Sürdürülebilir Kalkınma Amaçları
Yazarlar
- Turk, Kadir(7)
- Akinoglu, Bulent G.(6)
- Bingol, Ozkan(5)
- Ozden, Talat(5)
- Simsek, Cemaleddin(5)
- Albayrak, Cenk(4)
- Basoglu, Mustafa Engin(4)
- Dogan, Ramazan Ozgur(4)
- Ekinci, Murat(4)
- Herencsar, N.(4)
- Kayikcioglu, Temel(4)
- Dogan, Hulya(3)
- Gedikli, Eyup(3)
- Yanarates, Cagfer(3)
- Özden, Talat(3)
- Altan, Aytac(2)
- Altas, Ismail H.(2)
- Benli, Emrah(2)
- Cakmak, Recep(2)
- Demirbag, Kubra Simsek(2)
- Essaaidi, M.(2)
- Genemo, Musa Dima(2)
- Gul, Fatih(2)
- Kucuk, Mehmet Ali(2)
- Maleki, Masoud(2)
- Manshouri, Negin(2)
- Motai, Yuichi(2)
- Sreeram, G.(2)
- Tonyali, Samet(2)
- Tugcu, Emin(2)
- Turan, Raşit(2)
- Ture, Hayati(2)
- Yazgan, Ayhan(2)
- Yildirim, Nihan(2)
- Zaz, Y.(2)
- Aiordachioaie, D.(1)
- Akkaya, Kemal(1)
- Aklnoǧlu, Bülent Gültekin(1)
- Akmoǧlu, Bülent Gültekin(1)
- Akyurek, Feyzullah(1)
Yayınlar
- BildiriYalnız künye2023Pedestrian Inertial Navigation with Multi-Head CNN
Cetin, Gokhan; Kucuk, Mehmet Ali; Koroglu, Muhammed Taha
Traditional pedestrian dead-reckoning (DR) methods utilizing inertial measurement units (IMU) have been successfully employed in GPS-denied environments over the past two decades. However, despite continuous advancements in wearable IMU technology, the long-term solution still suffers from the issue of drift. In light of this, Deep Learning (DL) has emerged as a potential candidate for inertial navigation solutions, leveraging its powerful non-linear regression capabilities. Recent research has demonstrated that DL models trained on public datasets can effectively serve as end-to-end solutions. Most studies focus on smartphones, where the IMU is typically situated at the torso, and generally work with transformed data represented in the navigation coordinate frame to estimate pedestrian velocity and heading change at rates lower than the IMU sampling rate. In contrast, this study uses raw foot-mounted IMU data as input to a multi-headed structure consisting of independent convolutional neural networks (CNNs) and targets displacement directly and heading change. The proposed model is trained on a publicly available foot-mounted IMU dataset where pseudo ground-truth (GT) data is generated heuristically to provide supervision for the learning process. The results indicate that the Multi-Head CNN (MHCNN) model is capable of producing pedestrian trajectories at the IMU sampling rate, with positioning errors of less than 2m throughout the duration of the walks. The code for the trained network can be accessed in the associated repository, i.e., github.com/mtkoroglu/PIN-MHCNN.
- BildiriYalnız künye2023An Efficient 1D Autoencoder-Based Approach for R-Peaks Detection in Electrocardiogram Signals
Dogan, Ramazan Ozgur; Dogan, Hulya; Kayikcioglu, Temel
Electrocardiogram (ECG) signal which is composition of multiple segments such as P-wave, QRS complex and T-wave plays a crucial role in evaluating human heart cardiac diagnosis. For an analysis of cardiac diagnosis, it is required that clinicians scan the ECG signal for R-peaks (the highest peak of the QRS complex) detection, which relies on their expertise and takes enormous time. In order to provide more realistic treatment of cardiovascular diseases in the ECG signal with noises and different characteristics, computer-based R-peaks detection approaches have been actively developed in the research article for many years and generally compose of two major operations; preprocessing and decision. Contrary to previous approaches which require high computational costs and complexity, appropriate initial parameters, a novel CNN based approach is presented for R-peaks detection in this paper. Both qualitative and quantitative analysis are performed in the real ECG signal taken from typical MIT-BIH arrhythmia database. In order to validate the success of the recommended approach, total 18 different R-peaks detection approaches reported in the literature are compared by utilizing performance evaluation metrics. Average values of sensitivity, positive predictivity, error rate, accuracy and f-score are computed as 99,96%, 99,95%, 0,09%, 99,90% and 99,95% respectively, which are the best values among well-established studies for R-peaks detection. It is demonstrated with qualitative and quantitative results that better performance is achieved by our suggested approach.
