By Topic

Information Technology and Computer Science (ITCS), 2010 Second International Conference on

Date 24-25 July 2010

Filter Results

Displaying Results 1 - 25 of 152
  • [Front cover]

    Page(s): C1
    Save to Project icon | Request Permissions | PDF file iconPDF (436 KB)  
    Freely Available from IEEE
  • [Title page i]

    Page(s): i
    Save to Project icon | Request Permissions | PDF file iconPDF (10 KB)  
    Freely Available from IEEE
  • [Title page iii]

    Page(s): iii
    Save to Project icon | Request Permissions | PDF file iconPDF (377 KB)  
    Freely Available from IEEE
  • [Copyright notice]

    Page(s): iv
    Save to Project icon | Request Permissions | PDF file iconPDF (104 KB)  
    Freely Available from IEEE
  • Table of contents

    Page(s): v - xiv
    Save to Project icon | Request Permissions | PDF file iconPDF (171 KB)  
    Freely Available from IEEE
  • Message from the Conference Chairs

    Page(s): xv
    Save to Project icon | Request Permissions | PDF file iconPDF (81 KB)  
    Freely Available from IEEE
  • Organizing Committee

    Page(s): xvi
    Save to Project icon | Request Permissions | PDF file iconPDF (61 KB)  
    Freely Available from IEEE
  • Program Committee

    Page(s): xvii
    Save to Project icon | Request Permissions | PDF file iconPDF (46 KB)  
    Freely Available from IEEE
  • list-reviewer

    Page(s): xviii
    Save to Project icon | Request Permissions | PDF file iconPDF (56 KB)  
    Freely Available from IEEE
  • Research of Similarity Measurements in the Clustering Analysis

    Page(s): 3 - 6
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (151 KB) |  | HTML iconHTML  

    Similarity measurements play an important role in the clustering analysis, so any good or bad methods of measuring similar degree directly affect the clustering algorithm. In the paper, several approaches to similarity measurements for single attribute type data, which had been proposed, have been discussed. Moreover, a way has been obtained so as to calculate the similar degree of multiple attribute type data. At last a experiment was tested. The result shows that the method is not only feasible but also effective. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Novel Protein Secondary Structure Prediction System Based on Compound Pyramid Model

    Page(s): 7 - 12
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (289 KB) |  | HTML iconHTML  

    Protein Secondary structure prediction is essential for the tertiary structure modeling, and it is the one of the major challenge of bioinformatics. In this article, we proposed a gradually enhanced, multi-layered prediction systematic model, Compound Pyramid Model (CPM). This model is composed of four independent coordination's layers by intelligent interfaces, synthesizes several methods, such as SVM, KDD* process model and so on. The model penetrates the whole domain knowledge, and the effective attributes are chosen by Causal Cellular Automata, and the high pure structure database is constructed for training. On the RS126 data set, state overall per-residue accuracy, Q3, reached 83.99%. On the CB513 data set, Q3 reached 85.58%. Meanwhile, on the CASP8's sequences, the results are found to be superior to those produced by other methods, such as SAM, PSI-Blast, Prospect, JUFO, and so on. The result shows that our method has strong generalization ability. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Median Filter Method for Image Noise Variance Estimation

    Page(s): 13 - 16
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (206 KB) |  | HTML iconHTML  

    Image noise estimation is of crucial importance for the computer vision algorithm, for the algorithm parameter is always adjusted to account for the variations in noise level over the captured images. A median filter method is provided for the image noise variance estimation in the paper. The image was first processed with a group of high pass digital filters constructed by several finite difference operators with different orders. For each filtered image data, a variance was estimated. And the noise variance is approximated by the median of those estimated variances. In order to avoid outlier issues when there are left image details in the residue, variances are estimated from each filtered image data for several different inter-quartile ranges, then a median is taken. The supposed median filter approach to image noise estimation is simple and effective, which has been verified by the experiments. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Security Routing Algorithm of P2P Network Based on Asymmetric Nested Encryption

    Page(s): 17 - 20
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (143 KB) |  | HTML iconHTML  

    Correct routing is a key factor to maintain the stability and efficiency of P2P network. There are many types of attacks aiming at P2P routing, which seriously threats the security of P2P network. We proposed an improved routing algorithm based on asymmetric nested encryption detection. The algorithm can periodically inspect every node in routing path, and eliminate bad nodes and instable nodes in routing path with little time, so as to raise the security capability of P2P routing in high. Simulation experiments demonstrate the improved algorithm can effectively enhance the routing security of P2P network. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Pairwise Key Management Scheme Using Sub Key Pool for Wireless Sensor Networks

