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 Erişim2024Classifying induction motor faults using spectrogram images with deep transfer learning
Ertargin, Merve; Yildirim, Ozal; Orhan, Ahmet; Benedicenti, L.
For industrial systems to be reliable and efficient, motor faults detection is important. Conventional methods of fault detection are typically expensive and time-consuming. The ability to detection motor faults has advanced significantly in recent years thanks to the application of deep learning techniques. Deep learning algorithms have the ability to automatically extract complicated features from big data sets, which can speed up and improve the accuracy of motor faults detection. Since collecting motor acoustic data is cost-effective and easy, it is advantageous to use it in fault detection. In this study, motor acoustic signals were converted into spectrograms and faults in induction motors were detected using a transfer learning approach with pre-trained models. Totally 8-class fault detection was performed with an accuracy rate of 91.52% using VGG16 and 92.11% using VGG19.
AtıfScopus4OpenAlex4
İncele - BildiriYalnız künye2024Assessing Environmental Pollution and Noise Levels at End-of-Life Vehicle Recycling Centers: A Comparative Study
Harun, Zambri; Akkurt, Nevzat; Hashim, Hashimah; Molla, Altaf Hossain; Cahyadi, Mokhamad Nur; Zuhal, Lavi R.
This study investigates the environmental impact of end-of-life vehicle (EL V) recycling operations by assessing pollution parameters and noise levels at formal and informal recycling centers compared to a green zone reference area. U sing an integrated monitoring system. This research measured concentrations of particulate matter (PM2.5, PMlO), nitrogen dioxide (N02), carbon dioxide (C02), ozone (03), and noise levels at selected sites in Selangor, Malaysia. Results reveal elevated pollutant concentrations and noise levels at both formal and informal EL V recycling centers relative to the green zone reference area. Diurnal variations in pollutant levels highlight the influence of operational activities and atmospheric conditions. The findings underscore the need for stringent regulatory measures and pollution control strategies to mitigate environmental and health risks associated with EL V recycling activities and promote sustainable practices in the recycling industry.
AtıfScopus2OpenAlex2
İncele - BildiriYalnız künye2023Investigation of corrosion behavior of ZrN-based PVD coatings on Ti-29Nb-13Ta-4.6Zr alloy in Hank's solution
Ali, Leila Ait; Aslan, Naim; Yilmazer, Hakan; Niinomi, Mitsuo; Sen, Anil; Dikici, Burak; Benhala, B.; Raihani, A.; Mansouri, K.; Qbadou, M.
In this study, the TiNbTaZr (TNTZ) alloys, which do not contain toxic and allergic elements, have been coated with hard ZrN physical vapor deposition (PVD) coatings to increase their in-vitro corrosion resistance. In-vitro electrochemical behavior of the ZrN coating and uncoated TNTZ alloy was evaluated using open circuit potential (OCP) and potentiodynamic polarization (PDS) techniques, respectively. The characterizations of the coatings were carried out using scanning electron microscopy (SEM), energy dispersion spectroscopy (EDS), and X-ray diffraction (XRD). The SEM examinations showed that ZrN coating is homogeneous. Besides, ZrN coating had a higher corrosion resistance than uncoated TNTZ alloy in Hank's solution.
- BildiriAçık Erişim2023Chat with ChatGPT: Access to cultural heritage with ChatGPT
Yilmazer, Merve; Karakose, Mehmet
Cultural heritage, in the most general sense, refers to the historical accumulations from the past to the present. Digital systems are being integrated as an alternative to physical interventions for the management, maintenance and supervision of cultural heritage sites. For these purposes, advanced intelligent systems such as machine learning and deep learning are generally used. In this study, the competence of ChatGPT, an artificial intelligence robot developed by OpenAI with a high learning rate, in the field of cultural heritage is investigated. Questions such as cultural heritage, digital cultural heritage, protection of cultural heritage, etc. were asked to ChatGPT, and the timeliness and adequacy of the answers produced in response to the questions were evaluated. In addition, a comparison of experimental studies in the literature for the preservation and cultural heritage digitalization sites is also included in this study.
