Home > Archives > Latest issue

 

 

 

International Review on
Computers and Software
(IRECOS)
April 2013
(Vol. 8 N. 4)




 



    Entropy Based Approach to Prevent the DDoS Attacks for Secured Web Services

    by S. Igni Sabasti Prabu, V. Jawahar Senthil Kumar

    Vol. 8. n. 4, pp. 888-891

     

    Abstract - A web service is a standards-based, language-agnostic software entity, that it accepts specially formatted requests from other software entities on remote machines via vendor and transport neutral communication protocols, producing application specific responses. Web services are used in every nook and corner of the world. The main strategy of web service is the availability of web service to all and its security over a distributed architecture. To ensure customer satisfaction web services must be available to all the users without any hindrance. The intrusion of attackers may be in any form such as a person or a program to cease the availability of the server. The Distributed Denial of Service attack is one of the severe attacks. The proposed system is an entropy based system which prevents the web service from the denial of service attack.

    Copyright © 2013 Praise Worthy Prize S.r.l. - All rights reserved

     

    Keywords: DDoS, Entropy, Security, Web Service.

     

    Dynamic Extended Rectangle Based Method for 3D Visual Scene Segmentation

    by N. Charara, , M. Sokhn,I. Jarkass, O. Abou Khaled, E. Mugellini

    Vol. 8. n. 4, pp. 892-899

     

    Abstract - A novel approach for semantic scene segmentation with computer vision is presented in this paper.The principle goal is to capture the scene distribution of the different zones of any multipurpose hall, taking into account both monocular visual cues (texture feature) and depth information. A feature extraction strategy based on a dynamic extension of the rectangular patchesis proposed in order to provide a more accurate segmentation and to avoid redundancy penalties.The depth constraints control the initial classification decision that is obtained by a neuro-fuzzy classifier.An experimental study is applied on our dataset to demonstrate this approach on his different optimization stages.

    Copyright © 2013 Praise Worthy Prize S.r.l. - All rights reserved

     

    Keywords: Scene Segmentation, Texture, Depth Information, Neuro-Fuzzy Classification, Pattern Recognition.

     

    Enhancement of Game Theoretic Approach Using Nash Equilibrium with Markov Chains for VANET Security

    by Prabakaran M., A. R. Deepti, G. Mahadevan, R. M. S. Parvathy

    Vol. 8. n. 4, pp. 900-903

     

    Abstract - Vehicular ad-hoc networks (VANETs) are a special type of Mobile ad-hoc networks, which provides safety and commercial applications to the vehicles. Typically, this technology uses every moving car as nodes to form a network. To make a travel more convenient for the user, the VANET has provided a good service and security for them. Recently, game theoretic models are used to address network security issues. The VANET faces the greatest security threats in the game theoretic approach. In this paper a Game theoretic potential for VANET security is applied. This new technique is termed as NE (Nash Equilibrium) with Markov chains based on the game model, is used for VANET to improve the performance and security better.

    Copyright © 2013 Praise Worthy Prize S.r.l. - All rights reserved

     

    Keywords: Nash Equilibrium, Markov Chain, VANET.

     

    A Novel Approach for Hiding Image Using Pixel Intensity

    by M. Shobana, P. Gitanjali, M. Rajesh, R. Manikandan

    Vol. 8. n. 4, pp. 904-908

     

    Abstract - Data communication technologies has leaped into a great level of acceptance globally as it goes hand-in-hand with the other types of data in the carry plane of communication providing every ounce of optimized data. When it has been put in to the public network. Data can be coded as an image or audio or video using a cipher technique named steganography, where image preferred as a cover object. Taking into account of the RGB channel of the given image three kinds of algorithm are utilized in the method that exist earlier whereas with slight alteration were rendered to the proposed system to improve embedding capability .Color channels were used for designing three algorithm with intensity as its cornerstone. Analyzing the accomplishment of three algorithms the most efficient one is considered.

    Copyright © 2013 Praise Worthy Prize S.r.l. - All rights reserved

     

    Keywords: Non-Data Plane, Data Plane, Random Image Steganography.

