Abstract:
"Sinhala Letter Writing difficulty identification and letter writing practice in Dyslexia is a
research project aimed at identifying letter writing difficulties in individuals with dyslexia
in Sinhala language, which has not been extensively studied before. The project's focus
on Sinhala language is crucial, as it is a unique language with its own set of challenges in
letter writing. The project incorporates machine learning algorithms and mobile
applications to provide personalized interventions and support to individuals with dyslexia
in their letter writing practice.
The project emphasizes the importance of early identification and intervention in dyslexia
research, and the scope of the project can lead to better outcomes for individuals with
dyslexia by providing timely support. The project also focuses on the identification of
underlying neural mechanisms involved in letter writing difficulties in dyslexia, which
can contribute to a better understanding of the disorder.
The project's scope is important, as it aims to develop interventions that are culturally and
linguistically sensitive to Sinhala language, addressing the unique needs of individuals
with dyslexia in Sinhala-speaking countries. The use of assistive technologies such as
speech-to-text and text-to-speech in the project's scope can greatly benefit individuals with
dyslexia in their letter writing practice.
The evaluation of the project included feedback from domain experts and the target
audience, highlighting the importance, development, usability, and other aspects of the
system. The evaluation on functional and non-functional requirements indicated that the
project has met its initial objectives and provided personalized interventions and support
to individuals with dyslexia.
Despite the promising results, the evaluation of the project has some limitations. These
limitations include a small sample size, lack of a control group, and limited
generalizability to other languages and cultures. Nonetheless, the project's scope and focus
on early identification and intervention, combined with the use of machine learning "
