Browsing by Author "Şengül,G."

Now showing 1 - 7 of 7

Application of Kalman Filter for the Estimation of Human Head Tissue Conductivities;
(2011) Şengül,G.; Baysal,U.; Computer Engineering; 06. School Of Engineering; 01. Atılım University
In this study Extended Kalman Filtering is proposed for the estimation of human head tissue conductivities by using EEG data. The proposed method first linearizes the relationship between the tissue conductivities and surface potentials (EEG measurements) and then iteratively estimates the tissue conductivities. In the study the mathematical background of the proposed method is presented and then performance of the proposed method is investigated by a simulation study. In the simulation study a three layered realistic head model (composed of scalp, skull and brain compartments) obtained from MR images of a real patient is used. The surface potential is calculated by using an arbitrarily chosen conductivity distribution. Then conductivity estimation is iteratively performed by using the calculated potentials and at each iteration relative error rates are calculated by comparing the orginal conductivities and estimated ones. It is found that the relative error rates decrease below of 1% after five iterations. © 2011 IEEE.
Citation - Scopus: 12
Classification of parasite egg cells using gray level cooccurence matrix and kNN
(Scientific Publishers of India, 2016) Şengül,G.; Computer Engineering; 06. School Of Engineering; 01. Atılım University
Parasite eggs are around 20 to 80 μm dimensions, and they can be seen under microscopes only and their detection requires visual analyses of microscopic images, which requires human expertise and long analysis time. Besides visual analysis is very error prone to human procedures. In order to automatize this process, a number of studies are proposed in the literature. But there is still a gap between the preferred performance and the reported ones and it is necessary to increase the performance of the automatic parasite egg classification approaches. In this study a learning based statistical pattern recognition approach for parasite egg classification is proposed that will both decrease the time required for the manual classification by an expert and increase the performance of the previously suggested automated parasite egg classification approaches. The proposed method uses Gray-Level Co-occurrence Matrix as the feature extractor, which is a texture based statistical method that can differentiate the parasite egg cells based on their textures, and the k-Nearest Neighbourhood (kNN) classifier for the classification. The proposed method is tested on 14 parasite egg types commonly seen in humans. The results show that proposed method can classify the parasite egg cells with a performance rate of 99%. © 2016, Scientific Publishers of India. All rights reserved.
Citation - Scopus: 1
Computer Vision Based Automated Cell Counting Pipeline: a Case Study for Hl60 Cancer Cell on Hemocytometer
(Scientific Publishers of India, 2018) Özkan,A.; İşgör,S.B.; Şengül,G.; İşgör,Y.G.; Department of Electrical & Electronics Engineering; Computer Engineering; Chemical Engineering; 15. Graduate School of Natural and Applied Sciences; 06. School Of Engineering; 01. Atılım University
Counting of cells can give useful information about the cell density to understand the concerning cell culture condition. Usually, cell counting can be achieved manually with the help of the microscope and hemocytometer by the domain experts. The main drawback of the manual counting procedure is that the reliability highly depends on the experience and concentration of the examiners. Therefore, computer vision based automated cell counting is an essential tool to improve the accuracy. Although the commercial automated cell counting systems are available in the literature, their high cost limits their broader usage. In this study, we present a cell counting pipeline for light microscope images based on hemocytometer that can be easily adapted to the various cell types. The proposed method is robust to adverse image and cell culture conditions such as cell shape deformations, lightning conditions and brightness differences. In addition, we collect a novel human promyelocytic leukemia (HL60) cancer cell dataset to test our pipeline. The experimental results are presented in three measures: recall, precision and F-measure. The method reaches up to 98%, 92%, and 95% based on these three measures respectively by combining Support Vector Machine (SVM) and Histogram of Oriented Gradient (HOG). © 2018, Scientific Publishers of India. All rights reserved.
