Sürdürülebilir Kalkınma Amaçları
Yazarlar
- Yildirim, Ozal(10)
- Bulut, Hasan(9)
- Atangana, A(8)
- Baskonus, HM(8)
- Bulut, H(8)
- Demir, Yakup(8)
- Hammouch, Z(8)
- Karakose, Mehmet(8)
- Mekkaoui, T(8)
- Baskonus, Haci Mehmet(7)
- Yilmazer, Merve(7)
- Orhan, Ahmet(5)
- Agoujil, S(4)
- Aslan, Serpil(4)
- Baloglu, Ulas Baran(4)
- Belgacem, FB(4)
- Boydak, Merve(4)
- Caliskan, Abuzer(4)
- Cattani, C(4)
- Celik, Erkan(4)
- Kaya, Mehmet(4)
- Talo, Muhammed(4)
- Çil, Zeynel Abidin(4)
- Özceylan, Eren(4)
- Barros, J.(3)
- Benedicenti, L.(3)
- Cachim, P.(3)
- Drobne, S.(3)
- El Naggar, H.(3)
- Eristi, Belkis(3)
- Eristi, Huseyin(3)
- Gunay, Mihriban(3)
- Kljajic Borstar, M.(3)
- Koseoglu, Murat(3)
- Mete, Süleyman(3)
- Sivasundaram, S(3)
- Uyanik, Hakan(3)
- Yalcin, Beyza Furtana(3)
- Yilmaz, Mehmet(3)
- Zadnik Stirn, L.(3)
Yayınlar
- BildiriAçık Erişim2020Speed Control of DC Motor under Load Condition Using Single Phase Matrix Converter
Boydak, Merve; Orhan, Ahmet; Caliskan, Abuzer
In this study, speed control of a separately excited DC motor was performed using Single Phase Matrix Converter (SPMC). The driver circuit that operates SPMC in buck-boost mode was used. The DC motor was first run without any controller and the change in speed was observed in the case of loading. Then, the motor was run by using PI controller and speed of the motor was kept constant during loading. Switches in the single-phase matrix converter are switched using Sinusoidal Pulse Width Modulation (SPWM) technique. MATLAB/Simulink was used for simulation.
AtıfScopus1
İncele - BildiriYalnız künye2020A risk assessment approach using both stochastic data and subjective judgments
Mete, Suleyman; Oz, Nurdan Ece; Gul, Muhammet; Serin, Faruk; Celik, Erkan; Kahraman, C.; Cevik Onar, S.; Oztaysi, B.; Sari, I.U.; Cebi, S.
Risk assessment describes the overall process regarding identifying hazards and risk factors that have the potential to cause harm, analyzing and evaluating the risk associated with that hazard and determining appropriate ways to eliminate the hazard or control the risk. In the literature, lots of approaches are proposed to prioritize hazards and associated risks quantitatively. Fuzzy sets-based multi-criteria decision-making approaches are forefront that they have the ability in expressing the risks verbally based on decision-maker’s opinions and judgments. MCDA-based risk assessment approaches explain different types of uncertainties, which are generally modeled using stochastic analysis or fuzzy sets. The stochastic analysis is more suitable in modelling the probabilistic uncertainty. Therefore, in this study, a risk assessment approach using both stochastic data and subjective judgments is proposed, and a case study is also performed in a construction project. The VIKOR method is extended and a new risk assessment approach is developed where part of the data is stochastic. A three-year data is used to determine a fitted probability distribution of respected frequency. Evaluation of risks with respect to severity and probability parameters are then made by subjective judgments. In conclusion, a risk prioritization and potential action plan suggestion is performed.
AtıfScopus2OpenAlex3İncele - BildiriYayıncıda açık erişim2020Multimode Operation of Single Phase Matrix Converter with Safe Commutation Strategy
Boydak, Merve; Orhan, Ahmet; Caliskan, Abuzer
In this study, the multimode operation of Single-Phase Matrix Converter (SMPC) is examined. The SPMC was operated as a controlled rectifier and frequency converter using a single driver circuit. Mode selection is provided by changing the value of the constant block in the driver circuit. In the rectifier mode, the sinusoidal input voltage was rectified and transferred to the output. Output voltage at the desired frequency value was generated in the frequency changer mode. Voltage peaks in frequency converter mode were prevented with the safe commutation strategy used. Harmonics in the output voltage were examined for different modulation index values. Switches in the SPMC are switched using Sinusoidal Pulse Width Modulation (SPWM) technique. MATLAB/Simulink was used for simulation.
