Browsing by Author "Sengul, Gokhan"

Now showing 1 - 20 of 25

Analysis of Turkey's Institutional Open Repositories: an Example of Dokuz Eylul University Institutional Open Repository
(Turkish Librarians Assoc, 2012) Erturk, Korhan Levent; Sengul, Gokhan
After the declaration of the Budapest Open Access Initiative in 2001, institutional open repositories are known as the most important tool of the self archiving, which is also known as green road. There are 26 institutional repositories, which are all compatible to international standards. All the institutional open repositories of Turkey mentioned before are listed in international open archive directories. In this study institutional open repository of Dokuz Eylul University is examined and institutional open repositories of Turkey are discussed.
Citation - WoS: 9
Citation - Scopus: 9
Benchmarking Classification Models for Cell Viability on Novel Cancer Image Datasets
(Bentham Science Publ Ltd, 2019) Ozkan, Akin; Isgor, Sultan Belgin; Sengul, Gokhan; Isgor, Yasemin Gulgun
Background: Dye-exclusion based cell viability analysis has been broadly used in cell biology including anticancer drug discovery studies. Viability analysis refers to the whole decision making process for the distinction of dead cells from live ones. Basically, cell culture samples are dyed with a special stain called trypan blue, so that the dead cells are selectively colored to darkish. This distinction provides critical information that may be used to expose influences of the studied drug on considering cell culture including cancer. Examiner's experience and tiredness substantially affect the consistency throughout the manual observation of cell viability. The unsteady results of cell viability may end up with biased experimental results accordingly. Therefore, a machine learning based automated decision-making procedure is inevitably needed to improve consistency of the cell viability analysis. Objective: In this study, we investigate various combinations of classifiers and feature extractors (i.e. classification models) to maximize the performance of computer vision-based viability analysis. Method: The classification models are tested on novel hemocytometer image datasets which contain two types of cancer cell images, namely, caucasian promyelocytic leukemia (HL60), and chronic myelogenous leukemia (K562). Results: From the experimental results, k-Nearest Neighbor (KNN) and Random Forest (RF) by combining Local Phase Quantization (LPQ) achieve the lowest misclassification rates that are 0.031 and 0.082, respectively. Conclusion: The experimental results show that KNN and RF with LPQ can be powerful alternatives to the conventional manual cell viability analysis. Also, the collected datasets are released from the "biochem.atilim.edu.tr/datasets/ " web address publically to academic studies.
Citation - WoS: 6
Classification of Parasite Egg Cells Using Gray Level Cooccurence Matrix and Knn
(Scientific Publishers india, 2016) Sengul, Gokhan
Parasite eggs are around 20 to 80 mu m 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%.
Citation - WoS: 11
Citation - Scopus: 12
A Comprehensive Assessment Plan for Accreditation in Engineering Education: A Case Study in Turkey
(Tempus Publications, 2015) Turhan, Cigdem; Sengul, Gokhan; Koyuncu, Murat; Information Systems Engineering; Software Engineering; Computer Engineering
This paper describes the procedure followed by Computer Engineering and Software Engineering programs at Atilim University, Ankara, Turkey, which led to the granting of five years of accreditation by MUDEK, the local accreditation body authorized by The European Network for Accreditation of Engineering Education (ENAEE) to award the EUR-ACElabel, and a full member signatory of Washington Accord of International Engineering Alliance (IEA). It explains the organizational structure established for preparation, determination and measurement of the educational objectives, program outcomes, course outcomes, and the continuous improvement cycle carried out during the preparation period. The aim of the paper is to share methods and experiences which may be beneficial for the other programs that are intended for accreditation.
