736 resultados para adaptive walking
Resumo:
Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)
Resumo:
Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)
Resumo:
Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)
Resumo:
Self-adaptive Software (SaS) presents specific characteristics compared to traditional ones, as it makes possible adaptations to be incorporated at runtime. These adaptations, when manually performed, normally become an onerous, error-prone activity. In this scenario, automated approaches have been proposed to support such adaptations; however, the development of SaS is not a trivial task. In parallel, reference architectures are reusable artifacts that aggregate the knowledge of architectures of software systems in specific domains. They have facilitated the development, standardization, and evolution of systems of those domains. In spite of their relevance, in the SaS domain, reference architectures that could support a more systematic development of SaS are not found yet. Considering this context, the main contribution of this paper is to present a reference architecture based on reflection for SaS, named RA4SaS (Reference Architecture for SaS). Its main purpose is to support the development of SaS that presents adaptations at runtime. To show the viability of this reference architecture, a case study is presented. As result, it has been observed that RA4SaS has presented good perspective to efficiently contribute to the area of SaS.
Resumo:
Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)
Resumo:
Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)
Resumo:
Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)
Resumo:
Both Semi-Supervised Leaning and Active Learning are techniques used when unlabeled data is abundant, but the process of labeling them is expensive and/or time consuming. In this paper, those two machine learning techniques are combined into a single nature-inspired method. It features particles walking on a network built from the data set, using a unique random-greedy rule to select neighbors to visit. The particles, which have both competitive and cooperative behavior, are created on the network as the result of label queries. They may be created as the algorithm executes and only nodes affected by the new particles have to be updated. Therefore, it saves execution time compared to traditional active learning frameworks, in which the learning algorithm has to be executed several times. The data items to be queried are select based on information extracted from the nodes and particles temporal dynamics. Two different rules for queries are explored in this paper, one of them is based on querying by uncertainty approaches and the other is based on data and labeled nodes distribution. Each of them may perform better than the other according to some data sets peculiarities. Experimental results on some real-world data sets are provided, and the proposed method outperforms the semi-supervised learning method, from which it is derived, in all of them.
Resumo:
Disorders in gait are identified in Parkinson’s disease patients. As a result, the capacity of walking independently and the interaction with the environment can be impairment. So, the auditory cues have been utilized as a non-pharmacological treatment to improve the locomotor impairment of the PD patients. However, these effects were observed in the regular lands and it’s not known the effects of auditory cues in gait during avoidance obstacles that could be more threaten for these patients. Yet, few studies in the literature compare the Parkinson’s disease patients with the older adults during the locomotor tasks and obstacle avoidance in association with the effects of auditory cues. The aim of the study is to compare the effects of the auditory cues in the gait and during obstacle avoidance in PD patients and older adults. 30 subjects distributed in two groups (Group 1 - 15, Parkinson’s disease patients; Group 2 - 15, healthy older adults) are going to participate of this study. After the participation approval, the assessment of clinical condition will be done by a physician. So, to investigate the locomotor pattern, it will be done a kinematic analysis. The experimental task is to walk on 8 m pathway and 18 trials will be done (6 for the free gait and 12 for adaptive gait). For the adaptive gait, two different obstacle heights will be manipulated: high obstacle (HO) and low obstacle (LO). In order to verify possible differences between the groups and the experimental condition, multivariance tests will be used with a significance level of 0.05. MANOVA revealed effect of condition and task. Thus, with DA, we observed an increase in cadence and reduced single support and stride length. When the tasks were compared, it was observed that the LO task, subjects had lower velocity and stride length... 9Complete abstract click electronic access below)
Resumo:
Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)
Resumo:
Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)