- BildiriYalnız künye2023Analysis Of The Performance Of The Distributed Maximum Power Point Tracking In Building Integrated Photovoltaic Systems
Basoglu, Mustafa Engin; Aiordachioaie, D.
Building-integrated/applied photovoltaic (PV) systems have been widespread recently in terms of electrical energy generation in buildings. These systems are applications with much lower power than land type large-scale systems, addressing the area/building where they are installed rather than centralized production. In this framework, maximum power point (MPP) tracking (MPPT) approaches at module level and sub-module level, balcony railing, Carport or solar tile etc. will be investigated in terms of building integrated PV systems (BIPV). Solar panels act as a building material, insulation material and energy generator in BIPV applications. In building-applied (BAPV) examples, the solar panel is mounted on the building. However, there is no difference between BIPV and BAPV in terms of electrical model. A unique method will be developed for MPPT at module level and sub-module level for such applications. Depending on the power processing strategy in the optimizer power stage, amplifier, synchronous reducer or bidirectional differential power processing topologies will be examined and the most suitable power converter for the module and sub-module level will be determined. Technically, comparisons of the performances of MPPT strategies were made in the MATLAB/Simulink program at the central, module level or sub-module level, and it was shown that the power that can be obtained from the PV module or sub-module increases with the MPPT at the module and sub-module level.
- BildiriAçık Erişim2023Saw-YOLOv5: Scale-Aware YOLOv5 for Object Detection in Aerial Images
Doruk, Abdullah Enes; Algul, Mucteba; Akyurek, Feyzullah; Alpaydm, Osman Kursat; Uslu, Fatmatulzehra
The detection of objects in aerial images is impor-tant for many real world problems related to military defense, transportation, and etc. However, this is a challenging task as a result of the presence of various scales of objects in the same image, the large variety of contexts across aerial images, various brightness levels due to image acquisition at different times of the day and so on. To address these challenges, this paper introduces Saw-YOLOv5 for object detection in aerial images. Saw-YOLOv5 is a deep network based on YOLOv5, which was proposed for object detection in natural images. Saw-YOLOv5 extends YOLOv5 with the addition of several attention modules in its design. The results of our experiments, conducted on the aerial dataset delivered by the Turkey Technology Team for the Artificial Intelligence in Transportation Competition, showed that Saw-YOLOv5 outperforms previous methods, particularly for pedestrian detection, by yielding a mean mAP of 80.23% over all objects.
- BildiriYalnız künye2023A Hybrid CNN-LSTM Framework for Unsupervised Anomaly Detection in Water Distribution Plant
Sahin, Ali Kivanc; Cavdar, Bora; Dogan, Ramazan Ozgur; Ayas, Selen; Ozgenc, Busra; Ayas, Mustafa Sinasi
To reduce potential threats to public health and economic losses, water distribution systems, which are critical parts of industrial control systems, require accurate and effective anomaly detection. The successful incorporation of machine learning models into anomaly detection procedures has been made possible by recent developments in computer science. In this research, a hybrid CNN-LSTM framework for anomaly detection in water distribution systems is presented using Python programming language in the JupyterLab environment. The performance of the proposed CNN-LSTM network model is carefully evaluated on the publicly available WADI dataset, which contains several types of attacks for a water distribution testbed, using a statistical window-based anomaly detection approach. The experimental results show acceptable precision, recall and F1 scores of 0.8619, 0.7041, and 0.775, respectively, demonstrating the efficiency of the framework in detecting anomalies in the water distribution system.
