EMGs are a natural means of HCI because the electrical activity induced by the human's arm muscle movements can be interpreted to used as computer's control commands. In this paper, we present an on-line EMG-MOUSE system that controls movements of a cursor, which are interpretations of 6 pre-defined wrist motions: up, down, left, right, click, and rest. To emphasize a wearability, we designed the hardware in a way that electrodes are located on a circular armband, which wraps around the forearm. The prototype hardware device has as integrated parts both the EMG electrodes and an amplifier for magnifying EMG signals, without using adhesive to attach the electrodes on the forearm. A fuzzy min-max neural network (FMMNN) was used as a classifier. Also, stochastic values such as integral absolute value were used as features for an appropriate classification of the intended wrist motions. From our experiments, we could observe that six distinctive wrist motions can be classified well, once the patterns are learned
[1]
Patrick K. Simpson,et al.
Fuzzy min-max neural networks. I. Classification
,
1992,
IEEE Trans. Neural Networks.
[2]
Robert Rosenberg.
The biofeedback pointer: EMG control of a two dimensional pointer
,
1998,
Digest of Papers. Second International Symposium on Wearable Computers (Cat. No.98EX215).
[3]
Toshio Tsuji,et al.
An EMG controlled pointing device using a neural network
,
1999,
IEEE SMC'99 Conference Proceedings. 1999 IEEE International Conference on Systems, Man, and Cybernetics (Cat. No.99CH37028).
[4]
Jin-Shin Lai,et al.
Design of the human/computer interface for human with disability using myoelectric signal control
,
1997,
Proceedings of the 19th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. 'Magnificent Milestones and Emerging Opportunities in Medical Engineering' (Cat. No.97CH36136).
[5]
P. K. Simpson.
Fuzzy Min-Max Neural Networks-Part 1 : Classification
,
1992
.