Scheduled System Maintenance:
Some services will be unavailable Sunday, March 29th through Monday, March 30th. We apologize for the inconvenience.
By Topic

Intelligent Information Technology Application, 2008. IITA '08. Second International Symposium on

Date 20-22 Dec. 2008

Go

Filter Results

Displaying Results 1 - 25 of 193
  • [Front cover - Vol 3]

    Publication Year: 2008 , Page(s): C1
    Save to Project icon | Request Permissions | PDF file iconPDF (451 KB)  
    Freely Available from IEEE
  • [Title Page i - Volume 3]

    Publication Year: 2008 , Page(s): i
    Save to Project icon | Request Permissions | PDF file iconPDF (30 KB)  
    Freely Available from IEEE
  • [Title page iii - Volume 3]

    Publication Year: 2008 , Page(s): iii
    Save to Project icon | Request Permissions | PDF file iconPDF (121 KB)  
    Freely Available from IEEE
  • [Copyright notice - Volume 3]

    Publication Year: 2008 , Page(s): iv
    Save to Project icon | Request Permissions | PDF file iconPDF (148 KB)  
    Freely Available from IEEE
  • Table of contents - Volume 3

    Publication Year: 2008 , Page(s): v - xviii
    Save to Project icon | Request Permissions | PDF file iconPDF (144 KB)  
    Freely Available from IEEE
  • Message from the IITA 2008 Symposium Chairs - Volume 3

    Publication Year: 2008 , Page(s): xix
    Save to Project icon | Request Permissions | PDF file iconPDF (132 KB)  
    Freely Available from IEEE
  • Organizing Committees - Volume 3

    Publication Year: 2008 , Page(s): xx
    Save to Project icon | Request Permissions | PDF file iconPDF (127 KB)  
    Freely Available from IEEE
  • Committee Members - Volume 3

    Publication Year: 2008 , Page(s): xxi - xxii
    Save to Project icon | Request Permissions | PDF file iconPDF (134 KB)  
    Freely Available from IEEE
  • A Novel IP Traffic Prediction Method of Chaos Theory with Support Vector Regression

    Publication Year: 2008 , Page(s): 3 - 7
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (506 KB) |  | HTML iconHTML  

    IP traffic prediction plays an important role in network-layout, traffic-management, as well as the emphasis of traffic-project, congestion-control and network management. Poor prediction performance would be acquired generally as a result of intense nonlinearity of networks traffic. To tackle it, a modeling method for exact representing IP trafficpsilas movement tendency and a regression algorithm with powerful nonlinear approaching ability should be employed. Consequently, chaos theory and support vector machine (SVM) win the bid. Then, an improved algorithm based-on local SVM method for small scale data-set is proposed. Experimental results demonstrate the validity of improvement by a real-life paradigm that successful forecasting with continuously daily IP traffic during a few days gathered from campus network. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Novel Approach for Speeding Up RBF-Based Interpolation Methods

    Publication Year: 2008 , Page(s): 8 - 13
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2794 KB) |  | HTML iconHTML  

    A popular and effective method for interpolation of data is by means of radial basis functions, but the most significant drawback of this method, which made researchers unwilling to use it for practical purposes, is its severe computational cost. Introduction of different methods by the researchers active in this field, however, has alleviated this problem. This paper presents a new method for reducing the computational cost of radial basis function interpolation, which is intrinsically different from those in common use (such as center reduction and fast multipole method), and can actually be regarded as a divide and conquer solution. Also, some experiments are provided which demonstrate the efficiency of the proposed approach. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Research on Counting Method of Bus Passenger Flow Based on Kinematics of Human Body and SVM

    Publication Year: 2008 , Page(s): 14 - 18
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (649 KB) |  | HTML iconHTML  

    According to the current research on the bus passengers flow counting, this paper proposes a new counting method of bus passenger flow based on kinematics of human body and SVM. This method solves the problem that low cost device canpsilat count the number of passengers accurately and canpsilat distinguish the direction of passengerspsila movement. Finally, this paper proves the feasibility and effectivity of the new method through experimental results. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Conjunction Graph-Based Frequent-Sets Fast Discovering Algorithm