- BildiriYalnız künye2023Performance Evaluation of Quantum-Resistant TLS for Consumer IoT Devices
Bozhko, Jessica; Hanna, Yacoub; Harrilal-Parchment, Ricardo; Tonyali, Samet; Akkaya, Kemal
Post-quantum (PQ) cryptographic algorithms are currently being developed to be able to resist attacks by quantum computers. The practical use of these algorithms for securing networks will depend on their computational and communication efficiency. In particular, this is critical for the security of wireless communications within the context of consumer IoT devices that may have limited computational power and depend on a constrained wireless bandwidth. To this end, there is a need to evaluate the performance of widely used application layer security standards such as transport layer security (TLS) to understand the use of the existing PQ algorithms that are being evaluated by NIST as a replacement to the current cryptographic algorithms. This paper focuses on two widely used IoT standards Bluetooth Low Energy (BLE) and WiFi to find out the optimal performing PQ algorithm for their security when used in end-to-end connections over the Internet. By implementing the capability for IP over BLE and all options of TLS connection establishment, we developed a client-server IoT testbed to measure the efficiency of PQ key encapsulation mechanisms (KEMs) and PQ digital signature algorithms. The test results showed that Kyber512 is the ideal KEM while Falcon-512 and Dilithium2 are the best signatures for BLE and WiFi devices. Based on this outcome, we developed a mechanism for IoT devices with multiple communication interfaces, that dynamically chooses a PQ KEM algorithm based on the MAC layer protocol being used at the time.
- BildiriYalnız künye2023Recoil Stabilization of Two-Wheeled Robot Through Control Moment Gyroscope (CMG)
Unker, Faruk
In this study, the weapon and gyroscopes mounted on the armored two-wheeled robot have been studied for controlling recoil dynamics. To date, the interaction between recoil energy and control moment gyroscope (CMG) has not been investigated for a two-wheeled robot. Therefore, this study will be interesting academic research in the dynamic response and control strategy of a CMG subjected to recoil impulsive loads resulting from firing the weapon. The first aim of this study is to maintain the stabilization of the robot within the CMG limits when subjected to impulsive loads without needing the allowable stroke as being for a hydraulic damper. Equations of motion and the correlation between the shot recoil and angular momentum are derived by the Lagrangian method and simulated by Matlab. Then RecurDyn model of the two-wheeled robot is used to control and analyze dynamic parameters under applied recoil energy. As a result, the comparison of RecurDyn simulation and Matlab data are extremely exact and the Lagrangian equations can be used to obtain optimal parameters of the two-wheeled robot concerning the correlation between gyroscopes and weapon.
- BildiriAçık Erişim2022Performance Evaluation of TLS 1.3 Handshake on Resource-Constrained Devices Using NIST's Third Round Post-Quantum Key Encapsulation Mechanisms and Digital Signatures
Saribas, Sultan; Tonyali, Samet
Towards the end of the 20. century, quantum computing came into sight by the main effect of Shor's Algorithm. While this algorithm offers a solution for the factorization problem, which makes it exponentially faster, it alongside becomes a critical threat for the encryption schemes since mostly their security mechanisms rely on the difficulty of integer factorization or discrete log problems. Despite it is not known when advanced quantum computers will show up, yet, once it is developed, most existing cryptography will be rendered useless, which means all existing information security will be vulnerable. Owing to this risky situation, The National Institute of Standards and Technology (NIST) launched post-quantum cryptography (PQC) standardization process for the development of PQC schemes. In this paper, we have chosen three key encapsulation mechanisms and two digital signature algorithms with different parameter sets from the round three submissions. We measured their TLS 1.3 handshake performance using two resource-constrained devices and compared it to that of classical encryption and digital signature schemes. Experiment results showed that post-quantum algorithms come with an extra message overhead while their handshake delay values are promising.
