Automatic suggestions in computational tool to support communication for people with severe motor limitations

• Grant number: 15/13931-8
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: November 01, 2015
• End date: October 31, 2016
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computer Systems
• Principal Investigator: César Augusto Camillo Teixeira
• Grantee: Guilherme Matheus de Almeida Ramos
• Host Institution: Centro de Ciências Exatas e de Tecnologia (CCET). Universidade Federal de São Carlos (UFSCAR). São Carlos , SP, Brazil

Abstract

The candidate, in collaboration with his supervisor and another student, developed in voluntary activity in the last year, a computational tool (software) to support the communication of people with severe motor limitations but preserving cognitive functions. A camera + software ("eye tracker") captures the movement of the subject's eyes when she looks at the screen of a notebook, and continuously informs to the developed program the coordinates of the point in the screen which is in the viewing focus. Latin alphabet and numeric characters are associated with specific movements. A proper graphical interface guides the person giving direct clues about the necessary movement to specify a character. A sequence of movements define a character sequences that in turn form words and phrases. The high tolerance to precision movements is a quality of the tool which enables the use of low cost "eye tracker" systems and imposes less stress to the user. What is proposed in this project is to promote ways to increase the rate of words generation to increase user communication speed and to reduce her effort and stress. The candidate will study, adapt and implement algorithms that promote word suggestion, depending on the user communication history and on the initial characters of the word under construction. Accepting the suggestion relieve the user to finish the remaining characters specification. In addition to the effectiveness and efficiency of algorithms, the candidate must still worry about the graphical interface and forms of appropriate interaction for accepting suggestions. (AU)