Venue : Coral Deira - Dubai, Deira, Dubai, UAE..  &  Date : April 24 ~ 25, 2015

Accepted papers

  • Performance study of classification algorithms for consumer online shopping attitudes and behavior using data mining
    Rana Alaa El-Deen Ahmed, M.Elemam.Shehab, Shereen Morsy and Nermeen Mekawie, Arab academy for science and technology, Egypt
    With the growing popularity and acceptance of e-commerce platforms, users face an ever increasing burden in actually choosing the right product from the large number of online offers. Thus, techniques for personalization and shopping guides are needed by users. For a pleasant and successful shopping experience, users need to know easily which products to buy with high confidence. Since selling a wide variety of products has become easier due to the popularity of online stores, online retailers are able to sell more products than a physical store. The disadvantage is that the customers might not find products they need. In this research the customer will be able to find the products he is searching for because recommender systems are used in some ecommerce web sites.

    Recommender system learns from the information about customers and products and provides appropriate personalized recommendations to customers to find the needed product. In this paper eleven classification algorithms are comparatively tested to find the best classifier fit for consumer online shopping attitudes and behavior in the experimented dataset. The WEKA knowledge analysis tool which is an open source data mining work bench software used in comparing conventional classifiers to get the best classifier was used in this research. In this research by using the data mining tool(WEKA) with the experimented classifiers the results show that decision table and filtered classifier gives the highest accuracy and the lowest accuracy classification via clustering and simple cart.
  • Parameterization of RBF Neural Networks Via Combination of Unsupervised Procedures and a New Way of Scaling Parameters
    Carlos Alberto Murari Pinheiro, Flavia Aparecida Oliveira Santos, Pedro Paulo Balestrassi and Benedito Isaias Lima Lopes, Federal University of Itajuba, Brazil
    With the increasing applications of image processing techniques is various areas contrast image masking methods. Among the availability of image masking methods is encryption with different keys is the one of the most efficient approach. This entitles “Image Encryption Using Used defined Private Key” work to encrypt the image. In this work we make a random numbers and few operations applies on images we get Masking images in the form of image encryption. Finally the Experiments are conducted to demonstrate the feasibility of the security is providing to the image in network security.
  • Performance Evaluation Of Channel State Prediction for Multi secondary users in cognitive radio
    Nakisa Shamsi, K.N.T University of technology, Iran
    Cognitive radio networks can be designed to manage the radio spectrum efficiently by utilizing the spectrum holes in primary users’ licensed frequency bands. This spectrum utilization can be improved significantly by making access this spectrum holes for secondary users. As spectrum sensing to detect spectrum holes consumes considerable energy, using prediction methods of available channels, the secondary user will select only those channels which are predicted to be idle. In this paper a channel state predictor using Time-Delay Neural Network and Recurrent Neural Network is designed by supervised learning to predict the next state of a communication channel based on a delayed sequence of previous channel states. Performance of channel status prediction, when the channel state occupancy of primary users are assumed to be Poisson distributed, is investigated. Also, we propose an algorithm for dynamic spectrum allocation in cognitive radio networks. Simulation results show that using channel state prediction and the proposed channel allocation algorithm to secondary users, probability of wrongly predicting the idle channel status in a multichannel system, in other words, the probability of channel switching for access to the idle channels, is less than 0.2%. On the other hand, channel status prediction helps to save the sensing energy and also to improve the spectrum utilization. The percentage of improvement in spectrum utilization using predictor is more than 77%.
  • A Linguistic Color Space
    Reshmalakshmi C and M.Sasikumar, Marian Engineering College, India
    Color prediction is still a critical issue in computer vision and image processing. It is necessary to ensure that the perceived color of object remains constant under varying illumination conditions. Novelty of this paper lies in introduction of a linguistic color space using fuzzy system for better color constancy and white balancing.In addition, mapping from RGB to linguistic space retains the precision and accuracy. While evaluating the algorithm, it is clear that the color components are preserved effectively and accurately with the help of combination of different types of membership functions.Inference rules with membership functions results intuitive and efficient color space.