Time filter

Source Type

Sarajevo, Bosnia and Herzegovina

The International University of Sarajevo is a private university located in the capital city Sarajevo, Bosnia and Herzegovina. The university was established by the Foundation for the Development of Education in 2004-2005. IUS is open to students from all over the world, and the language of instruction and communication is English. It offers four year education according to Bologna system .IUS has nearly 2000 students from 40 countries and faculty members from 20 countries performing academic and research activities in various disciplines of Science, Engineering, Arts and Social science. First generation of 32 IUS graduates received their diplomas on June 26, 2009.IUS has the largest and modern campus in the region.The majority of the students attending the university are Turkish citizens. Students from Bosnian national background are favoured in fees and scholarships. Wikipedia.

Sharif M.H.,International University of Sarajevo
Digital Signal Processing: A Review Journal | Year: 2016

Suppose that we wish to get a comprehensive match of a target in the next frame. Where would we search the target in the next frame? Brute-force search has an asymptotic runtime of O(n!) with problem size n. Yet we can search the target only from a number of automatically generated specific regions, named candidate regions, in the next frame. But how can we get those regions? Deeming the silhouettes of movers, this paper denotes a detailed deliberation of how to generate those candidate regions automatically and then how to track unknown number of individual targets with them. Phase-correlation technique aids to find the key befitting matches of the targets using them. Hungarian method in combination with a state estimation process called Kalman filter finds the best correspondence of the targets among those matches, allowing us to construct full trajectories of unknown number of individual targets in 3D space irresistibly swift as compared to brute-force search since the relative runtime reduced from O(n!) to O(n3). Favorable outcomes, upon conducting experiments on videos from three different datasets, show the robustness and effectiveness of our approach. © 2016 Elsevier Inc.

Findik F.,Sakarya University | Findik F.,International University of Sarajevo
Materials and Design | Year: 2012

Spinodal decomposition is regarded as small composition fluctuations over a large space, while a classical nucleation process is categorized by large composition fluctuations over a small space. Since the recent phases form the interface transversely by a permanent diffusional process with a steady alteration in composition, they must contain analogous crystal structures of the unique solid solution and be primarily coherent. The consequential microstructure contains a homogeneous distribution of diminutive, coherent interconnected particles. Experimental annotations have revealed that spinodal decomposition arises in metallic, glass and polymer structures. In this study, after detection the theories of spinodal reactions and hardening mechanisms experimental research and numerical studies on spinodal decomposition are reviewed for the last five decades. Also, future developments in spinodal decomposition are predicted and criticized in an outlook. © 2012 Elsevier Ltd.

Kusakci A.O.,International University of Sarajevo
11th Symposium on Neural Network Applications in Electrical Engineering,NEUREL 2012 - Proceedings | Year: 2012

Authorship attribution, namely determination of the author of a text, may become an extraordinarily complex and sensitive job due to its relatively difficult feature extraction phase and highly nonlinear nature. This paper proposes a classification tool using committee machines consisting of multilayered perceptron neural networks (MLP) to identify the author of a text. Each expert is an individual MLP learning complex input-output relation composed of 14 lexical, stylometric attributes extracted from the corpus. The resulting mapping after training is used to identify the texts in German language written by two different authors. Unlike other committee based classification tools individual answers of the experts are combined with a novel voting method, k-nearest neighbors rated voting. The proposed method shows very promising results when benchmarked with simple majority voting technique. © 2012 IEEE.

Jabr R.A.,American University of Beirut | Dzafic I.,International University of Sarajevo
IEEE Transactions on Power Systems | Year: 2015

This paper discusses the need for short circuit analysis in real-time applications of modern distribution networks and presents a short circuit tool that builds on recent advances in Fortescue-based current injection power flow. The proposed short circuit computation (SCC) method is fundamentally based on the symmetrical components transformation of three-phase, two-phase, and one-phase systems. Unlike the classical symmetrical components SCC method that postulates a structurally symmetrical three-phase pre-fault network with balanced loading, the proposed method accounts for multiphase networks that are comprised of three-phase, two-phase, and one-phase network parts; given a pre-fault power flow solution, it requires a maximum of three current injection iterations to compute the short circuit current flow in the entire network. Numerical results show that the Fortescue SCC approach with multiphase lines exhibits significant computational performance improvement on large-scale networks as compared to classical SCC in phase coordinates. © 2014 IEEE.

Strom F.,Linkoping University | Koker R.,Sakarya University | Koker R.,International University of Sarajevo
Expert Systems with Applications | Year: 2011

Recently the neural network based diagnosis of medical diseases has taken a great deal of attention. In this paper a parallel feed-forward neural network structure is used in the prediction of Parkinson's Disease. The main idea of this paper is using more than a unique neural network to reduce the possibility of decision with error. The output of each neural network is evaluated by using a rule-based system for the final decision. Another important point in this paper is that during the training process, unlearned data of each neural network is collected and used in the training set of the next neural network. The designed parallel network system significantly increased the robustness of the prediction. A set of nine parallel neural networks yielded an improvement of 8.4% on the prediction of Parkinson's Disease compared to a single unique network. Furthermore, it is demonstrated that the designed system, to some extent, deals with the problems of imbalanced data sets. © 2010 Elsevier Ltd. All rights reserved.

Discover hidden collaborations