Browsing by Author "Yeganli, Faezeh"

Now showing 1 - 3 of 3

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 - WoS: 9
Citation - Scopus: 16
The Lidar and Uwb Based Source Localization and Initialization Algorithms for Autonomous Robotic Systems
(Institute of Electrical and Electronics Engineers Inc., 2019) Bostanci B.; Tekkok S.C.; Soyunmez E.; Oguz-Ekim P.; Yeganli F.; Bostanci, Bekir; Yeganli, Faezeh; Soyunmez, Emre; Oguz-Ekim, Pinar; Tekkok, Sercan
This paper covers the source localization algorithm based on the least squares techniques and the squared range measurements obtained from ultra-wide band (UWB) sensors to locate the robot in an indoor environment. Additionally, the initialization algorithm which is based on light detection and Ranging (LiDAR) scans is proposed. It takes the advantage of the estimated location to find the initial orientation of the robot with respect to the previously obtained map. Thus, the crucial problem of the autonomous initialization and localization in robotics is solved. To enable wide-spread adoption, we provide an open source implementation of our algorithms and the modules for the robot operating system (ROS) for real environment. Furthermore, an open source simulation environment is created for applications which employ UWB/LiDAR data. © 2019 Chamber of Turkish Electrical Engineers.
Olfactory Emotion Recognition Using EEG Spectral Topographic Heatmaps and CNNs
(Institute of Electrical and Electronics Engineers Inc., 2025) Yeganli, Faezeh; Sadikzade, Riza; Akan, Aydin