DCIT Lecturers' Papers
Permanent URI for this collection
Papers, abstracts and publications authored by staff of the Department of Computing and Information Technology, UWI St. Augustine.
Browse
Recent Submissions
Item Quick fuzzy backpropagation algorithm(2011-06-14) Nikov, Alexander; Stoeva, StefkaA modification of the fuzzy backpropagation (FBP) algorithm called QuickFBP algorithm is proposed, where the computation of the net function is significantly quicker. It is proved that the FBP algorithm is of exponential time complexity, while the QuickFBP algorithm is of polynomial time complexity. Convergence conditions of the QuickFBP, resp. the FBP algorithm are defined and proved for: (1) single output neural networks in case of training patterns with different targets; and (2) multiple output neural networks in case of training patterns with equivalued target vector. They support the automation of the weights training process (quasi-unsupervised learning) establishing the target value(s) depending on the network's input values. In these cases the simulation results confirm the convergence of both algorithms. An example with a large-sized neural network illustrates the significantly greater training speed of the QuickFBP rather than the FBP algorithm. The adaptation of an interactive web system to users on the basis of the QuickFBP algorithm is presented. Since the QuickFBP algorithm ensures quasi-unsupervised learning, this implies its broad applicability in areas of adaptive and adaptable interactive systems, data mining, etc. applications.Item A methodology for human factors analysis in office automation systems(2011-06-14) Nikov, Alexander; Matarazzo, Giacinto; Orlando, AntoninoA methodology for computer-aided human factors analysis in office automation systems (OAS) design and implementation process has been developed. It incorporates a fuzzy knowledge-based evaluation mechanism which is employed to aggregate data measured in scales of different type. The methodology has a high degree of flexibility which allows it to be adjusted to the individual client situation. A case study in public administration for assessing OAS introduction from users' point of view has been carried out. On the basis of the results recommendations on further implementation have been proposed. The advantages, disadvantages, and further developments are discussedItem NN-AirPol: a neural-networks-based method for air pollution evaluation and control(2011-06-14) Karaca, Ferhat; Nikov, Alexander; Alagha, OmarA method for air pollution evaluation and control, based on one of the most popular neural networks – the backpropagation algorithm, is proposed. After the backpropagation training, the neural network, based on weather forecasting data, determines the future concentration of critical air pollution indicators. Depending on these concentrations, relevant episode warnings and actions are activated. A case study is carried out to illustrate and validate the method proposed, based on Istanbul air pollution data. Sulphur dioxide and inhalable particulate matter are selected as air pollution indicators (neural network outputs). Relevant episode measures are proposed. Among ten backpropagation algorithms, the BFGS algorithm (Quasi-Newton algorithms) is adopted since it showed the lowest training error. A comparison of NN-AirPol method against regression and perceptron models showed significantly better performanceItem A fuzzy backpropagation algorithm(2011-06-14) Stoeva, Stefka; Nikov, AlexanderThis paper presents an extension of the standard backpropagation algorithm (SBP). The proposed learning algorithm is based on the fuzzy integral of Sugeno and thus called fuzzy backpropagation (FBP) algorithm. Necessary and sufficient conditions for convergence of FBP algorithm for single-output networks in case of single- and multiple-training patterns are proved. A computer simulation illustrates and confirms the theoretical results. FBP algorithm shows considerably greater convergence rate compared to SBP algorithm. Other advantages of FBP algorithm are that it reaches forward to the target value without oscillations, requires no assumptions about probability distribution and independence of input data. The convergence conditions enable training by automation of weights tuning process (quasi-unsupervised learning) pointing out the interval where the target value belongs to. This supports acquisition of implicit knowledge and ensures wide application, e.g. for creation of adaptable user interfaces, assessment of products, intelligent data analysis, etc.Item Swarm-Optimization-Based Affective Product Design Illustrated by a Pen Case-Study(2011-06-14) Mohais, Arvind; Nikov, Alexander; Sahai, Ashok; Nesil, SelahattinAn optimization approach for suggesting product design parameters based