Ahmad Al-Taani1, Mohammed Msallam2, and Sana Wedian1
1Department of Computer Science, Yarmouk University, Jordan
2Department of Computer Science, Al-Aqsa University, Palestine

 

Abstract: Parsing of Arabic sentences is a necessary mechanism for many natural language processing applications such as machine translation; question answering, knowledge extraction and information retrieval. In this study, we present a top-down chart parser for parsing simple Arabic sentences, including nominal and verbal sentences within specific domain Arabic grammar. We used the Context Free Grammar (CFGs) to represent the Arabic grammar. We first developed the Arabic grammar rules that give precise description of grammatical sentences. Then, we implemented the parser that assigns grammatical structure to the input sentence. The parser is tested on sentences extracted from real documents. Experimental results showed the effeteness of the proposed top-down chart parser for parsing modern standard Arabic sentences. From a practical perspective, the parser is able to satisfy syntactic constraints and reduce parsing ambiguity.

  

Full Text

Fadoua Samoud, Samia Maddouri,  and Noureddine Ellouze
Image Processing and Pattern Recognition Lab, National School of Engineers of Tunis, Tunis

 

Abstract: The main theme of this paper is the segmentation of handwritten Arabic script into blocks, connected components and characters using a combination between Hough Transform (HT) and Mathematical Morphology (MM) tools. We start by a segmentation methodology of a complex document into its distinct entities namely handwritten components. Each extracted handwritten blocks are then segmented into sub-words as a main specificity of Arabic script. Finally a character segmentation method is presented. For each segmentation step, some concepts are needed such as dynamic kernel and Harris corner detectors. The proposed method is tested on the CENPARMI Arabic check database and on the IFN/ENIT database. We present a concept for automatic evaluation of the results, based on label tools for the different parts of used documents. 

  

Full Text

Saeed Farzi
 Faculty of Computer Engineering, Islamic Azad University of Kermanshah, Iran

 

Abstract: Nowadays, the development of advanced techniques of system modelling has received much attention .Polynomial Neural Network (PNN) is a GMDH-type algorithm (Group Method of Data Handling), which is one of the useful methods for modelling nonlinear systems but PNN performance depends strongly on the number of input variables and the order of polynomial which are determined by trial and error. In this paper, we discuss a new design methodology for polynomial neural networks PNN in the framework of learnable evolution model (LEM3). LEM3 is a new approach to evolutionary computation, which employs machine learning to guide evolutionary processes. LEM3 is obtained better performance in shorter time in comparing with other well-known methods. Also, LEM3 appears to be particularly suitable for solving complex optimization problems in which the fitness evaluation function is time consuming. In this paper, we use LEM3 to search between all possible values for the number of input variables and the order of polynomial. Evolved PNN performance is obtained by two nonlinear systems. The experimental part of the study involves two representative time series such as Box-Jenkins gas furnace process and the Dow Jones stock index.

  

Full Text

Raed Almomani and Ismail Ababneh
 Department of Computer Science, Al Al-Bayt University, Jordan

 

Abstract: Various contiguous and non-contiguousprocessor allocation policies have been proposed for two-dimensional mesh-connected multicomputers. Contiguous allocation suffers from high processor fragmentation because it requires that a parallel job be allocated a single contiguous processor subset of the exact shape and size requested. In non-contiguousallocation, a job may be allocated multiple dispersed processor subsets. This can reduce processor fragmentation, however it may increase the communication overhead because inter-processor distances can be longer and messages from different jobs can contend for communication resources. The extra communication overhead depends on how allocation requests are partitioned and assigned processors. In this paper, we investigate non-contiguousallocation for three-dimensional meshes. A greedy policy where partitioning is based on the processors available is proposed and compared, using simulation, to contiguous first-fit allocation, and to non-contiguousschemes adapted from previous two-dimensional schemes. In the detailed flit-level simulator, developed for this research, several common communication patterns are considered. The results show that non-contiguousallocation is expected to improve system performance in three-dimensional mesh-connected multicomputers substantially.

