TY - JOUR
T1 - Communication aid system for users with physical impairments
AU - Yang, Cheng Huei
AU - Chung, Pau Choo
AU - Chuang, Li Yeh
AU - Yang, Cheng Hong
N1 - Funding Information:
This work was supported in part by the National Science Council R.O.C. under contract NSC-89-2614-E151-001.
PY - 2002/3
Y1 - 2002/3
N2 - For some physically-disabled persons, the conventional computer keyboard may be inappropriate as a usable communication device. They instead require an assistive tool for entering text into a computer or for word-processing for purposes of augmentative and alternative communication in their daily lives. In this study, Morse code is selected as one possible adapted access communication method for persons with impaired hand coordination and limited dexterity. Inherently, a stable switch activation rate is strictly required for the most accurate recognition of Morse code. However, because maintaining a stable switch activation rate is a challenge for many persons who are physically disabled, automatic recognition of Morse code with standardized computer programs is difficult. Therefore, a suitable adaptive automatic recognition method is needed. This study presents a least-mean-square algorithm applied to adaptive Morse code recognition. Four processes are involved in this adaptive Morse code recognition method: space recognition, tone recognition, adaptive processing, and character recognition. Statistical analyses demonstrated that the recognition rate of the proposed method resulted in an 83% improvement over alternative methods described in previous literature.
AB - For some physically-disabled persons, the conventional computer keyboard may be inappropriate as a usable communication device. They instead require an assistive tool for entering text into a computer or for word-processing for purposes of augmentative and alternative communication in their daily lives. In this study, Morse code is selected as one possible adapted access communication method for persons with impaired hand coordination and limited dexterity. Inherently, a stable switch activation rate is strictly required for the most accurate recognition of Morse code. However, because maintaining a stable switch activation rate is a challenge for many persons who are physically disabled, automatic recognition of Morse code with standardized computer programs is difficult. Therefore, a suitable adaptive automatic recognition method is needed. This study presents a least-mean-square algorithm applied to adaptive Morse code recognition. Four processes are involved in this adaptive Morse code recognition method: space recognition, tone recognition, adaptive processing, and character recognition. Statistical analyses demonstrated that the recognition rate of the proposed method resulted in an 83% improvement over alternative methods described in previous literature.
UR - http://www.scopus.com/inward/record.url?scp=0036498846&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0036498846&partnerID=8YFLogxK
U2 - 10.1016/S0898-1221(01)00330-3
DO - 10.1016/S0898-1221(01)00330-3
M3 - Article
AN - SCOPUS:0036498846
SN - 0898-1221
VL - 43
SP - 901
EP - 910
JO - Computers and Mathematics with Applications
JF - Computers and Mathematics with Applications
IS - 6-7
ER -