Browsing by Author "Ekim, Pinar Oguz"

Now showing 1 - 7 of 7

Citation - WoS: 1
Citation - Scopus: 2
The Application of Kalman Filter for Lead-Acid Battery State of Charge Estimation
(IEEE, 2021) Tekkok, Sercan Cagdas; Bostanci, Bekir; Soyunmez, Mehmet Emre; Oğuz Ekim, Pınar; Ekim, Pinar Oguz
Battery systems are crucial part of the most applications which are mobile and have electronic components from autonomous mobile robots to mobile phones. Hence, it is important to keep track of the state of the battery and its health in order to make these devices reliable and also protect the battery from over discharges and overcharges. There are different methods to estimate it but not all of them applicable for mobile systems. Thus, this study discusses and compares three methods that can be used for mobile applications and batteries that are under continuous use. The coulomb counting method, the linear counting model and the extended Kalman filter with nonlinear battery model are tested with both simulated and real data with a lead acid battery.
Citation - WoS: 2
Citation - Scopus: 5
Decimal States Smart Grid Operations Concept: Technical Solution and Benefit for Renewable Energy Integration
(IEEE, 2022) Ouedraogo, Kiswendsida Elias; Ekim, Pinar Oguz; Demirok, Erhan; Oguz Ekim, Pinar
The energy transition is a global challenge that retains the attention of a wide range of stakeholders including engineers, regulators, consumers, investors, and academicians. With higher intermittent renewable energy penetration, electrification of mobility, and intensification of air conditioning demand, important stress on the power grid, resulting in overloading of distribution network infrastructures and grid stability issues may arise in near future. Various solutions such as smart metering, demand response, and energy storage have been explored, however, their cost-to-benefit ratio is still not satisfying. This paper explores a new grid operation concept named "Decimal State" grid which dynamically throttles the subscribed power to match the grid supply capability without a direct load control. A simple yet effective communication method has been built and tested to support the implementation of the decimal state grid. Also, simulations showed that decimal state grid operation can avoid power outages in both fossil fuel or fully solar powered grid with a power deficit. Further, the simulation revealed that a decimal state grid can significantly reduce the size of long-duration energy storage.
Citation - Scopus: 1
Face Detection Via Hog and Ga Feature Selection With Support Vector Machines
(Institute of Electrical and Electronics Engineers Inc., 2019) Binli M.K.; Can Demiryilmaz B.; Ekim P.O.; Yeganli F.; Can Demiryilmaz, Burak; Ekim, Pinar Oguz; Yeganli, Faezeh; Binli, Mustafa Keman
This work employs a new method of feature selection and classification of image objects by combining previous studies in literature of feature selection and classification of images. In the new algorithm, instead of sliding a window on the image and scaling the window by applying normalized cuts and image segmentation algorithms, information related to the position of objects is considered. Accordingly, the scaling of searching image window process is been exceeded. For this purpose, the obtained segments of image features extracted by employing Histogram Oriented Gradient (HOG) descriptor, which clears the images from the curse of dimensions. These extracted features optimized by applying Genetic Algorithm (GA) method, to detect faces and compared with HOG feature results. The main objective of this work is to improve the accuracy of Support Vector Machine (SVM) classifier in detail description applications. © 2019 Chamber of Turkish Electrical Engineers.
Citation - Scopus: 4
Face Detection, Tracking and Recognition With Artificial Intelligence
(Institute of Electrical and Electronics Engineers Inc., 2021) Tekkok S.C.; Soyunmez M.E.; Bostanci B.; Ekim P.O.; Bostanci, Bekir; Ekim, Pinar Oguz; Soyunmez, Mehmet Emre; Tekkok, Sercan Cagdas
Due to the COVID-19 pandemic, the face masks are mandatory everywhere so it might be beneficial to automatize the detection and tracking of whether people wear a mask or not with the help of the computer vision. Furthermore, it can be implemented on mobile robots as well. Additionally, face recognition of people is discussed with two different techniques which are based on neural networks and eigenface approach in this study. Hence, a complete system which can be used with mobile platforms has been achieved with the proposed procedure. © 2021 IEEE.
Localization With Particle Filter Based on Odometer and Uwb
(IEEE, 2020) Oğuz Ekim, Pınar; Ekim, Pinar Oguz
In this paper, the particle filter structure that uses odometer and Ultra-wide band (UWB) sensors for positioning autonomous ground vehicles used in confined spaces was investigated. Accordingly, UWB sensor packages written for Turtlebot3 libraries are mentioned. The positioning algorithm has been evaluated both in simulation environment using Robot Operating System (ROS) and in real test environment. Positioning accuracy is sufficient for practical applications, but as the number of reference sensors increases, results with better precision are obtained.
Citation - Scopus: 3
Real-Time Facial Emotion Recognition for Visualization Systems
(Institute of Electrical and Electronics Engineers Inc., 2022) Ozkara C.; Ekim P.O.; Ekim, Pinar Oguz; Ozkara, Ceren
This project aims to review the most popular deep learning algorithms and their performances in camera systems based on real-time facial emotion recognition and suggest a new model for future applications. Firstly, convolutional neural network (CNN) algorithms that recognize human emotions, such as AlexNet, GoogleNet, and VGG19, are investigated according to their performances. Then, the CNN algorithm with the best numerical performance is chosen for enhancement. After, the new hybrid model is constructed via chosen CNN and long short-term memory (LSTM). Lastly, the proposed model and face images achieved from the camera are combined to simulate real-time application. © 2022 IEEE.
Citation - WoS: 1
Tracking neighborhood closed-loop pumped hydro storage potential
(IEEE Computer Society, 2023) Ouedraogo, Kiswendsida Elias; Oğuz Ekim, Pınar; Demirok, Erhan; Ekim, Pinar Oguz
Worldwide, energy is at the center of the socio-economical, geopolitical, and climate crises. For this reason, governments, businesses, and communities are promoting green energy to boost their energy resilience and energy independence sustainably. However, the bottleneck of replacing fossil fuel power plants entirely with intermittent renewable energy remains the high cost of energy storage systems. The study explored the existence of megawatt-hours scale closed-loop pumped hydro storage reservoirs near communities' centers. A MATLAB algorithm has been developed to detect pairs of reservoirs with one, four, and nine hectares each, and a head of one to three hundred meters, corresponding to an energy capacity of 20 to 540 megawatt hours per pair. For the three cities studied, (Banfora / Burkina, Syracuse / New York, Manisa / Turkey) the results revealed the existence of more than 10.000 megawatt-hours storage capacity in each city which meets or exceeds the need of the communities. Therefore, a 100% renewable energy power grid that is resilient, and reliable, can be achieved faster by adopting distributed closed-loop pumped hydro storage which is likely to attract a large number of smaller investors. © 2023 IEEE.