Publication date: 29/07/2016

Namesort descending Role

Examining board:

Namesort descending Role
ANSELMO FRIZERA NETO Internal Examiner *

Summary: People with disabilities have difficulty interacting with their home devices, due to the limitations inherent to their disability. Simple activities like to turn on or off the lamp, fan, television or any other equipment, independently, may be impossible for this group of people. This work presents a multimodal assistive system to control an intelligent environment through biological signals. The intended users of this system are individuals with severe mobility impairments who desired to acquire more independence inside the home environment. The biological signals considered are sEMG, EOG and VOG. This allows two types of interactions: one employing facial gestures and eye movement, and the other using the eye / gaze tracking. A contribution of this work is the use of conventional low-cost devices, easy to use and quick setup. In the first set of tests, the objective was to evaluate system performance using the Emotiv EPOC and the Eye Tracker, comparing the Transfer Information Rate (ITR) and Utility (U) of both Human-Machine Interfaces (HMI), developed to control the Intelligent Environment. For these tests were preestablished five tasks, which were conducted by ten volunteers. In the second set of tests, the objective was to evaluate the usability (SUS) and performance (GAS) from the user's point of view, by using the Eye Tracker in three different applications: Intelligent Environment Control (IE), Augmentative and Alternative Communication
(AAC) and Virtual Environment (VE). The tests were performed by 17 volunteers (within two people with disabilities in all applications) and 5, 5 and 18 tasks for the three applications (IE, AAC and VE, respectively). Regarding the performance evaluation results, it was observed that 15 of the 17 participants achieved expected or better than expected results on the first use. This result can be further improved, as the participant gets more familiar with the system.

Access to document

Acesso à informação
Transparência Pública

© 2013 Universidade Federal do Espírito Santo. Todos os direitos reservados.
Av. Fernando Ferrari, 514 - Goiabeiras, Vitória - ES | CEP 29075-910