著者

村上 知子 瀬戸口 久雄 鳥居 健太郎 内平 直志 Murakami Tomoko Setoguchi Hisao Torii Kentaro Uchihira Naoshi

雑誌

SIG-DOCMAS = SIG-DOCMAS

巻号頁・発行日

no.B102, 2012-03-11

---

In this paper we propose a method to estimate working activities from sensor datawithout user annotation. Estimation of working activities are much more difficult than that ofsimple activities such as ’walking’ and ’still’ in terms of their complexity and length. To addressthis issue, we assume that they are a probabilistic combination of various simple activities andpropose a method to discover working activities by multistage estimation, in which firstly classifysensor data into some basic activities and then estimate them by using topic model.We focusedon nursing service as one of professional working activities, in whicn visualization by estimation ofworking activities is critical, conducted the experiment to observe it in the hospital and verifiedour method.