Thesis (Ph.D.)--University of Nebraska-Lincoln, 2008. / Title from title screen (site viewed Nov. 20, 2008). PDF text: xii, 176 p. : ill. ; 870 K. UMI publication number: AAT 3311253. Includes bibliographical references. Also available in microfilm and microfiche formats.

Participation in regular physical activity provides health, psychological and physiological benefits for people both with and without physical impairment. This thesis describes three sequential studies that were undertaken to examine current patterns of physical and sedentary behaviours and evaluate the impact of internet-based intervention (Get Set) on activity patterns of adolescents with cerebral palsy.

Thesis (Ph. D.)--Auburn University, 2008. / Abstract. Includes bibliographical references (p. 73-75).

Thesis (Ph.D.) - University of Queensland, 2002. / Includes bibliography.

Thesis (M.S.)--Duquesne University, 2007. / Title from document title page. Abstract included in electronic submission form. Includes bibliographical references (p. 92-99) and index.

Thesis (M.S.L.T.)--University of Canterbury, 2009. / Typescript (photocopy). Includes bibliographical references (p. 104-115). Also available via the World Wide Web.

There is no abstract available for this thesis. / Department of Computer Science

Thesis (M.E.E.)--University of Delaware, 2005. / Principal faculty advisor: Kenneth Barner, Dept. of Electrical and Computer Engineering. Includes bibliographical references.

Orientadora: Ligia Maria Presumido Braccialli / Banca: Rita de Cássia Tibério Araújo / Banca: Nilson Rogério da Silva / Banca: Adriana Garcia Gonçalves / Banca: Gerusa Ferreira / Resumo: O computador tem sido cada vez mais utilizado por professores como recurso para o ensino de alunos com paralisia cerebral durante as atividades escolares. Devido aos comprometimentos motores impostos por tal desordem, estes alunos podem apresentar dificuldades de acesso ao computador dependendo do dispositivo de entrada utilizado. Existem dispositivos convencionais, como o mouse e o teclado padrão, e também aqueles de maior tecnologia como a tela sensível ao toque e os acionadores eletrônicos pelo olhar, como o eye tracker, que podem auxiliar neste processo. Mas qual deles proporciona ao aluno com paralisia cerebral, melhor acesso ao computador: o mouse convencional, a tela sensível ao toque ou o eye tracker? O objetivo deste estudo foi avaliar a eficácia destes três dispositivos de entrada no acesso ao computador por alunos com paralisia cerebral. Participaram do estudo 15 alunos com paralisia cerebral com idade entre 6 e 14 anos, com níveis GMFCS e MACS de I a V. Para a avaliação da eficácia dos dispositivos, os participantes usaram um notebook com tela sensível ao toque, um mouse convencional e um eye tracker para realizar tarefas com os seguintes softwares: o Discrete Aiming Task 2.0, para avaliar o tempo de resposta do usuário na tarefa de seleção de alvo; o Tracking Task 2.0, para avaliar o a porcentagem de tempo no círculo e a frequência de erros na seleção e rastreamento de alvo e, o Single Switch Performance Test (SSPT) 1.0 para avaliar o tempo médio de acionamento d... (Resumo completo, clicar acesso eletrônico abaixo) / Abstract: Computer has been increasingly used by teachers as a resource for teaching students with cerebral palsy in school activities. Due to the motor impairments imposed by such disorder, these students may have difficulties in computer access depending on the input device used. There are conventional devices, such as mouse and standard keyboard, as well as those with higher technology such as touch screen and electronic triggers by the look, such as eye tracker, that can help in this process. But which one gives the cerebral palsy students better computer access: the conventional mouse, touch screen or eye tracker? The objective of this study was to evaluate the effectiveness of these three input devices in computer access by cerebral palsy students. Participated in the study fifteen cerebral palsy students aged 6 to 14 years with GMFCS and MACS levels from I to V. For evaluation device efficacy, participants used a notebook with a touch screen, a conventional mouse and a eye tracker to perform tasks with the following softwares: the Discrete Aiming Task 2.0, to evaluate the user response time in the target selection task; Tracking Task 2.0, to evaluate the percentage of time in the circle and the errors frequency in selection and tracking target, and the Single Switch Performance Test (SSPT) 1.0 to evaluate the average trigger time of a target. In order to evaluate the participants' satisfaction with the devices, was used the an analogue visual scale. Finally, users were asked about the devices preference. Non-parametric statistical analysis was performed with significance level p≤0.05. Statistically significant results showed that: (1) Eye tracker caused less error frequency in the use of the Tracking Task v.2.0 software; (2) Mouse had the shortest average drive time in the SSPT; (3) Touch screen was the most effective in the variable ... (Complete abstract click electronic access below) / Doutor

In the hearing-loss community, sign language is a primary tool to communicate with people while there is a communication gap between hearing-loss people with normal hearing people. Sign language is different from spoken language. It has its own vocabulary and grammar. Recent works concentrate on the sign language video caption which consists of sign language recognition and sign language translation. Continuous sign language recognition, which can bridge the communication gap, is a challenging task because of the weakly supervised ordered annotations where no frame-level label is provided. To overcome this problem, connectionist temporal classification (CTC) is the most widely used method. However, CTC learning could perform badly if the extracted features are not good. For better feature extraction, this thesis presents the novel self-attention-based fully-inception (SAFI) networks for vision-based end-to-end continuous sign language recognition. Considering the length of sign words differs from each other, we introduce the fully inception network with different receptive fields to extract dynamic clip-level features. To further boost the performance, the fully inception network with an auxiliary classifier is trained with aggregation cross entropy (ACE) loss. Then the encoder of self-attention networks as the global sequential feature extractor is used to model the clip-level features with CTC. The proposed model is optimized by jointly training with ACE on clip-level feature learning and CTC on global sequential feature learning in an end-to-end fashion. The best method in the baselines achieves 35.6% WER on the validation set and 34.5% WER on the test set. It employs a better decoding algorithm for generating pseudo labels to do the EM-like optimization to fine-tune the CNN module. In contrast, our approach focuses on the better feature extraction for end-to-end learning. To alleviate the overfitting on the limited dataset, we employ temporal elastic deformation to triple the real-world dataset RWTH- PHOENIX-Weather 2014. Experimental results on the real-world dataset RWTH- PHOENIX-Weather 2014 demonstrate the effectiveness of our approach which achieves 31.7% WER on the validation set and 31.2% WER on the test set. Even though sign language recognition can, to some extent, help bridge the communication gap, it is still organized in sign language grammar which is different from spoken language. Unlike sign language recognition that recognizes sign gestures, sign language translation (SLT) converts sign language to a target spoken language text which normal hearing people commonly use in their daily life. To achieve this goal, this thesis provides an effective sign language translation approach which gains state-of-the-art performance on the largest real-life German sign language translation database, RWTH-PHOENIX-Weather 2014T. Besides, a direct end-to-end sign language translation approach gives out promising results (an impressive gain from 9.94 to 13.75 BLEU and 9.58 to 14.07 BLEU on the validation set and test set) without intermediate recognition annotations. The comparative and promising experimental results show the feasibility of the direct end-to-end SLT