- BildiriAçık Erişim2022Is COVID-19 Friend or Foe to Industry 4.0: Experiences of Turkish White Goods Suppliers
Demirbag, Kubra Simsek; Yildirim, Nihan
This study, in the two years since the beginning of the COVID-19 pandemic, reveals the most focused issues by the Turkish white goods suppliers regarding Industry 4.0 and the challenges encountered while engaging in Industry 4.0 practices. The data were obtained through a questionnaire form participated by the managers of 36 different companies that are members of the Turkish White Goods Suppliers Association. The collected data were classified, and it was found that the most focused issues of the companies were technology investments, ERP and MES, data collection, business processes, investment plans, organizational transformation, occupational health and safety, and participation in Industry 4.0-related events, respectively. Moreover, the most common challenges companies face concerning Industry 4.0 are related to the not being able to come together, finance, technology providers, postponement of investment plans, and loss of employees. On the other hand, 16% of the participating companies stated that they did not encounter any difficulties.
- BildiriYalnız künye2020Nine Years Long Term Performance and Degradation Assessment of Two On-Grid PV Systems
Ozden, Talat; Ozgun, Ensar Mesut; Keles, Bedirhan; Akinoglu, Bulent G.
Nine years outdoor testing of the two on-grid PV systems at Central Anatolia under the same ambient conditions is very important to be discovered toward transition to renewables. The systems consist of a monocrystalline silicon and micro-crystalline silicon based amorphous thin film PV technologies. The analyses are carried out on monthly based using the outdoor efficiencies. In addition, degradation rates of these systems are calculated and compared with each other and also with international literature. It is also compared the results using the degradation rates of an earlier study carried out using measurements of a shorter period of time.
- MakaleYalnız künye2020Robust Detection of Infrared Maritime Targets for Autonomous Navigation
Wang, Bin; Benli, Emrah; Motai, Yuichi; Dong, Lili; Xu, Wenhai
This paper addresses a problem on infrared maritime target detection robustly in various situations. Its main contribution is to improve the infrared maritime target detection accuracy in different backgrounds, for various targets, using multiple infrared wave bands. The accuracy and the computational time of traditional infrared maritime searching systems are improved by our proposed Local Peak Singularity Measurement (LPSM)-Based Image Enhancement and Grayscale Distribution Curve Shift Binarization (GDCSB)-Based Target Segmentation. The first part uses LPSM to quantize the local singularity of each peak. Additionally, an enhancement map (EM) is generated based on the quantitative local singularity. After multiplying the original image by the EM, targets can be enhanced and the background will be suppressed. The second part of GDCSB-Based Target Segmentation calculates the desired threshold by cyclic shift of the grayscale distribution curve (GDC) of the enhanced image. After binarizing the enhanced image, real targets can be segmented from the image background. To verify the proposed algorithm, experiments based on 13,625 infrared maritime images and five comparison algorithms were conducted. Results show that the proposed algorithm has solid performance in strong and weak background clutters, different wave bands, different maritime targets, etc.
- BildiriYalnız künye2020Duplicated Audio Segment Detection with Local Binary Pattern
Kucukugurlu, Busranur; Ustubioglu, Beste; Ulutas, Guzin; Herencsar, N.
Due to the advantages of convenience, and difficulty of detection, copy-move forgery is one of the most common audio forgery forms. It is significant to decide whether there is a duplicated segment in the audio. In order to detect copy-move forgery, a new method is proposed in this paper. In the proposed algorithm, first the audio is segmented into syllables using a pitch tracking method. Second, each syllable analyzed with a 1-D local binary pattern operator. This operator calculates the histogram of each syllable. Mean square error is used to compute the similarities of histograms. The syllables which have similar histograms are detected as forged audio segments. Compared to another 1-D local binary pattern method, the proposed method has better detection results for copy-move forgery. Our experiments show that the proposed algorithm is feasible and effective, and robust against many common postprocessing operations such as noise addition, filtering, and compression.
