July 2013, No. 4
Print E-mail

ROBOSOFA-Low Cost Multimodal I/O
Fusion for Smart Furniture

Rytis Maskeliunas and Vidas Raudonis
Information Faculty, Kaunas University of Technology, Lithuania

 
Abstract: The smart furniture provide various services alone or by communication with other devices. The cost and time for building such devices is a barrier to the deployment of various novel applications. Since the smart devices are typically equipped with embedded or traditional computers, various sensors and multimodal I/O devices, it can provide various services in public spaces as well as in private spaces. The goal of our research was to introduce affordable techniques on how to build and model the acceptable multimodal HCIs and interactions with the environment all integrated in the mobile smart furniture device. In this paper we present a detailed analysis of the associated, promising state of the art techniques and the initial set of techniques we have used to realize the multimodal HCI interaction, followed by the descriptions of implemented control algorithms and some first-hand experimental evaluation analysis.

Keywords: Human computer interaction, information interfaces and representation, user interfaces, image processing and computer vision, natural language processing, algorithms and applications.
 
Received August 16, 2011; accepted December 30, 2012; published online August 5, 2012
 
Print E-mail

A Hybrid Neural Network and Maximum Likelihood Based Estimation of Chirp
Signal Parameters


Samir Shaltaf1 and Ahmad Mohammad2
1Department of Electrical Engineering, Aljouf University, Saudia Arabia
2Department of Electronics Engineering, Princess Sumaya University for Technonlogy, Jordan

 

Abstract:
This research introduces the hybrid Multilayer feed forward Neural Network (NN) and the Maximum Likelihood (ML) technique into the problem of estimating a single component chirp signal parameters. The unknown parameters needed to be estimated are the chirp-rate, and the frequency parameters. NN was trained with several thousands noisy chirp signals as the NN inputs, where the chirp-rate and the frequency parameters were embedded into those chirp signals, and those parameters were used as the corresponding NN output.  The NN resulted in parameter estimates that were near the global maximum point. ML gradient based technique then used the NN output parameter estimates as its initial starting point in its search of the global point parameters. The ML gradient based search improved the accuracy of the NN parameter estimates and the new estimates were very much near the exact parameter values.  Hence it can be said that NN working in corporation with the ML gradient based search results in accurate parameter estimates for the case of large signal to noise ratio.



Keywords: Chirp parameter estimation, frequency estimation, NN, ML.

Received August 28, 2011; accepted December 29, 2011; published online August 5, 2012
 
Print E-mail

Enhanced Graph Based Approach for Multi Document Summarization

Shanmugasundaram Hariharan1, Thirunavukarasu Ramkumar2, and Rengaramanujam Srinivasan3
1Department of Computer Science and Engineering, TRP Engineering College, India
2Department of Computer Application, A.V.C College of Engineering, India
3School of Computer Science, Bangladeshi Students Association University, India

 
Abstract: Summarizing documents catering the needs of an user is tricky and challenging. Though there are varieties of approaches, graphical methods have been quite popularly investigated for summarizing document contents. This paper focus its attention on two graphical methods namely-LexRank (threshold) and LexRank (Continuous) proposed by Erkan and Radev. This paper proposes two enhancements to the above work investigated earlier by adding two more features to the existing one. Firstly, discounting approach was introduced to form a summary which ensures less redundancy among sentences. Secondly, position weight mechanism has been adopted to preserve importance based on the position they occupy. Intrinsic evaluation has been done with two data sets. Data set 1 has been created manually from the news paper documents collected by us for experiments. Data set 2 is from DUC 2002 data which is commercially available and distributed or accessed through National Institute of Standards Technology (NIST). We have shown that the based upon precision and recall parameters were comprehensively better as compared to the earlier algorithms.

Keywords:
Page rank, lexical rank, damping, threshold, summarization.
 