on emotive responses is proposed that combines Kansei techniques and particle swarm optimization algorithm (PSO). The approach involves designing a Kansei survey for collecting data on customers’ affective responses to various aspects of a product, using several exemplars of the product. After information gathering, the PSO algorithm is employed to build a prediction binary linear model that aggregates the survey data. Subsequently, another binary linear model links product design parameters to the outputs of the first model to establish mathematical connections between the subjective impression of a product (Kansei) and its properties. This approach is illustrated by a case study for pen design. Three PSO neighborhood configurations are tested, and the results yield insight into the nature of the optimization function. Experimental work in implementing the proposed approach was able to suggest customers’ preferences for pen design attributes that would be considered optimal by all of those surveyed. They can be used for improvement and development of new future products.Item Computational intelligence-based personalization of interactive web systems(2011-06-14) Rambharose, Tricia; Nikov, AlexanderThe main Computational Intelligence (CI) models for personalization of interactive web systems are identified as Fuzzy Systems, Genetic Algorithms, Neural Networks, Artificial Immune Systems and Swarm Intelligence which includes Particle Swarm Optimization, Ant Colony Optimization, Bee Colony Optimization and Wasp Colony Optimization. These models are reviewed and compared regarding their inception, functions, performance and application to personalization of interactive web systems. A taxonomy for personalization of interactive web systems based on CI methods is proposed. It uses two approaches to personalize web-based systems as profile generation and profile exploitation. Based on this taxonomy a general procedure and recommendations for personalization of interactive web systems are suggested. Future directions for application of CI modelling for personalization are discussed.Item An Image Authentication Based on Discrete Fourier Transform(2011-06-14) Kieu, Duc; chang, Chin-ChenThe advances of network technologies and digital devices facilitate users to exchange multimedia data over the public networks. However, this also raises significant concerns about how to protect sensitive multimedia data from being illegally copied and unauthorized modifications. Thus, this paper proposes a fragile watermarking method to detect illegitimate alterations of the watermarked data. The proposed method embeds a grayscale watermark image into a grayscale cover image in a block-by-block manner by using discrete Fourier transform. Experimental results show that the proposed method can successfully and exactly detect and localize any tampered regions of the watermarked image.Item A Novel Information Concealing Method Based on(2011-06-14) Wang, Zhi-Hui; Kieu, Duc; Chang, Chin-Chen; Li, Ming-ChuA steganographic scheme with a very good visual quality of stego images was proposed by Zhang and Wang. However, the maximum hiding capacity of this method is 1 bit per pixel (bpp). To improve the hiding capacity of Zhang and Wang's method, we propose a steganographic scheme. The proposed method embeds 2K secret digits in the 5-ary notational systems into each group of (2K + 1) cover pixels, where K is a positive integer. Thus, the maximum hiding capacity of the proposed method can approach 2 bpp. The experimental results show that the PSNR values of the proposed method are always higher than 45 dB at the hiding capacity of 1.99 bpp for all test images.Item A Sudoku Based Wet Paper Hiding Scheme(2011-06-14) Kieu, Duc; Wang, Zhi-Hui; Chang, Chin-Chen; Li, Ming-ChuGood image quality and high hiding capacity are two basic requirements of information hiding systems. Technically, it is very challenging to achieve these two factors simultaneously. The purpose of obtaining either high hiding capacity or good image quality are various from application to application. Inspired from the wet paper codes proposed by Fridrich et al., we propose an information hiding scheme for grayscale images. The proposed scheme first uses a secret key to randomly select a subset of pixels from a cover image as dry pixels. Next, the toral automorphism is applied to the cover image to maximize the number of dry pixel pairs. Then, each secret digit in the base-9 numeral system is embedded into one dry pixel pair. The experimental results show that the proposed scheme can achieve good image quality (i.e., PSNR > 46 dB) and flexible hiding capacity. In addition, unauthorized users without knowing the secret key and the secret parameters used for the toral automorphism can not extract the embedded messageItem