- MakaleYalnız künye2020Visual Perception for Multiple Human-Robot Interaction from Motion Behavior
Benli, Emrah; Motai, Yuichi; Rogers, John
Visual perception is an important component for human-robot interaction processes in robotic systems. Interaction between humans and robots depends on the reliability of the robotic vision systems. The variation of camera sensors and the capability of these sensors to detect many types of sensory inputs improve the visual perception. The analysis of activities, motions, skills, and behaviors of humans and robots have been addressed by utilizing the heat signatures of the human body. The human motion behavior is analyzed by body movement kinematics, and the trajectory of the target is used to identify the objects and the human target in the omnidirectional (O-D) thermal images. The process of human target identification and gesture recognition by traditional sensors have problem for multitarget scenarios since these sensors may not keep all targets in their narrow field of view (FOV) at the same time. O-D thermal view increases the robots' line-of-sights and ability to obtain better perception in the absence of light. The human target is informed of its position, surrounding objects and any other human targets in its proximity so that humans with limited vision or vision disability can be assisted to improve their ability in their environment. The proposed method helps to identify the human targets in a wide FOV and light independent conditions to assist the human target and improve the human-robot and robot-robot interactions. The experimental results show that the identification of the human targets is achieved with a high accuracy.
- BildiriYalnız künye2019Realization of a low cost and fast boost converter based MPPT for PV system
Basoglu, Mustafa Engin
Photovoltaic (PV) modules have a small power conversion efficiency since material technologies used in commercial PV modules is weak and not well developed. In order to provide the maximum available efficiency in a PV module, a power processing unit (PPU) is connected between PV module and load to extract more power from PV modules In other words, DC-DC converters are used for impedance matching between PV module and load in any kind of loading and environmental conditions. Several maximum power point tracking (MPPT) algorithms have been proposed in the literature. But there are still shortcomings to be improved such as reducing the steady state ripples in power, dynamic response time under changing conditions. In this paper, design steps of the boost converter for an MPPT application have been presented and some experiments have been performed. Consequently, a low cost and fast boost converter based MPPT is implemented.
- MakaleYalnız künye2019Circuit implementation of nano-scale TiO2 memristor using only metal-oxide-semiconductor transistors
Gul, Fatih
A metal-oxide-semiconductor (MOS)-based circuit model that emulates a TiO2 memristor is proposed in this study. First, a TiO2 (10-nm active layer thickness)-based memristor device was fabricated. The structural properties of the device were confirmed via energy dispersive X-ray spectroscopy. The memristive characteristics of the device were resolved by applying a time-dependent voltage. The typical pinched hysteresis memristive loops of the current-voltage curves were obtained. After physical implementation and characterization of the device, a circuit model was implemented using only four MOS transistors to emulate the fabricated TiO2 memristor. In addition to emulating the fabricated memristor, the proposed circuit model is suitable for use in general memristor-based applications. No active element or circuit blocks were used in the circuit to achieve memristive characteristics. The simulation and experimental results are in good agreement; moreover, the circuit is very simple compared to those presented in previous studies in the literature and it was able to emulate the fabricated memristor. All simulations were completed using 180 nm TSMC CMOS process parameters.
- BildiriYalnız künye2019Object-based classification of Izmir Metropolitan City by using sentinel-2 images
Ozlem Yilmaz, Elif; Varol, Beril; Hale Topaloglu, Raziye; Sertel, Elif; Menekay, S.; Cetin, O.; Alparslan, O.
This study aims to create Land Cover Land Use (LCLU)map of a part of the Izmir metropolitan city in Turkey, based on an enhanced Urban Atlas nomenclature and object based classification approach. Multi-temporal Sentinel-2 images from different seasons are used and rule-based object oriented classification techniques are applied on the images. Totally 20 LCLU classes are identified in the study area with different accuracy values. Thematic open source data were also integrated into classification to better identify some land use classes and to increase the total classification accuracy. Our results show that 10-m bands of Sentinel-2 images are capable to produce thematically detailed LCLU map with an overall accuracy of 86% and 0.852 Kappa values.
- MakaleYalnız künye2019An improved 0.8 V OC model based GMPPT technique for module level photovoltaic power optimizers
Basoglu, Mustafa Engin
Photovoltaic modules may experience some mismatching conditions that affect their available power capacity, causing inefficient maximum power point tracking (MPPT). Furthermore, their power-voltage (P-V) characteristic curve becomes a multi-peak structure in such conditions owing to the presence of bypass diodes included since every part of the modules may receive different solar irradiance. By taking into account these facts, this paper introduces an improved global MPPT technique comprising 0.8 V OC model and the limited and adaptive scan approach. The proposed technique eliminates the requirement of some threshold value, leading to unreliable operation which the classical 0.8 V OC model based studies suffer from. Furthermore, the tracking time has been reduced substantially with the proposed technique by limiting scanning interval. Performance of the proposed technique has been verified by experimental studies and compared with classical 0.8 V OC model and a full scanning technique, which have been already presented in the literature. Experimental results show that the proposed technique is simple to be implemented and it has better performance than classical 0.8 V OC model, full scanning, and perturb and observe algorithms. Therefore, the proposed technique is feasible and it can be used technically in module level distributed MPPT (DMPPT) applications.
