Few-shot similarity learning for motion classification via electromyography
Liu R, Paaßen B (2024)
In: 32nd European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN). Verleysen M (Ed); .
Konferenzbeitrag | Englisch
Download
Es wurden keine Dateien hochgeladen. Nur Publikationsnachweis!
Autor*in
Liu, Rui;
Paaßen, BenjaminUniBi 
Herausgeber*in
Verleysen, Michel
Abstract / Bemerkung
Accurate motion classification from surface electromyography signals is crucial for controlling bionic prostheses. Unfortunately, most state-of-the-art classifiers need to be re-trained with lots of data to recognize any new motion. Therefore, we propose a few-shot similarity learning approach that can be applied to new classes without any re-training, just using one to five reference points per new class. In experiments on two real-world data sets, we find that our proposed approach outperforms two state-of-the-art approaches for few-shot learning on sEMG signals, namely a transfer learning and a contrastive learning approach. Our experiments also reveal that the choice of loss function is crucial for performance whereas the choice of similarity function has less effect.
Erscheinungsjahr
2024
Titel des Konferenzbandes
32nd European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN)
Konferenz
32nd European Symposium on Artificial Neural Networks (ESANN)
Konferenzort
Bruges, Belgium
Konferenzdatum
2024-10-09 – 2024-10-11
Page URI
https://pub.uni-bielefeld.de/record/2993304
Zitieren
Liu R, Paaßen B. Few-shot similarity learning for motion classification via electromyography. In: Verleysen M, ed. 32nd European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN). 2024.
Liu, R., & Paaßen, B. (2024). Few-shot similarity learning for motion classification via electromyography. In M. Verleysen (Ed.), 32nd European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN). https://doi.org/10.14428/esann/2024.ES2024-43
Liu, Rui, and Paaßen, Benjamin. 2024. “Few-shot similarity learning for motion classification via electromyography”. In 32nd European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN), ed. Michel Verleysen.
Liu, R., and Paaßen, B. (2024). “Few-shot similarity learning for motion classification via electromyography” in 32nd European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN), Verleysen, M. ed.
Liu, R., & Paaßen, B., 2024. Few-shot similarity learning for motion classification via electromyography. In M. Verleysen, ed. 32nd European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN).
R. Liu and B. Paaßen, “Few-shot similarity learning for motion classification via electromyography”, 32nd European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN), M. Verleysen, ed., 2024.
Liu, R., Paaßen, B.: Few-shot similarity learning for motion classification via electromyography. In: Verleysen, M. (ed.) 32nd European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN). (2024).
Liu, Rui, and Paaßen, Benjamin. “Few-shot similarity learning for motion classification via electromyography”. 32nd European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN). Ed. Michel Verleysen. 2024.
Open Access
Google Scholar