Shucheng Dai

PutMode: prediction of uncertain trajectories in moving objects databases

Objective: Prediction of moving objects with uncertain motion patterns is emerging rapidly as a new exciting paradigm and is important for law enforcement applications such as criminal tracking analysis. However, existing algorithms for prediction in spatio-temporal databases focus on discovering frequent trajectory patterns from historical data. Moreover, these methods overlook the effect of some important factors, such as speed and moving direction. This lacks generality as moving objects may follow dynamic motion patterns in real life.Methods: We propose a framework for predicating uncertain trajectories in moving objects databases. Based on Continuous Time Bayesian Networks (CTBNs), we develop a trajectory prediction algorithm, called PutMode (Prediction of uncertain trajectories in Moving objects databases). It comprises three phases: (i) construction of TCTBNs (Trajectory CTBNs) which obey the Markov property and consist of states combined by three important variables including street identifier, speed, and direction; (ii) trajectory clustering for clearing up outlying trajectories; (iii) predicting the motion behaviors of moving objects in order to obtain the possible trajectories based on TCTBNs.Results: Experimental results show that PutMode can predict the possible motion curves of objects in an accurate and efficient manner in distinct trajectory data sets with an average accuracy higher than 80%. Furthermore, we illustrate the crucial role of trajectory clustering, which provides benefits on prediction time as well as prediction accuracy.

Optimal Multiple Sink Nodes Deployment in Wireless Sensor Networks Based on Gene Expression Programming

In wireless sensor networks (WSN) data transmission is usually performed by sensors in manner of multi-hop forwarding towards a central static control center (sink). A lot of cheap, low-powered and energy-limited sensors are deployed in the monitored area and some of these nodes closer to the sink node use up their energy more quickly than other nodes because they relay more packets. Although most of the sensor nodes have enough energy left to work, the energy consumption imbalance leads to connectivity holes and coverage holes, and finally the whole network failure. The main contributions of this paper include: (a) a new scheme based on multiple sink nodes is proposed to prolong the network lifetime and to reduce the response time. It is effective, especially in the target tracking applications, (b) the deployment strategy with given number of multiple sink nodes is explored in the grid sensor network, (c) Gene Expression Programming based Multiple Sink Nodes deployment algorithm (GEP-MSN) is proposed to optimally deploy multiple sink nodes over the monitored region, (d) a data transmission cost model (TCM) is introduced to measure the cost for optimizing during the transmission phase, (e) extensive simulations are conducted to show that the scheme can greatly extend the network lifetime by around 16.6% and 36.3% on average compared with two naive methods based on random distributed sink nodes.

PartSpan: Parallel Sequence Mining of Trajectory Patterns

The trajectory pattern mining problem has recently attracted increasing attention. This paper precisely addresses the parallel mining problem of trajectory patterns as well as the newly proposed concepts with regard to trajectory pattern mining. An efficient parallel trajectory sequential pattern mining (PartSpan) is proposed by incorporating three key techniques: prefix-projection, parallel formulation, and candidate pruning. The prefix-projection technique is used to decompose the search space as well as greatly reducing candidate trajectory sequences. The parallel formulation integrates the data parallel formulation and the task parallel formulation to partition the computations and to assign them to multiple processors in an efficient and effective manner that helps reduce the communication cost across processors. Representative experiments are used to evaluate the performance of PartSpan. The results show that PartSpan outperforms GSP-based and SPADE-based parallel algorithms in mining very large trajectory databases.

Constrained k-closest pairs query processing based on growing window in crime databases

Spatial analysis in crime databases has recently been an active research topic. To solve the problem of finding the closest pairs of objects within a given spatial region, as required in crime geo-data applications, this paper proposes an efficient constrained k-closest pairs query processing algorithm based on growing window. It expands the window gradually instead of searching the whole workspace for multiple types of spatial objects. It employs a density-based range estimation approach to calculate the square query range and an optimized R-tree to store the index entities. In addition, a distance threshold T for the closest pair of objects is introduced to prune tree nodes. Experiments evaluate the effect of three important factors, i.e., the portion of overlapping between the workspaces of two data sets, the value of k, and the size of buffer. The results show that the new algorithm outperforms the heap-based approach.