  

Full Text

1Khaled AbdElSalam, 2Mahmoud Maree, and 1Gamal AbdElAzeem
1Faculty of Engineering, Suez Canal University, Egypt
2Faculty of Engineering, El- Azhar University, Egypt

 

Abstract: All IP networks become increasingly visible. The various communication networks are aimed to be connected with each other through a common IP core, so that the user will stay always online, anytime and anywhere. However a lot of challenges remain unsolved until today. One of the major challenges is how to achieve a seamless and fast handoff while moving from one point off attachment to another. In this paper we propose a new fast and smooth handoff approach called Pre-MIFA (pre registration mobile IP fast authentication protocol). Pre-MIFA uses the layer 2 trigger to eliminate the latency resulting from the agent discovery procedure (pre-registration method), and the MIFA procedures to eliminate the latency resulting from the communication between the foreign agent and the home agent especially when the home gent is far a way from the foreign agent. Our approach minimizes the handoff latency without introducing intermediate node and without making any restriction on network topology .we also present a simple program analysis comparing the hand off latency of MIP, MIFA, Pre-Registration and our approach. Our results have shown that Pre-MIFA outperforms Pre-Registration method, MIP and MIFA with respect to handoff latency.

  

Full Text

Shahaboddin Shamshirband
Department of Computer System and Technology, University of Malaya (UM), Malaysia

 

Abstract: Traffic signal control agent can improve its control ability by using the NNQ-learning method. This paper proposes a neural network Q-learning approach with fuzzy reward designed for online learning of traffic lights behaviors. The Q-function table usually becomes too large for the required state/action resolution. In these cases, tabular Q-learning needs a very long learning time and memory requirements which makes the implementation of the algorithm impractical, in real-time control architecture. We considered the problem of coordinating three traffic signals control. The coordination is done using control agents and the concept of game theory. To test the efficiency of the coordination mechanism, a prototype traffic simulator was programmed in visual Studion.net. Results using cooperative traffic agents are compared to results of control simulations where non-cooperative agents were deployed. It indicated that the new coordination method proposed in this paper is effective.

  

Full Text

Saurabh Mehta and Kyungsup Kwak
UWB Wireless Communication Research Center, Inha University, Korea

 

Abstract: The Wireless Personal Area Network (WPAN) is an emerging wireless technology for future short range indoor and outdoor communication applications. The IEEE 802.15.3 Medium Access Control (MAC) is proposed, specifically, for short range and high data rates applications, to coordinate the access to the wireless medium among the competing devices. This paper uses analytical model to study the performance analysis of WPAN (IEEE802.15.3) MAC in terms of throughput, efficient bandwidth utilization, and delay with various acknowledgment schemes and aggregation mechanism under different parameters. From the performance analysis we can determine the optimal payload size, burst-size, and ACK policy for a given set of parameters. Moreover, numerical results demonstrate the advantage of frame aggregation with Dly-ACK policy over basic policies of WPAN.       

  

Full Text

Khaled Alallayah1, Mohamed Amin2, Waiel AbdElwahed3, and Alaa Alhamami4
1Department of Computer Science, IBB University, Yemen
2Department of Mathematical and Computer Science, El-Menoufia University, Egypt
3Department of Operation Research and Decision, El-Menoufia University, Egypt
4Faculty of Computing Studies, Amman Arab University for Graduate Studies, Jordan

 

Abstract: The problem in cryptanalysis can be described as an unknown and the neural networks are ideal tools for black-box system identification. In this paper, a mathematical black-box model is developed and system identification techniques are combined with adaptive system techniques, to construct the Neuro-Identifier. The Neuro-Identifier is discussed as a black-box model to attack the target cipher systems. In this paper a new addition in cryptography has been presented and the methods of block Simplified DES (SDES) crypto systems are discussed. The constructing of Neuro-Identifier mode is to achieve two objectives: the first one is to emulator construction Neuro-model for the target cipher system, while the second is to (cryptanalysis) determine the key from given plaintext-ciphertext pair.