    Publication Year: 2008 , Page(s): 19 - 23
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (236 KB) |  | HTML iconHTML  

    Existing algorithms that mine graph datasets to discover patterns corresponding to frequently occurring sub-graphs can operate efficiently on graphs that are sparse, contain a large number of relatively small connected components, have vertices with low and bounded degrees, and contain well-labeled vertices and edges. However, for graphs those do not share these characteristics, these algorithms become highly unintelligent. In this paper, we present a novel algorithm conjunction graph-based frequent fast discovering(CGFD) for mining complete frequent itemsets. This algorithm is referred to as the CGFD algorithm from hereon. In this algorithm, we employ the graph-based pruning to produce frequent patterns. Experimental data show that the CGFD algorithm outperforms that algorithm TM. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Mining User Interest Change for Improving Collaborative Filtering

    Publication Year: 2008 , Page(s): 24 - 27
    Cited by:  Papers (4)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (325 KB) |  | HTML iconHTML  

    Collaborative filtering recommendation system is a widely used method of providing recommendations using explicit ratings on items from users, which provides personalized recommendations on products or services to customers. However, the current research on recommendation has paid little attention to the use of time-related data in the recommendation process and the study on collaborative filtering to reflect changes in user interest. This paper proposed a methodology for mining a userpsilas time interest change in order to improve the performance of collaborative filtering recommender algorithms. The methodology consists of four phases of calculating time weight for the ratings, improving Pearsonpsilas correlation, forming neighbors, and recommendations. Empirical results show our time-incorporated collaborative filtering recommender system is significantly more accurate than a pure collaborative filtering system. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An Efficient Collaborative Filtering Algorithm with Item Hierarchy

    Publication Year: 2008 , Page(s): 28 - 31
    Cited by:  Papers (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (325 KB) |  | HTML iconHTML  

    Recommender systems are becoming increasingly popular with the evolution of the Internet, and collaborative filtering that using explicit ratings on items from users is the most successful technology for building recommendation systems. But traditional collaborative filtering algorithm is not suitable for itempsilas multiple content and multiple level recommendations. So, a new concept hierarchy methodology improving user-item matrix and integrating items of similar users and those multiple level association is presented, which not only overcomes the difficulty of data sparsity, but also solves the item's multiple content and level problem. Experimental results indicate that the algorithm can achieve better prediction accuracy and provide better recommendation results than with the traditional collaborative filtering algorithms. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Evolutionary Algorithm and Its Application in Artificial Immune System

    Publication Year: 2008 , Page(s): 32 - 36
    Cited by:  Papers (8)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (349 KB) |  | HTML iconHTML  

    Analyses were made on the basic principles of evolutionary algorithm, evolution strategies and evolution programming. Considering the superiority of evolutionary algorithm in intellectual computing, we analyze a typical optimizing algorithm for artificial immune system (AIS). Combining evolutionary algorithm and artificial immunity, we present an immune intrusion analysis scheme based on statistical analyzing model. The scheme introduces the prominent characteristics of evolutionary algorithm, such as parallel operating, successive optimizing into intrusion parameter selecting, data collecting and intrusion analyzing, thus it effectively improves the applicableness of immune IDS. The scheme avoids the security threats and weakness arising from the transfer of immune pathology metaphor mechanisms into AIS. As a comparison with other artificial immune schemes, we also provide an application case of the immune analyzing scheme in intrusion detecting and dealing, the comparison further justifies the scheme's adaptability, stability, robustness and parallel operating regarding its application in software and hardware circumstances. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Novel Reversible Semi-Fragile Watermarking Algorithm of MPEG-4 Video for Content Authentication

    Publication Year: 2008 , Page(s): 37 - 41
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (453 KB) |  | HTML iconHTML  