Citation - WoS: 15
Citation - Scopus: 15
Construct and Face Validity of the Educational Computer-Based Environment (ece) Assessment Scenarios for Basic Endoneurosurgery Skills
(Springer, 2017) Cagiltay, Nergiz Ercil; Ozcelik, Erol; Sengul, Gokhan; Berker, Mustafa
Background In neurosurgery education, there is a paradigm shift from time-based training to criterion-based model for which competency and assessment becomes very critical. Even virtual reality simulators provide alternatives to improve education and assessment in neurosurgery programs and allow for several objective assessment measures, there are not many tools for assessing the overall performance of trainees. This study aims to develop and validate a tool for assessing the overall performance of participants in a simulation-based endoneurosurgery training environment. Methods A training program was developed in two levels: endoscopy practice and beginning surgical practice based on four scenarios. Then, three experiments were conducted with three corresponding groups of participants (Experiment 1, 45 (32 beginners, 13 experienced), Experiment 2, 53 (40 beginners, 13 experienced), and Experiment 3, 26 (14 novices, 12 intermediate) participants). The results analyzed to understand the common factors among the performance measurements of these experiments. Then, a factor capable of assessing the overall skill levels of surgical residents was extracted. Afterwards, the proposed measure was tested to estimate the experience levels of the participants. Finally, the level of realism of these educational scenarios was assessed. Results The factor formed by time, distance, and accuracy on simulated tasks provided an overall performance indicator. The prediction correctness was very high for the beginners than the one for experienced surgeons in Experiments 1 and 2. When non-dominant hand is used in a surgical procedure-based scenario, skill levels of surgeons can be better predicted. The results indicate that the scenarios in Experiments 1 and 2 can be used as an assessment tool for the beginners, and scenario-2 in Experiment 3 can be used as an assessment tool for intermediate and novice levels. It can be concluded that forming the balance between perceived action capacities and skills is critical for better designing and developing skill assessment surgical simulation tools.
Deep Learning and Current Trends in Machine Learning
(Ieee, 2018) Bostan, Atila; Sengul, Gokhan; Tirkes, Guzin; Ekin, Cansu; Karakaya, Murat
Academic interest and commercial attention can be used to identify how much potential a novel technology may have. Since the prospective advantages in it may help solving some problems that are not solved yet or improving the performance of readily available ones. In this study, we have investigated the Web of Science (WOS) indexing service database for the publications on Deep Learning (DL), Machine Learning (ML), Convolutional Neural Networks (CNN), and Image Processing to reveal out the current trend. The figures indicate the strong potential in DL approach especially in image processing domain.
Citation - WoS: 46
Citation - Scopus: 65
Deep Learning Based Fall Detection Using Smartwatches for Healthcare Applications
(Elsevier Sci Ltd, 2022) Sengul, Gokhan; Karakaya, Murat; Misra, Sanjay; Abayomi-Alli, Olusola O.; Damasevicius, Robertas
We implement a smart watch-based system to predict fall detection. We differentiate fall detection from four common daily activities: sitting, squatting, running, and walking. Moreover, we separate falling into falling from a chair and falling from a standing position. We develop a mobile application that collects the acceleration and gyroscope sensor data and transfers them to the cloud. In the cloud, we implement a deep learning algorithm to classify the activity according to the given classes. To increase the number of data samples available for training, we use the Bica cubic Hermite interpolation, which allows us to improve the accuracy of the neural network. The 38 statistical data features were calculated using the rolling update approach and used as input to the classifier. For activity classification, we have adopted the bi-directional long short-term memory (BiLSTM) neural network. The results demonstrate that our system can detect falling with an accuracy of 99.59% (using leave-one-activityout cross-validation) and 97.35% (using leave-one-subject-out cross-validation) considering all activities. When considering only binary classification (falling vs. all other activities), perfect accuracy is achieved.
