Bahaeddin Turkoglu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Bahaeddin Turkoglu has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Tunc Asuroglu
Tampere University
6 shared publications - Ersin Kaya
Konya Teknik Üniversitesi
4 shared publications - Muhammed Abdulhamid Karabiyik
Department of Computer Technologies, Nigde Omer Halisdemir University, Nide, Trkiye
4 shared publications - Sait Ali Uymaz
Konya Teknik Üniversitesi
3 shared publications Hacer Alan Dikmen
1 shared publicationHavva Gül Koçer
1 shared publication
Latest Publications
- Open Access
SC-EfficientNet: Preventing Attention Collapse in Consistency-Regularized Skin Lesion Classification
Attention-based consistency regularization aims to focus skin lesion classifiers on lesions, but whether the attention behaves as intended is rarely verified. The main contribution is the analysis and prevention of attention collapse in Kullback–Leibler (KL) consistency training, not improved classification performance. In SC-EfficientNet (Supervised-Consistency EfficientNet), an attention-masked prediction branch is supervised with the class labels and regularized toward the original prediction by a Kullback–Leibler term, and its spatial mask is constrained by area and binarization priors. Models were evaluated with lesion-level five-fold cross-validation on ISIC 2018 Task 3 (three seeds, EfficientNet-B0/B4) and on the official test set. Trained only through the consistency term, the mask collapsed to a nearly constant map in every run, also with a tenfold larger consistency weight, a shared head, or zero-initialized attention. SC-EfficientNet prevented this collapse, produced spatially selective masks, and raised agreement with Grad-CAM from r = 0.04–0.08 to 0.31–0.44. A matched headless control explained most of the B4 gain over a standard baseline; relative to this control, SC-EfficientNet improved B0 macro-F1 by 2.16 ± 0.31 points but did not change B4 performance (85.12% ± 0.10% out-of-fold accuracy), and no variant improved robustness to synthetic artifacts. Melanoma sensitivity under the default decision rule remained low (SC-EfficientNet-B4: 53.5% out of fold, 55.2% on the test set). Matched controls and mask diagnostics are needed before attributing gains to attention.
Open AccessSC-EfficientNet: Preventing Attention Collapse in Consistency-Regularized Skin Lesion Classification
Attention-based consistency regularization aims to focus skin lesion classifiers on lesions, but whether the attention behaves as intended is rarely verified. The main contribution is the analysis and prevention of attention collapse in Kullback–Leibler (KL) consistency training, not improved classification performance. In SC-EfficientNet (Supervised-Consistency EfficientNet), an attention-masked prediction branch is supervised with the class labels and regularized toward the original prediction by a Kullback–Leibler term, and its spatial mask is constrained by area and binarization priors. Models were evaluated with lesion-level five-fold cross-validation on ISIC 2018 Task 3 (three seeds, EfficientNet-B0/B4) and on the official test set. Trained only through the consistency term, the mask collapsed to a nearly constant map in every run, also with a tenfold larger consistency weight, a shared head, or zero-initialized attention. SC-EfficientNet prevented this collapse, produced spatially selective masks, and raised agreement with Grad-CAM from r = 0.04–0.08 to 0.31–0.44. A matched headless control explained most of the B4 gain over a standard baseline; relative to this control, SC-EfficientNet improved B0 macro-F1 by 2.16 ± 0.31 points but did not change B4 performance (85.12% ± 0.10% out-of-fold accuracy), and no variant improved robustness to synthetic artifacts. Melanoma sensitivity under the default decision rule remained low (SC-EfficientNet-B4: 53.5% out of fold, 55.2% on the test set). Matched controls and mask diagnostics are needed before attributing gains to attention.
- Open Access
- 31 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 187740-187757
HENOS: A Henon Map-Based Chaotic Oversampling Strategy for Imbalanced Data Classification
The effectiveness of machine learning models is profoundly influenced by the quality and distribution of training data. However, real-world datasets are often highly imbalanced, where conventional classification algorithms tend to favor the majority class, resulting in poor recognition of minority instances. To address this challenge, we propose HENOS, a novel oversampling method that leverages the nonlinear dynamics of the Henon map to synthesize minority class samples in a more structurally diverse and boundary-aware manner. Unlike traditional interpolation-based techniques such as SMOTE, which often fail to capture complex data distributions, HENOS introduces a deterministic yet chaotic mechanism to generate synthetic instances that preserve local data characteristics while enhancing class separability. We conduct comprehensive experiments on 37 benchmark datasets, evaluating HENOS across three distinct classifiers AdaBoost, Naive Bayes, and Artificial Neural Networks (ANN) using Area Under the Curve (AUC) and F1-score metrics. The results, validated by the Friedman statistical test, demonstrate that HENOS consistently outperforms existing oversampling methods with statistically significant gains. These findings highlight the potential of chaos-theoretic principles in tackling data imbalance and open avenues for their integration into advanced learning systems, including deep architectures.
