A pointing facilitation system for motor-impaired users combining polynomial smoothing and time-weighted gradient target prediction models. Issue 1 (2nd January 2017)

• Record Type: Journal Article
• Authors: Blow, Nikolaus; Biswas, Pradipta
• Is Part Of: Assistive technology. Volume 29:Issue 1(2017)
• Page Start: 48
• Page End: 60
• Publication Date: 2017-01-02
• Subjects: hand strength evaluation -- motor-impairment -- pointing facilitation -- polynomial smoothing -- target prediction; Self-help devices for people with disabilities -- Periodicals; Medicine, Physical -- Equipment and supplies -- Periodicals; Rehabilitation -- Equipment and supplies -- Periodicals; Biomedical Engineering -- instrumentation -- Periodicals; 617.03305
• DOI: 10.1080/10400435.2016.1178670
• Languages: English
• ISSNs: 1040-0435

Abstract

ABSTRACT: As computers become more and more essential for everyday life, people who cannot use them are missing out on an important tool. The predominant method of interaction with a screen is a mouse, and difficulty in using a mouse can be a huge obstacle for people who would otherwise gain great value from using a computer. If mouse pointing were to be made easier, then a large number of users may be able to begin using a computer efficiently where they may previously have been unable to. The present article aimed to improve pointing speeds for people with arm or hand impairments. The authors investigated different smoothing and prediction models on a stored data set involving 25 people, and the best of these algorithms were chosen. A web-based prototype was developed combining a polynomial smoothing algorithm with a time-weighted gradient target prediction model. The adapted interface gave an average improvement of 13.5% in target selection times in a 10-person study of representative users of the system. A demonstration video of the system is available athttps://youtu.be/sAzbrKHivEY