Ch. Yang et al., The application of the neural network on Morse code recognition for users with physical impairments, P I MEC E H, 215(H3), 2001, pp. 325-331
Citations number
17
Categorie Soggetti
Mechanical Engineering
Journal title
PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART H-JOURNAL OF ENGINEERING IN MEDICINE
Morse code is a simple, speedy and low cost means of communication composed
of a series of dots, dashes and space intervals. Each tone element (either
a dot, dash or space interval) is transmitted by sending a signal for a de
fined length of time. This poses a challenge as the automatic recognition o
f Morse code is dependent upon maintaining a stable typing rate. In this pa
per, a suitable adaptive automatic recognition method, combining the least-
mean-square (LMS) algorithm with a neural network, was applied to this prob
lem. The method presented in this paper is divided into five modules: space
recognition, tone recognition, learning process, adaptive processing and c
haracter recognition. Statistical analyses demonstrated that the proposed m
ethod elicited a better recognition rate in comparison with other methods i
n the literature.