AtıfOpenAlex1İncele - BildiriYalnız künye2019Pneumonia Detection from Radiography Images using Convolutional Neural Networks
Talo, Muhammed
Pneumonia continues to be the leading cause of child mortality in children under the age of five, and 2,400 children, most of whom are babies under 2 years of age, die from pneumonia. In this study, an automated detection system is proposed for the diagnosis of pneumonia with chest radiography images. With the transfer learning technique, ResNet-152 convolutional neural network was customized to recognize pneumonia from radiography images. With this customized architecture, a recognition success of 97.4% was obtained in the detection of pneumonia disease without any preprocessing of raw data or manual feature extraction on radiography images. This model, which was proposed for the detection of pneumonia, found to be more successful when compared with the other successful studies in the literature.
AtıfWoS6OpenAlex16İncele - BildiriYalnız künye2019An Intrusion Detection System Using Apache Log Files
Ince, Cemile; Omaç, Zeki
Today, thousands of systems are exposed to attacks every day. For this reason, many studies have been done in this area. These studies, using data mining (VM) and machine learning techniques, are trying to determine the intrusion detection by examining the log files in different OSI layers. These studies generally use standard data sets and propose hybrid systems to increase the success rate. In this study, an attack detection system (STS) has been developed by using Inonu University web page log files. The log files used as a data set consist of more than 35 million requests and a total of 326 attacks. As a result, the system was trained using artificial neural network (ANN) and attacks were detected with 99.3% success.
- BildiriAçık Erişim2019Person Recognition via Facial Expression Using ELM Classifier Based CNN Feature Maps
Baloglu, Ulas Baran; Yildirim, Ozal; Uçar, AySegul; Miche, Y; Cao, J; Vong, CM; Lendasse, A
Extreme learning machine (ELM) and deep learning methods are well-known with their efficiency, accuracy, and speed. In this study, we focus on the application of ELM to a deep learning structure for person recognition with facial expressions. For this purpose, a new convolutional neural network (CNN) model containing Kernel ELM classifiers was constructed. In this model, ELM was not used only as a fully connected layer replacement and energy function was employed to generate feature maps for the ELM. There are two advantages of the proposed model. First, it is fast and successful in face recognition studies. Second, it can drastically improve the performance of a partially-trained CNN model. Consequently, the proposed model is very suitable for CNN models, where the learning process requires a lot of time and computational power. The model is tested with the Grimace data set and experimental results are presented in details.
AtıfOpenAlex3İncele - BildiriAçık Erişim2019Predicting Links in Complex Bipartite Networks Based on Strengthening Projections
Aslan, Serpil; Kaya, Mehmet
Link prediction in complex networks is a topic of high interest for many scientists that studied different areas. Many real-world complex networks have naturally bipartite structured. In this work, we proposed a link prediction method for the complex bipartite network. Recently, while link prediction in complex bipartite networks has been extensively studied, there isn't still sufficiently suitable methods for this networks. The previous works usually have some limitations. They first map the bipartite network into the unimodal projection networks. Then, they perform the link prediction using only the properties of the projection networks. However, these projection networks involve many node pairs with weak relationships when used in networks constructed from real-world data. These weak relationships lead to low probability predictions and high computation time for the algorithm. In this paper, to overcome these limitations, we first map the bipartite network into strengthening projection network model that consists of nodes that have only strong relationships. Based on this projection network, we presented the link prediction method for the complex bipartite network. We conducted extensive experiments on complex bipartite networks. The results of the experiments demonstrate that our proposed method can effectively solve the link prediction problem in complex bipartite networks.
AtıfScopus2OpenAlex2İncele - BildiriAçık Erişim2019Predicting Collaboration Relationships on Social Network
Aslan, Serpil; Kaya, Buket; Varol, A.; Yazici, A.; Yazici, M.A.; Varol, C.; Aygunes, G.S.; Cotur, A.
