Holloway Catherine, Heravi Behzad, Barbareschi Giulia, Nicholson Sarah, Hailes Stephen
Annu Int Conf IEEE Eng Med Biol Soc. 2016 Aug;2016:3167-3170. doi: 10.1109/EMBC.2016.7591401.
As part of the Accessible Routes from Crowdsourced Cloud Services project (ARCCS) we conducted a series of experiments using the ARCCS sensor to identify push style of wheelchair users. The aim of ARCCS is to make use of a set of well-calibrated sensors to establish a processing chain that then provides ground truth of known accuracy about location, the nature of the environment, and physiological effort. In this paper we focus on two classification problems 1) The push style employed by people as they push themselves and 2) Whether the person is being pushed by an attendant or pushing themselves (independent of push style). Solving the first enables us to develop a level of granularity to pushing classification which transcends rehabilitation and accessibility. The first problem was solved using a wrist-mounted ARCCS sensor, and the second using a wheel-mounted ARCCS sensor. Push styles were classified between semi-circular and arc styles in both indoor and outdoor environments with a high-decrees of precision and recall (>95%). The ARCCS sensor also proved capable of discerning attendant from self-propulsion with near perfect accuracy and recall, without the need for a body-worn sensor.
作为众包云服务无障碍路线项目（ARCCS）的一部分，我们使用ARCCS传感器进行了一系列实验，以识别轮椅使用者的推动方式。ARCCS的目标是利用一组经过良好校准的传感器建立一个处理链，然后提供关于位置、环境性质和生理努力的已知精度的地面真值。在本文中，我们关注两个分类问题：1）人们自行推动时所采用的推动方式；2）此人是由护理人员推动还是自行推动（与推动方式无关）。解决第一个问题使我们能够开发一种推动分类的粒度级别，超越康复和无障碍领域。第一个问题通过佩戴在手腕上的ARCCS传感器解决，第二个问题通过安装在轮椅轮子上的ARCCS传感器解决。在室内和室外环境中，推动方式被分类为半圆形和弧形，精度和召回率都很高（>95%）。ARCCS传感器还证明能够以近乎完美的精度和召回率辨别护理人员推动和自行推动，而无需佩戴在身体上的传感器。