AtıfScopus6OpenAlex4İncele - BildiriAçık Erişim2023Yolov5 Based Fault Detection Approach in Railway Components
Yilmazer, Merve; Karakose, Mehmet
For safe transportation on the railway, the faults occurring in its components must be detected and repaired. Recently, fault detection methods have been developed on railway visual data using methods such as image processing, machine learning and deep learning. Especially since deep learning-based algorithms have a self-learning structure, the data used in model training and testing significantly affect the performance of the model. In the proposed method within the scope of this study, railway visual data were obtained using autonomous drone. YOLOv5 deep neural network is trained to detect faults that may occur in various components such as rail, fastener, sleeper and ballast in the railway. In order to increase the efficiency of the model, images obtained under different lighting conditions were included in the data set. In addition, by using the OpenCV library, the video stabilization process and the vibrations that occur during data acquisition in the video are eliminated. Thus, with the proposed method, it has been shown that the errors due to many components in the railway can be detected with a mAP rate of 94.5%.
AtıfScopus5OpenAlex3İncele - BildiriYalnız künye2022Machine Learning-Based A Comparative Analysis for Air Quality Prediction
Utku, Anil; Can, Umit
Air pollution affects human life negatively, especially in terms of health, and causes the death of millions of people every year. Today, air pollution in many regions is still above the limits indicated by the World Health Organization. In this study, the prediction of the rate of PM2.5, which is an important air pollutant, in the Beijing region of China is emphasized. For this purpose, weather prediction models were created using Random Forest Algorithm, Support Vector Regression, XGBoost and K-Nearest Neighbor Algorithm, which are popular machine learning algorithms, and the results were compared using various metrics. The best prediction result in all the metrics used was obtained with the Support Vector Regression method.
AtıfWoS2OpenAlex8İncele - BildiriYalnız künye2022Privacy Concerns and Measures in Metaverse: A Review
Canbay, Yavuz; Utku, Anil; Canbay, Pelin; Ozbudak, F.; Sagiroglu, S.; Selcuk, A.A.
Metaverse is the new buzzword in today's digital world. It is a new internet application and a new form of the social world that integrates new technologies such as; Artificial Intelligence (AI), Virtual Reality (VR), Augmented Reality (AR), Extended Reality (XR), Blockchain (BC),etc. The metaverse can be seen as a virtual world that mimics the real world. Most things that can be done in the real world, such as shopping, making new friends, attending concerts, playing games, and so on, can be done differently in Metaverse. While a person who represents himself with his presence in the real world realizes this representation in the digital world with his personal data. Hence, the Metaverse exploits personal data to create and maintain this virtual world. At this point, privacy concerns of users in Metaverse occur, and Metaverse Service Providers (MSP) should take these concerns into account. This paper focuses on privacy concerns in Metaverse, presents some measures in order to minimize these concerns, and provides a comprehensive list of personal data collected and processed in Metaverse.
AtıfScopus44OpenAlex53İncele - BildiriAçık Erişim2022Railway Condition Monitoring and Fault Detection Based on YOLOv4
Yilmazer, Merve; Karakose, Mehmet
Regular maintenance of the line is critical for safety in railway transportation, which constitutes an important part of the transportation system. Due to the high error rate of manual fault detection methods, non-contact fault detection methods have been developed. Railway switch state and level crossing faults are frequently encountered in the occurrence of train accidents. A new method based on YOLOv4 has been proposed for condition monitoring and fault detection in these rail sections. The YOLOv4 deep neural network was trained using four class label datasets consisting of real railway visual data. Model evaluated using test data. Performance evaluation was made using evaluation metrics. Experimental results showed that the model could detect correctly with 96.8% accuracy.
AtıfScopus8OpenAlex9İncele - BildiriYalnız künye2022Assessment of protective properties of glasses with the application of golmium oxide against Gamma radiation
Shirmanov, I.A.; Strugov, E.D.; Aladailah, M.W.; Tashlykov, O.L.; Abualsayed, M.I.; Askin, A.; Volkovich, V.A.; Kashin, I.V.; Smirnov, A.A.; Narkhov, E.D.
