Chen Yinpeng, Baran Michael, Sundaram Hari, Rikakis Thanassis
School of Arts, Media and Engineering, Arizona State University, Tempe, AZ 85287, USA.
Annu Int Conf IEEE Eng Med Biol Soc. 2011;2011:1827-30. doi: 10.1109/IEMBS.2011.6090520.
This paper presents a novel, low-cost, real-time adaptive multimedia environment for home-based upper extremity rehabilitation of stroke survivors. The primary goal of this system is to provide an interactive tool with which the stroke survivor can sustain gains achieved within the clinical phase of therapy and increase the opportunity for functional recovery. This home-based mediated system has low cost sensing, off the shelf components for the auditory and visual feedback, and remote monitoring capability. The system is designed to continue active learning by reducing dependency on real-time feedback and focusing on summary feedback after a single task and sequences of tasks. To increase system effectiveness through customization, we use data from the training strategy developed by the therapist at the clinic for each stroke survivor to drive automated system adaptation at the home. The adaptation includes changing training focus, selecting proper feedback coupling both in real-time and in summary, and constructing appropriate dialogues with the stroke survivor to promote more efficient use of the system. This system also allows the therapist to review participant's progress and adjust the training strategy weekly.
本文提出了一种新颖、低成本、实时自适应的多媒体环境,用于中风幸存者在家中进行上肢康复。该系统的主要目标是提供一种交互式工具,使中风幸存者能够维持在临床治疗阶段取得的进展,并增加功能恢复的机会。这种基于家庭的介导系统具有低成本传感、用于听觉和视觉反馈的现成组件以及远程监测能力。该系统旨在通过减少对实时反馈的依赖并专注于单个任务和任务序列后的总结反馈来持续进行主动学习。为了通过定制提高系统有效性,我们使用治疗师在诊所为每个中风幸存者制定的训练策略中的数据来驱动家庭中的自动化系统适应。这种适应包括改变训练重点、实时和总结时选择适当的反馈耦合,以及与中风幸存者构建适当的对话以促进对系统的更有效使用。该系统还允许治疗师每周审查参与者的进展并调整训练策略。