IJCSA                                         ISSN 0972-9038

Aims & Scope
Editorial Board
Submission Guidelines
Copyright Form
Referee Form
Special Issue Proposal
CFP for Special Issue

Disclaimer & Re-publication 






Year 2008: Volume V Issue II


Paper Title: Biomedical Named Entity Recognition Based on Classifiers Ensemble. (PDF)
Authors: Haochang Wang,  Tiejun Zhao,  Hongye Tan, and  Shu Zhang
Abstract: In this paper, we present classifiers ensemble approaches for biomedical named entity recognition. Generalized Winnow, Conditional Random Fields, Support Vector Machine, and Maximum Entropy are combined through three different strategies. We demonstrate the effectiveness of classifiers ensemble strategies and compare its performances with standalone classifier systems. In the experiments on the JNLPBA 2004 evaluation data, our best system achieves an F-score of 77.57%, which is better than most state of the art systems. The experiment show that our proposed classifiers ensemble method especially the stacking method can lead to significant improvement in performances of biomedical named entity recognition.
Paper Title: A DNA Sticker Algorithm for Solving N-Queen Problem. (PDF)
Authors: H. Ahrabian , A. Mirzaei, and A. Nowzari-Dalini 
Abstract: Over the past few decades numerous attempts have been made to solve combinatorial optimization problems that are NP-complete or NP-hard. It has been evidenced that DNA computing can solve those problems which are currently intractable on even fastest electronic computers. This paper proposes a new DNA algorithm for solving N-Queen problem, a complex optimization problem. The algorithm not only shows whether or not a solution exists, but provides all possible solutions by massively parallel computations. The proposed algorithm can be easily extended to solve other optimization problems.

Paper Title: The GOQL Language and its Formal Specifications. (PDF)
Author: Euclid Keramopoulos, Philippos Pouyioutas , Tasos Ptohos
Abstract: The Graphical Object Query Language (GOQL) is a graphical query language that complies with the ODMG standard and runs on top of the o2 DBMS.  The language provides users with the Userís View (UV) and the Folders Window (FW), which serve as the foundation upon which end-users can pose ad-hoc queries. The UV is a graphical representation of any underlying ODMG scheme.  Among its advantages is that it hides from end-users most of the perplexing details of the object-oriented database model, such as methods, hierarchies and relationships. To achieve this, the UV does not distinguish between methods, attributes and relationships, it encapsulates is-a hierarchies and it utilises a number of desktop metaphors whose semantics can be easily understood by end-users. The FW is a condensed version of the UV and provides the starting point for constructing queries. In this paper, we demonstrate, using an example, the UV and the FW and the way they support the construction of graphical queries. We then present the formal specifications of the language. We first give a formal definition of an object-oriented database schema in the GOQL model. The UV is then formally defined as a mapping from a GOQL object-oriented database schema. The formal definition of the UV allows us to formally define the graphical constructs of GOQL and the syntax analysis of the language.
Paper Title: Algorithms to Improve Performance of Natural Language Interface. (PDF)
Authors: M. R. Joshi and R. A. Akerkar
Abstract:  Performance of Natural Language Interface often deteriorates due to linguistic phenomena of Semantic Symmetry and Ambiguous Modification. In this paper we present algorithms to handle problems caused by semantic symmetry and ambiguous modification. Use of these algorithms has improved the precision of Natural Language Interface. Proposed shallow parsing based algorithms reduce the amount of syntactic processing required to deal with problems caused by semantic symmetry and ambiguous modification. These algorithms need only POS (Part of Speech) information that is generated by shallow parsing of corpus text. Results are compared with the results of basic Natural Language Interface without such algorithm. Dealing with linguistic phenomena using shallow parsing is a novel approach as we overcome the usual brittleness associated with in depth parsing. We also present computational results that produced comparative charts based on answers extracted for a same query posed to these two systems. 

Paper Title: Traffic Analysis Based Identification of Attacks. (PDF)
Authors: Dima Novikov, Roman V. Yampolskiy, and Leon Reznik
Abstract: This paper is devoted to the problem of identification of network attacks via traffic analysis. Neural networks are chosen by us due to their capability to recognize an attack, to differentiate one attack from another, i.e. classify attacks, and, most important, to detect new attacks that were not included into the training set. Performed experiments demonstrate the advantage of our intrusion detection system compared to those created by the winner of the KDD Cup the leading data mining and knowledge discovery competition in the world. The results obtained indicate that it is possible to recognize attacks that the intrusion detection system never faced before on an acceptably high level.

Paper Title:The Design of Decomposed Scorm Structure With Embedded LCMS Broker. (PDF)
Authors: Fu-Chien Kao, Chih-Wei Tseng, Wen-Yu Chang, and Chang-Yu Huang
Abstract: This study proposed a decomposed SCORM (Sharable Course Object Reference Model) structure with embedded LCMS Broker that provides the integration of learning resources and balance of network traffic. The system consists of the Learning Management System (LMS) for processing basic data, learning data and learning records of learners, and the Learning Content Management Systems (LCMSs) for managing and storing course resources. The Web Service cross-platform distribution configuration of this study provides common communications between systems and enhances the capability of integrating learning resources.  The proposed embedded LCMS Broker ensures a load-balancing functionality for LCMS of different domains.  The connection program embedded into the PC of the learner via LMS connects to the embedded LCMS Broker for access to required teaching materials from each LCMS.  The LCMS with the minimum load is then selected from suitable LCMS as the source of the teaching materials.  Since the SCORM standard integrates teaching materials and platforms using JAVA Script, cross-domain scripting issues may occur when the learning system and course resources are stored in subsystems of two different domains.  This study proposed a SCORM learning environment by creating a cross-domain server with URL-rewrite technology to provide a solution for this issue.

© COPYRIGHT 2010 ALL RIGHTS RESERVED Technomathematics Research Foundation

TMRF Publication

This is an online open - access
journal of Technomathematics  Research Foundation.
Visit TMRF!