136 results
Search Results
Now showing 1 - 10 of 136
Conference Object Deep Learning and Current Trends in Machine Learning(Institute of Electrical and Electronics Engineers Inc., 2018) Bostan,A.; Ekin,C.; Sengul,G.; Karakaya,M.; Tirkes,G.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. © 2018 IEEE.Conference Object Citation - Scopus: 2Enhancing Image Resolution With Generative Adversarial Networks(Institute of Electrical and Electronics Engineers Inc., 2022) Yildiz,B.Super-resolution is the process of generating high-resolution images from low-resolution images. There are a variety of practical applications used in real-world problems such as high-definition content creation, surveillance imaging, gaming, and medical imaging. Super-resolution has been the subject of many researches over the past few decades, as improving image resolution offers many advantages. Going beyond the previously presented methods, Generative Adversarial Networks offers a very promising solution. In this work, we will use the Generative Adversarial Networks-based approach to obtain 4x resolution images that are perceptually better than previous solutions. Our extensive experiments, including perceptual comparison, Peak Signal-to-Noise Ratio, and classification success metrics, show that our approach is quite promising for image super-resolution. © 2022 IEEE.Conference Object Citation - Scopus: 1Multiple Underwater Target Bearing Tracking Using Member Filter;(Institute of Electrical and Electronics Engineers Inc., 2018) Gunes,A.; Guldogan,M.B.Underwater acoustic vector sensors (AVS) are devices which can measure scalar pressure and three dimensional acceleration or particle velocity with only one sensor. By using these four measurements, target detection and tracking is possible. In case multiple targets exist, multi-target detection and tracking methods must be applied. Because these methods are more general, the algorithms are more involved and complex. In this framework, multi-target multi-Bernoulli (MeMBer) is a promising filter based on random finite sets (RFS) for multi-target tracking problems. In this work, for the first time in the literature, MeMBer filter is analyzed using a single underwater acoustic vector sensor in a scenario including two targets. Simulation results indicate that MeMBer filter can successfully track the targets. © 2018 IEEE.Conference Object Citation - Scopus: 8Parking space occupancy detection using deep learning methods;(Institute of Electrical and Electronics Engineers Inc., 2018) Akinci,F.C.; Karakaya,M.This paper presents an approach for gathering information about the availabilty of the parking lots using Convoltional Neural Network (CNN) for image processing running on an embedded system. By using an eflicent neural network model, we made it possible to use a very low cost embedded system compared to the ones used in previous works on this topic. This efficient model's performance is compared to one of the models that proved its accuracy in image classification competitions. In these tests, we used datasets that has thousands of different images taken from parking lots in different light and weather conditions. © 2018 IEEE.Conference Object Citation - Scopus: 8Simulation-Based Environments for Surgical Practice(Institute of Electrical and Electronics Engineers Inc., 2017) Dalveren,G.G.M.; Çağıltay,N.E.; Özçelik,E.; Maraş,H.Modeling and simulation environments provide several insights about the real situations such as endoscopic surgery. Endoscopic surgery requires both hand skills, so, understanding the effect of using dominant or non dominant hand on mental workload is important to better design, develop and implement modeling and simulation environments to support real-life implementations of surgical procedures. This experimental study presents a simulation application of eye-tracking approach to understand mental workload in different hand conditions: dominant hand, non-dominant hand and both hand. The results of the study show that, performing simulated surgical tasks by both hands compared to dominant hand, increases mental workload which is evident by higher pupil size. Accordingly, to manage the mental-load problems of surgeons while performing complex tasks that require both hand usage simulation-based environments can be used. Consequently, collection of detailed information such as eye-data, can give several insights about the behaviors of the surgeons. Also, their required skills can be improved by development of simulation and training environments. © 2017 IEEE.Conference Object Microstrip Antennas for Wimax Applications;(Institute of Electrical and Electronics Engineers Inc., 2015) Demirci,T.; Caliskan,F.; Aydin,E.In this paper, four different antenna types have been designed to be used for WiMAX applications. These antennas have been designed using HFSS simulation software. This paper