An assessment of the radiation-protective parameters of glass samples with different ratios of holmium oxide Ho2O3 was carried out using a system of libraries for computer modeling of the processes of passage of elementary particles through the Geant4 substance and the NIST XCOM database. The results of calculations of the mass attenuation coefficient and the half-attenuation layer for the samples under study at the energy of gamma radiation varying from 0.122 to 1.408 MeV are presented.
- BildiriAçık Erişim2021Control of automatic fire extinguishing operation for 5 forest areas with SCADA
Ustundag, Aybike; Gencer, Cetin
The number of forest fires has increased significantly in recent years. Interventions to forest fires from air and land are very difficult and dangerous. In addition, since these interventions are time-consuming, forest fire can spread to a much wider area. In this study, an automatic fire extinguishing system was designed using SCADA for 5 forest regions up to 5 hectares. In the event of a fire in the system, the smoke sensor in the fire area becomes active and the IP camera image in this area is displayed on the screen. The pressurized water flushing tap, which automatically rotates 360 degrees, works in the area. If desired, automatic operation can be canceled and manually adjusted water flushing tap can be operated. The system gives a warning when the tank water drops below 1 ton. The aim of this study is to automatically intervene early in any fire that may occur in the forest and to control the fire before it spreads.
AtıfScopus1OpenAlex1İncele - BildiriAçık Erişim2021Deep Neural Network Trained on Surface ECG Improves Diagnostic Accuracy of Prior Myocardial Infarction over Q Wave Analysis
Yildirim, Ozal; Baloglu, Ulas B; Talo, Muhammed; Ganesan, Prasanth; Tung, Jagteshwar S; Kang, Guson; Tooley, James; Alhusseini, Mahmood I.; Baykaner, Tina; Wang, Paul J.
Clinical screening of myocardial infarction is important for preventative treatment and risk stratification in cardiology practice, however current detection by electrocardiogram Q-wave analysis provides only modest accuracy for assessing prior cardiac events. We set out to evaluate the ability of a deep neural network trained on the electrocardiogram to identify patients with clinical history of myocardial infarction. We assessed 608 patients at two academic centers with adjudicated history of myocardial infarction. Surface electrocardiograms were used to train a neural network-based model that classifies patients with and without a history of infarction. Endpoints were assessed by clinical record review and accuracy of the model was compared against the manual assessment of pathologic Q waves. The neural network outperformed the accuracy of pathologic Q waves (62%). In training, the model accuracy converged to >98%. Validation was performed by cross-validation (k=5) with validation accuracy 71 ± 5%. Receiver-operator characteristics analysis resulted in a c-statistic of 0.730. Deep learning of a 12-lead ECG can identify features of prior myocardial injury more accurately than clinical Q-wave analysis and may serve as a valuable clinical screening tool.
AtıfScopus3OpenAlex3İncele - BildiriAçık Erişim2021Designing the Clamp System with the Emergency Braking System in the trains by using PLC and SCADA
Ustundag, Aybike; Gencer, Cetin; Paul, R.
As a result of the developments in rail technologies, the vehicles and equipment used in these systems are also developing rapidly. It is in a rapid technological development in vehicles used in rail systems. The resistance forces affecting the movement of the rail system vehicles try to prevent its movement. In addition, the incident adherence and skidding that occur during the course of the rail system vehicles play an important role in the movements of these vehicles. Calculation of forces affecting the movement of rail system vehicles and designing these vehicles accordingly is also important for the safety of these vehicles. When braking is applied on a train running at a certain speed; It stops for a certain time and distance according to road condition, braking and speed on the train. The distance traveled until braking and stopping is the braking distance. Trains have an emergency braking system, but this system locks the train wheels. In this study along with the Anti-Lock Braking System (ABS), the rail clamping system was designed with PLC and SCADA. By using the ABS used in cars on the locomotive and wagons of the train, it is aimed to lock the wheels when the train brakes and to prevent the train from derailment in case of sudden braking with the rail clamp system.