- 31 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 187740-187757
Open AccessHENOS: A Henon Map-Based Chaotic Oversampling Strategy for Imbalanced Data Classification
The effectiveness of machine learning models is profoundly influenced by the quality and distribution of training data. However, real-world datasets are often highly imbalanced, where conventional classification algorithms tend to favor the majority class, resulting in poor recognition of minority instances. To address this challenge, we propose HENOS, a novel oversampling method that leverages the nonlinear dynamics of the Henon map to synthesize minority class samples in a more structurally diverse and boundary-aware manner. Unlike traditional interpolation-based techniques such as SMOTE, which often fail to capture complex data distributions, HENOS introduces a deterministic yet chaotic mechanism to generate synthetic instances that preserve local data characteristics while enhancing class separability. We conduct comprehensive experiments on 37 benchmark datasets, evaluating HENOS across three distinct classifiers AdaBoost, Naive Bayes, and Artificial Neural Networks (ANN) using Area Under the Curve (AUC) and F1-score metrics. The results, validated by the Friedman statistical test, demonstrate that HENOS consistently outperforms existing oversampling methods with statistically significant gains. These findings highlight the potential of chaos-theoretic principles in tackling data imbalance and open avenues for their integration into advanced learning systems, including deep architectures.
- Open Access
- 2 September 2025
- Published by PeerJ in PeerJ Computer Science
- Vol. 11, e3177
A cluster-assisted differential evolution-based hybrid oversampling method for imbalanced datasets
Class imbalance remains a significant challenge in machine learning, leading to biased models that favor the majority class while failing to accurately classify minority instances. Traditional oversampling methods, such as Synthetic Minority Over-sampling Technique (SMOTE) and its variants, often struggle with class overlap, poor decision boundary representation, and noise accumulation. To address these limitations, this study introduces ClusterDEBO, a novel hybrid oversampling method that integrates K-Means clustering with differential evolution (DE) to generate synthetic samples in a more structured and adaptive manner. The proposed method first partitions the minority class into clusters using the silhouette score to determine the optimal number of clusters. Within each cluster, DE-based mutation and crossover operations are applied to generate diverse and well-distributed synthetic samples while preserving the underlying data distribution. Additionally, a selective sampling and noise reduction mechanism is employed to filter out low-impact synthetic samples based on their contribution to classification performance. The effectiveness of ClusterDEBO is evaluated on 44 benchmark datasets using k-Nearest Neighbors (kNN), decision tree (DT), and support vector machines (SVM) as classifiers. The results demonstrate that ClusterDEBO consistently outperforms existing oversampling techniques, leading to improved class separability and enhanced classifier robustness. Moreover, statistical validation using the Friedman test confirms the significance of the improvements, ensuring that the observed gains are not due to random variations. The findings highlight the potential of cluster-assisted differential evolution as a powerful strategy for handling imbalanced datasets.
- 2 September 2025
- Published by PeerJ in PeerJ Computer Science
- Vol. 11, e3177
Open AccessA cluster-assisted differential evolution-based hybrid oversampling method for imbalanced datasets
Class imbalance remains a significant challenge in machine learning, leading to biased models that favor the majority class while failing to accurately classify minority instances. Traditional oversampling methods, such as Synthetic Minority Over-sampling Technique (SMOTE) and its variants, often struggle with class overlap, poor decision boundary representation, and noise accumulation. To address these limitations, this study introduces ClusterDEBO, a novel hybrid oversampling method that integrates K-Means clustering with differential evolution (DE) to generate synthetic samples in a more structured and adaptive manner. The proposed method first partitions the minority class into clusters using the silhouette score to determine the optimal number of clusters. Within each cluster, DE-based mutation and crossover operations are applied to generate diverse and well-distributed synthetic samples while preserving the underlying data distribution. Additionally, a selective sampling and noise reduction mechanism is employed to filter out low-impact synthetic samples based on their contribution to classification performance. The effectiveness of ClusterDEBO is evaluated on 44 benchmark datasets using k-Nearest Neighbors (kNN), decision tree (DT), and support vector machines (SVM) as classifiers. The results demonstrate that ClusterDEBO consistently outperforms existing oversampling techniques, leading to improved class separability and enhanced classifier robustness. Moreover, statistical validation using the Friedman test confirms the significance of the improvements, ensuring that the observed gains are not due to random variations. The findings highlight the potential of cluster-assisted differential evolution as a powerful strategy for handling imbalanced datasets.
