By Topic

Frontiers of Information Technology (FIT), 2013 11th International Conference on

Date 16-18 Dec. 2013

Filter Results

Displaying Results 1 - 25 of 55
  • [Front cover]

    Page(s): C4
    Save to Project icon | Request Permissions | PDF file iconPDF (1307 KB)  
    Freely Available from IEEE
  • [Title page i]

    Page(s): i
    Save to Project icon | Request Permissions | PDF file iconPDF (111 KB)  
    Freely Available from IEEE
  • [Title page iii]

    Page(s): iii
    Save to Project icon | Request Permissions | PDF file iconPDF (146 KB)  
    Freely Available from IEEE
  • [Copyright notice]

    Page(s): iv
    Save to Project icon | Request Permissions | PDF file iconPDF (122 KB)  
    Freely Available from IEEE
  • Table of contents

    Page(s): v - x
    Save to Project icon | Request Permissions | PDF file iconPDF (157 KB)  
    Freely Available from IEEE
  • Foreword

    Page(s): xi - xii
    Save to Project icon | Request Permissions | PDF file iconPDF (101 KB)  
    Freely Available from IEEE
  • Committees

    Page(s): xiii - xv
    Save to Project icon | Request Permissions | PDF file iconPDF (125 KB)  
    Freely Available from IEEE
  • List of Reviewers

    Page(s): xvi - xxiii
    Save to Project icon | Request Permissions | PDF file iconPDF (138 KB)  
    Freely Available from IEEE
  • Analytical Model for Delay Distribution of PRMAC

    Page(s): 1 - 6
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (275 KB) |  | HTML iconHTML  

    Delay is one of the most important parameters of interest while providing QOS guarantees for Wireless Sensor Networks (WSN). Various MAC layer protocols for WSN have been proposed for efficient management of delay. Analyzing single hop and end to end delay using queuing analysis can provide significant help in modeling various real time WSN applications. This paper parameterizes the cross-layer analysis framework for investigating the single hop delay distribution of a cross layer WSN MAC protocol PRMAC. The analysis demonstrates how the methodology can be applied to a cross layer protocol embedding key details of the protocol such as impact of control packets (PION) modeling. An example of the analysis is illustrated using a single hop delay for a node with a small buffer. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Mitigating the Effect of Malicious Users in Cognitive Networks

    Page(s): 7 - 12
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (213 KB) |  | HTML iconHTML  

    Open medium access is an inherent feature of wireless networks that makes them vulnerable to security threats and unauthorized access by foreign entities and malicious users. In cognitive radio networks, effect of these malicious users on network performance becomes more threatening, where they impersonate primary users by emitting similar signals, causing secondary users to vacate the occupied channel needlessly. As a result, network resources are unfairly monopolized by malicious users denying other secondary users their fair share. In this paper, we introduce a cross-layered approach to provide secondary users the ability to differentiate between a primary user and a malicious user, using Hidden Markov Model at MAC layer. Hence, our proposed framework allows the transport layer protocol to respond appropriately in a way that the effect of the presence of malicious user on the network is mitigated. The effectiveness of our proposed approach is shown by calculating the throughput of the network and number of channel switches with respect to varying number of secondary and malicious nodes and by comparing it to an earlier proposed TCP protocol. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Foreground Object Detection and Tracking for Visual Surveillance System: A Hybrid Approach

    Page(s): 13 - 18
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (722 KB) |  | HTML iconHTML  

    Foreground detection is one of the fundamental preprocessing steps in many image processing and computer vision applications. In spite of significant efforts, however, slowly moving foregrounds or temporarily stationary foregrounds remains challenging problem. To address these problems, this paper presents a hybrid approach, which combines background segmentation and long-term tracking with selective tracking and reducing search area, we robustly and effectively detect the foreground objects. The evaluation of realistic sequences from i-LIDS dataset shows that the proposed methodology outperforms with most of the state-of-the-art methods. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Detecting Edges in an Image with the Help of Fuzzy Parameters

    Page(s): 19 - 24
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (371 KB) |  | HTML iconHTML  