AtıfScopus7OpenAlex7İncele - BildiriYalnız künye2020The Effect of Different Noise Levels on The Performance of The Audio Search Algorithm
Köseoglu, Murat; Uyanik, Hakan
Audio fingerprint technique is a method that creates a unique and compact identity for audio data and is also used to distinguish these identities from each other. In this study, an algorithm, based on the methods used in Shazam 's audio fingerprint technique and hash functions, was developed to recognize multimedia audio files by using MATLAB software, and it was tested against noise factor of different levels. Experimental results have shown that the developed algorithm gives successful results against the noise factor. In addition, it has been understood that the preferred hash function technique has revealed satisfying results in comparison with the conventional techniques.
AtıfOpenAlex5İncele - BildiriAçık Erişim2020Speed Control of DC Motor Using Single Phase Matrix Converter
Boydak, Merve; Orhan, Ahmet; Caliskan, Abuzer
This paper focuses on speed control of DC motor using new driver circuit of Single-Phase Matrix Converter (SPMC). Changing of modulation index has been provided with closed loop PI control. Thus, the voltage applied to the armature has been controlled and rotating of motor at the desired speed has been enabled. Insulated Gate Bipolar Transistors (IGBTs) are used to perform SPMC topology. Sinusoidal Pulse Width Modulation (SPWM) technique is used to obtain switching signals. MATLAB / Simulink is used to implement simulation.
AtıfScopus3WoS3OpenAlex3İncele - BildiriYalnız künye2020Classification of Hand-Drawn Circuit Components by Considering the Analysis of Current Methods
Gunay, Mihriban; Koseoglu, Murat
In this paper, at first, existing classification methods for classifying hand drawn circuits and circuit components are briefly introduced by examining advantages and disadvantages of each classification method. The handled methods are Support Vector Machine method (SVM), nearest neighbor method (KNN) and convolutional neural network method (CNN). Then, in the experimental part of the study, four different hand-drawn circuit components, which are diode, capacitor, resistor and ac voltage source, have been tried to be classified by using CNN method which is a highly recommended classification method in literature. The classification tables and graphics have been presented for the performed study. According to the obtained results and accuracy rate, it is concluded that CNN method can be used reliably to achieve high performance in the classification of hand-drawn circuit components.
AtıfScopus5OpenAlex5İncele - BildiriAçık Erişim2020Using Buck-Boost Rectifier with Single-Phase-Matrix Converter to Reduce Switch Count Operation
Boydak, Merve; Orhan, Ahmet; Caliskan, Abuzer
Recently, the development of advanced power semiconductor devices has made widespread use of power switching circuits and other power electronics applications in commercial and industrial environments. This paper focuses on Single Phase Matrix Converter (SPMC) as a AC-DC boost rectifier and AC-DC buck rectifier. The SPMC was operated in the desired mode using a single driver circuit. Insulated Gate Bipolar Transistors (IGBTs) are used in the power circuit as switching devices to implement SPMC topology. Switching signals are obtained by Sinusoidal Pulse Width Modulation (SPWM) technique. The simulation is carried out using MATLAB / Simulink.
AtıfScopus7WoS3OpenAlex5İncele - BildiriYalnız künye2020Design factors for sustainable university campus via interval type 2 fuzzy set
Kaya, Sema Kayapinar; Erginel, Nihal; Kahraman, C.; Cevik Onar, S.; Oztaysi, B.; Sari, I.U.; Cebi, S.; Tolga, A.C.
Sustainable development has gained importance in recent years as a development model that aims to create environmental awareness for future generations within the economic and social development goals of the countries. Sustainable development is concerned with the effective and efficient use of rapidly declining natural resources for the growing population. The achievement of the goals determined in sustainable development and the transfer to the next generations is realized through sustainable education. Due to the innovative and pioneering role of universities in society, they are the most important educational institutions that contribute to the spread of a sustainable lifestyle in society. In this study, Interval Type-2 Fuzzy Quality Function Deployment (IT2_FQFD) approach was developed to improve sustainable university attributes. Firstly, the most important 12 sustainability criteria (SRs) were weighted with Interval Type-2 Fuzzy Analytic Hierarchy Process (IT2_FAHP). Then QFD approach was used to determine the importance of sustainability factor of university campus, the relations between SRs and SDs, and the correlations matrix among SDs via interval type-2 fuzzy sets. After that, the design attributes were ranked with fuzzy trade-off method. The fuzzy trade-off is a novel ranking method covering all of the solution space in order to find an optimal solution in decision-making problems with conflict criteria. This paper is the first study that presents a new method of combined IT2_FQFD and IT2_FAHP, which evaluates the sustainable university model considering the needs of student and academicians. As a result of this study, the most appropriate SDs were determined and ranked according to their importance level.