Scientific papers are mostly performed by collaboration between research groups. Researchers work in various subjects and in several research areas. Therefore, identifying a strong research group is a quite complex task. To cope with this complex task, we propose a network-based method that predicts the best appropriate collaborations for researchers in a co-authorship network. In this paper, we have constructed a weighted co-authorship network by using a real database of scientific papers. Almost all of the methods in this area use the unweighted network model. But, weighted networks are particularly important when representing the network-based properties. The constructed network consists of nodes and links which represent respectively authors and their collaborations. In these networks, if two researchers are the common authors in the same paper, they are considered connected. Typically, the link weights represent the number of papers that two authors have made collaboratively. We also use local LCP-based algorithms to calculate the betweenness and closeness of the authors in this paper. The experimental results demonstrate the success of the proposed method.
AtıfScopus3OpenAlex2İncele - BildiriAçık Erişim2019Bigailab-4race-50K: Race Classification with a New Benchmark Dataset
Talo, Muhammed; Ay, Betul; Makinist, Semiha; Aydin, Galip
Face analysis is the process of extracting useful information such as gender, age and race from a face image. In this study, we look at ways of closing the gap between the capabilities of automatic facial recognition and race classification methods. For this purpose, we take the following two steps. (1) We offer a public race dataset consisting of labeled images to overcome the challenges of real-world race estimation tasks. (2) We present a benchmark study to find race of a human face using a pre-trained Convolutional Neural Network (CNN) model on the large-scale face dataset. We are able to achieve a remarkable accuracy of 97.6% in race classification task.
AtıfScopus3OpenAlex5İncele - BildiriAçık Erişim2019A Hybrid recommendation system in co-Authorship networks
Aslan, Serpil; Kaya, Mehmet
Recommender systems are an important field that aim to direct users more quickly to their needs. Scientific research studies in academic field are mostly carried out by collaboration between scientists. Finding new collaborations and analyzing the quality of them are quite complicated situations. Therefore, developing a system that recommend strong collaborations for scientists can be an invaluable tool. In this study, we present a hybrid recommendation method that uses both collaborative filtering and a network-based method by examining the structure of the co-Authorship network that was created by using a real database of scientific articles in computer science. In the constructed network, the nodes represent scientists and links represent the coauthorship relationships. If two scientists in the network have been co-Author of at least one article, they are considered to be connected. Many of the present recommendation methods in this area take into account only the common neighbors of the nodes, while calculating the similarity of the node pairs in the network. To overcome these limited methods, we use the local community-based similarity indexes which also take into account the similarities between the common neighbors of the nodes. When the experimental results are examined, they prove the success of the proposed method.
AtıfScopus7WoS3OpenAlex6İncele - BildiriYalnız künye2018Geometric Methods in Deep Learning
Ünal, Inan; Yildirim, Ozal; Ozyildirim, BM; Yildirim, T
Deep learning algorithms have recently become the most widely used machine learning approaches. Remarkable approaches have emerged in the field of machine learning studies with the use of geometric methods for deep learning. The manifold theory, which is simply regarded as the general state of an Euclidean space, has become applicable in the field of deep learning and this field has been named Geometric Deep Learning. In this study, applications of manifold theory and differential geometry to deep learning is presented.
- BildiriAçık Erişim2018Example of A Kinetic Mathematical Modeling in Food Engineering
Ertekin, Ozlem; Cattani, C; Atangana, A; Bulut, H; Hammouch, Z; Baskonus, HM; Mekkaoui, T; Agoujil, S
Mathematical modeling of biochemical, chemical reaction processes facilitates understanding. The kinetics of these reaction processes can be analyzed mathematically and kinetics are presented as systems of differential equations. Mathematical model of a reaction kinetic is studied in this study. Bernoulli-Sub equation function method is used in this study. This example can be new model for food engineering applications.
AtıfWoS1OpenAlex1İncele - BildiriAçık Erişim2018Risk Analysis of Ports in Maritime Industry in Turkey using FMEA Based Intuitionistic Fuzzy TOPSIS Approach
Senel, Mine; Senel, Bilgin; Havle, Celal Alpay; Cattani, C; Atangana, A; Bulut, H; Hammouch, Z; Baskonus, HM; Mekkaoui, T; Agoujil, S
Today, international trade is extremely important for countries' economies. It is possible to show the ship's transport as one of the most important execution channels of this trade. International commercial maritime transport subject to many rules and regulations carries many risks in processes such as loading, handling and unloading. Commercial ports are the places where these risks are seen intensely. From this point, many risk components in terms of the process in the port, one of the international commercial port in Turkey, based on a risk analysis is tried to be evaluated in this study. Especially, loading and unloading processes are focused with the directions of industrial experts. The main dimensions of the risks in the port are determined via expert opinions, and the sub-criteria of these dimensions are revealed. In this way, a generic model is proposed based on failure mode and effect analysis and the model is digitized using intuitionistic fuzzy TOPSIS. Interpretations are made in the direction of the obtained analysis results.