The Effect of Split Attention in Surgical Education
(Springer-verlag Berlin, 2014) Ozcelik, Erol; Cagiltay, Nergiz Ercil; Sengul, Gokhan; Tuner, Emre; Unal, Bulent
Surgical education through simulation is an important area to improve the level of education and to decrease the risks, ethical considerations and cost of the educational environments. In the literature there are several studies conducted to better understand the effect of these simulation environments on learning. However among those studies the human-computer interaction point of view is very limited. Surgeons need to look at radiological images such as magnetic resonance images (MRI) to be sure about the location of the patient's tumor during a surgical operation. Thus, they go back and forth between physically separated places (e.g. the operating table and light screen display for MRI volume sets). This study is conducted to investigate the effect of presenting different information sources in close proximity on human performance in surgical education. For this purpose, we have developed a surgical education simulation scenario which is controlled by a haptic interface. To better understand the effect of split attention in surgical education, an experimental study is conducted with 27 subjects. The descriptive results of study show that even the integrated group performed the tasks with a higher accuracy level (by traveling less distance, entering less wrong directions and hitting less walls), the results are not statistically significant. Accordingly, even there are some evidences about the effect of split attention on surgical simulation environments, the results of this study need to be validated by controlling students' skill levels on controlling the haptic devices and 2D/3D space perception skills. The results of this study may guide the system developers to better design the HCI interface of their designs especially for the area of surgical simulation.
The Effect of Statistically Constrained Minimum Mean Square Estimation Algorithm Which Is Used for Human Head Tissue Conductivity Estimation To Source Localization
(Journal Neurological Sciences, 2012) Sengul, Gokhan; Şengül, Gökhan; Baysal, Ugur; Şengül, Gökhan; Computer Engineering; Computer Engineering; Computer Engineering
Determining the electrical active regions of human brain by using EEG and/or MEG data is known as "EEG/MEG bioelectromagnetic inverse problem" or "source localization". A typical source localization system intakes not only EEG/MEG data but also geometry information of subject/patient, a priori information about the electrically active sources, the number and 3-D positions of measurement electrodes and conductivities/resistivities of the tissues in the head model. In this study we investigated the conductivity estimation performance previously proposed Statistically Constrainted Minimum Mean Square Error Estimation (MiMSEE) algorithm by simulation studies and we also investigated the effect of the estimation to source localization activities. In simulation studies we used a three-layered (composed of scalp, skull and brain regions) realistic head model to estimate 100 different conductivity distributions in vivo. As a result we found that the proposed algorithm estimates the conductivity of scalp with an average error of 23%, the conductivity of skull with an average error of 40% and finally the conductivity of brain with an average error of 17%. In the second part of the study we compared the source localization errors for two cases: one, when the average conductivities of tissues given in the literature are used, and second when the subject-specific conductivity estimation is performed with MiMSEE algorithm. The results showed 10.1 mm localization error is obtained when the average conductivities given in the literature are used and 2.7 mm localization is obtained when subject-specific conductivity estimation is performed with MiMSEE algorithm. The results shows that the localization error is reduced by 73.07% when subject-specific conductivity estimation is performed with MiMSEE algorithm. We conclude that using the conductivities obtained from MiMSEE algorithm reduces the source localization error and we recommend to perform subject-specific conductivity estimation for source localization applications.
Citation - WoS: 7
Estimation of Polypropylene Concentration of Modified Bitumen Images by Using K-Nn and Svm Classifiers
(Asce-amer Soc Civil Engineers, 2015) Tapkin, Serkan; Sengoz, Burak; Sengul, Gokhan; Topal, Ali; Ozcelik, Erol
The goal of this study is to design an expert system that automatically classifies the microscopic images of polypropylene fiber (PPF) modified bitumen including seven different contents of fibers. Optical microscopy was used to capture the images from thin films of polypropylene fiber modified bitumen samples at a magnification scale of 100 x. A total of 313 images were pre-processed, and features were extracted and selected by the exhaustive search method. The k-nearest neighbor (k-NN) and multiclass support vector machine (SVM) classifiers were applied to quantify the representation capacity. The k-NN and multiclass SVM classifiers reached an accuracy rate of 87% and 86%, respectively. The results suggest that the proposed expert system can successfully estimate the concentration of PPF in bitumen images with good generalization characteristics. (C) 2014 American Society of Civil Engineers.