- BildiriYalnız künye2019Design of a MATLAB GUI for Day Ahead Forecasting of PV Panel Power
Bektas, Sibel Cevik; Cakmak, Recep; Altas, Ismail H.
This paper introduces design and utilization of a MATLAB graphical user interface (GUI) platform to forecast day ahead hourly Photovoltaic (PV) panel power by using forecasted day ahead global horizontal solar radiation. This platform, which would be a useful and practical tool for researchers who are study on energy management, planning and forecasting studies, consists of three parts. The first part predicts day ahead global horizontal solar radiation by trained artificial neural network (ANN) model. The second part performs the calculation of solar irradiation on the module, which has a tilted angle according to forecasting solar radiation data. The last part estimates the power generated by PV panel according to the calculated incident radiation. In this study, the solar irradiation forecasting, the calculation of incident radiation to tilted module and prediction of the solar power to be generated by the PV module are done. The designed GUI has been utilized to forecast solar radiation and PV output power for test days. Then obtained forecasted data have been evaluated with mean absolute percentage error (MAPE) and correlation coefficient (R).
- BildiriYalnız künye2019Module Level Global Maximum Power Point Tracking Strategy
Basoglu, Mustafa Engin
Partial shading of photovoltaic (PV) modules can occur at any time due to the obstacles such as chimney, tree, antenna, bird flock etc. Due to such obstacles, the entire surface of the PV module cannot receive an equal amount of irradiance; Therefore, PV modules cannot operate at its maximum power point (MPP). In this paper, an improved version of a 0.8VOC model based global maximum power point tracking (GMPPT) strategy has been proposed. Single ended primary inductance converter (SEPIC) is used as a power converter between PV module and load. Effectiveness of the proposed technique is presented by experimental studies with the comparison of a full scanning approach. Results of experimental studies show that proposed GMPPT strategy outperforms than full scanning based algorithm known.
- BildiriAçık Erişim2018Thermal modeling and verification of pv module temperature and energy yield using outdoor measurements for Ankara, Turkey
Tuncel, Bilge; Akinoglu, Bulent G.; Ozden, Talat; Balog, Robert S.
Ankara is in the Central Anatolia region of Turkey where the climate is dry-continental with an annual solar insolation of around 1750 kWh/m 2 . In the transition to renewable energy, detailed analyses are required to ensure effective and economic utilization of the available solar resource. An essential part of these analyses is to calculate expected energy yield. For photovoltaic (PV) systems, this includes the effect of temperature on the PV efficiency, which determines the power yield of the PV modules. In this study, a first-principles thermal modeling approach is improved by adding the speed and direction of wind across the PV module into a forced convection term as well as including the temperature dependency of the module conversion efficiency. The analytical model is based on the principle of conservation of energy and uses meteorological data that are readily available from most state meteorological services. The mathematical analysis is suitable to predict the performance of a proposed PV installation without the time and expense of installing and monitoring a pilot system. The mathematical model is compared against measured data from the METU-GUNAM Outdoor Test Facility in Ankara to validate the methodology. Preliminary analyses showed that the model performs well especially during sunrise and sunsets shoulders of the diurnal cycle with a deviation of only a few W/m 2 for the electrical power yield and about 2°C for the module temperature. However, these deviations could become as large as 12 W/m 2 and 8°C at solar noon which suggests that the model still requires further improvement. In general, this error was found to be less that obtained by using basic explicit correlation methods and offers the advantage that it can be used for other geographical environments for which insolation and meteorological data is available without needing to construct a test-site.