[Show abstract][Hide abstract]ABSTRACT: A Personal DataSpace Management System is a platform to manage personal data with heterogeneous data types, in which keyword query is a primary query form for users who know little about the structure of the dataspace. Unlike exploratory queries in web search, a user in a personal dataspace usually has a specific search target and wants to find some known items in mind. To improve result quality in terms of query relevance in a personal dataspace, we propose the concept of compact index in this paper. We refer to the most important and representative semantics from documents as core content, and build compact index on it. We propose algorithm for selecting core content from a document based on semantic analysis, which can process English and Chinese documents uniformly. Furthermore, a software platform named Versatile is introduced for flexible personal data management, in which core content is extracted for building compact indexes and generating query-biased snippet efficiently and accurately. Finally, extensive experiments have been conducted to show the effectiveness and feasibility of compact indexes in personal dataspace management system.
[Show abstract][Hide abstract]ABSTRACT: Fragment assembly is one of the most important problems of sequence assembly. Algorithms for DNA fragment assembly using de Bruijn graph have been widely used. These algorithms require a large amount of memory and running time to build the de Bruijn graph. Another drawback of the conventional de Bruijn approach is the loss of information. To overcome these shortcomings, this paper proposes a parallel strategy to construct de Bruijin graph. Its main characteristic is to avoid the division of de Bruijin graph. A novel fragment assembly algorithm based on our parallel strategy is implemented in the MapReduce framework. The experimental results show that the parallel strategy can effectively improve the computational efficiency and remove the memory limitations of the assembly algorithm based on Euler superpath. This paper provides a useful attempt to the assembly of large-scale genome sequence using Cloud Computing.
Article · Aug 2012 · Biochemical and Biophysical Research Communications
[Show abstract][Hide abstract]ABSTRACT: Cloud computing is a state-of-the-art distributed computing paradigm which can support on-demand service sharing with flexibility and scalability. Cloud computing provides sharable heterogeneous computing resources using internet and data storage on a third party server. In order to use the heterogeneous computing resources in a much more efficient, scalable and flexible way, a Cloud computing infrastructure HCCloud (Heterogeneous Computing Cloud) has developed. With HCCloud, users no longer have to manually setup machine, or determine where and when to schedule their tasks. By pooling together clusters all over the network, resources are used more efficiently as the infrastructure is self-adaptive to the resources changes, and tasks distribution is fully automated with the best match between task requirements and compute capacity which deployed across a variety physical resources. In this paper we introduce the basic principles of the HCCloud design, and discuss some techniques that have made in order to allow HCCloud to be easily accessed over the Web. The main intention of HCCloud is to decrease the configuration scale of the cluster system through heterogeneous workloads, while increasing the number of requests for parallel workload by provisioning enough resources.
[Show abstract][Hide abstract]ABSTRACT: Considered the commercialization and the virtualization characteristics of cloud computing, the paper proposed for the first time an algorithm of job scheduling based on Berger model. In the job scheduling process, the algorithm establishes dual fairness constraint. The first constraint is to classify user tasks by QoS preferences, and establish the general expectation function in accordance with the classification of tasks to restrain the fairness of the resources in selection process. The second constraint is to define resource fairness justice function to judge the fairness of the resources allocation. We have expanded simulation platform CloudSim, and have implemented the job scheduling algorithm proposed in this paper. The experimental results show that the algorithm can effectively execute the user tasks and manifests better fairness.
Article · Jul 2011 · Advances in Engineering Software
[Show abstract][Hide abstract]ABSTRACT: SIP provides powerful capabilities for building audio conferencing services. However, the scalability for SIP-based telephony systems is mainly limited by both the capability of server and the availability of bandwidth. Based on the study of the SIP and P2P protocol, the paper proposes a pure hierarchical P2P architecture for SIP-based telephony systems. The architecture can dynamically increase the number of users without negative influence on the stability of system. Experimental results show that the hierarchical P2P architecture can significantly reduce both resource lookup latency and physical hops.
[Show abstract][Hide abstract]ABSTRACT: Efficient search in unstructured P2P networks has been extensively studied in the literature. And search in unstructured P2P networks shows promise to become an alternative to the state-of-the-art search engines. However, efficient search techniques for guaranteed location of shared resource in unstructured P2P networks are yet to be devised. The paper presents a simple but highly effective search method based on a hierarchical architecture in unstructured P2P networks. Index management for registered resource and routing algorithm for resource search are employed in the architecture. Simulation results show that the solution is efficient.
[Show abstract][Hide abstract]ABSTRACT: In contrast to single-user applications, most collaborative multi-member applications have been developed as vehicles for investigating various research issues, and even existing commercial collaborative multi-member applications have not widely accepted by end-users. The paper will describe an innovative approach and relative techniques that can be used to convert existing single-user applications into collaborative applications, without modifying the source code and knowledge of the API of the original single-user applications. The main idea is that user events occurring through the interactions with the application can be caught, distributed, and reconstructed. This approach and supporting techniques were tested in the process of transparently converting a single-user AutoCAD application into a real-time collaborative AutoCAD application called CoAutoCAD, which not only retains the original function and user interface of the single-user AutoCAD application, but supports group collaboration capabilities as well.
