Jidong Chen

Modeling and Predicting Future Trajectories of Moving Objects in a Constrained Network

Advances in wireless sensor networks and positioning technologies enable traffic management (e.g. routing traffic) that uses real-time data monitored by GPS-enabled cars. Location management has become an enabling technology in such application. The location modeling and trajectory prediction of moving objects are the fundamental components of location management in mobile locationaware applications. In this paper, we model the road network and moving objects in a graph of cellular automata (GCA), which makes full use of the constraints of the network and the stochastic behavior of the traffic. A simulation-based method based on graphs of cellular automata is proposed to predict future trajectories. Our technique strongly differs from the linear prediction method, which has low prediction accuracy and requires frequent updates when applied to real traffic with velocity changes. The experiments, carried on two different datasets, show that the simulation-based prediction method provides higher accuracy than the linear prediction method.

Update-efficient indexing of moving objects in road networks

Recent advances in wireless sensor networks and positioning technologies have boosted new applications that manage moving objects. In such applications, a dynamic index is often built to expedite evaluation of spatial queries. However, the development of efficient indexes is a challenge due to frequent object movement. In this paper, we propose a new update-efficient index method for moving objects in road networks. We introduce a dynamic data structure, called adaptive unit, to group neighboring objects with similar movement patterns. To reduce updates, an adaptive unit captures the movement bounds of the objects based on a prediction method, which considers road-network constraints and the stochastic traffic behavior. A spatial index (e.g., R-tree) for the road network is then built over the adaptive unit structures. Simulation experiments, carried on two different datasets, show that an adaptive-unit based index is efficient for both updating and querying performances.

Personalization as a service: the architecture and a case study

Cloud computing has become a hot topic in the IT industry. Great efforts have been made to establish cloud computing platforms for enterprise users, mostly small businesses. However, there are few researches about the impact of cloud computing over individual users. In this paper we focus on how to provide personalized services for individual users in the cloud environment. We argue that a personalized cloud service shall compose of two parts. The client side program records user activities on personal de-vices such as PC. Besides that, the user model is also computed on the client side to avoid server overhead. The cloud side program fetches the user model periodically and adjusts its results accordingly. We build a personalized cloud data search engine prototype to prove our idea.

iMecho: an associative memory based desktop search system

Traditional desktop search engines only support keyword based search that needs exact keyword matching to find resources. However, users generally have a vague picture of what is stored but forget the exact location and keywords of the resource. According to observations of human associative memory, people tend to remember things from some memory fragments in their brains and these memory fragments are connected by memory cues of user activity context. We developed iMecho (My Memory Echo), an associative memory based desktop search system, which exploits such associations and contexts to enhance traditional desktop search. Desktop resources are connected with semantic links mined from explicit and implicit user activities according to specific access patterns. Using these semantic links, associations among memory fragments can be built or rebuilt in a users brain during a search. Moreover, our personalized ranking scheme uses these links together with a users personal preferences to rank results by both relevance and importance to the user. In addition, the system provides a faceted search feature and association graph navigation to help users refine and associate search results generated by full-text keyword search. Our experiments investigating precision and recall quality of iMecho prototype show that the association-based search system is superior to the traditional keyword search in personal search engines since it is closer to the way that human associative memory works.

Indexing future trajectories of moving objects in a constrained network

Advances in wireless sensor networks and positioning technologies enable new applications monitoring moving objects. Some of these applications, such as traffic management, require the possibility to query the future trajectories of the objects. In this paper, we propose an original data access method, the ANR-tree, which supports predictive queries. We focus on real life environments, where the objects move within constrained networks, such as vehicles on roads. We introduce a simulation-based prediction model based on graphs of cellular automata, which makes full use of the network constraints and the stochastic traffic behavior. Our technique differs strongly from the linear prediction model, which has low prediction accuracy and requires frequent updates when applied to real traffic with velocity changing frequently. The data structure extends the R-tree with adaptive units which group neighbor objects moving in the similar moving patterns. The predicted movement of the adaptive unit is not given by a single trajectory, but instead by two trajectory bounds based on different assumptions on the traffic conditions and obtained from the simulation. Our experiments, carried on two different datasets, show that the ANR-tree is essentially one order of magnitude more efficient than the TPR-tree, and is much more scalable.

Effective density queries for moving objects in road networks

Recent research has focused on density queries for moving objects in highly dynamic scenarios. An area is dense if the number of moving objects it contains is above some threshold. Monitoring dense areas has applications in traffic control systems, bandwidth management, collision probability evaluation, etc. All existing methods, however, assume the objects moving in the Euclidean space. In this paper, we study the density queries in road networks, where density computation is determined by the length of the road segment and the number of objects on it. We define an effective road-network density query guaranteeing to obtain useful answers. We then propose the cluster-based algorithm for the efficient computation of density queries for objects moving in road networks. Extensive experimental results show that our methods achieve high efficiency and accuracy for finding the dense areas in road networks.

Clustering moving objects in spatial networks

Advances in wireless networks and positioning technologies (e.g., GPS) have enabled new data management applications that monitor moving objects. In such new applications, realtime data analysis such as clustering analysis is becoming one of the most important requirements. In this paper, we present the problem of clustering moving objects in spatial networks and propose a unified framework to address this problem. Due to the innate feature of continuously changing positions of moving objects, the clustering results dynamically change. By exploiting the unique features of road networks, our framework first introduces a notion of cluster block (CB) as the underlying clustering unit. We then divide the clustering process into the continuous maintenance of CBs and periodical construction of clusters with different criteria based on CBs. The algorithms for efficiently maintaining and organizing the CBs to construct clusters are proposed. Extensive experimental results show that our clustering framework achieves high efficiency for clustering moving objects in real road networks.

Search your memory ! - an associative memory based desktop search system

We present XSearcher, an associative memory based desktop search system, which exploits associations by creating semantic links of personal desktop resources from explicit and implicit user activities. With these links, associations among memory fragments can be built or rebuilt in a users brain during a search. The personalized ranking scheme uses these links together with a users personal preferences to rank results by both relevance and importance. XSearcher enhances traditional keyword based search systems since it is closer to the way that human associative memory works.

Tracking network-constrained moving objects with group updates

Advances in wireless sensors and position technologies such as GPS enable location-based services that rely on the tracking of continuously changing positions of moving objects. The key issue in tracking techniques is how to minimize the number of updates, while providing accurate locations for query results. In this paper, for tracking network-constrained moving objects, we first propose a simulation-based prediction model with more accurate location prediction for objects movements in a traffic road network, which lowers the update frequency and assures the location precision. Then, according to their predicted future functions, objects are grouped and only the central object in each group reports its location to the server. The group update strategy further reduces the total number of objects reporting their locations. A simulation study has been conducted and proved that the group update policy based on the simulation prediction is superior to traditional update policies with fewer updates and higher location precision.

iMecho: a context-aware desktop search system

In this demo, we present iMecho, a context-aware desktop search system to help users get more relevant results. Different from other desktop search engines, iMecho ranks results not only by the content of the query, but also the context of the query. It employs an Hidden Markov Model (HMM)-based user model, which is learned from users activity logs, to estimate the query context when he submits the query. The results from keyword search are re-ranked by their relevances to the context with acceptable overhead.