AtıfScopus2OpenAlex2İncele - BildiriYalnız künye2020Performance Evaluation of Different Window Functions for Audio Fingerprint Based Audio Search Algorithm
Uyanik, Hakan; Koseoglu, Murat
Window functions are structures that are frequently used to increase the quality of the transformation when processing the signal in the time-frequency domain, especially when creating the spectrogram of the signal. In calculations for frequency information, Fourier transforms of short-time samples of the signal are transformed into spectrogram data with the help of window functions, and then operations are performed by using these data. In this study, the performance of three different window functions, which are used in obtaining spectrogram data in the algorithm developed for audio fingerprint-based audio recognition, have been tested under different artificial noise conditions. The results of these three different window functions were compared graphically, and a truth table was obtained based on the analyzed database. As a result of the simulations carried out in MATLAB, it has been observed that the hanning window function gives better spectral results for different noise levels, and accordingly it produces better matching results compared to the other two window functions as reported in former studies on different applications. In addition, some improvements about window length have been added into algorithm to obtain better results.
AtıfScopus12OpenAlex10İncele - BildiriYalnız künye2020Scopus SJRQ3Dynamic Features Spaces and Machine Learning: Open Problems and Synthetic Data Sets
Kaya, Sema Kayapinar; Navarro-Arribas, Guillermo; Torra, Vicenç; Huynh, V.; Entani, T.; Jeenanunta, C.; Inuiguchi, M.; Yenradee, P.
Dynamic feature spaces appear when different records or instances in databases are defined in terms of different features. This is in contrast with usual (static) feature spaces in standard databases, where the schema of the database is known and fixed. Then, all records in the database have the same set of variables, attributes or features. Dynamic feature mining algorithms are to extract knowledge from data on dynamic feature spaces. As an example, spam detection methods have been developed from a dynamic feature space perspective. Words are taken as features and new words appearing in new emails are, therefore, considered new features. In this case, the problem of spam detection is represented as a classification problem (a supervised machine learning problem). The relevance of dynamic feature spaces is increasing. The large amounts of data currently available or received by systems are not necessarily described using the same feature spaces. This is the case of distributed databases with data about customers, providers, etc. Industry 4.0, Internet of Things, and RFIDs are and will be a source of data in dynamic feature spaces. New sensors added in an industrial environment, new devices connected into a smart home, new types of analysis and new types of sensors in healthcare, all are examples of dynamic feature spaces. Machine learning algorithms are needed to deal with these type of scenarios. In this paper we motivate the interest for dynamic feature mining, we give some examples of scenarios where these techniques are needed, we review some of the existing solutions and its relationship with other areas of machine learning and data mining (e.g., incremental learning, concept drift, topic modeling), we discuss some open problems, and we discuss synthetic data generation for this type of problem.
AtıfScopus4WoS3OpenAlex3İncele - BildiriYalnız künye2020Classification of Hand-Drawn Basic Circuit Components Using Convolutional Neural Networks
Gunay, Mihriban; Koseoglu, Murat; Yildirim, Ozal
In this paper, the Convolutional Neural Network (CNN) architecture, which is one of the deep learning architectures, is used to classify the basic circuit components drawn by hand. During the training and testing stages of the model, a new dataset containing images of 863 circuit components manually drawn by different people is created. The data set contains images of four different classes of circuit components such as resistor, inductor, capacitor and voltage source. All images have been fixed to the same size and converted to grayscale to increase recognition performance and reduce process complexity. In the study, training for four classes is performed with CNN architecture. Based on the CNN architecture, four new CNN models are employed with different the number of layers. The training and validation results of these models are compared separately, the model with the highest training and validation performance is observed with four layer CNN model (CNN-4). This model obtained 84.41% accuracy rate at classification task.
AtıfScopus16WoS5OpenAlex17İncele