Abstract: In this article, we evaluate features and algorithms for the task of prosodic boundary prediction for Greek. For this purpose a prosodic corpus composed of generic domain text was constructed. Feature contribution was evaluated and ranked with the application of information gain ranking and correlation-based feature selection filtering methods. Resulted datasets were applied to C4.5 decision tree, one-neighbour instance based learner and Bayesian learning methods. Models performance exploitation led as to the construction of a practically optimal feature set whose prediction effectiveness was evaluated with two prosodic databases. In terms of total accuracy and F-measure, evaluation results established the decision tree effectiveness in learning rules for prosodic boundary prediction.

Abstract: Genetic algorithm plays a significant role, as search techniques for handling complex spaces, in many fields such as artificial intelligence, engineering, robotic, etc. The genetic processes on the natural evolution principles of populations have been fairly successful at solving problems and produce optimized solution from generation to generation. This is applied in students’ quantitative data analysis to identify the most impact factor in their performance in their curriculum. The results will help the educational institutions to improve the quality of teaching after evaluating the marks achieved by the students’ in academic career. This student analysis model considers the quantitative factors such as theoretical, mathematical, practical, departmental and other departmental marks to find the most impacting factor using real genetic algorithm.

Abstract: Iris recognition is one of the most reliable and applicable methods for a person's identification. The most complex and important phase of recognition is iris segmentation of an input eye image that affects iris recognition successful rate significantly. Due to missed parameters in noisy images, main error occurs in the performance of classic localization. Artificial neural networks (ANN) are appropriate substitutes for classic methods because of their flexibility on noisy images. In this paper, we use feedforward neural network (FFNN) for the improvement of iris localization accuracy. We apply two methods in order to reduce neural network error: first, designing one neural network for each output neuron .Second, using cascaded feedforward neural network (CFFNN). Then, we examine proposed methods on different datasets which cause remarkable reduction of localization error.

Abstract: Paintings which was handled roughly or made from low quality paint or base usually suffers from crack in a long run, which causes them to lose some of the information. This paper discuss about automatic approach for classification and interpolation of cracks. For classification supervised and unsupervised methods were implemented and for interpolation different order statistics filter were applied. Experimental result shows that unsupervised classification works better than supervised classification. And variable size window filter works best for interpolation of cracks.

Abstract: Clustering plays an important role in the image processing. It permits to assign a label to each point of the image from a collection of defined classes. Among the domains that use the clustering, we can mention the Remote Sensing for identification of different regions constituting a satellite image. Evaluation of the clustering algorithm results is based on the validity index. In this paper, we applied the Harmony Search algorithm (HS) for make an unsupervised clustering. Thereafter, we evaluated the performance of this tool by analyzing the results obtained. These results show that the validity index determines automatically the appropriate number of classes that represent an image. The study realized with several validity indices allowed us to find the best validity index to evaluate the performance and robustness of the algorithm HS. The experiences obtained with this algorithm show the effectiveness and performance in the stable clustering for given problem.

Abstract: In recent time, there has been high level of impersonation experienced on a daily basis in both private and public sectors, the ghost worker syndrome which has become a menace across all tiers of government, employers concerns over the levels of employee absence in their workforce and the difficulty in managing student attendance during lecture periods. Fingerprints are a form of biometric identification which is unique and does not change in one’s entire lifetime. This paper presents the attendance management system using fingerprint technology in a university environment. It consists of two processes namely; enrolment and authentication. During enrolment, the fingerprint of the user is captured and its unique features extracted and stored in a database along with the users identity as a template for the subject. The unique features called minutiae points were extracted using the Crossing Number (CN) method which extracts the ridge endings and bifurcations from the skeleton image by examining the local neighborhoods of each ridge pixel using a 3 x 3 window. During authentication, the fingerprint of the user is captured again and the extracted features compared with the template in the database to determine a match before attendance is made. The fingerprint-based attendance management system was implemented with Microsoft’s C# on the. NET framework and Microsoft’s Structured Query Language (SQL) Server 2005 as the backend. The experimental result shows that the developed system is highly efficient in the verification of users fingerprint with an accuracy level of 97.4%. The average execution time for the developed system was 4.29 seconds as against 18.48 seconds for the existing system. Moreover, the result shows a well secured and reliable system capable of preventing impersonation.

Abstract: This work present the use of ICTs among legal practitioners in Ibadan metropolis and to determine how often the lawyers used ICTs for their information needs and to ascertain the extent to which they were satisfied with the services provided by ICTs. The analyses are based on data from a questionnaire survey of the legal practitioners in the metropolis. The findings revealed that due to lack of awareness, majority of the lawyers were yet to take advantage of the huge potential benefits that can be derived from using ICTs. The study revealed that legal practitioners used some ICTs more than others; for instance, mobile phones and computers were the most frequently used ICTs. Furthermore, young legal practitioners embraced ICTs more than the older lawyers. In addition, about 75.2% of the respondents strongly agreed that the application of ICTs in the legal profession would go a long way in improving the efficiency and effectiveness of the profession. The major problems and constraints identified to the use of ICTs among lawyers are the unfavorable economic situation of the country, excessive cost of procurement of ICTs facilities and inadequate infrastructure such as telecommunication and electric supply.

Abstract: Implementation of Fast Hartley Transform in parallel manner on Graphics Processing Unit, using CUDA technology is presented in this paper. Calculating FHT in parallel, using multiple threads, gives us huge improvement in calculation speed. Developed CUDA based parallel algorithm, which experimental results compared with results of CPU based sequential algorithm. Edge detection algorithms can be speed up for large images, performing in frequency domain. Here experiments are done on various edge detection filters and different image sizes, using fast Hartlay transform.

Abstract: Modern educational technology with multimedia systems creates the preconditions for engaging all the senses in the process of acquiring new knowledge, develops students' creativity and provides greater activity of students in teaching and learning. Therefore, as computer science and information technology major features of education at all levels of education, from preschool to university. Today's students require different ways of learning. Growing up with the possibility of learning in virtual environments will become more independent and more willing to self-education and lifelong learning. Thus, young people who are now in elementary and secondary schools and those who are part of the formal education yet to enter, your life to be spent in active contact with information and communication technology in education and the need to be prepared for it. Information and communication technology (ICT) provides a good foundation for the creative and effective use of knowledge. Today at elementary schools educate a generation that will work in mid-21st century. Education in Serbia faces the challenges of reform and rapid adjustment to the demands of the developed environment, primarily the European Union standards, and intensive changes in science, technology, economics, and social relations as a whole. The question is what IT skills should be learned and how. What are the functional tasks of the educational process can be developed through teaching computer science? Are the students preparing for the process of lifelong learning and training? The role of contemporary modern teachers, among other things, to direct students to the creative use of information technology. The authors' intention is to highlight the problems that exist in Serbia in the application of modern ICT in teaching and education, but also some features of the implementation of ICT available to the Serbian students.

Abstract: Network performance evaluation has traditionally been done following the client/server model, using two processes to carry out the evaluation. In this paper we present a different approach. We propose an enhancement to the classical performance evaluation by using three processes: client, server, and a middle process that reports additional gauges which allow users to more accurately and rapidly detect network anomalies. For this third process we wrote two versions: one for PC-based routers, and the other for off-the-shelf wireless routers. The former version was presented in one of our previous works. In this paper, we present our experience in writing and porting our application to wireless routers. Additionally, we perform different experiments to validate the correctness of the results reported. Furthermore, we present additional experiments that illustrate another possible uses for our tool.