Unsupervised clustering and classification of upper limb EMG signals during functional movements: a data-driven
arXiv:2605.20599v1 Announce Type: new Abstract: This study presents a comprehensive approach for the clustering and classification of upper-limb surface electromyography (sEMG) signals during functional reach and grasp movements. The methodology was applied to the NINAPRO DB4 dataset, which provides multichannel EMG recordings of 52 gestures. A four-stage pipeline was designed, including signal preprocessing, fea-ture extraction, gesture selection via hierarchical clustering, and comparative model evaluation. Preprocessing involved a fourth-order low-pass filter (0.6 Hz) and Hilbert envelope t
This research is emerging now as advanced AI techniques, particularly in unsupervised learning, mature enough to handle complex biological signal data like electromyography for robust classification.
This study demonstrates data-driven methods for classifying upper limb movements, which is crucial for advancing human-computer interaction, prosthetics, and rehabilitation applications, impacting industries reliant on precise physical control.
The development of robust unsupervised clustering and classification for EMG signals simplifies the often complex and labor-intensive process of training systems for gesture recognition, enabling more adaptable and scalable solutions.
- · Prosthetics manufacturers
- · Rehabilitation therapy providers
- · Human-computer interface developers
- · Healthcare technology
- · Traditional supervised learning methods for gesture recognition
- · Companies relying on manual calibration of EMG systems
Improved control and functionality for advanced prosthetic limbs and exoskeletons.
Accelerated development of AI-driven rehabilitation tools and personalized therapy protocols.
Enhanced integration of bio-signals into daily technology, leading to more intuitive and seamless human-machine interfaces beyond upper limb control.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG