A sensory grammar for inferring behaviors in sensor networks

Abstract

The ability of a sensor network to parse out observable activities into a set of distinguishable actions is a powerful feature that can potentially enable many applications of sensor networks to everyday life situations. In this paper we introduce a framework that uses a hierarchy of Probabilistic Context Free Grammars (PCFGs) to perform such parsing. The power of the framework comes from the hierarchical organization of grammars that allows the use of simple local sensor measurements for reasoning about more macroscopic behaviors. Our presentation describes how to use a set of phonemes to construct grammars and how to achieve distributed operation using a messaging model. The proposed framework is flexible. It can be mapped to a network hierarchy or can be applied sequentially and across the network to infer behaviors as they unfold in space and time. We demonstrate this functionality by inferring simple motion patterns using a sequence of simple direction vectors obtained from our camera sensor network testbed.

Online Filtering, Smoothing and Probabilistic Modeling of Streaming data

“…• Probabilistically modeling high-level events from low-level sensor readings: Automatically recognizing higher level events such as user activities through use of unobtrusive sensing technologies is considered a key in the field of Ubiquitous computing [9,34,26]. For instance, Patterson et al [34] demonstrate how the transportation mode of a user can be learned using GPS readings, which they then use to design a guiding device for cognitively impaired people.…”

The BehaviorScope framework for enabling ambient assisted living

“…Figure 10a shows the occupancy of the living room of Deployment A (person living alone) for the duration of a week (August [9][10][11][12][13][14][15]2007). From this figure it is easy to observe that the person spends significant amounts of time in the living room, and usually around the same time of the day.…”

“…The basic interpretation blocks in this hierarchy are probabilistic context-free grammars (PCFGs) [11,12] that can be either specified by the user or even automatically extracted from the collected data as shown in [9,10]. Through a simple high-level interface, users provide a collection of probabilistic rules that form a PCFG.…”

Event Detection in Wireless Sensor Networks – Can Fuzzy Values Be Accurate?

“…Dempster-Shafer evidence theory has been applied to intrusion detection [12], sensor fusion [13,14], and assisted living applications [15]. Probabilistic context free grammars have been used to solve problems such as inferring behaviors [16] as well as movement and activity monitoring [17,18].…”