WoS İndeksli Yayınlar Koleksiyonu
Permanent URI for this collectionhttps://hdl.handle.net/20.500.12416/8653
Browse
8 results
Search Results
Article System-Level Prediction and Optimization of Cyclone Separator Performance Using a Hybrid CFD-DEM-ANN Approach(MDPI, 2026) Kocak, EyupIn this study, the separation performance of cyclone separators with different geometric configurations was investigated using a hybrid approach that combines Computational Fluid Dynamics, the Discrete Element Method, and Artificial Neural Networks. In the first stage, the flow field was solved using the Reynolds-Averaged Navier-Stokes equations together with the Reynolds Stress Model turbulence closure, and particle motion was evaluated in detail through DEM. To examine the effect of geometric parameters, the inlet aspect ratio, vortex finder diameter, and cylinder height were systematically assessed. The results revealed the formation of a pronounced Rankine-type vortex structure inside the cyclone and showed that secondary flow regions intensified as the vortex finder diameter and cylinder height increased, thereby reducing the separation efficiency. In the inlet section, an optimal aspect ratio was identified. In the second stage, an ANN model was developed to expand the limited dataset obtained from the CFD-DEM analyses. By optimizing the activation function and the number of neurons, the best performance was achieved with a ReLU-based neural network containing a single hidden neuron, reaching a test-set accuracy of approximately R2 approximate to 0.991 and an overall fit of R2 approximate to 0.895. The ANN model also captured interaction trends between flow velocity and geometry that could not be observed with the limited CFD dataset. This hybrid approach provides an effective and low-cost method for performance prediction and optimization in cyclone separator design.Article 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.Conference Object Citation - WoS: 2Citation - Scopus: 4Estimation of Cross Sections for Molecule-Cluster Interactions by Using Artificial Neural Networks(Springer, 2006) Boyukata, Mustafa; Kocyigit, Yucel; Guvenc, Ziya B.The cross sections Of D-2 (v,j) + Ni-n (T), n = 19 and 20, collision systems have been estimated by using Artificial Neural Networks (ANNs). For training, previously determined cross section values via molecular dynamics simulation have been used. The performance of the ANNs for predicting any quantities in molecule-cluster interaction has been investigated. Effects of the temperature of the clusters and the rovibrational states of the molecule are analyzed. The results are in good agreement with previous studies.Article Citation - WoS: 8Citation - Scopus: 9Numerical Computational Heuristic Through Morlet Wavelet Neural Network for Solving the Dynamics of Nonlinear Sitr Covid-19(Tech Science Press, 2022) Alnahdi, Abeer S.; Jeelani, Mdi Begum; Abdelkawy, Mohamed A.; Raja, Muhammad Asif Zahoor; Baleanu, Dumitru; Hussain, Muhammad Mubashar; Sabir, ZulqurnainThe present investigations are associated with designing Morlet wavelet neural network (MWNN) for solving a class of susceptible, infected, treatment and recovered (SITR) fractal systems of COVID-19 propagation and control. The structure of an error function is accessible using the SITR differential form and its initial conditions. The optimization is performed using the MWNN together with the global as well as local search heuristics of genetic algorithm (GA) and active-set algorithm (ASA), i.e., MWNN-GA-ASA. The detail of each class of the SITR nonlinear COVID-19 system is also discussed. The obtained outcomes of the SITR system are compared with the Runge-Kutta results to check the perfection of the designed method. The statistical analysis is performed using different measures for 30 independent runs as well as 15 variables to authenticate the consistency of the proposed method. The plots of the absolute error, convergence analysis, histogram, performance measures, and boxplots are also provided to find the exactness, dependability and stability of the MWNN-GA-ASA.Article Citation - WoS: 12Citation - Scopus: 17Dynamics of Multi-Point Singular Fifth-Order Lane-Emden System With Neuro-Evolution Heuristics(Springer Heidelberg, 2022) Ali, Mohamed R.; Fathurrochman, Irwan; Raja, Muhammad Asif Zahoor; Sadat, R.; Baleanu, Dumitru; Sabir, ZulqurnainThe objective of the presented communication is to examine and analyze the solutions of nonlinear multi-singular fifth-order Lane-Emden (LE) system for different scenarios by variation of shape factors settled on the equivalent design of the LE equations. The neuro-evolution based stochastic computing is explored for the numerical measures using the artificial neural networks (ANNs) models for the appropriate continuous mapping, while the learning of decision variables is conducted using the integrated meta-heuristic global search of genetic algorithms (GA) hybrid with the local search efficiency of active-set (AS) i.e., ANN-GA-AS scheme. The numerical approach ANN-GA-AS is applied efficiently for the fifth kind of nonlinear LE model and statistical calculations further validate the accuracy, robustness as well as convergence.Article Citation - WoS: 2Citation - Scopus: 3Control Structure Design With Constraints for a Slung Load Quadrotor System(Sage Publications Ltd, 2024) Leblebicioglu, Kemal; Ergezer, HalitWe propose a control structure for a quadrotor carrying a slung load with swing-angle constraints. This quadrotor is supposed to pass through the waypoints at specified speeds. First, a cascaded PID autopilot is designed, which adaptively gives attention to position and speed requirements as a function of their errors. Its parameters are found from an optimization problem solved using the PSO algorithm. Second, this controller's performance is improved by adding the Complementary Controller employing an ANN. 5. Training data for the ANN is created by solving optimal control problems. The ANN is activated when the swing angle constraint is about to be violated. It is trained using optimal control values corresponding to the cases where the swing angle falls in a particular band about the upper swing angle constraint. Simulations are performed in a MATLAB environment. Finally, some of the simulation results are validated on a physical system.Article Citation - WoS: 60Citation - Scopus: 68Fractional Mayer Neuro-Swarm Heuristic Solver for Multi-Fractional Order Doubly Singular Model Based on Lane-Emden Equation(World Scientific Publ Co Pte Ltd, 2021) Raja, Muhammad Asif Zahoor; Baleanu, Dumitru; Sabir, ZulqurnainThis research is related to present a novel fractional Mayer neuro-swarming intelligent solver for the numerical treatment of multi-fractional order doubly singular Lane-Emden (LE) equation using combined investigations of the Mayer wavelet (MW) neural networks (NNs) optimized by the global search effectiveness of particle swarm optimization (PSO) and interior-point (IP) method, i.e. MW-NN-PSOIP. The design of novel fractional Mayer neuro-swarming intelligent solver for multi-fractional order doubly singular LE equation is derived from the standard LE model and the shape factors; fractional order terms along with singular points are examined. The modeling based on the MW-NN strength is implemented to signify the multi-fractional order doubly singular LE model using the ability of mean squared error in terms of the merit function and the networks are optimized with the integrated capability of PSOIP scheme. The perfection, verification and validation of the fractional Mayer neuro-swarming intelligent solver for three different cases of the multi-fractional order doubly singular LE equation are recognized through comparative investigations from the reference results on different measures based on the convergence, robustness, stability and accuracy. Furthermore, the statics interpretations further validate the performance of the proposed fractional Mayer neuro-swarming intelligent solvers.Article Citation - WoS: 2Citation - Scopus: 3New Spectral Approaches To the Simultaneous Quantitative Resolution of a Combined Veterinary Formulation by Ann and Pca-Ann Methods(Walter de Gruyter & Co, 2011) Baleanu, Dumitru; Sen Koktas, Nigar; Dinc, Erdal; Köktaş, Nigar ŞenThe simultaneous spectral prediction of levamisole (LEV) and triclabendazole (TRI) in combined veterinary formulation was performed by the new chemometric methods, artificial neural network (ANN) and principal component analysis-artificial neural network (PCA-ANN). Despite the overlapping spectra of LEV and TRI in the same wavelength region, the proposed methods do not use any separation procedure for the analysis of the related compounds. Good precision and accuracy were observed for the applications of the proposed artificial neural network models to an independent binary mixture set consisting of the active compounds. These methods were successfully applied for the chemometric quantitation of a veterinary formulation of LEV and TRI.