Damla Coşkun, D. Karaboğa, Alper Bastürk, B. Akay, Ö. U. Nalbantoğlu, Serap Doğan, Ishak Pacal, Meryem Altin Karagöz
{"title":"A comparative study of YOLO models and a transformer-based YOLOv5 model for mass detection in mammograms","authors":"Damla Coşkun, D. Karaboğa, Alper Bastürk, B. Akay, Ö. U. Nalbantoğlu, Serap Doğan, Ishak Pacal, Meryem Altin Karagöz","doi":"10.55730/1300-0632.4048","DOIUrl":"https://doi.org/10.55730/1300-0632.4048","url":null,"abstract":"","PeriodicalId":49410,"journal":{"name":"Turkish Journal of Electrical Engineering and Computer Sciences","volume":"42 13","pages":""},"PeriodicalIF":1.1,"publicationDate":"2023-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139197366","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
: In this paper, we propose a design to detect and prevent IP spoofing-based distributed denial of service (DDoS) attacks on software-defined networks (SDNs). DDoS attacks are still one of the significant problems for internet service providers (ISPs) and individual users. These attacks can disrupt customer services by targeting the availability of the system, and in some cases, they can completely shut down the target infrastructure. Protecting the system against DDoS attacks is therefore crucial for ensuring the reliability and availability of internet services. To address this problem, we propose a lightweight source address validation (LSAV) framework that leverages the flexibility of SDN architecture in ISP networks and employs a lightweight filtering mechanism that considers the cost of operation to maintain high performance. Our setup for the proposed mechanism reflects client–server communication through an ISP SDN, and we use the entry points to eliminate malicious user requests targeting the systems. We then propose a novel algorithm on top of this setup to introduce a new and more efficient approach to existing mitigation methodologies. In addition to filtering the traffic against IP spoofing-based DDoS attacks, LSAV also prioritizes low resource consumption and high performance in terms of delay and bandwidth. With this approach, we believe that ISPs can effectively defend against IP spoofing-based DDoS attacks while still preserving low resource consumption for the infrastructure and high-quality internet services for their customers.
:在本文中，我们提出了一种设计方案，用于检测和预防软件定义网络（SDN）上基于 IP 欺骗的分布式拒绝服务（DDoS）攻击。DDoS 攻击仍然是互联网服务提供商（ISP）和个人用户面临的重大问题之一。这些攻击会破坏系统的可用性，从而中断客户服务，有时甚至会完全关闭目标基础设施。因此，保护系统免受 DDoS 攻击对于确保互联网服务的可靠性和可用性至关重要。为解决这一问题，我们提出了一种轻量级源地址验证（LSAV）框架，该框架充分利用了互联网服务提供商网络中 SDN 架构的灵活性，并采用了一种轻量级过滤机制，在保持高性能的同时考虑了运行成本。我们提出的机制设置反映了通过 ISP SDN 进行的客户端-服务器通信，我们利用入口点来消除针对系统的恶意用户请求。然后，我们在此基础上提出了一种新算法，为现有的缓解方法引入了一种更高效的新方法。除了过滤流量以抵御基于IP欺骗的DDoS攻击外，LSAV还优先考虑低资源消耗和高性能（延迟和带宽）。通过这种方法，我们相信互联网服务提供商可以有效抵御基于IP欺骗的DDoS攻击，同时还能为基础设施保留低资源消耗，为客户提供高质量的互联网服务。
{"title":"LSAV: Lightweight source address validation in SDN to counteract IP spoofing-based DDoS attacks","authors":"Ali Karakoç, Fati̇h Alagöz","doi":"10.55730/1300-0632.4042","DOIUrl":"https://doi.org/10.55730/1300-0632.4042","url":null,"abstract":": In this paper, we propose a design to detect and prevent IP spoofing-based distributed denial of service (DDoS) attacks on software-defined networks (SDNs). DDoS attacks are still one of the significant problems for internet service providers (ISPs) and individual users. These attacks can disrupt customer services by targeting the availability of the system, and in some cases, they can completely shut down the target infrastructure. Protecting the system against DDoS attacks is therefore crucial for ensuring the reliability and availability of internet services. To address this problem, we propose a lightweight source address validation (LSAV) framework that leverages