ESS - BBB - Livro, parte de livro ou capítulo de livro
Permanent URI for this collection
Browse
Browsing ESS - BBB - Livro, parte de livro ou capítulo de livro by Subject "Classification"
Now showing 1 - 2 of 2
Results Per Page
Sort Options
- Patient classification and automatic configuration of an intelligent wheelchairPublication . Faria, Brígida Mónica; Reis, Luís Paulo; Lau, Nuno; Soares, João Couto; Vasconcelos, SérgioThe access to instruments that allow higher autonomy to people is increasing and the scientific community is giving special attention on designing and developing such systems. Intelligent Wheelchairs (IW) are an example of how the knowledge on robotics and artificial intelligence may be applied to this field. IWs can have different interfaces and multimodal interfaces enabling several inputs such as head movements, joystick, facial expressions and voice commands. This paper describes the foundations for creating a simple procedure for extracting user profiles, which can be used to adequately select the best IW command mode for each user. The methodology consists on an interactive wizard composed by a flexible set of simple tasks presented to the user, and a method for extracting and analyzing the user’s execution of those tasks. The results showed that it is possible to extract simple user profiles, using the proposed method.
- Protein attributes-based predictive tool in a down syndrome mouse model: a machine learning approachPublication . Ribeiro-Machado, Cláudia; Silva, Sara Costa; Aguiar, Sara; Faria, Brígida MónicaDown syndrome is a disorder caused by an imbalance in the 21 chromosome, affecting learning and memorizing abilities, which was shown to be improved with memantine administration. In this study we intent to determine the most relevant proteins that could play a role in learning ability, suitable for possible biomarkers and to evaluate the accuracy of several bioinformatic models as a predictive tool. Five different supervised learning models (K-NN, DT, SVM, NB, NN) were applied to the original database and the newly created ones from eight attribute weighting models. Model accuracies were calculated through cross validation. Nine proteins revealed to be strong candidates as future biomarkers and K-NN and Neural Network had the better overall performances and highest accuracies (86.26% ± 0.23%; 81.51% ± 0.48%), which makes them a promising predictive tool to study protein profiles in DS patients’ follow-up after treatment with memantine.