By Topic

Computer Science and Information Technology (IMCSIT), Proceedings of the 2010 International Multiconference on

Date 18-20 Oct. 2010

Filter Results

Displaying Results 1 - 25 of 145
  • [Front cover]

    Publication Year: 2010 , Page(s): c1
    Save to Project icon | PDF file iconPDF (11 KB)  
    Freely Available from IEEE
  • [Title page]

    Publication Year: 2010 , Page(s): ii
    Save to Project icon | PDF file iconPDF (14 KB)  
    Freely Available from IEEE
  • [Copyright notice]

    Publication Year: 2010 , Page(s): iii
    Save to Project icon | PDF file iconPDF (22 KB)  
    Freely Available from IEEE
  • FW

    Publication Year: 2010 , Page(s): iv
    Save to Project icon | PDF file iconPDF (60 KB)  
    Freely Available from IEEE
  • Table of contents

    Publication Year: 2010 , Page(s): v - xii
    Save to Project icon | PDF file iconPDF (147 KB)  
    Freely Available from IEEE
  • 5th international symposium advances in Artificial Intelligence and applications

    Publication Year: 2010 , Page(s): 1 - 2
    Save to Project icon | PDF file iconPDF (76 KB)  
    Freely Available from IEEE
  • A breast cancer classifier based on a combination of case-based reasoning and ontology approach

    Publication Year: 2010 , Page(s): 3 - 10
    Cited by:  Papers (1)
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (1382 KB)  

    Breast cancer is the second most common form of cancer amongst females and also the fifth most cause of cancer deaths worldwide. In case of this particular type of malignancy, early detection is the best form of cure and hence timely and accurate diagnosis of the tumor is extremely vital. Extensive research has been carried out on automating the critical diagnosis procedure as various machine learning algorithms have been developed to aid physicians in optimizing the decision task effectively. In this research, we present a benign/malignant breast cancer classification model based on a combination of ontology and case-based reasoning to effectively classify breast cancer tumors as either malignant or benign. This classification system makes use of clinical data. Two CBR object-oriented frameworks based on ontology are used jCOLIBRI and myCBR. A breast cancer diagnostic prototype is built. During prototyping, we examine the use and functionality of the two focused frameworks. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Using data mining for assessing diagnosis of breast cancer

    Publication Year: 2010 , Page(s): 11 - 17
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (298 KB)  

    The capability of the classification SVM, Tree Boost and Tree Forest in analyzing the DDSM dataset was investigated for the extraction of the mammographic mass features along with age that discriminates true and false cases. In the present study, SVM technique shows promising results for increasing diagnostic accuracy of classifying the cases witnessed by the largest area under the ROC curve (area under empirical ROC curve =0.79768 and area under binomial ROC curve = 0.85323) comparable to empirical ROC and binomial ROC of 0.57575 and 0.58548 for tree forest while least empirical ROC and binomial ROC of 0.53452 and 0.53882 was accounted by tree boost. These results are confirmed by SVM average gain of 1.7323, tree forest average gain of 1.5576 and tree boost average gain of 1.5718. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Advanced scale-space, invariant, low detailed feature recognition from images - car brand recognition

    Publication Year: 2010 , Page(s): 19 - 23
    Cited by:  Papers (1)
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (2160 KB)  

    This paper presents analysis of a model for car brand recognition. The used method is an invariant keypoint detector - descriptor. An input for the method is a set of images obtained from the real environment. The task of car classification according its brand is not a trivial task. Our work would be a part of an intelligent traffic system where we try to collect some statistics about various cars passing a given area. It is difficult to recognize objects when they are in different scales, rotated or if they are low contrasted or when it is necessary to take into count high level of details. In our work we present a system for car brand recognition. We use scale space invariant keypoint detector and descriptor (SURF - Speeded-up Robust Features) for this purpose. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Evaluation of clustering algorithms for Polish Word Sense Disambiguation

    Publication Year: 2010 , Page(s): 25 - 32
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (154 KB)  

    Word Sense Disambiguation in text is still a difficult problem as the best supervised methods require laborious and costly manual preparation of training data. Thus, this work focuses on evaluation of a few selected clustering algorithms in task of Word Sense Disambiguation for Polish. We tested 6 clustering algorithms (K-Means, K-Medoids, hierarchical agglomerative clustering, hierarchical divisive clustering, Growing Hierarchical Self Organising Maps, graph-partitioning based clustering) and five weighting schemes. For agglomerative and divisive algorithm 13 criterion function were tested. The achieved results are interesting, because best clustering algorithms are close in terms of cluster purity to precision of supervised clustering algorithm on the same dataset, using the same features. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Generation of first-order expressions from a broad coverage HPSG grammar