    This paper proposes an invertible semi-fragile video watermarking algorithm using a hash function to authenticate the MPEG-4 video contents. The proposed algorithm embeds two watermarks into I frame while encoding YUV video to MPEG-4 format. One watermark using hash function aims to authenticate the contents and embed the frame number for manipulation location between frames, and the other one based on DC coefficients is used for the detection of manipulation location within the frame. The experimental results show that the proposed algorithm is able to authenticate the video contents and detect the manipulation location, and it is robust for MPEG-4 compression. In addition, the proposed algorithm is exactly invertible, which means that the original video data is available as long as the watermarked video is credible. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Application of BP Network and Principal Component Analysis to Forecasting the Silicon Content in Blast Furnace Hot Metal

    Publication Year: 2008 , Page(s): 42 - 46
    Cited by:  Papers (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (348 KB) |  | HTML iconHTML  

    A novel method for forecasting the silicon content in hot metal is proposed using principal component analysis (PCA) and BP network. PCA can consider the correlations among multiple quality characteristics to obtain uncorrelated principal components. These principal components are then taken as the input parameters of the BP neural network. Then the BP network models are established and trained to map out the functional relationship between the principal components and the silicon content. The application results show that it works well and it is better than BP neural network in efficiency and accuracy, and the hit rate comes up to 86% using the BP neural network and PCA. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Novel Semi-Supervised SVM Based on Tri-Training

    Publication Year: 2008 , Page(s): 47 - 51
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (335 KB) |  | HTML iconHTML  

    One of the main difficulties in machine learning is how to solve large-scale problems effectively, and the labeled data are limited and fairly expensive to obtain. In this paper a new semi-supervised SVM algorithm is proposed. It applies tri-training to improve SVM. The semi-supervised SVM makes use of the large number of unlabeled data to modify the classifiers iteratively. Although tri-training doesn't put any constraints on the classifier, the proposed method uses three different SVMs as the classification algorithm. Experiments on UCI datasets show that tri-training can improve the classification accuracy of SVM and can increase the difference of classifiers, the accuracy of final classifier will be higher. Theoretical analysis and experiments show that the proposed method has excellent accuracy and classification speed. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An Efficient Algorithm of Learning the Parametric Map of Locally Linear Embedding

    Publication Year: 2008 , Page(s): 52 - 56
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (439 KB) |  | HTML iconHTML  

    A method is presented to obtain maps between the high-dimensional data and the low-dimensional space deduced by locally linear embedding (LLE). Since LLE does not provide a parametric function that build maps between the image space and the low-dimensional manifold. In this paper, multivariate linear regression is applied to deduce the maps. It can successfully project a new data point onto the embedded space. Also it can be extended to supervised LLE. The performance analysis on the obtained experimental results demonstrated that the proposed method is effective and efficient. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An Efficient Algorithm of Gray Projection Cyclostyle Matching to Image Retrieval

    Publication Year: 2008 , Page(s): 57 - 60
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (368 KB) |  | HTML iconHTML  

    This paper presents an improved image retrieval algorithm which based on the gray projection cyclostyle matching to overcome the shortcomings of conventional content-based image retrieval methods. The algorithm based on the analysis that gray scale projection curves of horizontal and vertical direction of the images fully reflects the feature of gray distribution in the corresponding direction, then compares with them if it's not homology. The experimental results show that the presented algorithm can preferably meet the requirements of image retrieval and greatly decrease the amount of calculation. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An Isomap-Eigenanalysis-Regression Pose Estimation Algorithm of Three-Dimentional Object

    Publication Year: 2008 , Page(s): 61 - 65
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (417 KB) |  | HTML iconHTML  

    Diverse pose estimation of three-dimensional (3D) object in the whole view-space remains a challenge in the field of pattern recognition. In this paper, a pose estimation algorithm of 3D object named isomap-eigenanalysis-regression (Isomap-E-R), which estimates arbitrary pose of 3D object in the whole view space, is proposed. For the training set, the low-dimensional embedding of input pattern set is computed by isomap, and the eigen-images of the embedding are deduced on the basis of an eigenspace. A different projection direction in low dimensional embedding is utilized to improve the accuracy of pose estimation. The metrics on each direction, derived by linear regression, is then used to further deduce the projection of the training set. For a given new sample, its projection onto the eigen-images is first computed, and the training images nearest to those deduced for the new sample by the algorithm give the estimation poses. The performance analysis on the obtained experimental results demonstrated that the proposed method could estimate the diverse pose of 3D object with significant efficiency and precision. Finally, the algorithm can be also extended to real-time pose estimate of 3D object and other potential applications. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Towards Efficient Reality Mining with Contexts and Semantics: A Case Study of Telecommunication