Received July 13, 2011; accepted December 29, 2012; published online August 5, 2012
 
Print E-mail

An Implementation Framework (IF) for the National Information Assurance and Cyber Security Strategy (NIACSS) of Jordan


Ahmed Otoom1 and Issa Atoum2
1National Information Technology Center, Jordan
2Information Technology Department, Philadelphia University, Jordan

 
Abstract: This paper proposes an implementation framework that lays out the ground for a coherent, systematic, and comprehensive approach to implement the National Information Assurance and Cyber Security Strategy (NIACSS) of Jordan. The Framework 1). Suggests a methodology to analyze the NIACSS, 2). Illustrates how the NIACSS analysis can be utilized to design strategic moves and develop an appropriate functional structure, and 3). proposes a set of adaptable strategic controls that govern the NIACSS implementation and allow achieving excellence, innovation, efficiency, and quality.The framework, if adopted, is expected to harvest several advantages within the following areas: information security implementation management, control and guidance, efforts consolidation, resource utilization, productive collaboration, and completeness. The framework is flexible and expandable; therefore, it can be generalized.



Keywords: Strategy implementation framework, security management, cyber security, information assurance, and strategic controls.

 
Received December 6, 2011; accepted May 22, 2012; published online August 5, 2012
 
Print E-mail

Using Model Driven Architecture to Develop
Multi-Agent Systems

Mohamed Elammari and Zeinab Issa
Faculty of Information Technology, University of Benghazi, Libya

 
Abstract: In recent years, Multi-Agent Systems (MAS) had started gaining widespread acceptance in the field of information technology. This prompted many researchers to attempt to find ways to facilitate their development process, which typically includes building different models. The transformation of system specifications into models and their subsequent translation into code is often performed by relying on unstandardized methods, hindering adaptation to rapid changes in technology. Furhtermore, there is a big gap between the analysis, the design and the implementation in the methodologies of multi-agent systems development. On the other hand, we have seen that the top-down Model Driven Architecture (MDA) approach can be used to provide an efficient way to write specifications, develop applications and separation of business functions and application from the technical platform to be used. In this work, we propose using the MDA architecture for developing MAS. We demonstrate several different approaches, resulting in a variety of methods for developing MAS. This, in turn, increases the flexibility and ease of the development of MAS, and avoids any previously imposed restrictions.

Keywords:
MDA, MAS, web ontology language, XMI.
 
Received May 4, 2011; accepted July 28, 2011; published online August 5, 2012
 
Print E-mail

Classification of Acute Leukaemia Cells using Multilayer Perceptron and Simplified Fuzzy ARTMAP Neural Networks

Aimi Abdul Nasir1, Mohd Yusoff Mashor1, and Rosline Hassan2
 1Electronic and Biomedical Intelligent Systems Research Group, Universiti Malaysia Perlis, Malaysia
2Department of Haematology, Universiti Sains Malaysia, Malaysia

 

Abstract:
Leukaemia is a cancer of blood that causes more death than any other cancers among children and young adults under the age of 20. This disease can be cured if it is detected and treated at the early stage. Based on this argument, the requirement for fast analysis of blood cells for leukaemia is of paramount importance in the healthcare industry. This paper presents the classification of White Blood Cells (WBC) inside the Acute Lymphoblastic Leukaemia (ALL) and Acute Myelogenous Leukaemia blood samples by using the Multilayer Perceptron (MLP) and Simplified Fuzzy ARTMAP (SFAM) neural networks. Here, the WBC will be classified as lymphoblast, myeloblast and normal cell for the purpose of categorization of acute leukaemia types. Two different training algorithms namely Levenberg-Marquardt and Bayesian Regulation algorithms have been employed to train the MLP network. There are a total of 42 input features that consist of the size, shape and colour based features, have been extracted from the segmented WBCs, and used as the neural network inputs for the classification process. The classification results indicating that all networks have produced good classification performance for the overall proposed features. However, the MLP network trained by Bayesian Regulation algorithm has produced the best classification performance with testing accuracy of 95.70% for the overall proposed features. Thus, the results significantly demonstrate the suitability of the proposed features and classification using MLP and SFAM networks for classifying the acute leukaemia cells in blood sample.


Keywords: Acute leukaemia cells, feature extraction, classification, multilayer perceptron neural network, simplified fuzzy ARTMAP neural network.
 