- 8 July 2025
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 81 (10) , 1-32
BAHA: balanced artificial hummingbird algorithm and its application to space industry
- 8 July 2025
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 81 (10) , 1-32
BAHA: balanced artificial hummingbird algorithm and its application to space industry
- Open Access
- 19 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 50464-50479
Optimizing Artificial Neural Networks Using Mountain Gazelle Optimizer
The performance of artificial neural networks heavily depends on the optimization of network parameters, specifically weights and biases, during the training process. Effectively adjusting these parameters is essential to minimize the error between predicted and actual outputs. While traditional training algorithms, such as gradient-based methods, have been widely used, they often face challenges like premature convergence and stagnation in local optima. Training an ANN can, therefore, be viewed as an optimization problem, where the goal is to fine-tune parameters to achieve accurate and efficient performance. In this study, we introduce a novel approach to optimizing neural network parameters using the Mountain Gazelle Optimizer (MGO), a nature-inspired metaheuristic algorithm that mimics the social hierarchy and behavioral patterns of wild mountain gazelles. The MGO algorithm leverages its unique features, including hierarchical social structure and adaptive movement strategies, to effectively navigate the complex parameter space of neural networks. The algorithm’s search mechanism integrates four key behavioral strategies: Territorial Solitary Males (TSM) for refining optimal solutions, Maternity Herds (MH) for balancing exploration and exploitation, Bachelor Male Herds (BMH) for global exploration, and Migration to Search for Food (MSF) for introducing randomness to prevent stagnation in local optima. These mechanisms work collaboratively, ensuring a dynamic and balanced optimization process throughout the training phase. To evaluate the effectiveness of the proposed approach, we conducted comprehensive experiments using various classification datasets from the UCI repository. The performance of the MGO-based neural network optimizer was compared with traditional backpropagation and several state-of-the-art optimization algorithms. Experimental results demonstrate that the proposed method exhibits superior performance in terms of convergence speed and avoiding local optima, suggesting that MGO is a promising alternative for optimizing artificial neural networks during training.
- 19 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 50464-50479
Open AccessOptimizing Artificial Neural Networks Using Mountain Gazelle Optimizer
The performance of artificial neural networks heavily depends on the optimization of network parameters, specifically weights and biases, during the training process. Effectively adjusting these parameters is essential to minimize the error between predicted and actual outputs. While traditional training algorithms, such as gradient-based methods, have been widely used, they often face challenges like premature convergence and stagnation in local optima. Training an ANN can, therefore, be viewed as an optimization problem, where the goal is to fine-tune parameters to achieve accurate and efficient performance. In this study, we introduce a novel approach to optimizing neural network parameters using the Mountain Gazelle Optimizer (MGO), a nature-inspired metaheuristic algorithm that mimics the social hierarchy and behavioral patterns of wild mountain gazelles. The MGO algorithm leverages its unique features, including hierarchical social structure and adaptive movement strategies, to effectively navigate the complex parameter space of neural networks. The algorithm’s search mechanism integrates four key behavioral strategies: Territorial Solitary Males (TSM) for refining optimal solutions, Maternity Herds (MH) for balancing exploration and exploitation, Bachelor Male Herds (BMH) for global exploration, and Migration to Search for Food (MSF) for introducing randomness to prevent stagnation in local optima. These mechanisms work collaboratively, ensuring a dynamic and balanced optimization process throughout the training phase. To evaluate the effectiveness of the proposed approach, we conducted comprehensive experiments using various classification datasets from the UCI repository. The performance of the MGO-based neural network optimizer was compared with traditional backpropagation and several state-of-the-art optimization algorithms. Experimental results demonstrate that the proposed method exhibits superior performance in terms of convergence speed and avoiding local optima, suggesting that MGO is a promising alternative for optimizing artificial neural networks during training.