Light-Weight Target Tracking in Dense Wireless Sensor Networks

Wireless Sensor Networks (WSNs) are widely used in detecting, locating and tracking the moving objects. However, Some of the cheap, low-powered and energy-limited sensors that are deployed in large areas may use up their energy, which leads to the whole network failure finally. In order to reduce the energy consumption and prolong the network lifetime, (a) a new light-weight and energy-efficient locating scheme is proposed to estimate the current target location; (b) an energy-efficient parallel target tracking algorithm based on Gene Expression Programming (P-GEP) is put forward for collaboratively mining the trajectory of the moving target, then, the future locations where the target will appear can be predicted within a given prediction accuracy, and sensor nodes that are far away from the predicted locations can be scheduled to be on/off finally; (c) the sliding window technique is adopted to discard some of the historical locations to balance the trade-off between the prediction accuracy and the energy consumption during the trajectory mining process. Extensive simulations show that the proposed methods can greatly improve the tracking efficiency and extend the network lifetime by around 39.4% and 94.2% compared with other tracking algorithms, i.e., EKF and ECPA.

An Energy-Efficient Tracking Algorithm Based on Gene Expression Programming in Wireless Sensor Networks

Wireless Sensor Networks (WSNs) are widely used in detecting, locating and tracking moving objects. The cheap, low-powered and energy-limited sensors that are set up in large areas may consume large portion of energy and disable the whole network. In this paper, a new energy-efficient method based on Distributed Incremental Gene Expression Programming is proposed to discover the moving patterns of moving objects in order to turn on/off some sensor nodes at certain time to save energy. The main contributions include: a) Distributed GEP methods are used to perform collaborative mining the patterns of moving objects, b) adjustable sliding window are adopted to balance the trade-off of the high accuracy and low energy consumption, c) simulation results show that the proposed GEP-based motion prediction algorithm can greatly improve the tracking efficiency, increase the lifetime of the network by around 25% compared to other tracking algorithms, i.e., EKF and ECPA

Processing Constrained k-Closest Pairs Queries in Crime Databases

Recently, spatial analysis in crime databases has attracted increased attention. In order to cope with the problem of discovering the closest pairs of objects within a constrained spatial region, as required in crime investigation applications, we propose a query processing algorithm called Growing Window based Constrained k-Closest Pairs (GWCCP). The algorithm incrementally extends the query window without searching the whole workspace for multiple types of spatial objects. We use an optimized R-tree to store the index entities and employ a density-based range estimation approach to approximate the query range. We introduce a distance threshold with regard to the closest pair of objects to prune tree nodes in order to improve query performance. Experiments discuss the effect of three important factors, i.e., the portion of overlapping between the workspaces of two data sets, the value of k, and the buffer size. The results show that GWCCP outperforms the heap-based approach as a baseline in a number of aspects. In addition, GWCCP performs better within the same data set in terms of time and space efficiency.

GEP-NFM: Nested Function Mining Based on Gene Expression Programming

Mining the interesting functions from the large scale data sets is an important task in KDD. Traditional gene expression programming (GEP) is a useful tool to discover functions. However, it cannot mine very complex functions. To resolve this problem, a novel method of function mining is proposed in this paper. The main contributions of this paper include: (1) analyzing the limitations of function mining based on traditional GEP, (2) proposing a nested function mining method based on GEP (GEP-NFM), and (3) experimental results suggest that the performance of GEP-NFM is better than that of the existing GEP-ADF. Averagely, compared with traditional GEP-ADF, the successful rate of GEP-NFM increases 20% and the number of evolving generations decrease 25%.

Predicting the Total Workload in Telecommunications by SVMs

As a learning mechanic, support vector machine (SVMs) has been studied and applied in a wide area. This study deals with the special futures of SVM in predicting the total workload in telecommunication. The contributions include: (a) Building a predicted model of the total workload in telecommunications and predicting using it; (b)Analyzing the parameter of support vector regression(SVRs) which influence performance of SVRs. (c) Experiments demonstrate that SVM in this paper outperforms the others methods in this area.

Construct Distributed RFID Data Warehouse Based On Concept Hierarchy

Radio frequency identification (RFID) applications play an important role in business activities nowadays. With the rapidly increasing volume of RFID data, the traditional centralized data warehouses (CDW) can not process RFID efficiently. To solve the problem, this paper proposes a novel model of RFID distributed data warehouse based on concept hierarchy (RFID-CFIDDW). The main contributions include: 1) proposing a new warehousing model, 2) introducing the implementation of the new model, 3) demonstrating the utility and feasibility of the new model via experiments.