Browsing by Author "Ergezer, H."

Now showing 1 - 4 of 4

Comprehensive Analysis of Data Augmentation Methods in Classification for an Imbalanced Epilepsy Dataset
(Institute of Electrical and Electronics Engineers Inc., 2026) Calis, A.G.; Ergezer, H.
Imbalanced class distribution reduces the generalizability of classifiers in EEG-based epilepsy detection. This study examines the impact of the synthetic minority oversampling technique (SMOTE) and its variants on imbalanced electroencephalography (EEG) data, utilizing an end-to-end data processing pipeline. Band-limited filtering is applied as pre-processing, and then the training data is gradually oversampled by 20% increments in four scenes. Experiments are conducted on coarse-k-nearest neighbor (Coarse-KNN), bagged trees, and artificial neural network (ANN) classifiers, and evaluation is performed using accuracy, precision, recall, F1 score, and Matthew’s correlation coefficient (MCC) metrics. In Scene #4, where the inter-class imbalance is eliminated, Borderline-SMOTE yielded the highest and most consistent results (F1 Score = 0.903–0.937, MCC = 0.830–0.894). Safe level-SMOTE (SL-SMOTE) and SMOTE/Geometric-SMOTE(G-SMOTE) produced second-ranked results. The findings demonstrate that appropriate variant selection provides consistent gains even across classifiers, making Borderline-SMOTE the recommended approach for imbalanced EEG classification. Furthermore, in the detailed analysis of ensemble sampling limits, SMOTE-based combined approaches (e.g., SL + G SMOTE) also produced consistent results. Basic descriptive statistics (mode, median, variance, and kurtosis) of the synthetic samples were found to be comparable to those of the real data, providing additional evidence of distributional consistency. © 2013 IEEE.
Comprehensive Comparison of Various Machine Learning Algorithms for Rf Fingerprints Classification
(Institute of Electrical and Electronics Engineers Inc., 2023) Ergezer, H.; Gundogan, B.
In these days, the use of drones has become quite common. Remote controls can do the control of these drones with RF signals. It is important to prevent security vulnerabilities caused by using drones in our daily lives. A complex dataset was created by extracting the characteristics of the RF signals and preprocessing them. To solve this complex data set and problem, the application of models including Support Vector Machine (SVM), Random Forest, Decision Tree, Gradient Boosting, XGBoost and Neural Network (NN) models, including various ML models and comparison of optimization studies of these applied models are examined in this article. In addition, a wide range of studies was carried out to compare ML models, including comparison metrics such as Accuracy, Precision, Recall, Mean Squared Error (MSE), F1 Score, $R^{2}$ and Training Time. In line with these results, the highest score was obtained in the $\mathrm{R}^{2}$ comparison metric (97%) in the Neural Network (NN). Compared to the others, the results of Neural Network (NN) were more successful, but the Training Time (245 sec) in the Neural Network (NN) method is by far more than the other ML methods, which shows us that the NN method requires a very high computing process. As a result of the comparison, another outstanding Ensemble-based ML method is Decision Tree. This is because besides the very low Training Time $(5\sec)$, it has managed to be the 2nd ML algorithm with the highest $\mathrm{R}^{2}$ score (96%). Apart from these, among other ML methods, SVM performed slightly less well $(\mathrm{R}^{2}$ 91%) in solving this complex problem. The advanced Gradient Method (95%) and XGBoost (96%), which also have the Ensemble structure, showed a head-to-head performance regarding $\mathrm{R}^{2}$ scores. However, XGBoost (30 sec) has a very short Training Time compared to Gradient Boosting (180 sec). As a result, the approach of each ML method to solving the complex problem differed from each other, and the success rates and Training Time also differed equally. The most important work to be done here is to choose which ML method you want to achieve according to the limited system in hand and the performance-accuracy dilemma. © 2023 IEEE.
Citation - Scopus: 3
Controller Design for Quadrotor-Slung Load System With Swing Angle Constraints Using Particle Swarm Optimization
(Institute of Electrical and Electronics Engineers Inc., 2021) Cosan, O.; Degirmenci, B.; Ergezer, H.; Ozgehan, M.; Ates, A.
In this paper, the controller is designed for a quadrotor carrying a slung load with a rope. When we consider the quadrotor and load pair, there are two cases: the quadrotor carries the load, and the load is on the ground. Since the dynamics of the system are different for these two cases, they must be considered separately. Therefore, a different PID controller is designed for each case. The necessary mechanism has been created to ensure that the transitions between these two controllers are smooth. The controller coefficients are adjusted so that the swing angles of the load are minimal. IMU has been added to the load-bearing mechanism to find out what angle the load is. Also, images of the load have been obtained with the camera located under the quadrotor. The swing angles have been calculated according to the position of the load in the image. Although our physical system studies continue, both the IMU and camera models have been created and integrated into the quadrotor-slung load model. PID coefficients have been obtained using the Particle Swarm Optimization method. Tests have been carried out on different flight profiles and the results obtained are presented. © 2021 IEEE.
Citation - WoS: 2
Citation - Scopus: 4
Kinematic Analysis and Position Control of Motor Grader Blade Mechanism for Automatic Levelling
(Institute of Electrical and Electronics Engineers Inc., 2022) Ergezer, H.; Ozkan, E.C.
In this study, mechanism analysis, which is one of the necessary steps for automatic function control in construction machines, is emphasized. Motor grader construction machine has been chosen because there are a minimal number of studies in the literature. The blade mechanism of the motor grader has high degrees of freedom; it can perform various rotations and orientations in the XYZ axis. For this mechanism, which is very challenging to control and make kinematic analysis, functions that specify the motion behavior of the cutting-edge points are obtained using the polynomial surface fitting method. PI controllers were created for the MIMO system to reduce the existing steady-state error. Tests were performed for various scenarios on the actual machine, and the results were compared. © 2022 IEEE.