    Publication Year: 2010 , Page(s): 33 - 36
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (110 KB)  

    This paper describes an application for computing first-order semantic representations of English texts. It is based on a combination of hybrid shallow-deep components arranged within the middleware framework Heart of Gold. The shallow-deep semantic analysis employs Robust Minimal Recursion Semantics (RMRS) as a common semantic underspecification formalism for natural language processing components. In order to compute efficiently first-order representations of the input text, the intermediate RMRS results of the shallow-deep analysis are transformed into the dominance constraints formalism and resolved by the underspecification resolver UTool. First-order expressions can serve as a formal knowledge representation of natural text and thus can be utilized in knowledge engineering or textual reasoning. At the end of this paper, we describe their application for recognizing textual entailment. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • PSO based modeling of Takagi-Sugeno fuzzy motion controller for dynamic object tracking with mobile platform

    Publication Year: 2010 , Page(s): 37 - 43
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (340 KB)  

    Modeling of optimized motion controller is one of the interesting problems in the context of behavior based mobile robotics. Behavior based mobile robots should have an ideal controller to generate perfect action. In this paper, a nonlinear identification Takagi-Sugeno fuzzy motion controller has been designed to track the positions of a moving object with the mobile platform. The parameters of the controller are optimized with Particle swarm optimization (PSO) and stochastic approximation method. A gray predictor has also been developed to predict the position of the object when object is beyond the view field of the robot. The combined model has been tested on a Pioneer robot which tracks a triangular red box using a CCD camera and a laser sensor. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Hierarchical object categorization with automatic feature selection

    Publication Year: 2010 , Page(s): 45 - 51
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (615 KB)  

    In this paper, we have introduced a hierarchical object categorization method with automatic feature selection. A hierarchy obtained by natural similarities and properties is learnt by automatically selected features at different levels. The categorization is a top-down process yielding multiple labels for a test object. We have tested out method and compared the experimental results with that of a nonhierarchical method. It is found that the hierarchical method improves recognition performance at the level of basic classes and reduces error at a higher level. This makes the proposed method plausible for different applications of computer vision including object categorization, semantic image retrieval, and automatic image annotation. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Selecting the best strategy in a software certification process

    Publication Year: 2010 , Page(s): 53 - 58
    Cited by:  Papers (1)
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (137 KB)  

    In this paper, we propose the use of the pairwise comparisons (PC) method for selection of strategies for software certification. This method can also be used to rank alternative software certification strategies. The inconsistency analysis, provided by the PC method, improves the accuracy of the decision making. Some current methods of software certification are presented as they could be modified by the proposed method. Areas of potential future research are discussed in order to make the software certification process more feasible and acceptable to industry. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Extrapolation of non-deterministic processes based on conditional relations

    Publication Year: 2010 , Page(s): 59 - 65
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (384 KB)  

    A problem of extrapolation of a large class of processes and of their future states forecasting based on their occurrence in the past is considered. Discrete-time discrete-value processes are presented as instances of relations subjected to the general relations algebra rules. The notions of relative relations, parametric relations and non-deterministic relations have been introduced. For extrapolated process states assessment relative credibility levels of process trajectories are used. The variants of direct one-step, indirect one-step and direct multi-step process extrapolation are described. The method is illustrated by numerical examples. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Reasoning in RDF graphic formal system with quantifiers

    Publication Year: 2010 , Page(s): 67 - 72
    Cited by:  Papers (1)
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (216 KB)  

    Both associative networks and RDF model (here we consider especially its graph version) belong to formal systems of knowledge representation based on concept-oriented paradigm. To treat properties of both of them as common properties of the systems is therefore natural. The article shows a possibility to use universal and existential quantified statements introduced prior to associative networks also within RDF graphic system and to define a RDF formal system with extended syntax and semantic that can use inference rules of associative networks. As an example solution, a logical puzzle is presented. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Coevolutionary algorithm for rule induction

    Publication Year: 2010 , Page(s): 73 - 79
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (494 KB)  

    This paper describes our last research results in the field of evolutionary algorithms for rule extraction applied to classification (and image annotation). We focus on the data mining classification task and we propose evolutionary algorithm for rule extraction. Presented approach is based on binary classical genetic algorithm with representation of `if-then' rules and we propose two specialized genetic operators. We want to show that some search space reduction techniques make possible to get solution comparable to others from literature. To present our method ability of discovering the set of rules with high F-score we tested our approach on four benchmark datasets and ImageCLEF competition dataset. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Evolutionary algorithm in Forex trade strategy generation