  

Full Text

Tinghuai Ma1, Hao Cao1, Donghai Guan1, SungYoung Lee2
1Jiangsu Engineering Center of Network Monitoring, School of Computer and Software, Nanjing University of Information Science & Technology University, China
2Department of Computer Engineering, Kyung Hee University, Korea

 

Abstract: This paper presents a multi-agent based framework for managing, sharing, and accessing weather data in a geographical distributed environment. There are two tiers in this framework including national central centre and local centre. In each node, the services for querying and accessing datasets based on agent environment are designed, which includes data resource agent, local management system, and metadata system. Information retrieval can be conduced either locally or distributed, by querying local weather data or exploiting global metadata respectively. With a variety of advantages, this proposed platform is designed to provide a useful platform for research on weather data sharing system in a national area.

  

Full Text

Ayad Abbas and Juan Liu
School of Computer, Wuhan University, China

 

Abstract: Recommender systems have become fundamental in web-based applications and information access. They effectively prune large information spaces and provide appropriate decision making and suggestions so that users are directed toward those items that best meet their needs, preferences and interests. In web-based learning context, these systems usually neglect the learner’s ability, the difficulty level of the recommended item (e.g., learning resource, exam), and the learner self-assessment. Therefore, this paper suggests an intelligent recommendation system to provide adaptive learning. The suggested system consists of two main intelligent agents First, a personalized learning resource based on partial credit model (PLR-PCM) which considers both the learner’s ability and the learning resource difficulty to provide individual learning paths for learners. Second, BRS-Recommendation agent provides decision rules, as an instrument or guide for the learner’s self-assessment using Bayesian Rough Set (BRS), based inductive learning algorithm. Experimental results show that the proposed system can exactly provide a learning resource closer to the learner’s ability with appropriate feedback to the learner, resulting in the improvements of the learning efficiency and performance.

  

Full Text

Rashid Saeed
  Electronics Engineering Department, Engineering Faculty, Sudan University of Science and Technology (SUST), Sudan

 

Abstract: The needs for bridging of digital divide in rural communities and the economics of currently available broadband access technologies motivate for innovate and deploy new system designs and applications.  The widely available and flexible WiFi technique meets the cost and suitability targets for rural broadband applications. To cope with the special requirements of rural communication, amendments of 802.11 standards at the MAC protocol level has been introduced. These amendments were important due to the shortcomings of WiFi over long distances under the power constraints. This paper proposes a new 802.11 point-to-multipoint (PMP) technique based on TDD/TDMA technique, this by using one of the access points in the system as centralized/gateway point to the others APs. The discussion includes the TDMA design, architecture on top of the conventional 802.11 MAC. The protocol convergence at the gateway between the access network and the backhaul is also presented. The simulation results present the performance analysis and validate the efficiency of the proposed scheme.

  

Full Text

Fatima Meskine1 and Safia Nait Bahloul2
1Department of Computer Science, University of Es-Senia, Algeria
2Department of Computer Science, University Oran, Algeria

 

Abstract: The clustering is an exploratory task of data mining. This raised a real problem of privacy when the data are from different sources. Most of researches on privacy preservation in clustering are developed for k-means clustering algorithm, by applying the secure multi-party computation framework. . The distribution of data may be different (vertical, horizontal or arbitrary). Approaches allowing solving the problem on a vertical, horizontal and even arbitrary partitioned dataset were proposed.  The major interest is to reveal the minimum of information during the execution of the algorithm, especially in k-means iterations, which poses a real challenge for secure multi party computation.  This work consists to study and analyze all works of privacy preserving in the k-means algorithm, classify the various approaches according to the used data distribution while presenting the weaknesses and the strong points of each protocol regards to privacy. The interest is to arise the real needs of privacy  during the execution of the different steps of k-mean algorithm, thus to discover the best of approaches in case of preserving privacy in k-means algorithm.

  

Full Text