Support Vector Machines for Mandarin Phonetic Morse Code Recognition

Abstract

Morse code, with its single switch operation, has been shown to be a valuable tool in assistive technology, augmentative and alternative communication, and rehabilitation for people with various neuromuscular diseases, such as amyotrophic lateral sclerosis, multiple sclerosis, and muscular dystrophy. A major hindrance is difficult to maintain a stable typing rate for persons with severe disabilities. In this paper, a combination of two methods, support vector machines and the variable degree variable step least-mean-square algorithm was used to increase the prediction accuracy for Mandarin Morse code recognition. Experimental findings revealed that the proposed method results in a better recognition rate when compared to alternative methods from the literature.