    Page(s): 21 - 24
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (158 KB) |  | HTML iconHTML  

    Key management in sensor networks has become a challenging issue in the design and the development of secure wireless sensor networks since asymmetric cryptosystems are unsuitable for use in resource constrained sensor nodes, and also because the nodes are vulnerable to physical capture. In this paper, we present a new key management scheme using sub key pool to enlarge the size of key pool. With the more keys in the key pool, this scheme has higher security against node capture. The analysis shows that this scheme provides better security compared to the previous approaches, and can ensure reasonable connectivity at the same time. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Adaptive Correction of Errors from Segmented Digital Ink Texts in Chinese Based on Context

    Page(s): 25 - 35
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1333 KB) |  | HTML iconHTML  

    Digital ink texts in Chinese can neither be converted into users' desired layouts nor be recognized until their characters, lines, and paragraphs are correctly extracted. There are many errors in automatically segmented digital ink texts in Chinese because they are free forms and mixed with other languages, as well as their Chinese characters have small gaps and complex structures. Paragraphs, lines, and characters (recognizable language symbols) in digital ink may be wrongly extracted. An adaptive approach based on context is proposed to correct wrongly extracted these objects. Each extracted object is first adaptively visualized by color and shape labels according to relations between it and its neighbors. Users use simple gestures naturally and easily to merge and split wrongly extracted objects. Contexts are constructed from users' gestures and objects invoked by them, where users' intensions are identified. We have conducted experiments using real-life segmented digital ink texts in Chinese and compared the proposed approach with others. Experimental results demonstrate that the proposed approach is feasible, flexible, effective, and robust. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Summarizing Similar Questions for Chinese Community Question Answering Portals

    Page(s): 36 - 39
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (285 KB) |  | HTML iconHTML  

    As online community question answering (cQA) portals like Yahoo! Answers and Baidu Zhidao have attracted over hundreds of millions of questions, how to utilize these questions and accordant answers becomes increasingly important for cQA websites. Prior approaches focus on using information retrieval techniques to provide a ranked list of questions based on their similarities to the query. Due to the high variance of question quality and answer quality, users have to spend lots of time on finding the truly best answers from retrieved results. In this paper, we develop an answer retrieval and summarization system which directly provides an accurate and comprehensive answer summary instead of a list of similar questions to user's query. To fully explore the information of relations between queries and questions, between questions and answers, and between answers and sentences, we propose a new probabilistic scoring model to distinguish high-quality answers from low-quality answers. By fully exploiting these relations, we summarize answers using a maximum coverage model. Experiment results on the data extracted from Chinese cQA websites demonstrate the efficacy of our proposed method. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Web Content Extraction based on Webpage Layout Analysis

    Page(s): 40 - 43
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (352 KB) |  | HTML iconHTML  

    For web content extraction task, researchers have proposed many different methods, such as wrapper-based method, DOM tree rule-based method, machine learning-based method and so on. To some extent, all these methods ignore the layout information of the webpage, although the layout information such as the spatial and visual cues often plays a very important role in the process of locating the main content of the webpage when browsing. As a consequence, these methods often throw part of the main content away when extracting content from the webpage. In this paper, we present a method which combines webpage layout analysis with DOM tree rule-base method, it can make full use of the advantages of the two methods. It uses the layout information to guide the extraction work with a global view and can gain a better performance than the traditional methods. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An Optimized Multi-class Classification Algorithm Based on SVM Decision Tree

    Page(s): 44 - 47
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (129 KB) |  | HTML iconHTML  

    An optimized multi-class classification algorithm based on SVM decision tree (SVMDT) is proposed. But by SVMDT, the generalization ability depends on the tree structure. In this paper, the relativity separability measure between classes is defined based on the distribution of the training samples to improve the generalization ability of SVMDT. SVM is extended to non-linear SVM by using kernel functions and the classification experiments prove the algorithm is more effective and feasible for classification accuracy. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Novel Localization Algorithm for Wireless Sensor Network Using Two-hop Beacon Nodes

    Page(s): 48 - 51
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (134 KB) |  | HTML iconHTML  

    The location estimation of sensor nodes is a fundamental and essential issue for wireless sensor networks (WSNs), because the gathered data is meaningful only when the location information of the sensor nodes is known. In this paper, we proposed a novel localization algorithm. In the proposed scheme, we first estimate the location of sensor nodes using Convex Position Estimation (CPE), and then refine the location of sensor nodes using the location of the two-hop beacon nodes. Simulation shows that compared with convex localization algorithm, the proposed localization algorithm can enhance the localization accuracy efficiently. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Chinese Sign Language Animation System on Mobile Devices

