Search

A novel PSO algorithm called InformPSO is introduced in this paper. The premature convergence problem is a deficiency of PSOs. First, we analyze the causes of premature convergence for conventional PSO. Second, the principles of information diffusion and clonal selection are incorporated into the proposed PSO algorithm to achieve a better diversity and break away from local optima. Finally, when compared with several other PSO variants, it yields better performance on optimization of unimodal and multimodal benchmark functions.

This paper presents a novel genetic algorithm (GA) for multiple sequence alignment in protein analysis. The most significant improvement afforded by this algorithm results from its use of segment profiles to generate the diversified initial population and prevent the destruction of conserved regions by crossover and mutation operations. Segment profiles contain rich local information, thereby speeding up convergence. Secondly, it introduces the use of the norMD function in a genetic algorithm to measure multiple alignment Finally, as an approach to the premature problem, an improved progressive method is used to optimize the highest-scoring individual of each new generation. The new algorithm is compared with the ClustalX and T-Coffee programs on several data cases from the BAliBASE benchmark alignment database. The experimental results show that it can yield better performance on data sets with long sequences, regardless of similarity.

This paper studies a general QoS adaptive management mechanism in view of video server and active node. For the video server, we put forward an idea of video period task set as well as defining some video services with this set. This paper also designs a kind of mixed real time task scheduling arithmetic which taking QoS critical level as a character of task priority vector to build video period task set and accomplish dynamic resource management, based on QoS conveniently. Therefore, it realizes the service quality control of small granularity. Based on it, the paper further puts forward active node adaptive QoS control component. Through designing dynamic resource trading active queue and using mixed priority of video active packet, the new idea not only makes system support video application as much as possible, but also enables it to satisfy resource trading requirements of user. At last, a simulation experiment is carried out to illustrate the advantage of active queues after amelioration.

This paper presents our recent research work on mobile-agent based information content sharing in peer to peer system. Our work focuses on how to share the text content and recommend information based on mobile agent. The prototype uses terminology derived from the ant colony metaphor, including nest – a peer entity, and ant– an autonomous agent. Two mobile agents are proposed toimplementthe content-based text retrieval and information recommendation effectively. These agents are then evaluated through implementations and analysis. The simulated results demonstrate the advantages of our approach in the P2P system, and its potential applications in complex electric commerce and distributed information sharing.

The shifting bottleneck procedures are mainly based on one-machine scheduling algorithm, so the results of one-machine scheduling algorithm significantly affect the performance of the shifting bottleneck procedures. In this paper, inspired by two facts that the function of the release time and the delivery time of each job is uniform, an efficient algorithm for one-machine scheduling problem is presented. Based on this algorithm, an improved shifting bottleneck procedure is developed. The simulation results to the well-known benchmark problems show that the performance of the improved procedure can compete with that of the shifting bottleneck procedure and the modified ones.

Hybrid peer-to-peer architectures use special nodes to provide directory services for regions of the network (“regional directory services”). They are a potentially powerful model for developing large-scale networks of complex digital libraries. This paper presents our recent research work on the new content-based text filtering and collaborative filtering based on hybrid P2P (Peer-to-Peer) networks. From various perspectives, our work focuses on how to share the text content and recommend information based on hybrid P2P networks. Several models are proposed toimplementthe content-based text retrieval and collaborative filtering effectively. These models are then evaluated and validated through implementations and analyses. The results show some advantages of the proposed approach for the content-based filtering algorithm based on lexical chain and collaborative filtering algorithm in hybrid P2P network and potential applications in complex digital libraries and distributed information sharing.

A mass of distributed and dynamic information on the Web has resulted in "information overload". With the flood of information, it has become an important research issue to search the Web based on traditional information retrieval technology. However, various systems and ambiguous terminology of information retrieval on the Web bring much trouble to users in application and researchers in development as well. This paper proposes the same interface of Web document retrieval to users, it is the model based on multi-agent. Each document in the documents base or from Web is represented as a vector in the vector space of classifiable sememes. The query from user is also represented as a vector. The relevance between them can be measured by using the cosine angle between the query and its k nearest neighbors in the vector space. Experiments have been done and their results shown that this scheme yields good results.

This paper presents the basic principles of IP multicasting. The design and application in a multimedia network teaching system are then given.

This paper presents the basic architecture of CSCW (computer supported cooperative work). Then some issues of CSCW systems such as concurrency control and synchronization are discussed. Lastly, its application in a multimedia network teaching system such as a whiteboard, chatting system, etc. is given.

The WWW is increasingly being used as a source of information. The volume of this information is accessed by users using direct manipulation tools. The paper describes a module that sifts through a large number of texts retrieved by the user. We describe a system that learns a model of the user's preferences, filters the information, and notifies the user when relevant information becomes available. The user's model is represented as a vector in the vector space of classifiable sememes. The document is also represented as a vector. The relevance of the text to the user's interest can be measured by using the cosine angle between the two vectors. Experiments are given to demonstrate it to be a good idea.

A novel perspective invariant image matching framework is proposed in this paper, noted as Perspective-Invariant Binary Robust Independent Elementary Features (PBRIEF). First, we use the homographic transformation to simulate the distortion between two corresponding patches around the feature points. Then, binary descriptors are constructed by comparing the intensity of sample points surrounding the feature location. We transform the location of the sample points with simulated homographic matrices. This operation is to ensure that the intensities which we compared are the realistic corresponding pixels between two image patches. Since the exact perspective transform matrix is unknown, an Adaptive Particle Swarm Optimization (APSO) algorithm-based iterative procedure is proposed to estimate the real transformation angles. Experimental results obtained on five different datasets show that PBRIEF outperforms significantly the existing methods on images with large viewpoint difference. Moreover, the efficiency of our framework is also improved comparing with Affine-Scale Invariant Feature Transform (ASIFT).

In our previous research we have made literature analysis and discovered possible mind map application areas. We have pointed out why currently developed software and methods are not adequate and why we are developing a new one. We have defined system architecture and functionality that our software would have. After that, we proceeded with text-mining algorithm development and testing after which we have concluded with our plans for further research. In this paper we will give basic notions about previously published article and present our custom developed software for automatic mind map generation. This software will be tested. Generated mind maps will be critically analyzed. The paper will be concluded with research summary and possible further research and software improvement.