PubMed Health⌕ Search
Home/Archive/PubMed

PubMed · 9865887

EMG pattern recognition based on artificial intelligence techniques.

S H Park·S P Lee
View original source ↗Export metadata ↓

Abstract

This paper presents an electromyographic (EMG) pattern recognition method to identify motion commands for the control of a prosthetic arm by evidence accumulation based on artificial intelligence with multiple parameters. The integral absolute value, variance, autoregressive (AR) model coefficients, linear cepstrum coefficients, and adaptive cepstrum vector are extracted as feature parameters from several time segments of EMG signals. Pattern recognition is carried out through the evidence accumulation procedure using the distances measured with reference parameters. A fuzzy mapping function is designed to transform the distances for the application of the evidence accumulation method. Results are presented to support the feasibility of the suggested approach for EMG pattern recognition.

Explore related subjects

ArmArtificial IntelligenceArtificial LimbsElectromyographyFuzzy LogicHumansPattern Recognition, AutomatedJournal ArticleResearch Support, Non-U.S. Gov't

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

S H Park, S P Lee. 1998. EMG pattern recognition based on artificial intelligence techniques.. https://doi.org/10.1109/86.736154

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related citations

PubMed2000

Organization of cortical activities related to movement in humans.

The extent and function of synchronization of oscillatory elements in the human sensorimotor cortex during movement remains unclear. Here we determine whether synchronization is distributed in both the spatial and frequency domains and whether it changes according to task. Electrocorticographic (ECoG) signals were recorded from presumed nonpathological areas simultaneously with electromyographic (EMG) signals from upper limb muscles during isometric and phasic movement tasks in humans with subdural electrodes in situ for investigation of epilepsy. Functional mapping of the sensorimotor cortex was performed by previous electrical stimulation through the same ECoG electrodes used for recording. Significant coherence between ECoG and EMG was seen at discrete frequencies in the range of 7-100 Hz. There was no predilection for coherence within a given frequency band to be associated with cortical sites that had been functionally defined as producing contralateral arm motor responses on stimulation. However, coherence with muscle in the 7-14 and 15-30 Hz band tended to be associated with ECoG sites that lay close to or within the central sulcus as determined intraoperatively. The spatial pattern and frequency of coherence changed with different tasks, although similarities in the coherence pattern remained for tasks that shared common features. These findings provide support for the hypothesis that that synchronization at specific frequencies links cortical activities into a functional ensemble during voluntary movement.

Arm↗