Citation - WoS: 18
Citation - Scopus: 24
Fusion of Smartphone Sensor Data for Classification of Daily User Activities
(Springer, 2021) Sengul, Gokhan; Ozcelik, Erol; Misra, Sanjay; Damasevicius, Robertas; Maskeliunas, Rytis
New mobile applications need to estimate user activities by using sensor data provided by smart wearable devices and deliver context-aware solutions to users living in smart environments. We propose a novel hybrid data fusion method to estimate three types of daily user activities (being in a meeting, walking, and driving with a motorized vehicle) using the accelerometer and gyroscope data acquired from a smart watch using a mobile phone. The approach is based on the matrix time series method for feature fusion, and the modified Better-than-the-Best Fusion (BB-Fus) method with a stochastic gradient descent algorithm for construction of optimal decision trees for classification. For the estimation of user activities, we adopted a statistical pattern recognition approach and used the k-Nearest Neighbor (kNN) and Support Vector Machine (SVM) classifiers. We acquired and used our own dataset of 354 min of data from 20 subjects for this study. We report a classification performance of 98.32 % for SVM and 97.42 % for kNN.
Citation - WoS: 18
Citation - Scopus: 23
Gender Detection Using 3d Anthropometric Measurements by Kinect
(Polska Akad Nauk, Polish Acad Sciences, 2018) Camalan, Seda; Sengul, Gokhan; Misra, Sanjay; Maskeliunas, Rytis; Damasevicius, Robertas
Automatic gender detection is a process of determining the gender of a human according to the characteristic properties that represent the masculine and feminine attributes of a subject. Automatic gender detection is used in many areas such as customer behaviour analysis, robust security system construction, resource management, human-computer interaction, video games, mobile applications, neuro-marketing etc., in which manual gender detection may be not feasible. In this study, we have developed a fully automatic system that uses the 3D anthropometric measurements of human subjects for gender detection. A Kinect 3D camera was used to recognize the human posture, and body metrics are used as features for classification. To classify the gender, KNN, SVM classifiers and Neural Network were used with the parameters. A unique dataset gathered from 29 female and 31 male (a total of 60 people) participants was used in the experiment and the Leave One Out method was used as the cross-validation approach. The maximum accuracy achieved is 96.77% for SVM with an MLP kernel function.
Citation - WoS: 1
Gender Prediction by Using Local Binary Pattern and K Nearest Neighbor and Discriminant Analysis Classifications
(Ieee, 2016) Camalan, Seda; Çamalan, Seda; Sengul, Gokhan; Şengül, Gökhan; Çamalan, Seda; Şengül, Gökhan; Information Systems Engineering; Computer Engineering; Information Systems Engineering; Computer Engineering
In this study, gender prediction is investigated for the face images. To extract the features of the images, Local Binary Pattern (LBP) is used with its different parameters. To classify the images male or female, K-Nearest Neighbors (KNN) and Discriminant Analysis (DA) methods are used. Their performances according to the LBP parameters are compared. Also classification methods' parameters are changed and the comparison results are shown. These methods are applied on FERET database with 530 female and 731 male images. To have better performance, the face parts of the images are cropped then feature extraction and classification methods applied on the face part of the images.