     

    An Optimal Architecture for Dynamic Web Service Discovery and Selection

    by Abdallah Missaoui

    Vol. 8. n. 4, pp. 909-914

     

    Abstract - The composition of a set of Web services is an important aspect of Web services technology. This allows solving several types of problems by combining available services elementary and ordering them to best meets the requirements of problems. Automatic composition gives us flexibility of selecting best candidate services at composition time satisfying QoS requirements; This would require the user to define constraints for selecting and composing candidate Web services. In this paper, we present QoS broker - based architecture for web services. From the model architecture which allows the management of QoS that we have previously proposed, we focus on how we can use web service with a technique supporting QoS under dynamic web service composition. The main goal of the architecture is to support the client in selecting web services based on his/her required QoS. We also present an efficient method to predict QoS of Web service and to select the suitable web service based on the consumer’s requirements along with QoS.

    Copyright © 2013 Praise Worthy Prize S.r.l. - All rights reserved

     

    Keywords: Web Service, Architecture, QoS, Neuro-Fuzzy.

     

    The Implementation of Plagiarism Detection System in Health Sciences Publications in Arabic and English Languages

    by K. Omar, B. Alkhatib, M. Dashash

    Vol. 8. n. 4, pp- 915-919

     

    Abstract - There are many available algorithms for plagiarism detection in natural languages. Generally, these algorithms belong to main categories including plagiarism detection algorithms which is based on fingerprint and also plagiarism detection algorithms which is based on content comparison that contains string matching and tree matching algorithms. Available systems of plagiarism detection usually use specific types of detection algorithms or mixture of detection algorithms to achieve effective detection systems (fast and accurate). On rhetorical structure theory a system for plagiarism detection in Arabic and English health sciences publications has been developed using Bing search engine; Conclusion, all health sciences manuscripts should be tested through plagiarism detection system before accepting them for publications.

    Copyright © 2013 Praise Worthy Prize S.r.l. - All rights reserved

     

    Keywords: Health Sciences Plagiarism, Natural Language Processing, Plagiarism Detection.

     

    Sensitive Information Protection and Recovery Using One to One Compound Mapping

    by N. V. Chaithanya Kumar Reddy, Diwakar R. Marur, Vidhyacharan Bhaskar

    Vol. 8. n. 4, pp. 920-926

     

    Abstract - With rapid developments in software and hardware technology, nowadays documents are scanned and stored in Internet connected systems. Scanned images hold lot of confidential information. It is essential to protect sensitive information like Credit card number, Social security number, Medical reports etc. from unauthorized access. In this paper, a scheme is proposed to protect such images based on visible watermarking and encryption techniques. With this scheme, sensitive information in an image will be made unreadable with mask image using one-to-one compound mapping. The compound mappings are proved to be reversible, which allows for lossless recovery of original images from protected image. The mask image generation is discussed. This work is implemented in MATLAB.

    Copyright © 2013 Praise Worthy Prize S.r.l. - All rights reserved

     

    Keywords: Lossless Recovering; Mask Generation; Multiple Region Masking; One-To-One Compound Mapping; Reversible Mapping; Scrambling.

     

    Review of Methods of Distributed Barrier Synchronization of Parallel Processes in Matrix VLSI Systems

    by Jamil S. Al-Azzeh

    Vol. 8. n. 4, pp. 927-932

     

    Abstract - The problem of barrier synchronization between parallel processes in VLSI-based mesh-connected multicomputers is under consideration. This paper introduces and reviews description of hardware synchronization methods (HSM) in modern microprocessing systems.

    Copyright © 2013 Praise Worthy Prize S.r.l. - All rights reserved

     

    Keywords: VLSI, Multicomputers, Parallel Processes, Barrier Synchronization, Hardware.

