (Eds.), Converging Clinical and Engineering Research on Neurorehabilitation II: Proceedings of the 3rd International Conference on NeuroRehabilitation (ICNR2016) (pp. 153–157). Springer. doi: 10.1007/978-3-319-46669-9_28, preprint: https://pub.uni-bielefeld.de/publication/2904178

Course location

Forum 2

Course requirements


Instructor information.

Alexander Schulz


Alexander Schulz defended his PhD. thesis with the title Discriminative Dimensionality Reduction: Variations, Applications, Interpretations at CITEC, Bielefeld University in early 2017. Currently, he is working on the CITEC research project Towards Cognitive Control: Transfer Learning for Robust Steering of Myoelectric Devices in collaboration with the CD Laboratory for Restoration of Extremity Function from the Medical University of Vienna.



Cosima Prahm


Cosima Prahm works on her PhD in Clinical Neuroscience at the CD Laboratory for Restoration of Extremity Function at the Medical University of Vienna with a focus on Biomedical Engineering and Medical Informatics – human computer interfaces, advanced prosthesis control, virtual reality, game design and rehabilitation systems for upper limb amputees and nerve injuries.



Benjamin Paaßen


Benjamin Paaßen received his Masters degree in Intelligent Systems from Bielefeld University, Germany in 2015. Since then, he works on his PhD. in the DFG funded research project Learning Dynamic Feedback in Intelligent Tutoring Systems. His research interests include metrics for structured data, metric learning, transfer learning and intelligent tutoring systems.