- Open Access
Voice Analysis in Dogs with Deep Learning: Development of a Fully Automatic Voice Analysis System for Bioacoustics Studies
Extracting behavioral information from animal sounds has long been a focus of research in bioacoustics, as sound-derived data are crucial for understanding animal behavior and environmental interactions. Traditional methods, which involve manual review of extensive recordings, pose significant challenges. This study proposes an automated system for detecting and classifying animal vocalizations, enhancing efficiency in behavior analysis. The system uses a preprocessing step to segment relevant sound regions from audio recordings, followed by feature extraction using Short-Time Fourier Transform (STFT), Mel-frequency cepstral coefficients (MFCCs), and linear-frequency cepstral coefficients (LFCCs). These features are input into convolutional neural network (CNN) classifiers to evaluate performance. Experimental results demonstrate the effectiveness of different CNN models and feature extraction methods, with AlexNet, DenseNet, EfficientNet, ResNet50, and ResNet152 being evaluated. The system achieves high accuracy in classifying vocal behaviors, such as barking and howling in dogs, providing a robust tool for behavioral analysis. The study highlights the importance of automated systems in bioacoustics research and suggests future improvements using deep learning-based methods for enhanced classification performance.
Open AccessVoice Analysis in Dogs with Deep Learning: Development of a Fully Automatic Voice Analysis System for Bioacoustics Studies
Extracting behavioral information from animal sounds has long been a focus of research in bioacoustics, as sound-derived data are crucial for understanding animal behavior and environmental interactions. Traditional methods, which involve manual review of extensive recordings, pose significant challenges. This study proposes an automated system for detecting and classifying animal vocalizations, enhancing efficiency in behavior analysis. The system uses a preprocessing step to segment relevant sound regions from audio recordings, followed by feature extraction using Short-Time Fourier Transform (STFT), Mel-frequency cepstral coefficients (MFCCs), and linear-frequency cepstral coefficients (LFCCs). These features are input into convolutional neural network (CNN) classifiers to evaluate performance. Experimental results demonstrate the effectiveness of different CNN models and feature extraction methods, with AlexNet, DenseNet, EfficientNet, ResNet50, and ResNet152 being evaluated. The system achieves high accuracy in classifying vocal behaviors, such as barking and howling in dogs, providing a robust tool for behavioral analysis. The study highlights the importance of automated systems in bioacoustics research and suggests future improvements using deep learning-based methods for enhanced classification performance.
- Open Access
- 5 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 108154-108175
A Novel Diversity Guided Galactic Swarm Optimization With Feedback Mechanism
Galactic Swarm Optimization (GSO) is an optimization method inspired by the movements of stars and star clusters in the galaxy. This method aims to find the best solution in two phases using other known optimization methods. The first phase explores the search space, while the second phase tries to refine the best solution. In GSO, the population of the best individuals obtained from the first phase is used as the initial population for the second phase. This process is repeated until the stopping criterion is met. Although the knowledge obtained from the first phase is transferred to the second phase in GSO, there is no knowledge transfer from the second phase to the first phase. In this study, we propose a modification where the knowledge obtained in the second phase is transferred back to the first phase. Additionally, the Particle Swarm Optimization (PSO) method, used as the search method in the original study, has a fast convergence problem, which hinders an effective discovery process in the first phase of GSO. To address this, the proposed diversity-guided modification regulates population diversity and enhances exploration. To demonstrate the performance of the proposed method, twenty-six traditional benchmark functions and three engineering design problems were used. The proposed method was compared with the original GSO and six current optimization methods. The results of the experimental study were analyzed using statistical tests. The experimental results and analyses show that the proposed method performs successfully.
- 5 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 108154-108175
Open AccessA Novel Diversity Guided Galactic Swarm Optimization With Feedback Mechanism
Galactic Swarm Optimization (GSO) is an optimization method inspired by the movements of stars and star clusters in the galaxy. This method aims to find the best solution in two phases using other known optimization methods. The first phase explores the search space, while the second phase tries to refine the best solution. In GSO, the population of the best individuals obtained from the first phase is used as the initial population for the second phase. This process is repeated until the stopping criterion is met. Although the knowledge obtained from the first phase is transferred to the second phase in GSO, there is no knowledge transfer from the second phase to the first phase. In this study, we propose a modification where the knowledge obtained in the second phase is transferred back to the first phase. Additionally, the Particle Swarm Optimization (PSO) method, used as the search method in the original study, has a fast convergence problem, which hinders an effective discovery process in the first phase of GSO. To address this, the proposed diversity-guided modification regulates population diversity and enhances exploration. To demonstrate the performance of the proposed method, twenty-six traditional benchmark functions and three engineering design problems were used. The proposed method was compared with the original GSO and six current optimization methods. The results of the experimental study were analyzed using statistical tests. The experimental results and analyses show that the proposed method performs successfully.
