Pärkkä Juha, Cluitmans Luc, Ermes Miikka
VTT Technical Research Centre of Finland, P.O. Box 1300, Tampere 33101, Finland.
IEEE Trans Inf Technol Biomed. 2010 Sep;14(5):1211-5. doi: 10.1109/TITB.2010.2055060.
Inactive and sedentary lifestyle is a major problem in many industrialized countries today. Automatic recognition of type of physical activity can be used to show the user the distribution of his daily activities and to motivate him into more active lifestyle. In this study, an automatic activity-recognition system consisting of wireless motion bands and a PDA is evaluated. The system classifies raw sensor data into activity types online. It uses a decision tree classifier, which has low computational cost and low battery consumption. The classifier parameters can be personalized online by performing a short bout of an activity and by telling the system which activity is being performed. Data were collected with seven volunteers during five everyday activities: lying, sitting/standing, walking, running, and cycling. The online system can detect these activities with overall 86.6% accuracy and with 94.0% accuracy after classifier personalization.
如今，缺乏运动和久坐的生活方式在许多工业化国家都是一个主要问题。自动识别身体活动类型可用于向用户展示其日常活动的分布情况，并激励他养成更积极的生活方式。在本研究中，对一个由无线运动手环和个人数字助理（PDA）组成的自动活动识别系统进行了评估。该系统将原始传感器数据在线分类为活动类型。它使用决策树分类器，其计算成本低且电池消耗少。通过进行一小段活动并告知系统正在进行的活动，分类器参数可以在线个性化。在七名志愿者进行五项日常活动（躺、坐/站、步行、跑步和骑自行车）期间收集了数据。该在线系统在分类器个性化之前检测这些活动的总体准确率为86.6%，个性化之后准确率为94.0%。
