摘要: With recent progress in wearable sensing it becomes reasonable for individuals to wear different sensors all day, thus global activity monitoring is establishing. The goals systems are amongst others tell the type of that was performed, duration and intensity. information obtained this way, individual's daily routine can be described detail. One strong motivations achieve these comes from healthcare: able if were performing enough physical maintain or even promote their health. This paper focuses on aerobic activities, targets two main goals: estimate intensity identify basic/recommended activities postures. For purposes, a dataset with 8 subjects 14 recorded, including basic postures, but also examples household (ironing, vacuum cleaning), sports (playing soccer, rope jumping) everyday (ascending descending stairs). Data 3 accelerometers --- placed lower arm, chest foot heart rate monitor analyzed. In paper, first results shown both estimation recognition tasks, performance 87, 54% 86, 80%, respectively.
acm.org
sci-hub.se 参考文章(18)
Gerald Bieber, Jörg Voskamp, Bodo Urban, Activity Recognition for Everyday Life on Mobile Phones international conference on universal access in human-computer interaction. pp. 289- 296 ,(2009) , 10.1007/978-3-642-02710-9_32
L. Alford, What men should know about the impact of physical activity on their health International Journal of Clinical Practice. ,vol. 64, pp. 1731- 1734 ,(2010) , 10.1111/J.1742-1241.2010.02478.X
Tâm Huynh, Bernt Schiele, Analyzing features for activity recognition ambient intelligence. pp. 159- 163 ,(2005) , 10.1145/1107548.1107591
Scott E. Crouter, Kurt G. Clowers, David R. Bassett, A novel method for using accelerometer data to predict energy expenditure. Journal of Applied Physiology. ,vol. 100, pp. 1324- 1331 ,(2006) , 10.1152/JAPPLPHYSIOL.00818.2005
Gerald Bieber, Christian Peter, Using physical activity for user behavior analysis Proceedings of the 1st ACM international conference on PErvasive Technologies Related to Assistive Environments - PETRA '08. pp. 94- ,(2008) , 10.1145/1389586.1389692
J Pärkkä, L Cluitmans, M Ermes, Personalization Algorithm for Real-Time Activity Recognition Using PDA, Wireless Motion Bands, and Binary Decision Tree international conference of the ieee engineering in medicine and biology society. ,vol. 14, pp. 1211- 1215 ,(2010) , 10.1109/TITB.2010.2055060
Ling Bao, Stephen S. Intille, Activity Recognition from User-Annotated Acceleration Data Lecture Notes in Computer Science. pp. 1- 17 ,(2004) , 10.1007/978-3-540-24646-6_1
J. Mattila, Hang Ding, E. Mattila, A. Sarela, Mobile tools for home-based cardiac rehabilitation based on heart rate and movement activity analysis international conference of the ieee engineering in medicine and biology society. ,vol. 2009, pp. 6448- 6452 ,(2009) , 10.1109/IEMBS.2009.5333540
J. Parkka, M. Ermes, K. Antila, M. van Gils, A. Manttari, H. Nieminen, Estimating Intensity of Physical Activity: A Comparison of Wearable Accelerometer and Gyro Sensors and 3 Sensor Locations international conference of the ieee engineering in medicine and biology society. ,vol. 2007, pp. 1511- 1514 ,(2007) , 10.1109/IEMBS.2007.4352588
Miikka Ermes, Juha Parkka, Luc Cluitmans, Advancing from offline to online activity recognition with wearable sensors international conference of the ieee engineering in medicine and biology society. ,vol. 2008, pp. 4451- 4454 ,(2008) , 10.1109/IEMBS.2008.4650199