Received September 19, 2011; accepted December 30, 2011; published online August 5, 2012
 
Print E-mail

Shortest Node-Disjoint Path Using Dual-Network Topology in Optical Switched Networks

Mostafa Dahshan
College of Computer and Information Sciences, King Saud University, Saudi Arabia

 

Abstract:
This paper presents a new method for finding shortest node-disjoint paths in optical-switched networks with no wavelength conversion. The proposed method is based on a modified version of Dijkstra algorithm that works on an expanded so-called dual-network topology with n×n- nodes and 2×m×n links, where n is the number of nodes and m is the number of links in the original network. Despite the larger network size, the execution time of the algorithm is in polynomial order (mn + n2 log n). Considering that the problem is NP-complete, the presented algorithm takes much less time than using ILP, which takes exponential time. Yet, it is able to find all available disjoint paths obtainable by ILP.


Keywords: Disjoint paths, optical switched networks, network survivability, optimization algorithms.
 
Received March 17, 2011; accepted May 24, 2011
 
Print E-mail

Design and Analysis of Array Weighted Wideband Antenna using FRFT

Adari Satya Srinivasa Rao1 and Prudhivi Mallikarjuna Rao2
1Department of ECE, Aditya Institute of Technology and Management, India
2Department of ECE, Andhra University College of Engineering, India

 

Abstract:
The beamwidth of a linear array depends on number of elements in the array and frequency of the input signal. The main requirement of wideband beamformer is, the main beam pattern should be constant even there is a change in input signal frequency.  Various methods were proposed in literature, one method is called elemental lowpass filtering designed by using Finite Impulse Response (FIR) digital filters. In this paper, the elemental lowpass filtering method was implemented using Fractional Fourier Transform (FRFT) and performance analysis was carried out with array weighting.


Keywords: Antenna array, wideband antenna, FRFT, array weighting.
 
Received   December 28, 2010; accepted May 24, 2011; published online August 5, 2012
 
Print E-mail

Analysis of Face Recognition under Varying
Facial Expression: A Survey

Marryam Murtaza, Muhammad Sharif, Mudassar Raza, and Jamal Hussain Shah
 Department of Computer Sciences, COMSATS Institute of Information Technology, Pakistan

Abstract:
Automatic face recognition is one of the most emphasizing dilemmas in diverse of potential relevance like in different surveillance systems, security systems, authentication or verification of individual like criminals etc. Adjoining of dynamic expression in face causes a broad range of discrepancies in recognition systems. Facial expression not only exposes the sensation or passion of any person but can also be used to judge his/her mental views and psychosomatic aspects. This paper is based on a complete survey of face recognition conducted under varying facial expressions. In order to analyze different techniques, motion-based, model-based and muscles-based approaches have been used in order to handle the facial expression and recognition catastrophe. The analysis has been completed by evaluating various existing algorithms while comparing their results in general. It also expands the scope for other researchers for answering the question of effectively dealing with such problems.


Keywords: Facial expression, holistic, local, model, optical flow, muscles based and coding system.
 
Received January 1, 2011; accepted May 24, 2011; published online August 5, 2012
 
Print E-mail

An Efficient Certificateless Designated Verifier Signature Scheme

Debiao He and Jianhua Chen
School of Mathematics and Statistics, Wuhan University, China

 
Abstract:
To solve the key escrow problem in identity-based cryptosystem, Al-Riyami et al. introduced the CertificateLess Public Key Cryptography (CL-PKC). As an important cryptographic primitive, CertificateLess Designated Verifier Signature (CLDVS) scheme was studied widely. Following Al-Riyami et al. work, many certificateless Designated Verifier Signature (DVS) schemes using bilinear pairings have been proposed. But the relative computation cost of the pairing is approximately twenty times higher than that of the scalar multiplication over elliptic curve group. In order to improve the performance we propose a certificateless DVS scheme without bilinear pairings. With the running time of the signature being saved greatly, our scheme is more practical than the previous related schemes for practical application.

Keywords:
CL-PKC, DVS, bilinear pairings, elliptic curve, random oracle model.
 