Citation - WoS: 11
Citation - Scopus: 13
Gesture-Based Interaction for Learning: Time To Make the Dream a Reality
(Wiley, 2012) Ozcelik, Erol; Sengul, Gokhan
[No Abstract Available]
Citation - WoS: 1
Haptic User Interface Integration for 3d Game Engines
(Springer-verlag Berlin, 2014) Sengul, Gokhan; Cagiltay, Nergiz Ercil; Ozcelik, Erol; Tuner, Emre; Erol, Batuhan
Touch and feel senses of human beings provide important information about the environment. When those senses are integrated with the eyesight, we may get all the necessary information about the environment. In terms of human-computer-interaction, the eyesight information is provided by visual displays. On the other hand, touch and feel senses are provided by means of special devices called "haptic" devices. Haptic devices are used in many fields such as computer-aided design, distance-surgery operations, medical simulation environments, training simulators for both military and medical applications, etc. Besides the touch and sense feelings haptic devices also provide force-feedbacks, which allows designing a realistic environment in virtual reality applications. Haptic devices can be categorized into three classes: tactile devices, kinesthetic devices and hybrid devices. Tactile devices simulate skin to create contact sensations. Kinesthetic devices apply forces to guide or inhibit body movement, and hybrid devices attempt to combine tactile and kinesthetic feedback. Among these kinesthetic devices exerts controlled forces on the human body, and it is the most suitable type for the applications such as surgical simulations. The education environments that require skill-based improvements, the touch and feel senses are very important. In some cases providing such educational environment is very expensive, risky and may also consist of some ethical issues. For example, surgical education is one of these fields. The traditional education is provided in operating room on real patients. This type of education is very expensive, requires long time periods, and does not allow any error-and-try type of experiences. It is stressfully for both the educators and the learners. Additionally there are several ethical considerations. Simulation environments supported by such haptic user interfaces provide an alternative and safer educational alternative. There are several studies showing some evidences of educational benefits of this type of education (Tsuda et al 2009; Sutherland et al 2006). Similarly, this technology can also be successfully integrated to the physical rehabilitation process of some diseases requiring motor skill improvements (Kampiopiotis & Theodorakou, 2003). Hence, today simulation environments are providing several opportunities for creating low cost and more effective training and educational environment. Today, combining three dimensional (3D) simulation environments with these haptic interfaces is an important feature for advancing current human-computer interaction. On the other hand haptic devices do not provide a full simulation environment for the interaction and it is necessary to enhance the environment by software environments. Game engines provide high flexibility to create 3-D simulation environments. Unity3D is one of the tools that provides a game engine and physics engine for creating better 3D simulation environments. In the literature there are many studies combining these two technologies to create several educational and training environments. However, in the literature, there are not many researches showing how these two technologies can be integrated to create simulation environment by providing haptic interfaces as well. There are several issues that need to be handled for creating such integration. First of all the haptic devices control libraries need to be integrated to the game engine. Second, the game engine simulation representations and real-time interaction features need to be coordinately represented by the haptic device degree of freedom and force-feedback speed and features. In this study, the integration architecture of Unity 3D game engine and the PHANToM Haptic device for creating a surgical education simulation environment is provided. The methods used for building this integration and handling the synchronization problems are also described. The algorithms developed for creating a better synchronization and user feedback such as providing a smooth feeling and force feedback for the haptic interaction are also provided. We believe that, this study will be helpful for the people who are creating simulation environment by using Unity3D technology and PHANToM haptic interfaces.
Citation - WoS: 2
Citation - Scopus: 2
A Hybrid Approach for Semantic Image Annotation
(Ieee-inst Electrical Electronics Engineers inc, 2021) Sezen, Arda; Turhan, Cigdem; Sengul, Gokhan
In this study, a framework that generates natural language descriptions of images within a controlled environment is proposed. Previous work on neural networks mostly focused on choosing the right labels and/or increasing the number of related labels to depict an image. However, creating a textual description of an image is a completely different phenomenon, structurally, syntactically, and semantically. The proposed semantic image annotation framework presents a novel combination of deep learning models and aligned annotation results derived from the instances of the ontology classes to generate sentential descriptions of images. Our hybrid approach benefits from the unique combination of deep learning and semantic web technologies. We detect objects from unlabeled sports images using a deep learning model based on a residual network and a feature pyramid network, with the focal loss technique to obtain predictions with high probability. The proposed framework not only produces probabilistically labeled images, but also the contextual results obtained from a knowledge base exploiting the relationship between the objects. The framework's object detection and prediction performances are tested with two datasets where the first one includes individual instances of images containing everyday scenes of common objects and the second custom dataset contains sports images collected from the web. Moreover, a sample image set is created to obtain annotation result data by applying all framework layers. Experimental results show that the framework is effective in this controlled environment and can be used with other applications via web services within the supported sports domain.
