For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
Morse Code Recognition Using Learning Vector Quantization for Persons with Physical Disabilities
IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences
Publication Date: 2001/01/01
Print ISSN: 0916-8508
Type of Manuscript: PAPER
Category: Neural Networks and Bioengineering
Morse code, adaptive signal processing, least-mean-square algorithm, learning vector quantization,
Full Text: PDF(507.4KB)>>
For physically disabled persons, the conventional computer keyboard is insufficient as a useable communication device. In this paper, Morse code is selected as a communication adaptive device for persons with impaired hand coordination and dexterity. Morse code is composed of a series of dots, dashes, and space intervals. Each element is transmitted by sending a signal for a defined length of time. Maintaining a stable typing rate by the disabled is difficult. To solve this problem, a suitable adaptive automatic recognition method, which combines a variable degree variable step size LMS algorithm with a learning vector quantization method, was applied to this problem in the present study. The method presented here is divided into five stages: space recognition, tone recognition, learning process, adaptive processing, and character recognition. Statistical analyses demonstrated that the proposed method elicited a better recognition rate in comparison to alternative methods in the literature.