In this paper, we propose to use two EMI-Gloves connected to an IBM compatible PC via Degraded HyperEllipsoidal Composite Neural Networks (DHECNNs) to implement a prototype speaking aid for the deaf or non-vocal persons. Using a special learning scheme, the DHECNNs can quickly learn the complex mapping of measurements of ten fingers' flex angles to corresponding categories. The prototype speaking aid is evaluated for the classification of 51 static hand gestures from 4 'speakers'. The recognition accuracy for the testing set is 92.3%.
|頁（從 - 到）||351-357|
|期刊||Biomedical Engineering - Applications, Basis and Communications|
|出版狀態||已出版 - 1 1月 1996|