Mining Temporal Moving Patterns in Object Tracking Sensor Networks

Abstract

Advances in wireless communication and microelectronic devices technologies have enabled the development of low-power micro-sensors and the deployment of large scale sensor networks. With the capabilities of pervasive surveillance, sensor networks can be very useful in a lot of commercial and military applications for collecting and processing the environmental data. One of the very interesting research issues is the energy saving in object tracking sensor networks (OTSNs). However, most of the past studies focused only on the aspect of movement behavior analysis or location tracking and did not consider the temporal characteristics, which are very critical in OTSNs. In this paper, we propose a novel data mining method named TMP-Mine with a special data structure named TMP-Tree for discovering temporal moving patterns efficiently. To our best knowledge, this is the first study that explores the issue of discovering temporal moving patterns that contain both movement and time interval simultaneously. Through empirical evaluation on various simulation conditions, TMP-Mine is shown to deliver excellent performance in terms of accuracy, execution efficiency, and scalability.

Distributed object tracking using moving trajectories in wireless sensor networks

“…These algorithms reduce energy consumption by using a state transition model to transition the node's active state to a sleep state at a scheduled time, and causing them to remain in a sleep state for as long as possible. In addition to scheduling, other methods [8,25,26,32,36,37,41] use the movement and location information of an object to predict object future location, tracking the object by waking the predicted node(s) and transiting other nodes to a sleep state. The advantage of these methods is that a majority of nodes in the network are in a sleep state and only a few nodes are active, which reduces energy consumption and extends the lifetime of the network.…”

“…In recent years, many studies [7,13,26,27,36,37] have explored how to mine interesting patterns from object movement data and using these patterns to predict an object's location. The advantage of data mining is that it can find interesting patterns from the database by data processing.…”

“…Lin et al [26] improved Tseng and Lin's [36] proposed method and used it on WSNs. In this method, energy consumption was reduced by discovering seamless temporal movement patterns and considering the storage and energy constraints.…”

“…From [26,32,36], we know that data mining techniques applied to the prediction for target tracking in wireless sensor networks can obtain better prediction accuracy. In addition, distributed approaches for target tracking can lower power consumption.…”

Exploring Group Moving Pattern for an Energy-Constrained Object Tracking Sensor Network

“…Prediction-based schemes predict the future movement of the on-tracking objects according to their latest detected or average velocity to allow an energy efficient wake-up mechanism [6] [7]. Probability-based prediction approaches take advantage of object moving patterns for future location prediction [8] [9][10] [11]. While investigating the factors that dominate energy cost of OTSN, we observe that many creatures such as animals, birds, or insects have social behavior that is they usually form mass organization and migrate together for food, breeding, wintering or other unknown reasons.…”