ISSN: 2165- 7866
Workineh Tesema and Duresa Tamirat
This work presents a word prediction and completion for disable users. The idea behind this work is to open a chance to interact with computer software and file editing for disable users in their mother tongue languages. Like normal persons, disable users are also needs to access technology in their life. In order to develop the model we have used unsupervised machine learning. The algorithm that used in this work was N-grams algorithms (Unigram, Bigram and Trigram) for auto completing a word by predicting a correct word in a sentence which saves time, reduces misspelling, keystrokes of typing and assisting disables. This work describes how we improve word entry information, through word prediction, as an assistive technology for people with motion impairment using the regular keyboard, to eliminate the overhead needed for the learning process. We also present evaluation metrics to compare different models being used in our work. The result argued that prediction yields an accuracy of 90% in unsupervised machine learning approach. This work particularly helps disable users who have poor spelling knowledge or printing press, institutions or government organizations, repetitive stress injuries to their (wrist, hand and arm) but it needs more further investigation for users who have visual problems.