Title: REAL LIFE PILOT SOLUTION WITH ARTIFICIAL INTELLIGENCE FOR DISABLED COMPUTER USERS

Year of Publication: 2013
Page Numbers: 308-312
Authors: Karim Ouazzane, Markson Aigbodi
Conference Name: The Third International Conference on Digital Information Processing and Communications (ICDIPC2013)
- United Arab Emirates

Abstract:


A user’s typing stream contains all the information of user’s interaction with computer by using QWERTY keyboard, which may include user's vocabulary, typing habit and typing performance. This paper is intended to develop a real life pilot solution for disabled people to use computer keyboard more effectively. Also, in this paper an extensive disabled user investigation on the performance of computer QWERTY keyboard is carried out. Then a Focused Time-Delay Neural Network model with extendable input and hidden layer neurons to analyze plain text and user’s historical typing data is fulfilled. Finally, a development of a pilot application as an English input method is introduced. Approximately 50% FT Hitting Rate is obtained from experimental results which are considered as encouraging results and can be applied to symbol prediction and correction.