     

    Classification of Ultrasound Carotid Artery Images Using Texture Features

    by Dhanalakshmi Samiappan, Venkatesh Chakrapani

    Vol. 8. n. 4, pp. 933-940

     

    Abstract - The Cardio Vascular Disease (CVD) is the most fatal disease in the world in terms of deaths. The cardio vascular disease, associated with stroke and heart attack, is mainly caused by the increase in calcium deposition in the carotid artery. The Intima-Media Thickness (IMT) of the Common Carotid Artery (CCA) is widely used as an early indicator of CVD. The risk of CVD varies with age groups and this can be categorized based on the texture pattern of image of the carotid artery. This work presents an automated method to classify the carotid artery abnormalities by determining an appropriate Region of Interest (ROI), extracting the texture features, and calculating the IMT. The Ultrasound specimen image is acquired, intensity normalized, pre-processed to remove the speckle noise and then segmented. The texture analysis for segmented images is done using AM – FM techniques. The instantaneous values of the amplitude and frequency of each image specimen is obtained and it is quantized. It is then compared with the standard texture pattern, to identify whether the artery is normal or abnormal. Simulation results shows significant texture differences between the higher-risk age group of >60 years and the lower-risk age group of <50 and the 50-60 age group. Detecting the level of CVD was done by measuring the IMT. The overall process aims at implementing a fully automated system which helps in avoiding human errors, while measuring these values. The measurement technique is described in detail, highlighting the advantages compared to other methods and reporting the experimental results. Finally, the intrinsic accuracy of the system is estimated by an analytical approach. It also decreases inter-reader bias, potentially making it applicable for use in cardiovascular risk assessment.

    Copyright © 2013 Praise Worthy Prize S.r.l. - All rights reserved

     

    Keywords: Carotid Artery, Intima Media Thickness, Texture Features, Instantaneous Amplitude, Instantaneous Frequency.

     

    Fuzzy Based Congestion Detection Technique for Queuing in IP Networks

    by S. Nandhini, S. Palaniammal

    Vol. 8. n. 4, pp. 941-948

     

    Abstract - Internet Protocol (IP) has brought rapid development in many applications such as video and audio streaming, Voice-over-IP (VoIP) and e-commerce. However, these applications suffer from congestion problem, which severely worsens the network performance of real time data transmissions. In this paper, we propose a fuzzy based congestion detection technique for queuing in IP networks. This technique classifies the flow as real time and non real time and the priority scheduler prioritizes the classified flows as high and low, respectively. The congestion level of high priority flows is detected by means of fuzzy logic system. The queue delay and arrival rate are considered as input for Fuzzy logic and the level of congestion is estimated. According to the congestion level of flows, they are scheduled in two different queuing mechanisms. We simulate our technique using NS-2 and simulation results prove the efficiency of our approach. It eradicates unsolicited packet drops and improves packet delivery ratio.

    Copyright © 2013 Praise Worthy Prize S.r.l. - All rights reserved

     

    Keywords: Congestion Detection Techniques Internet Protocol (IP), Queuing, Fuzzy Logic.

     

    Combining UML Class and Activity Diagrams for MDA Generation of MVC 2 Web Applications

    by M’hamed Rahmouni, Samir Mbarki

    Vol. 8. n. 4, pp. 949-957

     

    Abstract - Model transformations are increasingly gaining attention in software design and development. Model transformation plays a key role in Object Management group (OMG) Model Driven Architecture (MDA) initiative. In this paper, we experience a high level modeling method based on MDA to generate MVC2 web model for an E-commerce web application. This idea is based on the fact that the source metamodel is composed by two metamodels which are: the class diagram and activity diagram. In order to model the internal logic of a complex operation and accurately determine the input jsp page of an Action class and all ingredients of this class, we begin by identifying the operations in view to establish the activity diagram for each operation. After modeling, we implement the transformation rules. These rules are expressed in ATL transformation language. In our algorithm, we consider only the operations belonging to the two diagrams already cited. Practically, we transform only the operations that have an activity diagram and belonging to the class diagram. The MVC2 web model generated can effectively simplify the development processing with less time and cost.

    Copyright © 2013 Praise Worthy Prize S.r.l. - All rights reserved

     

    Keywords: MDA, ATL transformation, MVC 2 web, e-commerce, CIM, PIM, PSM, Metamodel.