AtıfWoS15OpenAlex31İncele - BildiriAçık Erişim2018Risk Assessment with Failure Mode and Effects Analysis and Grey Relational Analysis Method in Plastic Injection Process
Ünlükal, Ceren; Senel, Mine; Senel, Bilgin; Cattani, C; Atangana, A; Bulut, H; Hammouch, Z; Baskonus, HM; Mekkaoui, T; Agoujil, S
This study aims to evaluate the risks that may arise during the production process in a plastic injection manufacturing enterprise with traditional Failure Mode and Effect Analysis (FMEA) and Grey Relational Analysis (GRA). Although it is a widely used analytical technique that helps to identify and reduce the risks of failure in a process, the Failure Mode and Effects Analysis (FMEA) has some drawbacks that the different risks can have the same risk priority values and the weight of risk factors is not take into consideration. This situation has been tried to be eliminated by integrating the FMEA with the GRA. As a result, it is seen that the order of risk priority values of the identified failure changes according to both methods.
AtıfWoS5OpenAlex15İncele - BildiriAçık Erişim2018Investigation of Earthquake Behaviour of Construction System and Materials in Traditional Turkish Architecture
Yardimli, Seyhan; Dal, Murat; Mihlayanlar, Esma; Cattani, C; Atangana, A; Bulut, H; Hammouch, Z; Baskonus, HM; Mekkaoui, T; Agoujil, S
In this study, it is aimed to present a point of view regarding the behaviour of construction systems implemented in traditional Turkish architecture against earthquakes. In the scope of the study, examples of civil architecture were considered and their structures were evaluated as building elements such as foundation, wall and flooring. Traditional Turkish architecture construction systems can be evaluated in two parts. One of them is the wooden carcass system and the other is the unreinforced masonry system. In the wooden carcass system, the carrier is the load bearing elements used in horizontal and vertical directions. Intermediate parts (strut, diagonal etc.) are placed between these elements to form triangles. The triangles (strut, diagonal) used in the wooden skeleton system comprise highly resistant forms against earthquakes. Moreover, due to the internal structure and physical properties of the wood, which is the skeleton material, the flexibility that it maintains can meet the lateral loads of earthquakes. The second construction system which is the system addressed in this application, is the unreinforced masonry system. In this system, the loadbearing system itself is the walls, which are not resistant to lateral loads. In order to provide this flexibility beams (hatillar) are installed at certain intervals. After the wall is built to a certain height, a different material is laid allowing a plane of movement on the wall. Thus, when the wall is exposed to a lateral load, it escapes from the planes where the beams (hatillar) are present, and is protected against large damages by absorbing the earthquake load. In order to establish that the foundation of the structure can withstand earthquakes by movement, wood is placed at the lower part of the foundation above a layer of sand ensuring lateral movement and flexibility of the building. In traditional buildings the slabs are connected to the building walls with beams (hatillar). Through the agency of the beams (hatillar) formed at the connection points, the slabs can act as a mass so that they can meet the earthquake load. Allowing the structure to move makes it resistant to earthquakes, seismic isolators are used for this purpose by absorbing the earthquake load and moving the foundation of the structure.
AtıfWoS1OpenAlex4İncele - BildiriYayıncıda açık erişim2018An investigation of the near-wake flow structure of a cylinder with guiding plates
Ekinci, Firat; Firat, Erhan; Özkan, Göktürk M.; Akilli, Hüseyin; Dancova, P.
