Feature extraction for multiclass classification: Application to hand gesture recognition

With the recent advances in the biomedical field, a massive amount of data and records (signals) is collected for diagnosis purposes. The correct interpretation and understanding of these signals presents a big challenge for digital health vision. In this work, Quantization-based position Weight Matrix (QuPWM) for feature extraction for multiclass classification is proposed to improve the interpretation of biomedical signals. This method is validated on surface electromyogram (sEMG) signals recognition for eight different hand gestures. The used CapgMyo dataset consists of high-density sEMG signals across 128 channels acquired from 7 intact subjects. The obtained results show that an accuracy of up to 87% can be achieved for some subjects using a logistic regression model, and an average accuracy of 77% has been reached for all subjects using the CapgMyo dataset. The proposed method can be used to extract relevant features in a wide range of biomedical signals such as electroencephalogram (EEG) and magnetoencephalogram (MEG) signals.

Research reported in this publication was supported by King Abdullah University of Science and Technology (KAUST) in collaboration with University of Technology Sydney (UTS).


Permanent link to this record