Time filter

Source Type

Engineering, Turkey

Altun H.,Mevlana University | Sinekli R.,Nigde University | Tekbas U.,Nigde University | Karakaya F.,Nigde University | Peker M.,Nigde University
INISTA 2011 - 2011 International Symposium on INnovations in Intelligent SysTems and Applications | Year: 2011

Color detection is generally a primary stage in most of the image processing application, if the application is based on the color information, such as road sign detection, face detection, skin color detection, object detection and object tracking etc. As the performance of subsequent modules in an image processing application is adversely affected by the previous modules, the accuracy of color detection with a high performance inevitably becomes crucial in some applications. This paper introduces a method for an efficient color detection in RGB space using an ensemble of experts in hierarchical structure. In this structure, a set of experts is assigned to evaluate R, G, B components of a pixel and then constructs a degree of membership to the set of predefined class of colors for the given pixel. Then a master neural network constructs its final decision based on the membership probabilities provided by the set of experts. Qualitative and quantitative evaluations of the results show that the proposed hierarchical structure of neural networks is superior over the conventional neural network classifier in color detection. © 2011 IEEE.

A sound content analysis is proposed to detect incident at intersections, which is suitable to implement on hardware such as FPGA. Due to confusion between the sound classes, an hierarchical classifier architecture is proposed to improve the classification performance. The proposed architecture and the feature extraction algorithm are suitable for parallel implementation. © 2012 IEEE.

Yetis C.M.,Mevlana University | Zeng Y.,Nanyang Technological University | Anand K.,Nanyang Technological University | Guan Y.L.,Nanyang Technological University | Gunawan E.,Nanyang Technological University
IEEE Symposium on Wireless Technology and Applications, ISWTA | Year: 2013

Signal-to-interference plus noise ratio (SINR) and rate fairness in a system are substantial quality-of-service (QoS) metrics. The acclaimed SINR maximization (max-SINR) algorithm does not achieve fairness between user's streams, i.e., sub-stream fairness is not achieved. To this end, we propose a distributed power control algorithm to render sub-stream fairness in the system. Sub-stream fairness is a less restrictive design metric than stream fairness (i.e., fairness between all streams) thus sum-rate degradation is milder. Algorithmic parameters can significantly differentiate the results of numerical algorithms. A complete picture for comparison of algorithms can only be depicted by varying these parameters. For example, a predetermined iteration number or a negligible increment in the sum-rate can be the stopping criterion of an algorithm. While the distributed interference alignment (DIA) can reasonably achieve sub-stream fairness for the later, the imbalance between sub-streams increases as the preset iteration number decreases. Thus comparison of max-SINR and DIA with a low preset iteration number can only depict a part of the picture. We analyze such important parameters and their effects on SINR and rate metrics to exhibit numerical correctness in executing the benchmarks. Finally, we propose group filtering schemes that jointly design the streams of a user in contrast to max-SINR scheme that designs each stream of a user separately. © 2013 IEEE.

Ali A.O.D.,University of Texas at Dallas | Yetis C.M.,Mevlana University | Torlak M.,University of Texas at Dallas
IEEE International Symposium on Personal, Indoor and Mobile Radio Communications, PIMRC | Year: 2015

In this paper, distributed antenna selection algorithms are proposed to improve uncoded bit-error-rate (BER) in multIPle-input multIPle-output (MIMO) interference channels. The well known distributed power control algorithm by Yates in 1995 is used in all proposed schemes together with distributed antenna search algorithms, explicitly distributed exhaustive search, relaxed exhaustive search, and cross-entropy optimization techniques. While maximization of minimum signal-to-interference plus noise ratio (SINR) is the antenna selection metric, power minimization subject to SINR constraint is the power control problem used in the proposed schemes. It is shown that the proposed algorithms improve the BER of the system with acceptable sum-rate and fairness achieved in the system. Prioritization of streams can improve the BER of the system such as by assigning higher priorities to more important streams. Although for simplicity, equal stream priority, i.e., fairness among streams, is considered in this work, the proposed schemes can be extended to prioritization scenarios. © 2014 IEEE.

Inci M.,Mustafa Kemal University | Zararsiz I.,Mevlana University | Davarci M.,Mustafa Kemal University | Gorur S.,Mustafa Kemal University
Turk Uroloji Dergisi | Year: 2013

Formaldehyde is a chemical substance with a pungent odor that is highly soluble in water and occurs naturally in organisms. Formaldehyde, when taken into organisms, is metabolized into formic acid in the liver and erythrocytes and is then excreted, either with the urine and feces or via the respiratory system. Formaldehyde is widely used in the industrial and medical fields, and employees in these sectors are frequently exposed to it. Anatomists and medical students are affected by formaldehyde gas during dissection lessons. Because full protection from formaldehyde is impossible for employees in industrial plants using this chemical and for workers in laboratory conditions, several measures can be implemented to prevent and/or reduce the toxic effects of formaldehyde. In this review, we aimed to identify the toxic effects of formaldehyde on the urinary system. © 2013 by Turkish Association of Urology.

Discover hidden collaborations