The challenge faced by content-based publish/subscribe systems is the ability to handle a vast amount of dynamic information with limited system resources. In current p/s systems, each subscription is processed in isolation. Neither relationships among individual subscriptions are exploited, nor historic information about subscriptions and publications is taken into account. We believe that this neglect limits overall system efficiency. In this paper, we represent subscriptions using modified binary decision diagrams (MBDs), and design an index data structure to maintain distinct predicates and manage associated Boolean variables. Our MBD-based approach can address, in a unified way, publication routing and subscription/advertisement covering and merging. We propose a novel covering algorithm based on MBDs. The algorithm can take historic information about subscription and publication populations into account and exploits relations between subscriptions. We explore merging, especially imperfect merging, and discuss an advertisement-based optimization applicable to subscription merging. 1.

RDF is increasingly being used to represent metadata. RDF Site Summary (RSS) is an application of RDF on the Web that has considerably grown in popularity. However, the way RSS systems operate today does not scale well. In this paper we introduce G-ToPSS, a scalable publish/subscribe system for selective information dissemination. G-ToPSS is particularly well suited for applications that deal with largevolume content distribution from diverse sources. RSS is an instance of the content distribution problem. G-ToPSS allows use of ontology as a way to provide additional information about the data. Furthermore, in this paper we show how G-ToPSS can support RDFS class taxonomies. We have implemented and experimentally evaluated G-ToPSS and we provide results in the paper demonstrating its scalability compared to alternatives.

Abstract. Workflow management systems are traditionally centralized, creating a single point of failure and a scalability bottleneck. In collaboration with Cybermation, Inc., we have developed a content-based publish/subscribe platform, called PADRES, which is a distributed middleware

An important problem for many location-based applications is the continuous evaluation of proximity relations among moving objects. These relations express whether a given set of objects is in a spatial constellation or in a spatial constellation relative to a given point of demarcation in the environment. We represent proximity relations as location constraints, which resemble standing queries over continuously changing location position information. The challenge lies in the continuous processing of large numbers of location constraints as the location of objects and the constraint load change. In this paper, we propose an adaptive location constraint indexing approach which adapts as the constraint load and movement pattern of the objects change. The approach takes correlations between constraints into account to further reduce processing time. We also introduce a new location update policy that detects constraint matches with fewer location update requests. Our approach stabilizes system performance, avoids oscillation, reduces constraint matching time by 70 % for in-memory processing, and reduces secondary storage accesses by 80 % for I/O-incurring environments. Categories and Subject Descriptors

Many location-based services require rich and expressive query language support for filtering large amounts of information. In prominent location-based services thousands of continuous queries execute concurrently. Parts of these queries may overlap or logically depend on each other suggesting to amortize the execution over shared sub-queries and ordering queries according to their dependency relations. In this paper spatio-temporal queries constitute location constraints monitored by applications. We develop Constraint Combination Binary Decision Diagrams (CCBDDs), an efficient location constraint matching algorithm based on Binary Decision Diagrams. With CCBDDs, redundant computations for shared sub-queries are avoided, and query dependencies are identified and pruned. Empirical results show that the CCBDD structure greatly improves matching performance by eliminating otherwise redundant computation and memory use in the evaluation. 1.

Given a set of points Q on a road network, an optimal meeting point (OMP) query returns the point on a road network G =(V,E) with the smallest sum of network distances to all the points in Q. This problem has many real world applications, such as minimizing the total travel cost for a group of people who want to find a location for gathering. While this problem has been well studied in the Euclidean space, the recently proposed state-of-the-art algorithm for solving this problem in the context of road networks is still not efficient. In this paper, we propose a new baseline algorithm for the OMP query, which reduces the search space from |Q | ·|E | to |V | + |Q|. We also present two effective pruning techniques that further accelerate the baseline algorithm. Finally, in order to support spatial applications that involve large flow of queries and require fast response, an extremely efficient algorithm is proposed to find a high-quality near-optimal meeting point, which is orders of magnitude faster than the exact OMP algorithms. Extensive experiments are conducted to verify the efficiency of our algorithms. 1.