Received October 31, 2010; accepted May 24, 2011; published online August 5, 2012
 
Print E-mail

The Technical Feasibility and Security of E-Voting

Abdalla Al-Ameen and Samani Talab
Department of Information Technology, University of Neelain, Sudan
 

Abstract:
An Electronic voting (E-voting) system is a voting system in which the election data is recorded, stored and processed primarily as digital information. E-voting may become the quickest, cheapest, and the most efficient way to administer election and count vote since it only consists of simple process or procedure and require a few worker within the process. The main task of this paper is to introduce the idea of the internet voting systems. It discusses the different ways in which voters can vote, then we introduce the concepts of E-voting system .This paper observes the security threats that may affect E-voting system. This paper discusses technical and secure attributes of a good E-voting system and the reason for each attributes with respect to the voting process. In this paper we analyze some researcher's efforts in E-voting systems in order to minimize the threats that compromise E-voting systems. We end with our opinion about technical feasibility of E-voting in developing countries.



Keywords: E-voting, EML, threats, security, authentications schemes, integrity.
 
Received May 4, 2011; accepted July 28, 2011; published online August 5, 2012
 
Print E-mail

Thai Monosyllabic Words Recognition using
Ant-Miner Algorithm

Saritchai Predawan1, Chom Kimpan1, and Chai Wutiwiwatchai2
1Faculty of Information Technology, Rangsit University, Thailand
2National Electronics and Computer Technology Center, Ministry of Science and Technology, Thailand
 
 
 
Abstract:
In this paper, Ant-Miner software is used to develop classification rules for Thai monosyllabic words. The hypothetical words used in this paper are composed of 65 command monosyllabic Thai words. The binary desired outputs were used during training 520 Thai words consist of 10 numerals and single-syllable, 65 words in each group were used for system evaluation. In order to improve recognition accuracy, initial consonants, vowels, final consonants and tonal level detected were conducted for speech preclassification. The parameters used in the metaheuritstic algorithms are optimized using pruning algorithm with the aim of improving the accuracy by generating minimum number of rule in order to cover more patterns. Thai monosyllabic words recognition using Ant-Miner yielded Thai monosysllabic words accuracy of recognition on test set of 88.65%, 87.69% and 91.54% for 50, 100 and 250 number of ants respectively.

Keywords:
Thai monosyllabic words recognition, ant-miner algorithm, classification, Thai language.

 
Received March 17, 2011; accepted May 24, 2011; published online August 5, 2012
 
Print E-mail

Multiuser Detection with Neural Network MAI Detector in CDMA Systems for AWGN and Rayleigh Fading Asynchronous Channels

Necmi Taspinar1 and Yalcin Isik2
1Department of Electrical and Electronics Engineering, Erciyes University, Turkey
2Silifke-Tasucu Vocational School, Selcuk University, Turkey

 

Abstract:
In this study, the performance of the proposed receiver with the neural network Multiple Access Interference (MAI) detector is compared with the matched filter bank (classical receiver), neural network that detects user's signal and single user bound for Additive White Gaussian Noise (AWGN) and Rayleigh fading asynchronous channels by computer simulations. There are a lot of study in the literature that compare the neural network receiver and other methods. These neural network receivers detect the user bits after the matched filter. In this study, MAI is detected after the matched filter with the proposed neural network receiver and then user bits are obtained by subtracting MAI from the matched filter output. The proposed receiver with the neural network MAI detector  has got better Bit Error Rate (BER) performance than the neural network that detects user`s signal in AWGN and Rayleigh fading asynchronous channels for Signal Noise Ratio (SNR) simulations, and in AWGN asynchronous channels for the number of users simulations, although both have the same complexity. However, both   have almost same BER performance in AWGN and Rayleigh fading asynchronous channels for Near Far Ratio (NFR) simulations, and in Rayleigh fading asynchronous channels for the number of users simulations.


Keywords: CDMA, multi-user detection, neural network, MAI detector.
 
  Received August 1, 2011; accepted December 30, 2012; published online August 5, 2012
 
<
 
Copyright 2006-2009 Zarqa Private University. All rights reserved.
Print ISSN: 1683-3198.
 
 
Warning: fsockopen(): php_network_getaddresses: getaddrinfo failed: Name or service not known in /hsphere/local/home/ccis2k/ccis2k.org/iajit/templates/rt_chromatophore/index.php on line 251 Warning: fsockopen(): unable to connect to oucha.net:80 (php_network_getaddresses: getaddrinfo failed: Name or service not known) in /hsphere/local/home/ccis2k/ccis2k.org/iajit/templates/rt_chromatophore/index.php on line 251 skterr