USING INTERACTIVE AGENTS TO PROVIDE DAILY LIVING ASSISTANCE FOR VISUALLY IMPAIRED PEOPLE
DEFESA DE TESE DE DOUTORADO – Programa de Pós-Graduação em Ciência da Computação
USING INTERACTIVE AGENTS TO PROVIDE DAILY LIVING ASSISTANCE FOR VISUALLY IMPAIRED PEOPLE
ALUNA: Juliana Damasio Oliveira
ORIENTADOR: Dr. Rafael Heitor Bordini
BANCA EXAMINADORA: Dra. Cecilia Dias Flores (PPGCS/UFCSPA), Dra. Regina de Oliveira Heidrich (PPGDCIS/FEEVALE), Dr. Márcio Sarroglia Pinho (PPGCC/PUCRS)
DATA: 10 de novembro de 2021
LOCAL: Videoconferência
HORÁRIO: 14:00
Link para acessar videoconferência
Meeting ID: 964 7478 3584
Passcode: 258504
RESUMO:
Ambient Intelligence (AmI) is considered as a future vision of intelligent computing, where people will be supported by the environment they inhabit. Based on AmI, the Ambient Assisted Living (AAL) technologies emerged to help monitor, assist, and promote a healthy environment. These technologies are an excellent opportunity to improve people´s lives, especially those who live with disabilities or illnesses, such as people who are visually impaired (PVI), who are the focus of this thesis. Our main objective in this work is to determine how AmI interfaces can be made more suitable for the interaction with users who are visually impaired. To do so, we developed an approach based on a multi-agent system, since AAL requires a very advanced form of human-computer interaction, and multi-agent systems are suitable for developing complex adaptive systems, especially distributed and dynamic ones, such as AmI. Our methodology is based on the four steps of the interactive design process. In the first step, we identify the needs of PVI, based on surveys and interviews with end-users and domain experts. In the second step, we create design alternatives based on two systematic literature reviews to identify the resources and guidelines used in ambient intelligence design. We then created the first design alternative based on the first and second steps, which we evaluated with a blind user. In the third step, we create an approach to AAL that includes an interactive multi-agent system to assist visually impaired people at home. Finally, in the last step, we evaluated our approach with human-computer interaction specialists and end-users. As a result, we determined that our approach has elements that allow for natural interaction with users, as well as we identified and discussed improvements and new features for future work. We believe that our findings can point to directions for building AmI systems that are capable of more natural interaction with users. Furthermore, with an important social impact for users who are not always guaranteed their rights to access technological innovations. to access technological innovations.