     

    Digital Image Watermarking and Encryption Using DWT and RSA

    by Omar Alirr, Kasmiran Jumari

    Vol. 8. n. 4, pp. 958-963

     

    Abstract - In DWT based watermarking technique the cover image is decomposed to its frequency bands, the coefficients in these bands are modified to hide secret messages. The main characteristics of DWT Watermarking are the imperceptibility, capacity and low complexity. However, this technique has some limitations if it is used alone; it will not be efficient in terms of data security. In this paper the aim is to incorporate the DWT technique with the RSA public-key algorithm, to accomplish a high capacity and secure communication system. The difficulty of factoring in the RSA algorithm has made it one of the most powerful cryptosystems. The proposed technique aims to transfer high capacity secure data by embedding it inside the cover image without affecting or degrading the imperceptibility of the cover image. The security, capacity and imperceptibility are the main criteria according to which the performance of the system is judged. Many scenarios with different cover images and secret messages, different sizes and different image types, these scenarios are used to evaluate the performance of the proposed system by computing the PSNR and the corresponding payload sizes. For the system to not show any suspension of secret data that is being transferred, the value of the PSNR should be around 40dB, so a trade off must be made between security, capacity and imperceptibility to find to what extent this system can reach.

    Copyright © 2013 Praise Worthy Prize S.r.l. - All rights reserved

     

    Keywords: DWT Watermarking, RSA, Public-Key Cryptography.

     

    Study on Multi-agent Q Learning Based on Prediction

    by Ya Xie, Zhonghua Huang

    Vol. 8. n. 4, pp. 964-969

     

    Abstract - Multi-agent Q learning algorithm(model) based on prediction is proposed in order to make multi-agent has the ability of online learning, which two layers of structure are adopted, planning, prediction and Q learning etc are integrated. The system state is predicted through the adoption of prediction, which the convergence speed of learning is accelerated, at the same time planning technology is used in the model through prior knowledge to solve the partial perception problems, the adaptive learning ability of algorithm has been greatly improved by the application of prediction technology, where learning algorithm has a strong ability of on-line learning and higher learning efficiency, the successful application of this algorithm in the RoboCup shows its good learning performance.

    Copyright © 2013 Praise Worthy Prize S.r.l. - All rights reserved

     

    Keywords: Q Learning, Online Learning, Multi-Agent, Robocup.

     

    Optimization of Processor Architecture for Sobel Real-Time Edge Detection Using FPGA

    by Fawnizu Azmadi Hussin, Zahraa E. M. Osman, Likun Xia, Noohul Basheer Zain Ali

    Vol. 8. n. 4, pp. 970-982

     

    Abstract - This paper presents an optimized processor architecture for Sobel edge detection operator on field programmable gate arrays (FPGA). The processor is optimized by the use of several optimization techniques that aim to increase the processor throughput and reduce the processor logic utilization. FPGA offers a high level of parallelism which is exploited by the processor to implement the parallel process of edge detection in order to increase the processor throughput and enable the processor to meet real-time performance constraints. To achieve real-time performance, the proposed processor consists of several Sobel instances that are able to produce massive output pixels in parallel. This parallelism enables data reuse within the processor block which reduces the number of calculations while increasing the processor throughput. Moreover, the processor gains performance with a factor equal to the number of instances contained in the processor block. By the application of the optimization techniques, the proposed Sobel processor is able to meet real-time performance constraints due to its high throughput even with a considerably low clock frequency. In addition, the logic utilization of the proposed processor is low compared to other Sobel processors when implemented on ALTERA Cyclone II DE2-70 board.

    Copyright © 2013 Praise Worthy Prize S.r.l. - All rights reserved

     

    Keywords: Real-Time and Embedded Systems, Processor Architecture, Optimization, Sobel Edge Detection.

