Discovery of topological relations for spatial Activity Recognition

Abstract

Abstract-Human Activity Recognition (HAR) is a challenging problem that could enable an outstanding number of applications in pervasive computing. Many approaches have been developed to overcome this issue, but they all suffer from major drawbacks. While some use invasive sensors such as video-cameras and wearable technology, other exploit complex models to only recognize coarse-grained activities. In this paper, we propose to exploit the largely neglected spatial aspects in the smart home to recognize the activity of daily living (ADLs) of a resident in a noninvasive fashion. To do so, we designed an extension to well-known data mining algorithms that we exploit to automatically learn the models of the resident ADLs. The models are built from the retrieval of spatial patterns corresponding to the topological relationships of the smart home entities. We demonstrate the advantages of our new semi-supervised system through comprehensive experiments inside a smart home and compare the results with expert defined models of activity.

Human activity recognition in smart homes based on passive RFID localization

“…Moreover, it is often very difficult to distinguish between a moving and a stationary object because of this issue. In fact, it was a major issue in our previous work on spatial HAR [9].…”

“…The steps of the ADLs possess a maximal normal duration that is used for errors detection. In this work, each ADL was defined by a human expert, but we believe that similarly to [9] we could automatically build that library.…”

“…In this paper, we introduce an enhanced version of our spatial activity recognition algorithm [9] exploiting the real-time elliptic trilateration of objects presented in the previous section. The first important modification is a direct consequence of our enhanced localization method.…”

“…The new version is enhanced for realtime simultaneously tracking of multiple objects in a noisy smart home. Secondly, we propose an updated version of our spatial HAR method that is now able o detect each distinctive step of the ADLs [9]. Very few methods are able to successfully do this on a fine-grained scale.…”

“…Furthermore, they are robust enough to be put in a dishwasher at high temperatures. Many researchers believe that the next step to enhance HAR reside in the better exploitation of temporal [8] and spatial knowledge [9] of what is happening in the smart home. The RFID tags can be used for toward that goal [10] by developing real-time localization algorithms.…”