DWT-Based Hand Movement Identification of EMG Signals Using SVM

Ahlawat, Vivek; Narayan, Yogendra; Kumar, Divesh

doi:10.1007/978-981-33-6546-9_47

Cited by 6 publications

(1 citation statement)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…SEMG is the study of the signals generated by muscles. The forearm muscles play a significant role in controlling hand motion [11], [12]. In similar ways, different programmed actions of any robotic arm which can include supination/pronation, opening/closing the hand, extended index, pincer, and a rest position; the muscles of interest are chosen from the desired biceps, triceps, thumb, and wrist movements.…”

mentioning

confidence: 99%

SEMG Signals Identification Using DT And LR Classifier by Wavelet-Based Features

Narayan

Kumari

Ranjan

2022

IJEER

Self Cite

View full text Add to dashboard Cite

In the recent era of technology, biomedical signals have been attracted lots of attention regarding the development of rehabilitation robotic technology. The surface electromyography (SEMG) signals are the fabulous signals utilized in the field of robotics. In this context, SEMG signals have been acquired by twenty-five right-hand dominated healthy human subjects to discriminate the various hand gestures. The placement of SEMG electrodes has been done according to the predefined acupressure point of required hand movements. After the SEMG signal acquisition, pre-processing and noise rejection have been performed. The de-noising and four levels of SEMG signal decomposition have been accomplished by discrete wavelet transform (DWT). In this article, the third and fourth-level detail coefficients have been utilized for time-scale feature extractions. The performance of ten time-scale features has been evaluated and compared to each other with the three-fold cross-validation technique by using a Decision Tree (DT) and Linear Regression (LR) classifier. The results demonstrated that the DT classifier classification accuracy was found superior to the LR classifier. By using the DT classifier technique 96.3% accuracy has been achieved, with all combined features as a feature vector.

show abstract

mentioning

confidence: 99%