     

    Aspect-Oriented Modeling Approaches and Aspect Code Generation

    by Abid Mehmood, Dayang N. A. Jawawi

    Vol. 8. n. 4, pp. 983-995

     

    Abstract - The integration of aspect oriented modeling approaches with model-driven engineering process achieved through their direct transformation into aspect-oriented code can enhance the software development from many perspectives. However, since no aspect modeling technique has been adopted as the standard so far, it becomes imperative to compare all existing techniques on the basis of some appropriate criteria. This study aims to assess existing UML-based aspect-oriented modeling techniques from the perspective of their suitability with regards to integration into model-driven engineering process through aspect-oriented code generation. For this purpose, an evaluation framework has been defined and employed to evaluate 14 well-published, UML-based aspect-oriented modeling approaches. Results of this comparison show that a majority of these approaches works well to handle the basic modeling tasks. However, in the context of their integration into model-driven engineering process, these approaches need to be improved from various perspectives.

    Copyright © 2013 Praise Worthy Prize S.r.l. - All rights reserved

     

    Keywords: Aspect-Oriented Modeling, Model-Driven Engineering, Code Generation.

     

    Achieving Energy Efficient MAC protocol for MANETs by Channel Utilization and Queue Size

    by P. Sivanesan, S. Thangavel

    Vol. 8. n. 4, pp. 996-1003

     

    Abstract - In mobile ad hoc networks (MANET), the existing Media Access Control (MAC) protocol does not maximize the overall network throughput. Also it causes the network links to utilize higher power for data transmission. In order to overcome these issues, in this paper, we propose an energy efficient MAC protocol in MANET based on channel utilization and queue size. In this protocol, the source node that desires to transmit the data packet to its destination node, appends its queue state and channel utilization with request to send (RTS) frame and transmits it to the destination utilizing the utility function. After the destination verifies the RTS frame for error, its sends the clear to send (CTS) frame along with queue state and channel utilization information to source node using utility function. Upon receiving CTS frame, the source transmits the data packet to the destination node. By simulation results, we show that the proposed protocol improves the overall network throughput and minimizes the energy consumption.

    Copyright © 2013 Praise Worthy Prize S.r.l. - All rights reserved

     

    Keywords: Mobile Ad Hoc Networks (MANET), MAC Protocol, Request to Send (RTS), Clear to Send (CTS).

     

    Image Compression based on Crucial Region for Radiographic Weldment Images

    by V. Vaithiyanathan, B. Karthikeyan, B. Venkatraman

    Vol. 8. n. 4, pp. 1004-1011

     

    Abstract - Radiographic images are generally of high volume. These images when stored occupy a lot of storage space and the transmission of them is also difficult due their large size. So reduction of size plays an important role in storage and transmission of images. To achieve this reduction, compression techniques are being widely used. This paper focuses on the process of welding, Tungsten Inert Gas (TIG) welding in specific, the generation and development of photographic film of weldments and also a novel method is presented, which is intended to reduce the size of the radiographic image developed, by applying lossless compression technique on the crucial regions of the image. The crucial regions of the image are automatically detected by using segmentation technique in the proposed method. After the detection of crucial regions, lossless compression technique is applied on them. The compressed data obtained along with some information of the image is transmitted to the other validated user for reconstruction of the original image. Apparently, the original image data can’t be understood by the third party during transmission, which makes this method to be used for secure transmission of data. The image reconstructed by this method will not have any loss of data in the crucial regions of the image but certain loss is present in the non-crucial regions. This method is tested on some images and their results are shown in the paper along with the compression rates. The results are also compared with other methods.

    Copyright © 2013 Praise Worthy Prize S.r.l. - All rights reserved

     

    Keywords: TIG Welding, Radiographic Images, Huffman, Lossless Compression, Entropy.