    Publication Year: 2010 , Page(s): 81 - 88
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (404 KB)  

    This paper shows an evolutionary algorithm application to generate profitable strategies to trade futures contracts on foreign exchange market (Forex). Strategy model in approach is based on two decision trees, responsible for taking the decisions of opening long or short positions on Euro/US Dollar currency pair. Trees take into consideration only technical analysis indicators, which are connected by logic operators to identify border values of these indicators for taking profitable decision(s). We have tested the efficiency of presented approach on learning and test time-frames of various characteristics. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Emotion-based image retrieval—An artificial neural network approach

    Publication Year: 2010 , Page(s): 89 - 96
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (546 KB)  

    Human emotions can provide an essential clue in searching images in an image database. The paper presents our approach to content based image retrieval systems which takes into account its emotional content. The goal of the research presented in this paper is to examine possibilities of use of an artificial neural network for labeling images with emotional keywords based on visual features only and examine an influence of used emotion filter on process of similar images retrieval. The performed experiments have shown that use of the emotion filter increases performance of the system for around 10 percent. points. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Automatic visual object formation using image fragment matching

    Publication Year: 2010 , Page(s): 97 - 104
    Cited by:  Papers (1)
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (1266 KB)  

    Low-level vision approaches, such as local image features, are an important component of bottom-up machine vision solutions. They are able to effectively identify local visual similarities between fragments of underlying physical objects. Such vision approaches are used to build a learning system capable to form meaningful visual objects out of unlabelled collections of images. By capturing similar fragments of images, the underlying physical objects are extracted and their visual appearances are generalized. This leads to formation of visual objects, which (typically) represent specific underlying physical objects in a form of automatically extracted multiple template images. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Learning taxonomic relations from a set of text documents

    Publication Year: 2010 , Page(s): 105 - 112
    Cited by:  Papers (1)
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (214 KB)  

    This paper presents a methodology for learning taxonomic relations from a set of documents that each explain one of the concepts. Three different feature extraction approaches with varying degree of language independence are compared in this study. The first feature extraction scheme is a language-independent approach based on statistical keyphrase extraction, and the second one is based on a combination of rule-based stemming and fuzzy logic-based feature weighting and selection. The third approach is the traditional tf-idf weighting scheme with commonly used rule-based stemming. The concept hierarchy is obtained by combining Self-Organizing Map clustering with agglomerative hierarchical clustering. Experiments are conducted for both English and Finnish. The results show that concept hierarchies can be constructed automatically also by using statistical methods without heavy language-specific preprocessing. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Metric properties of populations in artificial immune systems using Hadamard representation

    Publication Year: 2010 , Page(s): 113 - 119
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (134 KB)  

    A Hadamard representation, which is an alternative towards the binary representation, is considered in this study. It operates on numbers +1 and -1. Several properties of such defined representation were pointed out and properties of the immune system were expressed based on this representation. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The development features of the face recognition system

    Publication Year: 2010 , Page(s): 121 - 128
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (1009 KB)  

    Nowadays personal identification is a very important issue. There is a wide range of applications in different spheres, such as video surveillance security systems, control of documents, forensics systems and etc. We consider a range of most significant aspects of face identification system based on support vector machines in this paper. At first we propose improved face detector to get the region of interest for next face recognition. In paper the technique of face detection jointly image normalization is introduced. We compare three algorithms of feature extraction in application on face identification (PCA NIPALS, NNPCA, kernel PCA). The presented system is intended for process the image with low quality, the photo with the different facial expressions. Our goal is to develop face recognition techniques and create the system for face identification. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Multiscale segmentation based on mode-shift clustering

    Publication Year: 2010 , Page(s): 129 - 133
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (633 KB)  

    We present a novel segmentation technique that effectively segments natural images. The method is designed for the purpose of image retrieval and follows the principle of clustering the regions visible in the image. The concept is based on the multiscale approach where the image undergoes a number of diffusions. The algorithm has been visually compared with a reference segmentation. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Relational database as a source of ontology creation

    Publication Year: 2010 , Page(s): 135 - 139
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (189 KB)  

    The article headed “Relational database as a source of an ontology creation” deals with mapping relational data into ontology, or filling ontology with data from relational databases. It describes the issue of mapping database schemas (particularly relational models) for common data models expressed in the form of ontology. Generous room is given to methods of acquiring ontology from relational databases, where rules are specified and simple example are used to demonstrate their use, mapping of individual concepts of a relational data model into ontology concepts. View full abstract»

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