- Open Access
- 1 July 2024
- Published by Springer Nature in Arabian Journal for Science and Engineering
- Vol. 50 (2) , 1279-1306
Chaotic Artificial Algae Algorithm for Solving Global Optimization With Real-World Space Trajectory Design Problems
The artificial algae algorithm (AAA) is a recently introduced metaheuristic algorithm inspired by the behavior and characteristics of microalgae. Like other metaheuristic algorithms, AAA faces challenges such as local optima and premature convergence. Various strategies to address these issues and enhance the performance of the algorithm have been proposed in the literature. These include levy flight, local search, variable search, intelligent search, multi-agent systems, and quantum behaviors. This paper introduces chaos theory as a strategy to improve AAA's performance. Chaotic maps are utilized to effectively balance exploration and exploitation, prevent premature convergence, and avoid local minima. Ten popular chaotic maps are employed to enhance AAA's performance, resulting in the chaotic artificial algae algorithm (CAAA). CAAA's performance is evaluated on thirty benchmark test functions, including unimodal, multimodal, and fixed dimension problems. The algorithm is also tested on three classical engineering problems and eight space trajectory design problems at the European Space Agency. A statistical analysis using the Friedman and Wilcoxon tests confirms that CAA demonstrates successful performance in optimization problems.
- 1 July 2024
- Published by Springer Nature in Arabian Journal for Science and Engineering
- Vol. 50 (2) , 1279-1306
Open AccessChaotic Artificial Algae Algorithm for Solving Global Optimization With Real-World Space Trajectory Design Problems
The artificial algae algorithm (AAA) is a recently introduced metaheuristic algorithm inspired by the behavior and characteristics of microalgae. Like other metaheuristic algorithms, AAA faces challenges such as local optima and premature convergence. Various strategies to address these issues and enhance the performance of the algorithm have been proposed in the literature. These include levy flight, local search, variable search, intelligent search, multi-agent systems, and quantum behaviors. This paper introduces chaos theory as a strategy to improve AAA's performance. Chaotic maps are utilized to effectively balance exploration and exploitation, prevent premature convergence, and avoid local minima. Ten popular chaotic maps are employed to enhance AAA's performance, resulting in the chaotic artificial algae algorithm (CAAA). CAAA's performance is evaluated on thirty benchmark test functions, including unimodal, multimodal, and fixed dimension problems. The algorithm is also tested on three classical engineering problems and eight space trajectory design problems at the European Space Agency. A statistical analysis using the Friedman and Wilcoxon tests confirms that CAA demonstrates successful performance in optimization problems.
- 29 September 2023
- Published by Omer Halisdemir Universitesi in Ömer Halisdemir Üniversitesi Mühendislik Bilimleri Dergisi
Optimizasyon Problemleri için Gelişmiş Salp Sürüsü Algoritması
Salp Swarm Algorithm (SSA) is metaheuristic optimization algorithm inspired by the biological characteristics and colony strategies of salp swarms. There are a wide variety of studies conducted with SSA in the literature. In these studies, it was also emphasized that SSA has very critical main disadvantages. The most important of these disadvantages is the imbalance of exploration and exploitation. In this study, an equilibrium operator is developed using the ikeda chaotic map. Thanks to this improvement, the performance of the SSA algorithm has been increased and early convergence and stuck to local optima problems has been overcome. To evaluate the success of the proposed method, ten different fixed dimension benchmark problems and three popular engineering design optimization problems are solved. The reliability of the proposed method has been verified by comparing it with four well-known metaheuristic approaches and the original SSA. Experimental study results confirmed that the proposed method outperforms the compared methods.
- 29 September 2023
- Published by Omer Halisdemir Universitesi in Ömer Halisdemir Üniversitesi Mühendislik Bilimleri Dergisi
Optimizasyon Problemleri için Gelişmiş Salp Sürüsü Algoritması
Salp Swarm Algorithm (SSA) is metaheuristic optimization algorithm inspired by the biological characteristics and colony strategies of salp swarms. There are a wide variety of studies conducted with SSA in the literature. In these studies, it was also emphasized that SSA has very critical main disadvantages. The most important of these disadvantages is the imbalance of exploration and exploitation. In this study, an equilibrium operator is developed using the ikeda chaotic map. Thanks to this improvement, the performance of the SSA algorithm has been increased and early convergence and stuck to local optima problems has been overcome. To evaluate the success of the proposed method, ten different fixed dimension benchmark problems and three popular engineering design optimization problems are solved. The reliability of the proposed method has been verified by comparing it with four well-known metaheuristic approaches and the original SSA. Experimental study results confirmed that the proposed method outperforms the compared methods.