Multi-subject/daily-life activity EMG-based control of mechanical hands

Abstract

Background: Forearm surface electromyography (EMG) has been in use since the Sixties to feed-forward control active hand prostheses in a more and more refined way. Recent research shows that it can be used to control even a dexterous polyarticulate hand prosthesis such as Touch Bionics's i-LIMB, as well as a multifingered, multi-degree-of-freedom mechanical hand such as the DLR II. In this paper we extend previous work and investigate the robustness of such fine control possibilities, in two ways: firstly, we conduct an analysis on data obtained from 10 healthy subjects, trying to assess the general applicability of the technique; secondly, we compare the baseline controlled condition (arm relaxed and still on a table) with a "Daily-Life Activity" (DLA) condition in which subjects walk, raise their hands and arms, sit down and stand up, etc., as an experimental proxy of what a patient is supposed to do in real life. We also propose a cross-subject model analysis, i.e., training a model on a subject and testing it on another one. The use of pre-trained models could be useful in shortening the time required by the subject/patient to become proficient in using the hand.

Results: A standard machine learning technique was able to achieve a real-time grip posture classification rate of about 97% in the baseline condition and 95% in the DLA condition; and an average correlation to the target of about 0.93 (0.90) while reconstructing the required force. Cross-subject analysis is encouraging although not definitive in its present state.

Conclusion: Performance figures obtained here are in the same order of magnitude of those obtained in previous work about healthy subjects in controlled conditions and/or amputees, which lets us claim that this technique can be used by reasonably any subject, and in DLA situations. Use of previously trained models is not fully assessed here, but more recent work indicates it is a promising way ahead.

Figure 1

The three different grips employed in the experiment: (left) index precision grip; (center) other fingers precision grip; (right) power grasp.

Figure 2

Part of the experimental setup: (left) an EMG wireless electrode; (center) the force sensor; (right) typical placement of the EMG electrodes on a subject's forearm (ventral side).

Figure 3

(left) Typical raw EMG (red) and force (blue) signals, as read from the electrodes and force sensor; (right) frequency diagram of the EMG signal.

Figure 4

(left to right) Effects of the RMS on the bandwidth of the EMG signals, for T_RMS = 20, 100, 500 ms.

Figure 5

Classification (top) and regression (middle, correlation to target; bottom, NRMSE) results obtained by the system, on both phases of the experiment (FA and SA) and for each subject.

Figure 6

Comparing true (black continuous line) and guessed (red dotted line) force values for regression of a typical subject (number 6, FA phase).

Figure 7

Confusion matrices for the SA (left) and FA phase (right). Each matrix is the average over the confusion matrices of the 10 subjects. A confusion matrix C is such that its (i, j)th element is the fraction of i labels mistaken for j labels, over the total mistaken labels.

Figure 8

Classification (top) and regression (bottom, correlation to target) results obtained testing on SA-data models trained on FA, and vice-versa.

Figure 9

Size of the training set (red dotted line) and classification performance (blue continuous line), of subject 8 in the FA phase, as d changes.

Figure 10

Cross-subject performance matrices, for classification (top row) and regression (bottom row), in the SA (left column) and FA phase (right column); the numbers refer to all element of the matrices, excluding the diagonals.