Scopus İndeksli Yayınlar Koleksiyonu
Permanent URI for this collectionhttps://hdl.handle.net/20.500.12573/395
Browse
4 results
Search Results
Article Citation - WoS: 8Citation - Scopus: 16QoS-Aware LTE-A Downlink Scheduling Algorithm: A Case Study on Edge Users(Wiley, 2019-07-31) Uyan, Osman Gokhan; Gungor, Vehbi Cagri4G/LTE-A (Long-Term Evolution-Advanced) is the state of the art wireless mobile broadband technology. It allows users to take advantage of high Internet speeds. It makes use of the OFDM technology to offer high speed and provides the system resources both in time and frequency domain. A scheduling algorithm running on the base station holds the allocation of these resources. In this paper, we investigate the performance of existing downlink scheduling algorithms in two ways. First, we look at the performance of the algorithms in terms of throughput and fairness metrics. Second, we suggest a new QoS-aware fairness criterion, which accepts that the system is fair if it can provide the users with the network traffic speeds that they demand and evaluate the performance of the algorithms according to this metric. We also propose a new QoS-aware downlink scheduling algorithm (QuAS) according to these two metrics, which increases the QoS-fairness and overall throughput of the edge users without causing a significant degradation in overall system throughput when compared with other schedulers in the literature.Article Citation - WoS: 34Citation - Scopus: 44LRP: Link Quality-Aware Queue-Based Spectral Clustering Routing Protocol for Underwater Acoustic Sensor Networks(Wiley, 2016-12-20) Faheem, Muhammad; Tuna, Gurkan; Gungor, Vehbi CagriRecently, underwater acoustic sensor networks (UASNs) have been considered as a promising approach for monitoring and exploring the oceans in lieu of traditional underwater wireline instruments. As a result, a broad range of applications exists ranging from oil industry to aquaculture and includes oceanographic data collection, disaster prevention, offshore exploration, assisted navigation, tactical surveillance, and pollution monitoring. However, the unique characteristics of underwater acoustic communication channels, such as high bit error rate, limited bandwidth, and variable delay, lead to a large number of packet drops, low throughput, and significant waste of energy because of packets retransmission in these applications. Hence, designing an efficient and reliable data communication protocol between sensor nodes and the sink is crucial for successful data transmission in underwater applications. Accordingly, this paper is intended to introduce a novel nature-inspired evolutionary link quality-aware queue-based spectral clustering routing protocol for UASN-based underwater applications. Because of its distributed nature, link quality-aware queue-based spectral clustering routing protocol successfully distributes network data traffic load evenly in harsh underwater environments and avoids hotspot problems that occur near the sink. In addition, because of its double check mechanism for signal to noise ratio and Euclidean distance, it adopts opportunistically and provides reliable dynamic cluster-based routing architecture in the entire network. To sum up, the proposed approach successfully finds the best forwarding relay node for data transmission and avoids path loops and packet losses in both sparse and densely deployed UASNs. Our experimental results obtained in a set of extensive simulation studies verify that the proposed protocol performs better than the existing routing protocols in terms of data delivery ratio, overall network throughput, end-to-end delay, and energy efficiency.Article Citation - Scopus: 1Breast Cancer Detection Using a New Parallel Hybrid Logistic Regression Model Trained by Particle Swarm Optimization and Clonal Selection Algorithms(Wiley, 2025-04-29) Etcil, Mustafa; Dedeturk, Bilge Kagan; Kolukisa, Burak; Bakir-Gungor, Burcu; Gungor, Vehbi CagriBreast cancer is one of the most widespread kinds of cancer, especially in women, and it has a high mortality rate. With the help of technology, it is possible to develop a computer-aided method for the diagnosis of breast cancer, which is crucial for effective treatment. Recent breast cancer diagnosis studies utilizing numerous machine learning models were efficient and innovative. However, it has been observed that they may have problems such as long training times and low accuracy rates. To this end, in this study, we present a new classifier that utilizes a hybrid of the clonal selection algorithm (CSA) and the particle swarm optimization (PSO) algorithm for the training of the logistic regression (LR) model, which is named CSA-PSO-LR. The proposed method is evaluated using two publicly accessible breast cancer datasets, that is, the Wisconsin Diagnostic Breast Cancer (WDBC) database and the Wisconsin Breast Cancer Database (WBCD), with 10-fold cross-validation and Bayesian hyperparameter optimization techniques. Additionally, a CPU parallelization method is applied, which substantially shortens the training time of the model. The efficacy of the CSA-PSO-LR classifier is compared with state-of-the-art machine learning algorithms and related studies in the literature. Performance analysis indicates that the proposed method achieves 98.75% accuracy and 98.27% F1-score on the WDBC dataset, and 97.94% accuracy and 97.35% F1-score on the WBCD dataset. These results demonstrate the potential of the proposed method as an effective approach for improving breast cancer diagnosis.Article Citation - WoS: 3Citation - Scopus: 3Accelerated Artificial Bee Colony Optimization for Cost-Sensitive Neural Networks in Multi-Class Problems(Wiley, 2025-04-10) Hacilar, Hilal; Dedeturk, Bilge Kagan; Ozmen, Mihrimah; Celik, Mehlika Eraslan; Gungor, Vehbi CagriMetaheuristics are advanced problem-solving techniques that develop efficient algorithms to address complex challenges, while neural networks are algorithms inspired by the structure and function of the human brain. Combining these approaches enables the resolution of complex optimization problems that traditional methods struggle to solve. This study presents a novel approach integrating the ABC algorithm with ANNs for weight optimization. The method is further enhanced by vectorization and parallelization techniques on both CPU and GPU to improve computational efficiency. Additionally, this study introduces a cost-sensitive fitness function tailored for multi-class classification to optimize results by considering relationships between target class levels. It validates these advancements in two critical applications: network intrusion detection and earthquake damage estimation. Notably, this study makes a significant contribution to earthquake damage assessment by leveraging machine learning algorithms and metaheuristics to enhance predictive models and decision-making in disaster response. By addressing the dynamic nature of earthquake damage, this research fills a critical gap in existing models and broadens the understanding of how machine learning and metaheuristics can improve disaster response strategies. In both domains, the ABC-ANN implementation yields promising results, particularly in earthquake damage estimation, where the cost-sensitive approach demonstrates satisfactory outcomes in macro-F1 and accuracy. The best results for macro-F1, weighted-F1, and overall accuracy provides best results with the UNSW-NB15 and earthquake datasets, showing values of 64%, 72%, 68%, and 60%, 80%, and 79%, respectively. Comparative performance evaluations reveal that the proposed parallel ABC-ANN model, incorporating the novel cost-sensitive fitness function and enhanced by vectorization and parallelization techniques, significantly reduces training time and outperforms state-of-the-art methods in terms of macro-F1 and accuracy in both network intrusion detection and earthquake damage estimation.