Percorrer por data de Publicação, começado por "2021-04-22"
A mostrar 1 - 2 de 2
Resultados por página
Opções de ordenação
- Grasps in daily tasksPublication . Roldão, Elisabete; Pascoal, Augusto GilActivities are done using the hands. With the hand’s grasps are performed on objects, grabbing, manipulating, and using them. There are 33 grasps, according to the recent European Grasp Taxonomy. Grasps are the way objects are grabbed, in a secure mode, independent of the position of the wrist, forearm or arm. To better understand the use of the hands and the grasps in the daily activities and relate it with the difficulties identified by the patients, when they have a hand pathology, we need to know in which tasks are they performed. Using a Delphi Panel, composed by 20 Occupational Therapists also Hand Therapist, considerer experts in this area, we collect data, in two rounds. For each one of the 33 grasps was created a question, with some characteristics of the grasp, such as the number of used fingers and the diameter of the grasped object. Experts were asked to identify the tasks where the grasps are used. An image of the grasp was also presented to exemplify. After the language uniformization, the elimination of tasks that doesn’t complied with the grasp’s characteristics and unification of very similar tasks, there were identify tasks used in work, leisure, and self-care activities. For each one of the grasps there were identified at least 13 tasks. It will be easier for therapists to relate the difficulties in the use of the grasps with the performance of activities in daily living.
- Evolving a multi-classifier system with cartesian genetic programming for multi-pitch estimation of polyphonic piano musicPublication . Miragaia, Rolando; Vega, Francisco Fernandez de; Reis, GustavoThis paper presents a new method for multi-pitch estimation on piano recordings. We propose a framework based on a set of classifiers to analyze the audio input and identify the piano notes present on the given audio signal. Our system's classifiers were evolved using Cartesian Genetic Programming: we take advantage of Cartesian Genetic Programming to evolve a set of mathematical functions that act as independent classifiers for piano notes. Our latest improvements are also presented, including test results using F-measure metrics. Our system architecture is also described to show the feasibility of its parallelization and implementation as a real time system. The proposed approach achieved competitive results, when compared to the state of the art.