Zhu Zhi-liang

A Web Service QoS Prediction Approach Based on Collaborative Filtering

With the increasing numbers of Web services and service users on World Wide Web, predicting QoS( Quality of Service ) for users will greatly aid service selection and discovery. Due to the different backgrounds and experiences of users, they have different QoS experiences when interacting with the same service. Even two users who have similar experiences on some services can have diverging views when considering other services. This paper proposes an approach to predict QoS. It is based on not only other users’ QoS experiences, but also the environment factor and user input factor. First bring forwards usage information feature model and calculate the similarity of two users based on the feature model. Then consider not only the historic information, but also environment and users’ inputs, such as bandwidth and data size. Before calculating the user similarity, select a set of Web services that have the highest degree of similarity with the target service, not all of the services. The missing value can be calculated through the data of similar services. The results of the experiment prove that our approach is feasible and effective.

Performance Analysis of LT Codes with Different Degree Distribution

Degree distribution lies at the heart of design an LT code. It affects the encoding and decoding complexity and error performance of LT code. In this paper, some metrics of well-design LT code such as average degree, release probability, overhead factor is analyzed. It will compare the metrics among robust LT code, sub optimal LT code and SF-LT code. Moreover, it provides some mathematical guideline on how to design a well designed LT code.

Quality Analysis and Monitoring Strategy Research for Web Service in the Internet

For the accurate analysis of the quality of Web services on the Internet, this paper analyzes 2,383 Web services with the accessible attributes. We propose a feature of quality change of these Web services. The paper intends to illustrate a Web service monitoring strategy which classifies the Web service into different categories based on the different providers. The strategy can be used both in the process of Web service monitor and the Web service selection. At last, a diversity of the Web services are collected and tested through an experimental platform named Neuddi*.

Embedded Laboratory Environment Monitor System

This paper presents an introduction of an embedded processor-based laboratory environment monitor system and its design for hardware and software. This system aims at completing monitoring a variety of real-time data and the states of laboratory, judging environmental index automatically, and detecting intrusions from outside companied with sound and light alarm. To sum up, this system achieves the intelligent management of laboratory. By wired or wireless means, the laboratory monitoring system can communicate with PC and realize telemetry, meeting the needs of unmanned laboratory.

An Improved Network Topology Auto-layout Solution Based on Force-Directed Placement

To acquire the network topology which is complex, unknown and continually changed, automatic discovery and automatic layout can be the best reliable and effective ways. Because of the huge number of nodes, connections, and circles in backbone network, the Force-directed Placement model which is form the physical system is brought in to optimize visualization. In this model, network topology is auto-layout by random initiation and iterative adjustments. The FR (Fruchterman and Reingold) algorithm is improved to make the algorithm more suitable for backbone network topology auto-layout. By reevaluated the force function, the types and numbers of nodes can be identified for dynamic configuration. The placement can be edited and partly locked, and the crowded nodes are controlled in practice. The improvements and optimizations make it more available and adaptive in various networks. All the experimental data are derived from automatic discovery, which are authentic and practical.

Robust dynamical order assignment for linear descriptor systems

This paper considers the problem of robust dynamical order assignment by derivative input feedback of descriptor systems. Descriptor systems provide us a more general description of physical systems, and this description is of great advantage than normal systems. Consequently and undoubtedly, descriptor systems have led us into a virgin land which is full of challenges and opportunities. Because of the specialization of derivative matrix of descriptor systems, some performances could not be realized by proportional feedback, but it could be realized by derivative feedback under some conditions, which implies the superiority of derivative feedback. Finally, an example is given to illustrate the validity of our method.

Application of Case-Based Reasoning for Traction Substation Design

The paper analyzes traction substationpsilas structure and spare parts, product main model. It mainly studies the application of case-based reasoning (CBR) in the design of traction substation. The application adopts architecture and object-oriented presentation to represent productpsilas structure and case base. It adopts level-2 indexing to determine searching indexing and standardizes original data to make it suitable for systempsilas similarity calculation. It chooses corresponding similarity model calculation based on data type. It adopts case similarity calculation model with partial and whole similarity integrated and level-2 indexing based on database indexing and nearest algorithm.

An approach to eliminate false positive lung cancers based on state variance

This paper presents a new approach to eliminate false positive lung cancers based on state variance, according to the variance of morphologic features between adjacent CT slices. First, the regions of interest (ROI) in CT images are selected by dual fast marching method, and the morphologic features of ROI like area and centroid are extracted; then, the layer features are extracted with morphologic features by state variance, and another new method is used for modeling for the cancers and non-cancers respectively based on layer features, eventually, false positive lung cancers are eliminated by calculating the maximal similarity between uncertain sample and models. We take the experiment by actual chest CT images, eliminate 68 false positive lung cancers in 100 samples which include 72 suspect lung cancers, obtain a detection rate of 94% for false positive lung cancers, and validate the effectivity of this method.