基於歷史互動行為及活動相依性之居家多人活動辨識

Home Activity Recognition for Multiple Residents based on Historical Interactive Behaviors and Activity Dependency

褚祐任(You-Ren Chu)

指導教授 ： 曾煜棋

國立交通大學/資訊學院/資訊科學與工程研究所/碩士(2015年)

https://doi.org/10.6842/NCTU.2015.00727

摘要

由於全球人口快速老化，銀髮族的照護日益重要。過去的研究中，曾利用佈建多樣性的感測器在居住的環境中，經由感測器與活動間的配對達到活動辨識，進而得知居住人的生活情況，達成居家關懷的旨意；然而，對於多人的居住環境中，其無法正確得知的個別居住者的活動歸屬，因此將無法達到確切的關懷美意。因此，在這篇研究中，我們將探討多位銀髮族(居住者)環境下的活動辨識及歸屬問題，並提出四項方法來提高辨識表現，其主要的關鍵是利用居住者間的歷史互動習性、兩兩活動間之關聯性，或更進一步透過居住者身上穿戴的裝置提供之資訊，來有效評估觸發活動的可能使用人，進而提升多人環境下活動的辨識準確度。透過真實數據之實驗，其驗證了我們的居家活動辨識方法能夠有效辨識出大部分的活動使用者，其辨識的準確度最高可達89%。

關鍵字

環境輔助生活 ； 人類活動辨識 ； 無線感測網路

並列摘要

Because of aging population, home care system becomes more and more important. In previous works, they construct many types of sensors in living environment to recognize activities by using the match of sensors and activities. According to activity recognition, we can know the health status of residents to achieve home care. However, in multi-resident environment, previous works cannot know the individual activities, so that it cannot achieve home care correctly. Therefore, in this paper, we try to recognize individual activities in multi-resident environment. We propose several methods to increase recognition accuracy. The keys of our methods are using residents’ interactive behaviors, activity dependency and more information from wearable sensors. Through experimental results of real dataset, it verifies our methods can recognize most individual activities effectively. The recognition accuracy of our methods can reach up to 89%.

並列關鍵字

Ambient Assisted Living ； Human Activity Recognition ； Wireless Sensor Networks

參考文獻

[1] R. Costa, D. Carneiro, P. Novais, L. Lima, J. Machado, A. Marques, and J. Neves, “Ambient Assisted Living”, Ubiquitous Computing and Ambient Intelligence, vol. 51, pp. 86-94, 2009.

[2] M. Memon, S. R. Wagner, C. F. Pedersen, F. H. A. Beevi, and F. O. Hansen, “Ambient assisted living healthcare frameworks, platforms, standards, and quality attributes,” Sensors, vol. 14, no. 3, pp. 4312-4341, 2014.

[3] O. Rivera, F. Sancho, M. S?nchez, A. McCormick, A. van Berlo, ? Barrios, J. Benito, J. Yanguas, and I San Sebasti?n, “AAL summit 2012: The Basque country declaration,” Gerontechnology, vol. 11, no. 4, pp. 545-547, 2013.

[4] Y. Zigel, D. Litvak, and I. Gannot, “A method for automatic fall detection of elderly people using floor vibrations and sound-proof of concept on human mimicking doll falls,” IEEE Transactions on Biomedical Engineering, vol. 56, no. 12, pp. 2858-2867, 2009.

[5] H. Alemdar and C. Ersoy, “Wireless sensor networks for healthcare: A survey,” Computer Network, vol. 54, no. 15, pp. 2688–2710, 2010.