Estimating which Object Type a Sensor Node is Attached to in Ubiquitous Sensor Environment

Estimating which Object Type a Sensor Node is Attached to in Ubiquitous Sensor Environment

Takuya Maekawa (NTT Communication Science Laboratories, Japan), Yutaka Yanagisawa (NTT Communication Science Laboratories, Japan) and Takeshi Okadome (NTT Communication Science Laboratories, Japan)
DOI: 10.4018/jssci.2010101906
OnDemand PDF Download:
List Price: $37.50
10% Discount:-$3.75


By simply attaching sensor nodes to physical objects with no information about the objects, the method proposed in this article infers the type of the physical indoor objects and the states they are in. Assuming that an object has its own states that have transitions represented by a state transition diagram, we prepare the state transition diagrams for such indoor objects as a door, a drawer, a chair, and a locker. The method determines the presumed state transition diagram from prepared diagrams that matches sensor data collected from people’s daily living for a certain period. A 2 week experiment shows that the method achieves high accuracy of inferring objects to which sensor nodes are attached. The method allows us to introduce ubiquitous sensor environments by simply attaching sensor nodes to physical objects around us.
Article Preview

Background And Goal

Obtaining states and state changes of objects is becoming possible by attaching cheap sensor nodes to indoor objects (Intille et al., 2003). This has triggered surveillance studies concerned with end-user sensor installation. The following comments on end-user installation can be found in Beckmann (2004): ‘‘the monetary and time cost of professional installation is prohibitive for non-critical applications’’ and ‘‘leveraging the fact that an end-user is a domain expert for his own home can lead to an application better tailored to his needs or preferences.’’ However, some problems have arisen as regards end-user installation. For example, Beckmann et al. (2004) revealed that some end-users could not understand the meaning of the association itself in the experiment, where a bar-code reader and bar-codes attached to sensor nodes were used to associate a sensor node and the type of object to which the node is attached. Also, it takes an average of 84 minutes for participants to deploy ten sensor nodes in an experiment (this is not only the time needed for the association). If there are dozens of nodes, manual association will become a burden for end-users. Tapia et al. (2004) also mention that installation without association would dramatically reduce the installation time when engineers install the sensors in a home.

Complete Article List

Search this Journal:
Volume 15: 1 Issue (2023): Forthcoming, Available for Pre-Order
Volume 14: 4 Issues (2022): 1 Released, 3 Forthcoming
Volume 13: 4 Issues (2021)
Volume 12: 4 Issues (2020)
Volume 11: 4 Issues (2019)
Volume 10: 4 Issues (2018)
Volume 9: 4 Issues (2017)
Volume 8: 4 Issues (2016)
Volume 7: 4 Issues (2015)
Volume 6: 4 Issues (2014)
Volume 5: 4 Issues (2013)
Volume 4: 4 Issues (2012)
Volume 3: 4 Issues (2011)
Volume 2: 4 Issues (2010)
Volume 1: 4 Issues (2009)
View Complete Journal Contents Listing