has included the return loss and the radiation pattern of the designed antennas. Using the simulation results, it is shown that these four antennas are working on Wi-Fi and WiMAX frequency ranges. © 2015 IEEE.Conference Object Citation - Scopus: 2Detecting Errors in Automatic Image Captioning by Deep Learning;(Institute of Electrical and Electronics Engineers Inc., 2021) Karakaya,M.Automatic tagging of images is an important researcli topic in tlie field of image processing. Anotlier area similar to this is the automatic generation of picture captions. In this study, a deep learning model that automatically tags the pictures is used to detect errors in image captions. As a result of the initial experiments, it is observed that the proposed system can find up to 80% of the errors in the image captions. © 2021 IEEEConference Object Citation - Scopus: 1A Distributed Smart Pev Charging Algorithm Based on Forecasted Mobility Energy Demand(Institute of Electrical and Electronics Engineers Inc., 2017) Kisacikoglu,M.C.; Erden,F.; Erdogan,N.This study proposes a new distributed control strategy for the grid integration of plug-in electric vehicles. The proposed strategy consists of two stages: (i) an offline process to determine an aggregated reference charge power level based on mobility estimation and base load profile, and (ii) a real-time operation based on the distributed control approach. The control algorithm manages PEV charge load profiles in order to flatten the residential distribution transformer loading while ensuring the desired state of the charge (SOC) level. The proposed algorithm is tested on real distribution transformer loading data, and compared with heuristic charging scenarios. The numerical results are presented to demonstrate the impact of the proposed algorithm. © 2016 IEEE.Conference Object Citation - Scopus: 4Software engineering issues in big data application development(Institute of Electrical and Electronics Engineers Inc., 2017) Karakaya,Z.Big Data has become one of the most important concepts that is being studied in Computer/Software Engineering. The data produced in recent years have increased rapidly and exponentially, necessitating the solution of major problems such as the collection, processing and storage of huge volume of data. Big Data Frameworks are developed specifically to solve these problems that facilitates application developers by providing opportunities to collect, process, manage, monitor and analyze these data. A few examples of these frameworks are Hadoop, Spark, Storm, and Flink, which are developed by Software Engineers as open source projects. Although the challenges raised from coordination of IT resources such as huge amounts of computation power, storage area, memory, and network bandwidth in a distributed manner solved by these frameworks, there still remains many Software Engineering problems in application development phase, even if they based on these frameworks. High scalability, fault tolerance, flexibility, reliability and testability can be listed as the main issues need to be carefully considered in terms of Software Engineering. In this paper, we first clarify the terms Framework-Application, and then the overview information about Big Data and related frameworks are given before emphasizing the problems arising in terms of Software Engineering. Nevertheless, we tried to provide guidance to the people who would develop software for Big Data and tried to give the further research guidance. © 2017 IEEE.Conference Object Citation - Scopus: 4Convolution Neural Network (cnn) Based Automatic Sorting of Cherries(Institute of Electrical and Electronics Engineers Inc., 2021) Park,H.; Khan,M.U.Cherries are spring fruits enriched with nutrients, and are easily available in food markets around the world. Due to their excess demand, many enterprises solely focused on their processing. Cherries are especially susceptible to pathological-, physiological-diseases and structural degradation due to their soft outer skin. The post-harvest life of the fruit is limited by various characteristics. The agricultural industry has also been at the forefront to get benefits from the advanced machine learning tools. This study presents an image processing-based system for sorting cherries using the convolutional neural network (CNN). For this study, Prunus avium L cherries of export quality, available in Turkey, tagged as ‘0900 Ziraat’, are used. Surprisingly, there exists no dataset for these cherries; hence, we developed our dataset. Through the proposed approach based upon U-Net, the binary classification accuracy of 99% is achieved. Clear identification is demonstrated by the test results of varying mixture ratios of good and bad cherries. It can therefore be said that for cherry sorting and grading, U-Net can be applied as a reliable and promising machine learning tool. ©2021 IEEE