Article · Aug 2009 · Advances in Engineering Software
[Show abstract][Hide abstract]ABSTRACT: Proposed a novel online adaptive network anomaly detection model (OANAD). Purely normal dataset is not needed for training. It can process the network traffic data stream in real-time, alert the abnormal traffic, and dynamically build up its local normal pattern base and intrusion pattern base. The model has a relatively simple architecture which makes it efficient for processing online network traffic data. Also the detecting algorithms cost little computational time. The experiment on the KDD 99 intrusion detection datasets shows that our model achieves a detection rate of 90.51% and a false positive rate of only 0.19% within a very short running time.
[Show abstract][Hide abstract]ABSTRACT: Session initiation protocol (SIP) based on peer-to-peer (P2P) architecture has being gaining attentions due to its highly scalability and reliability. However, the original DHT model is not very suitable for VoIP communication system because the heterogeneity of nodes and their location information have not been taken into account. In this paper, we present a hierarchical P2P architecture considering the above- mentioned reasons for SIP communication and illustrate the process of initiating and maintaining sessions such as registration and resource location. At the end of this paper, we test the performances of our system. Simulation results have shown that our overlay can significantly reduce both lookup latencies and physical hops.
[Show abstract][Hide abstract]ABSTRACT: Session Initiation Protocol (SIP) based on Peer-to- Peer (P2P) architecture has being gaining attentions due to its highly scalability and reliability. However, the original DHT model is not very suitable for VoIP communication system because the heterogeneity of nodes and their location information have not been taken into account. In this paper, we present a hierarchical P2P architecture considering the abovementioned reasons for SIP communication and illustrate the process of initiating and maintaining sessions such as registration and resource location. At the end of this paper, we test the performances of our system. Simulation results have shown that our overlay can significantly reduce both lookup latencies and physical hops.
[Show abstract][Hide abstract]ABSTRACT: Wireless sensor networks (WSN) have emerged as an interesting and important research area in the last few years. Though the clock accuracy and precision requirements are often stricter than in traditional distributed systems, strict energy constraints limit the resources available to meet these goals. In this paper, we present a Bayesian approach to reduce time measurement uncertainty associated with message delivery delay. Our approach combines prior knowledge of time measurements from upstream nodes, measured time and measurement uncertainty of downstream nodes in order to obtain a more accurate time estimate. We verify the efficiency of this approach via simulations. For a 4 hop network, time synchronization precision with Bayesian estimation is about 4 times better than without it. We modeled a 100 hop network and show that time synchronization accuracy does not degrade significantly with the increase in number of hops being synchronized. Our approach is based on existing time synchronization algorithms and uses only local processing so that it does not add extra traffic
[Show abstract][Hide abstract]ABSTRACT: Web service architectures are being increasingly used as platforms for distributed applications. Mobile devices are already used everywhere. Both of them are paving the way for the emergence of pervasive computing systems. Many pervasive computing systems have not yet taken mobility and Web service architecture into account due to the lack of an appropriate supporting infrastructure. In this paper we present a new infrastructure for pervasive computing system. The infrastructure builds on both the Jini service architecture and the Web service technology. The combination allows designers to dynamically plugin and adapts pervasive computing. And in such infrastructure devices can discover each other and can utilize each other's services, whether they exist Jini lookup service or Web service registry
[Show abstract][Hide abstract]ABSTRACT: Collaborative support for a group of members that have common goals has been considered as a significant feature of the collaborative working environment. However, collaborative applications for multi-member generally lag behind in features with single-user applications. As a result, users often continue to use their favorite single-user applications that are less collaborative features. An efficient way is to convert single-user applications into collaborative applications. To our knowledge, there is no general technique available to convert single-user applications into multi-member collaborative applications. In this paper we give a novel approach to convert single-user, legacy CAD applications to collaborative CAD applications. The main characteristic of our approach is that it not only retains the original function of the single-user CAD application, but also supports the cooperative features. And it can improve the constructive efficiency of collaborative CAD applications
[Show abstract][Hide abstract]ABSTRACT: Cloud computing has emerged as a next generation high-performance computing infrastructure. This paper presents a Cloud computing infrastructure on clusters that aims to offer a virtual compute resource manager for compute nodes of clusters. Thus users can access and deploy theirs applications from anywhere on demand in transparent via web interface. The paper mainly introduces the basic ideas of the infrastructure, and discusses some techniques such as the method for efficient scheduling to obtain optimum job throughput, job scheduling using user and job resource attributes and so on.