A lossless data embedding technique by joint neighboring coding(2011-06-14) Chang, Chin-Chen; Kieu, Duc; Wen-Chuan, WuInformation hiding methods are currently exploited by many researchers for various applications. Proposing an efficient and feasible information hiding method is valuable. This paper presents a new reversible information hiding method for vector quantization (VQ)-compressed grayscale images by using joint neighboring coding (JNC) technique. The proposed method embeds secret data by using the difference values between the current VQ-compressed index and left or upper neighboring indices. The experimental results show that the proposed method achieves the best visual quality of reconstructed images compared with the two related works. In addition, the proposed method obtains as high embedding capacity as Lin and Chang's method, followed by Yang et al.'s method. As for execution speed, Yang et al.'s method is fastest, followed by the proposed method, and then Lin and Chang's method. With respect to bit rate, the proposed method has a little higher bit rate in comparison with the two related works.Item Item Reversible information hiding for VQ indices based on locally adaptive coding(2011-06-14) Chang, Chin-Chen; Kieu, Duc; Chou, Yung-ChenSteganography is one of protective methods for secret communications over public networks such as the Internet. This paper proposes a novel reversible information hiding method for vector quantization (VQ) compressed images based on locally adaptive coding method. The proposed steganographic method embeds a secret message into VQ indices in an index table during the process of compressing the index table in the block-by-block manner. The experimental results show that, in average, the proposed method achieves the best visual quality of reconstructed images and the best embedding rate compared to two related works. In terms of compression rate and encoding execution time, in average, Yang et al.’s method is the best, followed by our proposed method, and then Lin and Chang’s method.Item Better Global Polynomial Approximation for Image Rectification(2011-06-14) Ward, ChristopherWhen using images to locate objects, there is the problem of correcting for distortion and misalignment in the images. An elegant way of solving this problem is to generate an error correcting function that maps points in an image to their corrected locations. We generate such a function by fitting a polynomial to a set of sample points. The objective is to identify a polynomial that passes "sufficiently close" to these points with "good" approximation of intermediate points. In the past, it has been difficult to achieve good global polynomial approximation using only sample points. We report on the development of a global polynomial approximation algorithm for solving this problem.Item Education in Geographic information systems usability and user-adaptivity(2011-06-14) McAdams, Michael Andrew; Nikov, AlexanderThe objective of this paper is to advance the usability and adaption for users of geographic information systems(GIS) by developing suitably trained professionals via a tailored graduate program. Human-computer interaction models are useful in analyzing the use of GIS in specific task situations.Such analysis provides a sound basis for GIS use optiomization.GIS applications,i.e., in environmental protection or urban and regional planning, require entirely different user interfaces that for those where users are experts. Building such interfaces taking into account GIS usability and adaptation to the user appears to be a promising approach.This could be achieved by careful analysis of GIS utilization and dynamic adaptation to user preferences and interests, the given task,goals and actual work context.The students should learn the usablity principles and how to apply them for designing GIS user interfaces.In addition, they should know to analyze GIS user tasks,interests, and preferences and adapt GIS user interfaces to them.This paper integrates these two complementary disciplines.Examples using ArcView illustrating GIS usability and user adaptivity are given.A MS GIS program with specification in usability and user-adaptive systems is proposed.Item UWIS: An assessment methodology for usability of web-based information systems(2011-06-14) Oztekin, Asil; Nikov, Alexander; Zaim, SelimA methodology for usability assessment and design of web-based information systems (UWIS) is proposed. It combines web-based service quality and usability dimensions of information systems. Checklist items with the highest and the lowest contribution to the usability performance of a web-based information system can be specified by UWIS. A case study by a student information system at Fatih University is carried out to validate the methodology. UWIS