    In this research paper a novel image processing technique based on fuzzy logic has been proposed to detect edges in an image. The algorithm formulated for this purpose utilizes the concept of Attanassov's intuitionistic theory of fuzzy sets, which takes into account a hesitation degree. From this parameter, a new distance measure has been derived, which is termed as the intuitionistic fuzzy divergence or IFD, and is used for calculating the edges. The results obtained are better when compared to other edge detection techniques. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A novel approach for ensemble clustering of colon biopsy images

    Page(s): 25 - 30
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1531 KB) |  | HTML iconHTML  

    Colon cancer diagnosis based on microscopic analysis of biopsy sample is a common medical practice. However, the process is subjective, biased and leads to interobserver variability. Further, histopathologists have to analyze many biopsy samples per day. Therefore, factors such as tiredness, experience and workload of histopathologists also affect the diagnosis. These shortcomings require a supporting system, which can help the histopathologists in accurately determining cancer. Image segmentation is one of the techniques, which can help in efficiently segregating colon biopsy image into constituent regions, and accurately localizing the cancer. In this work, we propose a novel colon biopsy image segmentation technique, wherein segmentation has been posed as a classification problem. Local binary patterns (LTP), local ternary patters (LTP), and Haralick features are extracted for each pixel of colon biopsy images. Features are reduced using genetic algorithms and F-Score. Reduced features are given as input to random forest, rotation forest, and rotation boost classifiers for segregation of image into normal, malignant and connecting tissues components. The clustering performance has been evaluated using segmentation accuracy and Davies bouldin index (DBI). Performance of classifiers has also been evaluated using receiver operating characteristics (ROC) curves, and area under the curve (AUC). It is observed that rotation boost in combination with F-Score has shown better results in segmenting the images compared to other classifiers. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Image Clustering Using Discriminant Image Features

    Page(s): 31 - 36
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (220 KB) |  | HTML iconHTML  

    Manifold learning based image clustering models are usually employed at local level to deal with images sampled from nonlinear manifold. Usually, gray level image features are used that are obtained by resizing original images through linear interpolation approach. However, significant image variance information is lost in gray level image features. Clustering models that are based on discriminant analysis can be made more effective in principal component analysis (PCA) space whereas leading projection vectors contain significant image variance information. For optimal clustering performance, we used two-dimensional two-directional PCA technique to extract significant image features. We report clustering performance of Spectral Embedded Clustering (SEC) model using discriminant image features on 6 benchmark image databases. Clustering performance is compared with existing state-of-art clustering approaches. Significant overall performance improvement is observed using proposed discriminant image features over gray level image features. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Design and Analysis of Pyramidal Conformal Antenna with Circular Sub-arrays Mounted on a Moving Platform

    Page(s): 37 - 41
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (375 KB) |  | HTML iconHTML  

    In this paper, we have proposed the idea of designing a pyramidal conformal array antenna and install it on a moving vehicle. Uniform circular planar array is used and it is replicated to design pyramidal shape conformal array antenna. Single panel circular planar array at 72 degree and at 42 degree is used to build the array geometry of pyramidal shape conformal array. By using circular arrays at 42 degree and at 72 degree the 3-D radiation pattern of pyramidal conformal array antenna has been shown. By using same pyramidal conformal array antenna with different phase slopes the idea of tracking target in the air and on ground is introduced. The applications of pyramidal conformal phased array radar system in defense and in automotive industry are presented in the end. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An Efficient Power Divider for Dual-Band Microwave Applications

    Page(s): 42 - 44
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (187 KB) |  | HTML iconHTML  

    In this article, a modified Cheng dual-band power divider is proposed. In modified design, output ports of the divider have been redesigned by incorporating extended lines having electrical length (π/2)(f1/f2) where, f1 and f2 are center frequencies. The impedance of extended lines is calculated from an average value of bi-section impedance transformers used in the Cheng design. Dependent upon the frequencies, the modified design offered 5-20 dB improvement in return loss and thus exhibited enhanced transmission. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Hybrid Feature Selection and Tumor Identification in Brain MRI Using Swarm Intelligence

    Page(s): 49 - 54
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (576 KB) |  | HTML iconHTML  

