A preliminary investigation of the effect of force variation for myoelectric control of hand prosthesis

Ali H Al-Timemy, Guido Bugmann, Javier Escudero, Nicholas Outram

Research output: Contribution to conferencePaperpeer-review

Abstract / Description of output

The myoelectric control of prostheses has been an important area of research for the past 40 years. Significant advances have been achieved with Pattern Recognition (PR) systems regarding the number of movements to be classified with high accuracy. However, practical robustness still needs further research. This paper focuses on investigating the effect of the change in force levels by transradial amputee persons on the performance of PR systems. Two below-elbow amputee persons participated in the study. Three levels of forces (low, medium, and high) were recorded for different hand grips with the help of visual feedback from the Electromyography (EMG) signals. Results showed that changing the force level degraded the performance of the myoelectric control system by up to 60% with 12 EMG channels for 4 hand grips and a rest position. We investigated different EMG feature sets in combination with a Linear Discriminant Analysis (LDA) classifier. The performance was slightly better with Time Domain (TD) features compared to Auto Regression (AR) coefficients and Root Mean Square (RMS) features. Finally, the error of the classification was considerably reduced to approximately 17% when the PR system was trained with all force levels.
Original languageEnglish
Pages5758-61
Number of pages4
DOIs
Publication statusPublished - 2013
Event35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society - Osaka, Japan
Duration: 3 Jul 20137 Jul 2013

Conference

Conference35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society
Country/TerritoryJapan
CityOsaka
Period3/07/137/07/13

Fingerprint

Dive into the research topics of 'A preliminary investigation of the effect of force variation for myoelectric control of hand prosthesis'. Together they form a unique fingerprint.

Cite this