Citation - WoS: 9
Citation - Scopus: 30
An Improved Random Bit-Stuffing Technique With a Modified Rsa Algorithm for Resisting Attacks in Information Security (rbmrsa)
(Cairo Univ, Fac Computers & information, 2022) Mojisola, Falowo O.; Misra, Sanjay; Febisola, C. Falayi; Abayomi-Alli, Olusola; Sengul, Gokhan
The recent innovations in network application and the internet have made data and network security the major role in data communication system development. Cryptography is one of the outstanding and powerful tools for ensuring data and network security. In cryptography, randomization of encrypted data increases the security level as well as the Computational Complexity of cryptographic algorithms involved. This research study provides encryption algorithms that bring confidentiality and integrity based on two algorithms. The encryption algorithms include a well-known RSA algorithm (1024 key length) with an enhanced bit insertion algorithm to enhance the security of RSA against different attacks. The security classical RSA has depreciated irrespective of the size of the key length due to the development in computing technology and hacking system. Due to these lapses, we have tried to improve on the contribution of the paper by enhancing the security of RSA against different attacks and also increasing diffusion degree without increasing the key length. The security analysis of the study was compared with classical RSA of 1024 key length using mathematical evaluation proofs, the experimental results generated were compared with classical RSA of 1024 key length using avalanche effect in (%) and computational complexity as performance evaluation metrics. The results show that RBMRSA is better than classical RSA in terms of security but at the cost of execution time. (C) 2022 THE AUTHORS. Published by Elsevier B.V. on behalf of Faculty of Computers and Information, Cairo University.
Citation - WoS: 4
Citation - Scopus: 7
The Integrated Usage of Lbp and Hog Transformations and Machine Learning Algorithms for Age Range Prediction From Facial Images
(Univ Osijek, Tech Fac, 2018) Khalifa, Tariq; Sengul, Gokhan
Age prediction is an active study field that can be used in many computer vision problems due to its importance and effectiveness. In this paper, we present extensive experiments and provide an efficient and accurate approach for age range prediction of people from facial images. First, we apply image resizing to unify all images' size, and Histogram Equalization technique to reduce the illumination effects on all facial images taken from FG-NET and UTD aging databases. Second, Histogram of Oriented Gradient (HOG) and Local Binary Pattern (LBP) are used to extract the features of these images, and then we combined both HOG and LBP features in order to attain better prediction. Finally, Support Vector Machine (SVM) and k-Nearest Neighbour (k-NN) are used for the classification processes. In addition, k-fold, Leave-One-Out (LOO) and Confusion Matrix (CM) are used to evaluate the performance of proposed methods. The extensive and intensified experiments show that combining HOG and LBP features improved the age range predicting performance up to 99.87%.
An Iot Application for Locating Victims Aftermath of an Earthquake
(Ieee, 2017) Karakaya, Murat; Sengul, Gokhan; Gokcay, Erhan
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.
Citation - WoS: 1
Method Proposal for Distinction of Microscope Objectives on Hemocytometer Images
(Ieee, 2016) Ozkan, Akin; Isgor, S. Belgin; Sengul, Gokhan
Hemocytometer is a special glass plate apparatus used for cell counting that has straight lines (counting chamber) in certain size. Leveraging this special lam and microscope, a cell concentration on an available cell suspension can be estimated. The automation process of hemocytometer images will assist several research disciplines to improve consistency of results and to reduce human labor. Different objective measurements can be utilized to analyze a cell sample on microscope. These differences affect the detail of image content. Basically, while the objective value is getting increased, image scale and detail level taken from image will increase, yet visible area becomes narrower. Due to this variation, different self-cell counting approaches should be developed for images taken with different objective values. In this paper, using the hemocytometer images gathered from a microscope, a novel approach is introduced for which can estimate objective values of a microscope with machine learning methods automatically. For this purpose, a frequency-based visual feature is proposed which embraces hemocytometer structure well. As a result of the conducted tests, %100 distinction accuracy is achieved with the proposed method.