    Demand for automatic classification of Brain MRI (Magnetic Resonance Imaging) in the field of Diagnostic Medicine is rising. Feature Selection of Brain MRI is critical and it has a great influence on the classification outcomes, however selecting optimal Brain MRI features is difficult. Particle Swarm Optimization (PSO) is an evolutionary meta-heuristic approach that has shown great potential in solving NP-hard optimization problems. In this paper MRI feature selection is achieved using Discrete Binary Particle Swarm Optimization (DBPSO). Classification of normal and abnormal Brain MRI is carried out using two different classifiers i.e. Support Vector Machine (SVM) and K-Nearest Neighbor (KNN). Experimental results show that the proposed approach reduces the number of features and at the same time it achieves high accuracy level. PSO-SVM is observed to achieve high accuracy level using minimum number of selected features. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An Adaptive Learning Automata for Genetic Operators Allocation Probabilities

    Page(s): 55 - 59
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (192 KB) |  | HTML iconHTML  

    The conventional Genetic algorithms (GAs) use a single mutation operator for whole population, It means that all solutions in population apply same leaning strategy. This property may cause lack of intelligence for specific individual, which is difficult to deal with complex situation. Different mutation operators have been suggested in GAs, but it is difficult to select which mutation operator should be used in the evolutionary process of GAs. In this paper, the fast learning automata is applied in GAs to automatically choose the most optimal strategy while solving the problem. Experimental results on different benchmark problems determines that the proposed method obtains the fast convergence speed and improve the performance of GAs. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Automated Plant Disease Analysis (APDA): Performance Comparison of Machine Learning Techniques

    Page(s): 60 - 65
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (452 KB) |  | HTML iconHTML  

    Plant disease analysis is one of the critical tasks in the field of agriculture. Automatic identification and classification of plant diseases can be supportive to agriculture yield maximization. In this paper we compare performance of several Machine Learning techniques for identifying and classifying plant disease patterns from leaf images. A three-phase framework has been implemented for this purpose. First, image segmentation is performed to identify the diseased regions. Then, features are extracted from segmented regions using standard feature extraction techniques. These features are then used for classification into disease type. Experimental results indicate that our proposed technique is significantly better than other techniques used for Plant Disease Identification and Support Vector Machines outperforms other techniques for classification of diseases. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Motivational and De-motivational Factors for Software Engineers: An Empirical Investigation

    Page(s): 66 - 71
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (213 KB) |  | HTML iconHTML  

    This paper is based on an industrial survey conducted on software engineer motivation as previous research shows that motivation is amongst the most frequently highlighted causes of software projects failure. Motivation greatly impacts practitioner's productivity. Yet motivation is mostly ignored in software engineering literature and practice. Researchers have conducted studies on motivation in software engineering mostly in western culture. There have been very few studies on motivation of software engineers from Asia. We have not been able to find any empirical study conducted on this subject in South Asia, which is an important region in information technology industry worldwide. We therefore decided to conduct an empirical study in Pakistan to identify factors that motivate or de-motivate software engineers. Given the nature of the research we used an online questionnaire based on Job Characteristic Theory to identify (de)motivational factors that affect software engineers at work place. Results are based on 306 responses. Results are relatively different from previous studies as most of the previous work is done in western countries. These differences are analyzed in the light of Hofstede's Cultural Dimension 5 Dimensional Model. National culture impacts factors that (de)motivate software engineers in a country. Software companies should follow culture sensitive steps to deal with (de)motivational factors affecting their software engineers. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Software Engineering Challenges for Ubiquitous Computing in Various Applications

    Page(s): 78 - 82
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (147 KB) |  | HTML iconHTML  

    Ubiquitous Computing is a paradigm containing the characteristics to break away from the traditional desktop computing system and turn to such computer systems where everything is available & accessible everywhere through various devices while keeping them effectively invisible. The accomplishment of this vision requires a deep involvement of multiple areas including software engineering. Software engineering plays a major role in ubi-comp world, but the lack of appropriate software engineering approaches is identified as a major obstacle on the route to propose a general level framework that should be adopted for all kinds of ubi-comp applications. The very initial step which is still required for this vision is to identify all potential software engineering challenges in the ubi-comp era. In this paper we have made a survey of various ubi-comp applications and extracted a number of software engineering challenges faced by other researchers during the development of such applications. This work provides a future direction for other researchers and developers to make the process of providing an appropriate framework for building ubi-comp application more effectively. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Interactive Control through Hand Gestures