Disability Awareness in Turkey and an Assessment About Accessibility of Web Pages Related To Justice by Disabled People;
(University and Research Librarians Association (UNAK), 2014) Ertürk,K.L.; Şimşek,A.A.; Songür,D.G.; Şengül,G.; Information Systems Engineering; Computer Engineering; 06. School Of Engineering; 01. Atılım University
The people who have physical or mental disabilities which limit their movements, senses, activities or both of them are one of the groups in society. Those people have various problems in social life directly or indirectly in Turkey. Nowadays, they face many problems in accessibility on many fields such as education, healthcare, justice, social security, etc. Those individuals are willing to draw attention and resolve their problems. The level of development of countries is directly related with the solution of the aforementined problems. In this study we focused on the common terms about the people who have limited movements, senses, activities or both; and focused on the awereness of disabled people and we investigated the the accessibility of the web sites about the justice by disabled people. Making accessible of web pages will allow the disabled people to have the equal rights with the others and will also provide diversity about information and communication sources.
A Fully Automatic Photogrammetric System Design Using a 1.3 Mp Web Camera To Determine Eeg Electrode Positions;
(2010) Şengül,G.; Baysal,U.; Computer Engineering; 06. School Of Engineering; 01. Atılım University
In this study a fully automatic fotogrammetric system is designed to determine the EEG electrode positions in 3D. The proposed system uses a 1.3 MP web camera rotating over the subject's head. The camera is driven by a step motor. The camera takes photos in every 7.20 angles during the rotation. In order to realize full automation, electrodes are labeled by colored circular markers and an electrode identification algorithm is develeoped for full automation. The proposed method is tested by using a realistic head phantom carrying 25 electrodes. The positions of the test electrodes are also measured by a conventional 3-D digitizer. The measurements are repeated 3 times for repeatibility purposes. It is found that 3-d digitizer localizes the electrodes with an average error of 8.46 mm, 7.63 mm and 8.32 mm, while the proposed system localizes the electrodes with an average error of 1.76 mm, 1.42 mm and 1.53 mm. ©2010 IEEE.
Citation - Scopus: 1
An Iot Application for Locating Victims Aftermath of an Earthquake
(Institute of Electrical and Electronics Engineers Inc., 2017) Karakaya,M.; Şengül,G.; Gökçay,E.; Software Engineering; Computer Engineering; 06. School Of Engineering; 01. Atılım University
This paper presents an Internet of Things (IoT) framework which is specially designed for assisting the research and rescue operations targeted to collapsed buildings aftermath of an earthquake. In general, an IoT network is used to collect and process data from different sources called things. According to the collected data, an IoT system can actuate different mechanisms to react the environment. In the problem at hand, we exploit the IoT capabilities to collect the data about the victims before the building collapses and when it falls down the collected data is processed to generate useful reports which will direct the search and rescue efforts. The proposed framework is tested by a pilot implementation with some simplifications. The initial results and experiences are promising. During the pilot implementation, we observed some issues which are addressed in the proposed IoT framework properly. © 2017 IEEE.
Citation - Scopus: 3
Self Archiving in Atilim University
(2012) Ertürk,K.L.; Şengül,G.; Information Systems Engineering; Computer Engineering; 06. School Of Engineering; 01. Atılım University
Self archiving is defined as storing the scientific research outputs in researchers' own web pages/sites, organizational web sites or institutional repositories. In this study the self archiving activities of academicians of AtIlIm University are investigated. For the purpose of the study the web pages of the university, personal web pages of the academicians and open repository of the university are explored. We found the details of 2176 academic activities of the instructors in web pages. More than half of these activities (1147 - 53%) consist of refereed journal papers. Almost a quarter of the instructors saved their research outputs in the university's open repository. Yet, those instructors have not published their works in their personal web pages or institutional web pages. Only 4% of the works are published in personal/organizational web pages. According to the results obtained, the usage of institutional repository is the common self archiving method in the AtIlIm University. On the other hand, the personal/organizational web pages should be as a point of attraction in self archiving. While discussing the efficient usage of the institutional repository, we suggest that the social networks as a meeting point should include links to personal/institutional web pages containing academicians' papers. © 2012 Springer-Verlag.