    Page(s): 52 - 55
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (378 KB) |  | HTML iconHTML  

    Sign language is communication tool among the deaf. With popularation of computer, internet and other electronic device, sign language expressed as 3D animation is more effective to improve the exchange and access information for the deaf. In recent years, PDA, mobile phones and other mobile device's users increase rapidly, which makes 3D animation on the mobile devices become a research hotspot. This paper introduces a Chinese sign language animation system running on mobile devices, which includes three models: 3D virtual human model, word segment based on Chinese sign, and rendering. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Energy-Balanced Scheme Based Unequal Density of Backbone for Wireless Sensor Networks Under Coal Mine

    Page(s): 56 - 59
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (349 KB) |  | HTML iconHTML  

    In order to solve uneven data throughput phenomenon for wireless sensor networks under coal mine, which cause “hot spots” problem, energy-efficient uneven clustering scheme based on the energy and distribution density of cluster heads ( UCS-ED ) is proposed, which formed by many existing routing protocols used in wireless sensor networks. In the cluster heads election phase it put the energy and distribution density as two elements to join the election, form an uneven density of backbone around the Sink. Simulation results show that UCS-ED outperform LEACH and HEED in balancing energy consumption and prolonging the network lifetime. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Higher Order Spectra Analysis of EEG Signals in Emotional Stress States

    Page(s): 60 - 63
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (298 KB) |  | HTML iconHTML  

    This paper proposes an emotional stress recognition system with EEG signals using higher order spectra (HOS). A visual induction based acquisition protocol is designed for recording the EEG signals in five channels (FP1, FP2, T3, T4 and Pz) under two emotional stress states of participants, Calm neutral and Negatively exited. After pre-processing the signals, higher order spectra are employed to extract the features for classifying human emotions. We used Genetic Algorithm for optimum features selection for the classifier. Using the SVM classifier, our study achieved an average accuracy of 82% for the two-above mentioned emotional stress states. We concluded that HOS analysis could be an accurate tool in the assessment of human emotional stress states. We achieved to same results compared to our previous studies. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Texture Analysis Using GMRF Model for Image Segmentation on Spectral Clustering

    Page(s): 64 - 67
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (275 KB) |  | HTML iconHTML  

    Spectral clustering algorithms are newly developing technique in recent years. In this paper, we derive a new pairwise affinity function for spectral clustering based on a measure of texture features represented by Gaussian Markov Random Field (GMRF) model. This model is used to capture the statistical properties of the neighborhood at a pixel, and then pairwise affinities represented by it can cluster the pixels into coherent groups. Having obtained a local similarity measured by regions of coherent texture and brightness, we use the normalized cuts to find partitions of the image. Experimental results demonstrate that the proposed method is effective and robust for image segmentation. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An Automatic Carving Method for RAR File Based on Content and Structure

    Page(s): 68 - 72
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (211 KB) |  | HTML iconHTML  

    File carving is a digital forensic technique. It aims to reconstitute a file from unstructured data sources with no knowledge of the file system. This paper presents an automatically carving method for RAR files. Since RAR is one of the most popular archive formats, and it is widely used on the digital devices to package data for transport or storage. It is important for forensic investigation to obtain the information of RAR files. We apply mapping function to locate the header and footer of an archived file, utilize the distance between the header and footer of an archived file to determine whether the archived file is fragmented, and apply enumeration to reassemble bi-fragmentation of an archived file. Finally we validate the integrity of archived file and RAR file, repairing RAR files which miss header or footer. Based on artificial data and real world data, experiments show our method can automatically carve continuous and fragmented RAR files. Moreover, the comparative experiments demonstrate that this method is better than other's in accurateness and effectiveness. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Quick Recognition and Relative Minimum Distances Filtering Assisted Recognition Based on Noisy-robust Rough Set

    Page(s): 73 - 77
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (403 KB) |  | HTML iconHTML  

    With the development of rough set theory and it's strengths and weaknesses in the recognition field, the rule and recognition fusing method of noisy-robust rough set (NRRS) are proposed based on full normalized deposal, the non-uniform companding and simple dynamic clustering coding. The robustness of NRRS is improved by weighted reliability during training and recognition to dispose the accidental samples and conflict samples. At the same time, this paper gives the quick recognition and relative minimum distances between classes filtering assisted recognition algorithm based on NRRS. The recognition simulation shows that the method has a good anti-noise performance, processing efficiency and recognition effect. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.