    Publication Year: 2008 , Page(s): 66 - 70
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (318 KB) |  | HTML iconHTML  

    Recommendation systems need to employ efficient reality mining module to find out whether social relationships extracted from a collected dataset are really meaningful in real world. Also, the recommendation should be generated by taking current contexts (e.g., location and time) account into. In this paper, we want to propose an ontology-based framework to discover real social networks from a large amount of dataset. This framework can provide a semiautomatic approach to build meaningful social networks by repeating interactions with human experts. We assume that given a dataset, we have to discover the hidden social networks which express the contextual dependencies between people. The personal context of a certain person is interrelated with those of other people, and investigated how to take into account his neighborpsilas contexts, which possibly have an important influence on his personal context. Particularly, in this research project, the target dataset in this work is collected from user activities (about over two millions of people) in telecommunication industry. We have applied the proposed system to discover the social networks among the mobile subscribers to provide recommendation to mobile devices. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Classifying Documents with Maximum Likelihood Approximation of the Dirichlet Multinomial Gibbs Model

    Publication Year: 2008 , Page(s): 71 - 75
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (254 KB) |  | HTML iconHTML  

    In the text analysis, the Dirichlet compound multinomial (DCM)distribution has recently been shown to be a good model for documents because it captures the phenomenon of word burstiness, unlike the standard multinomial distribution. In this paper, for the sake of improving performance of modeling documents, we propose a variant of DCM and Gibbs distribution called Dirichlet multinomial Gibbs (DMG) model by introducing Gibbs parameters to DCM distribution. We demonstrate the maximum likelihood procedure of the DMG model with these Gibbs parameters. By our experiments, the DMG approach inherit the merits of methods of Gibbs distribution approximation and DCM estimation. More specifically, as revealed by our experimental results on various real-world text datasets, we show that maximum likelihood approximation of the DMG model is more desirable than some current state-of-the-art methods. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Hybrid Dynamical Evolutionary Algorithm for Classification Rule Discovery

    Publication Year: 2008 , Page(s): 76 - 79
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (317 KB) |  | HTML iconHTML  

    This paper studies hybrid dynamical evolutionary algorithm in the context of classification rule discovery. Nature inspired search algorithms such as genetic algorithms, Ant colonies and particle swarm optimization have been previously studied on data mining tasks, in particular, classification rule discovery. We extended this work by applying a hybrid algorithm which combines dynamical evolutionary algorithm and hill climbers and PSO, in same type of classification tasks. Our research focused on studying the hybrid algorithm of performance enhancements in classification rule discovery tasks. In this paper, we developed a hybrid algorithm based classifier and implemented different variations of it in Java. The algorithm has been benchmarked against the well-known decision tree induction algorithm C4.5. Results have been compared in terms of prediction accuracy,speed and comprehensibility. Our results showed that,the hybrid dynamical evolutionary algorithm based classifiers can compete with C4.5 in terms of prediction accuracy on certain data sets and outperform C4.5 in general in terms of comprehensibility. We also showed that hybrid algorithm could bring improvements in terms of execution speed in comparison to plain heuristic based classifiers. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Wavelet Transform Using Neyman-Pearson Criterion in Speech Recognition

    Publication Year: 2008 , Page(s): 80 - 83
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (359 KB)  

    To obtain a high robust of speech recognition for noisy conditions, a new pre-processing stage based on wavelet thresholding algorithm is proposed in this paper. The purpose of using the DWT is to benefit from its localization property in the time and frequency domains. Compromise function is proposed compared with hard and soft thresholding function. A new thresholding value, Neyman-Pearson criterion is proposed compared with the commonly used Sqtwolog, Rigrsure, minimaxi criterion. MSE and SNR are given to evaluate the improvement of noisy speech recognition performance. The result shows that the Neyman-Pearson criterion can get a better performance especially at adverse conditions. View full abstract»

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