    Page(s): 83 - 88
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1090 KB) |  | HTML iconHTML  

    In recent years, we have seen dramatic progress in motion capture techniques for digital character animation, yet these techniques are expensive due to the need of special hardware. Keeping in view the trend of making applications interactive and more natural and intuitive, as well as keeping the cost low, a vision-based system is developed to allow interactive control of applications, using hand gestures. The system is used for two types of applications: skeleton animation and image editing. The procedure steps mainly consist background subtraction, fingertips detection, tracking, and mapping of finger lengths to control parameters. For skeleton animation application, finger lengths are mapped to joint angles. For image editing application, finger lengths are mapped to parameters such as rotation angle of image or parameters for image cropping. In addition to the idea of using hand gestures for skeleton animation and image editing, we have introduced a novel method for detecting fingertips, in which the hand contour is traversed and a turning point is found using trailing buffer. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Human-Robot Interaction in an Unknown Human Intention Scenario

    Page(s): 89 - 94
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (251 KB) |  | HTML iconHTML  

    In this paper an approach is introduced to human robot interaction in a known scenario with unknown human intentions. Initially, the robot reacts by copying the human action. As the human-robot interaction proceeds, the level of human-robot interaction improves. Before each reaction, the robot hypothesizes its potential actions and selects one that is found most suitable. The robot may also use the human-robot interaction history. Along with the history, the robot also considers the action randomness and heuristic based action predictions. As solution, a general reinforcement Learning (RL) based algorithm is proposed that suggests learning of human robot interaction in an unknown human intention scenario. A Particle Filter (PF) based algorithm is proposed to support the probabilistic action selection for human-robot interaction. The experiments for human-robot interaction are performed by a robotic arm involving the arrangement of known objects with unknown human intention. The task of the robot is to interact with the human according to the estimated human intention. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • On the Fly Test Suite Optimization with FuzzyOptimizer

    Page(s): 101 - 106
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (328 KB) |  | HTML iconHTML  

    There occur frequent requirement changes in software systems even after the software has been developed. Regression testing is continuously performed to identify the undesired affects of these requirement changes on already tested system. Test suites grow enormously with these changes due to addition of new test cases for enhanced functionality. Optimization of test suite to perform regression testing within the budgetary and time restrictions is ultimate choice for a tester because "Retest all" test suite is un-economical and is not suitable choice. Test suite optimization can be either static or on the fly. With on the fly optimization, optimal suite keeps on changing with the requirement changes. On the fly optimization of test suite is preferable option for regression testing. Presently, static test suite optimization approaches exist. We have proposed an application specific, on the fly optimization approach for test suite optimization problem. We have implemented our approach on an academic testing problem. We use fuzzy logic to optimize the test suite with multiple optimization objectives. Our approach has been successful to generate on the fly optimized test suites for changing requirements. In future, we will implement this approach on considerably large sized testing problems. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Content Based Image Retrieval Using Localized Multi-texton Histogram

    Page(s): 107 - 112
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (645 KB) |  | HTML iconHTML  

    This paper presents a simple yet efficient image retrieval technique that defines image feature descriptors using localized multi-texton histogram. The proposed technique extracts a unique feature vector for each image in the image database based on its shape, texture and color. First, the image is divided into smaller equal size blocks and then for each block texture orientation is computed independently. Second, each block is filtered with a set of predefined textons and finally, a co-occurrence relation is established from the orientation and the filtered text on image. This relationship in turn provides a powerful feature vector. To retrieve similar images, the feature vector of the query image is computed and compared with the feature vectors of the stored images using Euclidean distance measure. The proposed algorithm is tested on standard image dataset Corel 1000 for accuracy and recall with favorable results. It is also compared with existing state of the art Context Based Image Retrieval algorithm and showed convincing results. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.