     

    Energy based Efficiency Evaluation of Cluster and Tree based Routing Protocols for Wireless Sensor Networks

    by M. Faheem, Zia Ud Din, M. A. Shahid, S. Ali, B. Raza, L. Sakar

    Vol. 8. n. 4, pp. 1012-1022

     

    Abstract - The wireless arena has been experiencing exponential growth in the last couple of years. In twenty- first century, due to recent advances in sensor and wireless communication technologies have enabled a new generation of massive-scale Wireless sensor network (WSN) and is not-too-distant future when miniature, low-cost sensors may be literally sprayed onto walls, roads, or machines, creating a digital skin that can observe a variety of interested physical phenomena. Due to the severe energy constraint of a sensor node, network architectures and protocol are important aspects in the design of Wireless sensor network due to their big impact on the energy consumption. Since last couple of years to prolong the network lifetime of a tiny sensor node various researchers have proposed a number of energy efficient routing protocols. Up till now, their performance superior or worse cannot be inspected without any suspicion by conventional techniques because of their transformed behavior in different environments. The aspire of this research is to evaluate the performance among energy efficient routing protocols in Wireless sensor networks (WSNs) based on metrics Overhead, Delay, Packet Delivery Ratio (PDR) and Congestion over Energy consumption and Network lifetime. The current research work can be utilized to guide protocol designing, application-specific protocol selection and modification of the existing routing protocols in Wireless sensor networks. Simulations between Energy Efficient Cluster based Data Gathering Protocol ECDGP and Energy Efficient Data Collection Protocol-Tree Based EEDCP-TB confirms their results in term of Overhead, Delay, Packet Delivery Ratio (PDR) and Congestion on Energy consumption and Network lifetime.

    Copyright © 2013 Praise Worthy Prize S.r.l. - All rights reserved

     

    Keywords: Wireless Sensor Network, Energy Efficient, Routing, Protocol, Cluster, Tree.

     

    A Wavelet Based Scheme for Video Watermarking

    by M. Sundararajan, G. Yamuna

    Vol. 8. n. 4, pp. 1023-1032

     

    Abstract - In rapid growth of network distributions of images and video, there is an urgent need for copyright protection against pirating. Different digital image and video watermarking schemes have been proposed to address this issue of ownership identification. This paper proposes a novel scheme for video watermarkin g scheme using discrete wavelet transform to protect the copyright of digital images. The efficiency of the proposed video watermarking technique is attained by two major steps: 1) Watermark embedding process and 2) Watermark extraction process. Before embedding the watermark into the digital video, the input video sequence is segmented into shots using well known shot segmentation technique. The segmented video shots are partitioned into number of frames for the embedding process. The proposed method renders the utilization of the grayscale image as a watermark to embed into the digital video sequence. The grayscale image is sliced into bit planes for analyzing the each bit of the image. Subsequently, the sliced bit plane images are permuted and each permuted watermark images are embedded into each frame of the segmented shots with the aid of the watermark embedding process. Then the recovery of the watermark is achieved with the help of the watermark extraction process. The experimentation results shows that the proposed video watermarking scheme provide better results with higher accuracy. The proposed scheme is robust against the various attacks such as frame dropping, frame averaging attack.

    Copyright © 2013 Praise Worthy Prize S.r.l. - All rights reserved

     

    Keywords: Digital Video Watermarking, Discrete wavelet transform, Embedding, Extraction, Copyright Protection.

     

    Signature Analyzer Block For Secure Node Entry

    by C. Navaneethan, K. Helen Prabha

    Vol. 8. n. 4, pp. 1033--1036

     

    Abstract - We address the problem of secure transmission between two or more systems involved in communication and to overcome those using Hardware and Software co-design. With the spreading of the Internet and online forums the trusted request for a channel is diminishing and at the same time safeguarding the data and the channel from intrusion has become an inevitable requirement. Apart from the concept, the use of the existing secured transmission nodes tends to travel either toward the theorems of advancements, syllogisms, techniques and algorithms of the software issues. Hence, data could be protected, via the software & hardware co-design, from the intruders. The focus is to identify the untrusted nodes in the initial stage itself into the transmission from the physical and data link layer without using firewalls. Signature-based IDSs aim to distinguish those events that deviate from the system’s network terms and conditions. Signature-based schemes (also denoted as misuse-based) identifies the defined patterns, or signatures, within the examined data and also defends the Distributed denial of service attacks.

