Search results
9 records were found.
Tese de Mestrado em Engenharia Mecânica, Universidade Técnica de Lisboa, 1988
Tese de Doutoramento em Engenharia Mecânica, Instituto Superior Técnico, 2005
Tese de Doutoramento em Engenharia Mecânica apresentada ao Instituto Superior Técnico da Universidade Técnica de Lisboa.
The relevance in the study of interaction between elderly and robots may depend on the choice of activities that robots can be developed to perform and the assessment of their impact and importance for older people. This research requires coordinated research between computer engineers and specialists in the humanities and social sciences. Being a recent research area, it is particularly relevant to carefully select the behavioural variables to be analyzed, the methodology adopted and the instruments that allow for a rigorous evaluation. Based on these assumptions, the present study aims to develop Innovative Initiatives for the Promotion of Active Aging in the EUROACE Region. The authors propose an appropriate methodology and instruments to evaluate the impact of the human-robot interaction in the promotion of a more active aging in a group of elderly in a nursing home. The analyzed variables focus on the involvement of the elderly in the activities, their capacity for initiative and to establish social interactions, indicators of well-being and a proactive attitude. The methodology of the study is mixed (qualitative and quantitative), organized as an exploratory case study. Data collection is based on naturalistic observation but variables are quantitatively assessed in a pre/post-test design. The research design identified the narratives of the elderly and the staff of the institution regarding the needs and interests of each elderly person, classified the participants according to the levels of prevailing social interactions, involvement and initiative in activities, considered important variables for an active ageing and, in this sense, demonstrated its adequacy to be used to evaluate the results of the intervention using social assistive robots.
The aim of this work was to develop computational intelligence models based on neural networks (NN), fuzzy models (FM), and support vector machines (SVM) to predict physicochemical composition of bee pollen mixture given their botanical origin. To obtain the predominant plant genus of pollen (was the output variable), based on physicochemical composition (were the input variables of the predictive model), prediction models were learned from data. For the inverse case study, input/output variables were swapped. The probabilistic NN prediction model obtained 98.4% of correct classification of the predominant plant genus of pollen. To obtain the secondary and tertiary plant genus of pollen, the results present a lower accuracy. To predict the physicochemical characteristic of a mixture of bee pollen, given their botanical origin, fuzzy models proven the best results with small prediction errors, and variability lower than 10%.
“This is a post-peer-review, pre-copyedit version of an article published in Journal of Intelligent & Robotic Systems. The final authenticated version is available online at: https://doi.org/10.1007/s10846-019-01107-w”.
