Accepted Papers

  • Using BP Neural Network for Adapting Playout Time in Communication Networks
    Sara A. Helmi1,2 N. M. Badra2 and Mohamed Elkattan3, 1British University in Egypt, 2Ain Shams University,3Nuclear Materials Authority, Egypt

    New multimedia Applications have a critical requirement on jitter. Network jitter is a dramatic problem in communication network especially in Voice over IP network (VOIP); as one of the proposed solutions to minimize jitter is to adapt the playout time. In our paper, we introduce an adaptive approach using Back Propagation neural network (BP) to identify the jitter and adjust the playout time according to several network conditions; the algorithm was tested using k-fold cross validation and the results show that the algorithm can achieve a promising results under a different delay conditions.
  • Cyborgism as a Model of Human-Computer Interaction
    Mohammad Ibrahim Aljayyousi, Philadelphia University, Jordan

    This paper proposes a new model for the human computer interaction that stems from rethinking the relations between humans and the computer as one of partnership, or the term I am suggesting, cyborgism. This model is based on a collaborative paradigm based on a division of “tasks” between man and machine which breaks the traditional hierarchy and open up more possibilities for AI as the paper exemplifies with a couple of applications, one is about machine tarsnaltion. The paradigm I am suggesting is adapted from the dominant ones in the field of HCI but it avoids the misconceptions and the underlying assumptions that have hindered the improvement of AI concepts.
  • Classification of Upper Airways Images for Endotracheal Intubation Verification
    Dror Lederman, Holon Institute of Technology, Israel

    This paper addresses the problem of classification of upper airways images for endotracheal intubation verification in order to improve the safety of patients undergoing general anaesthesia. The proposed method is based on textural features utilized in a continuous probabilistic framework using parallel Gaussian mixture models (GMMs). The classification decision is made based on a maximum likelihood approach, which is insensitive to the angle at which the image was taken. Evaluation of the proposed approach is done using a dataset of 200 images that includes three classes of anatomical structures of the upper airways. The results show that the approach can be used to efficiently and reliably represent and classify medical images acquired during various procedures.

  • Big Data Technology Accelerate Genomics Precision Medicine
    Hao Li, Intel Corporation, China

    During genomics life science research, the data volume of whole genomics and life science algorithm is going bigger and bigger, which is calculated as TB, PB or EB etc. The key problem will be how to store and analyze the data with optimized way. This paper demonstrates how Intel Big Data Technology and Architecture help to facilitate and accelerate the genomics life science research in data store and utilization. Intel defines high performance GenomicsDB for variant call data query and Lustre filesystem with Hierarchal Storage Management for genomics data store. Based on these great technology, Intel defines genomics knowledge share and exchange architecture, which is landed and validated in BGI China and Shanghai Children Hospital with very positive feedback. And these big data technology can definitely be scaled to much more genomics life science partners in the world.
  • Research of Recognition System of Web Intrusion Detection based on Storm
    Mohamed Lubani1 and Rohana Mahmud2, 1Universiti Kebangsaan Malaysia, 2University of Malaya, Malaysia

    Banjar is one of the world’s minority languages with very few language resources that can be used to facilitate the statistical language processing techniques. Translation is one of the least researched issues in Banjar language processing. In this paper we focus on the task of Malay-Banjar translation more specifically we tackle the issue of building conversion rules to be used when translating Malay words that contain vowels not supported in Banjar language. The goal is to minimize the size of word-to-word mapping list by utilizing the shared lexical patterns in Malay words. We conducted and evaluated a set of experiments to generate the conversion rules. As a result we found that rules can be successfully used to convert vowels when translating from Malay to Banjar since this conversion is regulated by character patterns.


Technically Sponsored by