IJMECS Vol. 7, No. 1, Jan. 2015
Cover page and Table of Contents: PDF (size: 126KB)
This research proposes an automatic question generation model for evaluating the understanding of semantic attributes in a sentence. The Semantic Role Labeling and Named Entity Recognition are used as a preprocessing step to convert the input sentence into a semantic pattern. The Artificial Immune System is used to build a classifier that will be able to classify the patterns according to the question type in the training phase. The question types considered here are the set of WH-questions like who, when, where, why, and how. A pattern matching phase is applied for selecting the best matching question pattern for the test sentence. The proposed model is tested against a set of sentences obtained from many sources such as the TREC 2007 dataset for question answering, Wikipedia articles, and English book of grade II preparatory. The experimental results of the proposed model are promising in determining the question type with classification accuracy reaching 95%, and 87% in generating the new question patterns.[...] Read more.
This paper deals with one of our research directions on software tools enhancing self-learning in computer science disciplines. In this study, we discuss an experiment on relational data bases learning using a tool for the edition and automated evaluation of learners’ solutions given as relational algebra trees. Indeed, in addition to the interest of the graphic languages for any training, the evaluation of our precedent works on modeling and evaluating solutions as algebraic expressions showed us some problems: first, there are various languages for the algebraic expressions. Second, among the detected errors by the prototype, developed in our precedent works for algebraic expressions, the form errors about the algebraic language have to be corrected before starting the semantic analysis. Third, in some cases, errors in the form have led to other non-committed errors which can cause inconsistencies in the errors’ diagnosis process. Starting from these problems, the two principal objectives of the work presented in this article concern the algebraic trees construction and the evaluation assisted by a graphic tool which essentially consists in a semantic analysis as recommended in ODALA (ontology driven auto-evaluation learning approach) that we have already proposed. The tool was evaluated by a set of tests and experimented with second year LMD license students. These experiments results were interesting and showed that the tool is particularly helpful for novice students and their teachers.[...] Read more.
Evidently, the results of a face recognition system can be influenced by image illumination conditions. Regarding this, the authors proposed a system using wavelet-based contourlet transform normalization as an efficient method to enhance the lighting conditions of a face image. Particularly, this method can sharpen a face image and enhance its contrast simultaneously in the frequency domain to facilitate the recognition. The achieved results in face recognition tasks experimentally performed on Yale Face Database B have demonstrated that face recognition system with wavelet-based contourlet transform can perform better than any other systems using histogram equalization for its efficiency under varying illumination conditions.[...] Read more.
These days different e-learning architecture provide different kinds of e-learning experiences due to “one size fits for all” concept. This is no way better than the traditional learning and does not exploit the technological advances. Thus the e-learning system began to evolve to adaptable e-learning systems which adapts or personalizes the learning experience of the learners. Systems infer the characteristics of the learners and identify the preferences of the learners and automatically generate personalized learning path and customize learning contents to the individuals needs. This process is known as adaptation and systems which adapt are known are adaptive systems. So the main objective of this research was to provide an adaptive e-learning system framework which personalizes the learning experience in an efficient way. In this paper a framework for adaptive e-learning system using user response theory is proposed to meet the research objectives identified in section 1.D.[...] Read more.
SOA (Service-Oriented Architecture) filled the gap between software and commercial enterprise. SOA integrates multiple web services. We bear to secure the caliber of web services that gives guarantee about what network services work and their output results. There is close to work has to be performed for an automatic test case generation for SOA based services. But, full coverage of XML elements is missing. To the best of our knowledge this all works do not attempt to cover all possible elements of the XML schema presents in the WSDL file. There is also a need to apply different assertions on each service operation for generating the test cases. To overcome this problem we proposed a novel testing model for SOA based application. This new testing model helps us to get the automatic test cases of SOA based application. We build up our new test model with the aid of our proposed test case generation algorithm and test case selection algorithm. In the end, we generate the test suite execution results and find the coverage of XML schema elements present in the WSDL file.[...] Read more.
Dealing with data means to group information into a set of categories either in order to learn new artifacts or understand new domains. For this purpose researchers have always looked for the hidden patterns in data that can be defined and compared with other known notions based on the similarity or dissimilarity of their attributes according to well-defined rules. Data mining, having the tools of data classification and data clustering, is one of the most powerful techniques to deal with data in such a manner that it can help researchers identify the required information. As a step forward to address this challenge, experts have utilized clustering techniques as a mean of exploring hidden structure and patterns in underlying data. Improved stability, robustness and accuracy of unsupervised data classification in many fields including pattern recognition, machine learning, information retrieval, image analysis and bioinformatics, clustering has proven itself as a reliable tool. To identify the clusters in datasets algorithm are utilized to partition data set into several groups based on the similarity within a group. There is no specific clustering algorithm, but various algorithms are utilized based on domain of data that constitutes a cluster and the level of efficiency required. Clustering techniques are categorized based upon different approaches. This paper is a survey of few clustering techniques out of many in data mining. For the purpose five of the most common clustering techniques out of many have been discussed. The clustering techniques which have been surveyed are: K-medoids, K-means, Fuzzy C-means, Density-Based Spatial Clustering of Applications with Noise (DBSCAN) and Self-Organizing Map (SOM) clustering.[...] Read more.
Due to simplicity and robustness, classical PID and SMC have been still widely used in practical applications. Performance of these controllers (PID and SMC) depends upon the value of some of the constant controller parameters. To avoid the most commonly used tedious trial and error method, this paper proposes an improved PSO based method for getting the optimized value of these parameters. For validation purpose these improved PSO tuned Proportional Integral Derivative (PID) and Sliding Mode (SMC) classical controllers have been applied for the motion control problem of the robotic manipulator. The chattering problem of SMC has been handled by using pseudo sliding function. Further results have been analyzed by comparing them with the basic conventional controllers. Results and conclusions are based on simulation results.[...] Read more.
Today major section of automatic speaker verification (ASV) research is focused on multiple objectives like optimization of feature subset and minimization of Equal Error Rate (EER). As such, numerous systems for feature dimension reduction are proposed. This includes framework coaching and testing analysis for every feature set that could be a time esurient trip. Because of its significance, the issue of feature selection has been researched by numerous scientists. In this paper, a new feature subset selection procedure is presented. Hybrid of Ant Colony and Artificial Bee Colony optimized the feature subset over 85% thereby decreased the computational complexity of ASV. Additionally an external record is maintained to store non-dominated solution vectors for which concept of Pareto dominance is used. An overall optimization of 87% is achieved thereby improved the recognition rate of ASV.[...] Read more.