    Copyright © 2013 Praise Worthy Prize S.r.l. - All rights reserved

     

    Keywords: Inevitable, Firewalls, Syllogisms, Signature based IDS, Distributed Denial of Service.

     

    Swarm Based Topology Control for Fault Tolerance in MANET

    by D. Manohari, G. S. Anandha Mala

    Vol. 8. n. 4, pp. 1037-1044

     

    Abstract - To perform fault-tolerant topology control in mobile ad hoc networks (MANET), selection of an appropriate transmission power for each node and maintenance of network connectivity are daunting tasks. Most of the related works have considered either transmission power or network connectivity and not both simultaneously. In this paper, we propose a swarm based topology control algorithm for fault tolerance in MANET. Initially, each node constructs its neighbor set by sending neighbor discovery message to its neighbors. The forward and backward ants are used to gather and update nodes minimum transmission power. Meanwhile, each node calculates its interference number and they are updated in neighbor set table. Before transmitting data to the destination, the source node finds multiple paths and calculates aggregate transmission power and interference value along each path. Finally, source chooses the optimal path that satisfies both minimum interference and minimum transmission power. By simulation, we prove that our work efficiently provide fault tolerant topology control in mobile ad hoc networks.

    Copyright © 2013 Praise Worthy Prize S.r.l. - All rights reserved

     

    Keywords: Mobile Ad Hoc Networks (MANET), Topology Control, Fault Tolerance, Ant Colony Optimization (ACO).

     

    A Bayesian Classification Approach for handling Uncertainty in Adaptive E-Assessment

    by V. Geetha, D. Chandrakala, R. Nadarajan, C. K. Dass

    Vol. 8. n. 4, pp. 1045-1052

     

    Abstract - New technologies have provided the educational field with innovations that allow significant improvement in the teaching learning process. The development of information technology has increased the popularity of Web based education, ; particularly E-assessment This paper provides an overview of Bayesian Network and its application to handle uncertainty in adaptive E-assessment. An adaptive assessment system was realized in PHP and MYSQL. The empirical data was collected and the relationship between the response time and the assessment grading was established. The classifier accuracy obtained using Bayesian classifier was compared with C4.5 Decision tree algorithm and Naïve Bayes classifier. The superiority of Bayesian algorithm over the well known algorithms in handling uncertainty of adaptive assessment data is established in this paper.

    Copyright © 2013 Praise Worthy Prize S.r.l. - All rights reserved

     

    Keywords: Adaptive Assessment, Degree of Toughness (DT), Bayesian Network, Naive Bayes Classifier, Classifier Accuracy, F-Measure, Area under Curve (AUC).

     

    A Technique to Mine the Multi-Relational Patterns Using Relational Tree and A Tree Pattern Mining Algorithm

    by M. RaviSankar, P. PremChand

    Vol. 8. n. 4, pp. 1053-1061

     

    Abstract - The reason of the powerful application and large availability of the databases, the data mining become chalengable and trustful research field. The pattern mining is one of the fields in the data mining. The multi-relational data mining allows pattern mining from multiple table, in recent years multi-relational pattern mining is developing rapid manner. Even though the existing multi-relational mining algorithms are not ideal for the large amount of data. In this paper, we have developed a technique to mine the multi-realtional pattern using a relational tree. The relational tree constructed by reading the records from multi-relational database one by one and make the combination (relations) according the presence of fields in the database. From this we get the relational tree data structure without violating the relations of the records. Subsequently , the tree pattern mining algorithm is formulated and applied to the developed tree structure for mining the important relational patterns from the relational tree. The experimentation is carried out on the patient medical database and comparative results are extracted and the performance of the proposed approach is evaluated based on the existing work.

    Copyright © 2013 Praise Worthy Prize S.r.l. - All rights reserved

     

    Keywords: Relational Tree, Pattern Mining, Multi-Relational Database, Single Relation, Multi-Relation, Multi-Relation Data Mining.

     







Please send any questions about this web site to info@praiseworthyprize.it
Copyright © 2005-2014 Praise Worthy Prize