In this study, the flow behind a circular cylinder with a pair of outer identical guiding plates was investigated using particle image velocimetry (PIV) for various angular positions of the plates (i.e. α=±70°, ±100°, and ±130°). The gaps between these plates and cylinder are equal and are 0.3D. Experiments were carried out at a subcritical Reynolds (Re=ρ·U∞·D/μ) number of 7500, based on the cylinder diameter (D) and the flow velocity (U∞). The features of the near-wake with and without the guiding plates were interpreted in terms of patterns of time-averaged vorticity and streamlines, time-averaged and fluctuating velocity components. The spectral analysis was also carried out to determine the time-dependent variation of the transverse velocity at given locations in the near-wake. Two-dimensional computations of flow around circular cylinders with and without guiding plates have also been performed to predict the timeaveraged and root-mean-square of force coefficients of the various models. It was seen that the guiding plates at an appropriate angular position can lead to substantial attenuation, or retardation, of the process of large-scale vortex formation in the near-wake, thus can lead to vortex-induced vibration (VIV) suppression without any increase in drag.
- BildiriYalnız künye2018Quality lignite coal detection with discrete wavelet transform, discrete fourier transform, and ANN based on k-means clustering method
Korkmaz, Sevcan Aytac; Esmeray, Furkan; Varol, A.; Karabatak, M.; Varol, C.
In this article, the lignite coal datas in the Kalburcayi area of the Sivas-Kangal Basin have been used. This original data obtained from Kalburcayi area of the Sivas-Kangal Basin consists of 66 observations in the lignite coal area, including lignite quality parameters such as moisture content, ash, sulfur content and calorific value. These lignite coal datas have been clustered in two group with k-means method according to calori values. This clustering lignite coal data is classified by the Artifical Neural Network (ANN) classifier. In addition, Discrete Fourier Transform (DFT) and Discrete Wavelet Transform (DWT) have been applied to coal data for ANN classifiers. DFT-ANN, DWT-ANN, and ANN classification success results are compared. The highest classification success rate was found by DWT-ANN method.
AtıfScopus8OpenAlex12İncele - BildiriAçık Erişim2018Scopus SJRQ2Evaluating deep learning models for sentiment classification
Ay Karakuş, Betül; Talo, Muhammed; Hallaç, İbrahim Rıza; Aydin, Galip
Deep learning has emerged as an effective solution to various text mining problems such as document classification and clustering, document summarization, web mining, and sentiment analysis. In this paper, we describe our work on investigating several deep learning models for a binary sentiment classification problem. We used movie reviews in Turkish from the website www.beyazperde.com to train and test the deep learning models. We also report a detailed comparison of the models in terms of accuracy and time performances. Two major deep learning architectures used in this study are Convolutional Neural Networks and Long Short-Term Memory. We built several variants of these models by changing the number of layers, tuning the hyper-parameters, and combining models. Additionally, word embeddings were created by applying the word2vec algorithm with a skip-gram model on a large dataset (∼ 13 M words) composed of movie reviews. We investigate the effect of using the pre-word embeddings with these models. Experimental results have shown that the use of word embeddings with deep neural networks effectively yields performance improvements in terms of run time and accuracy.
AtıfScopus55WoS40OpenAlex64İncele - BildiriYalnız künye2018Control of fluid flow around a square prism by fluid injection at low Reynolds number
Flrat, Erhan; Tsitouras, C.; Simos, T.; King Saud University, College of Sciences, Department of Mathematics , P. O. Box 2455, Riyadh; Ural Federal University, Group of Modern Computational Methods, 19 Mira Street, Ekaterinburg
The two-dimensional wake structure behind a fixed, rigid square prism with fluid injection from the single, relatively narrow slot (h/H=0.1) has been computed at low Reynolds number (Re=ρ·U∞·H/μ=100 based on the side length of the prism and freestream velocity) using a finite volume method (FVM). Injection surface (i.e. front and rear) and injection rate (from IR=UJ/U∞=0 to 3 by 0.2 step) are the key parameters that determine the aerodynamic and flow characteristics. Two flow patterns for the prism with front jet and four flow patterns for the prism with rear jet were identified with respect to IR. Flow patterns were associated with changes in flow and aerodynamic characteristics.
AtıfOpenAlex1İncele - BildiriYalnız künye2017New Complex and Hyperbolic Function Solutions to the Generalized Double Combined Sinh-Cosh-Gordon Equation
Baskonus, Haci Mehmet; Sivasundaram, S
In this study, we have applied the improved Bernoulli sub-equation function method to the generalized double combined Sinh-Cosh-Gordon equation. This method gives new analytical solutions such as complex and hyperbolic function solutions to the problem considered in this paper. Then, we plot the three and two dimensional surfaces of analytical solutions by using Wolfram Mathematica
AtıfWoS42OpenAlex48İncele