reveals a strong relationship between quality and usability which is assumed to exist by many researchers but not experimentally analyzed yet. This study depicts a strong relevance between web-based service quality and usability of web-based information systems. UWIS methodology can be used for designing more usable and higher quality web-based information systems.Item Emotion-Oriented eCommerce Systems(2010-06) LEON, SIMONE; NIKOV, ALEXANDERDuring recent years, the use of intelligent systems in eCommerce has increased significantly, providing a new perspective on the overall online shopping experience. The rapid growth of eCommerce has motivated many studies on the relationship between website design, company reputation, and purchase intent. Understanding emotion is important in gaining insight on how to efficiently satisfy the needs of the eCommerce customer. Emotion recognition techniques based on modern mathematical models using computational intelligence are presented. Progression within this field of study is highlighted. The requirements for designing of intelligent emotion-oriented eCommerce systems are defined. A model for simulation of intelligent emotion-oriented eCommerce systems is proposed. It is an important tool supporting the experimental study and design of emotion-oriented eCommerce systemsItem Expert Systems with Applications(2011-06-13) Kieu, Duc; Chang, Chin-ChenRecently, Zhang and Wang proposed a steganographic scheme by exploiting modification direction (EMD) to embed one secret digit d in the base-(2 × n + 1) notational system into a group of n cover pixels at a time. Therefore, the hiding capacity of the EMD method is log2(2 × n + 1)/n bit per pixel (bpp). In addition, its visual quality is not optimal. To overcome the drawbacks of the EMD method, we propose a novel steganographic scheme by exploiting eight modification directions to hide several secret bits into a cover pixel pair at a time. By this way, the proposed method can achieve various hiding capacities of 1, 2, 3, 4, and 4.5 bpp and good visual qualities of 52.39, 46.75, 40.83, 34.83, and 31.70 dB, respectively. The experimental results show that the proposed method outperforms three recently published works, namely Mielikainen’s, Zhang and Wang’s, and Yang et al.’s methods.Item A High Stego-image Quality Steganographic Scheme with Reversibility and High Payload Using Multiple Embedding Strategy(2011-06-13) Kieu, Duc; Chang, Chin-ChenTian’s method is a breakthrough reversible data embedding scheme with high embedding capacity measured by bits per pixel (bpp) and good visual quality measured by peak signal-to-noise ratio (PSNR). However, the embedding capacity and visual quality of this method can be significantly improved. Thus, we propose a simple reversible steganographic scheme in spatial domain for digital images by using the multiple embedding strategy. The proposed method horizontally and vertically embeds one secret bit into one cover pixel pair. The experimental results show that the proposed reversible steganographic method achieves good visual quality and high embedding capacity. Specifically, with the one-layer embedding, the proposed method can obtain the embedding capacity of more than 0.5 bpp and the PSNR value greater than 54 dB for all test images. Especially, with the five-layer embedding, the proposed method has the embedding capacity of more than 2 bpp and the PSNR value higher than 52 dB for all test images. Therefore, the proposed method surpasses many existing reversible data embedding methods in terms of visual quality and embedding capacityItem COMPARING A NOVEL QOS ROUTING ALGORITHM TO STANDARD(2010-11-19T16:42:41Z) Sivakumar, Shyamala; Phillips, Bill; Robertson, William; Goodridge S., WayneThe problem of finding QoS paths involving several combinations of network metrics is NP-complete. This motivates the use of heuristic approaches for finding feasible QoS paths. Many constraint based routing algorithms find QoSpaths by first pruning resources that do not satish the requirements of the trafic flow and then running a shortest path algorithm on the residual graph. This approach results in a QoS path that biases thefirst metric used in the search process. In addition, it can be shown that this approach may not alwaysfind the optimal path. Our research introduces a QoS routing algorithm that is based on a decision support system that is used to compute QoS paths. We demonstrate the feasibility of this approach by comparing it to standard pruning techniques.Item Burrokeet(2010-11-19T16:42:25Z) Gardler, Ross; Singh, Rajendra G.; Cummings, Thompson; Ramanan, Anil; Mohammed, Shareeda; Bernard, Margaret; Rudder, AndrewThis item relates to the development and deployment of an open-source Learning Content Management System called Burrokeet.