the flexibility of SDN architecture in ISP networks and employs a lightweight filtering mechanism that considers the cost of operation to maintain high performance. Our setup for the proposed mechanism reflects client–server communication through an ISP SDN, and we use the entry points to eliminate malicious user requests targeting the systems. We then propose a novel algorithm on top of this setup to introduce a new and more efficient approach to existing mitigation methodologies. In addition to filtering the traffic against IP spoofing-based DDoS attacks, LSAV also prioritizes low resource consumption and high performance in terms of delay and bandwidth. With this approach, we believe that ISPs can effectively defend against IP spoofing-based DDoS attacks while still preserving low resource consumption for the infrastructure and high-quality internet services for their customers.","PeriodicalId":49410,"journal":{"name":"Turkish Journal of Electrical Engineering and Computer Sciences","volume":"23 1","pages":""},"PeriodicalIF":1.1,"publicationDate":"2023-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139207830","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
: Classification model with imbalanced datasets is recently one of the most researched areas in machine learning applications since they induce to the emergence of low-performing machine learning models. The imbalanced datasets occur if target variables have an uneven number of examples in a dataset. The most prevalent solutions to imbalanced datasets can be categorized as data preprocessing, ensemble techniques, and cost-sensitive learning. In this article, we propose a new hybrid approach for binary classification, named FuzzyCSampling, which aims to increase model performance by ensembling fuzzy c-means clustering and data sampling solutions. This article compares the proposed approaches’ results not only to the base model built on an imbalanced dataset but also to the previously presented state-of-the-art solutions undersampling, SMOTE oversampling, and Borderline Smote Oversampling. The model evaluation metrics for the comparison are accuracy, roc_auc score, precision, recall and F1-score. We evaluated the success of the brand-new proposed method on three different datasets having different imbalanced ratios and for three different machine learning algorithms (k-nearest neighbors algorithm, support vector machines and random forest). According to the experiments, FuzzyCSampling is an effective way to improve the model performance in the case of imbalanced datasets.
:不平衡数据集分类模型是最近机器学习应用中研究最多的领域之一，因为它们会导致低性能机器学习模型的出现。如果目标变量在数据集中的示例数量不均衡，就会出现不平衡数据集。针对不平衡数据集最普遍的解决方案可分为数据预处理、集合技术和成本敏感型学习。在本文中，我们提出了一种新的二元分类混合方法，名为 "模糊采样"（FuzzyCSampling），旨在通过集合模糊均值聚类和数据采样解决方案来提高模型性能。本文不仅将所提方法的结果与建立在不平衡数据集上的基础模型进行了比较，还将其与之前提出的最先进解决方案欠采样、SMOTE 过度采样和边界 Smote 过度采样进行了比较。比较的模型评估指标包括准确率、roc_auc 分数、精确度、召回率和 F1 分数。我们在具有不同不平衡比率的三个不同数据集和三种不同的机器学习算法（k-近邻算法、支持向量机和随机森林）上评估了全新方法的成功率。实验结果表明，模糊采样是提高不平衡数据集模型性能的有效方法。
{"title":"FuzzyCSampling: A Hybrid fuzzy c-means clustering sampling strategy for imbalanced datasets","authors":"Abdullah Maraş, Çiğdem Selçukcan Erol","doi":"10.55730/1300-0632.4044","DOIUrl":"https://doi.org/10.55730/1300-0632.4044","url":null,"abstract":": Classification model with imbalanced datasets is recently one of the most researched areas in machine learning applications since they induce to the emergence of low-performing machine learning models. The imbalanced datasets occur if target variables have an uneven number of examples in a dataset. The most prevalent solutions to imbalanced datasets can be categorized as data preprocessing, ensemble techniques, and cost-sensitive learning. In this article, we propose a new hybrid approach for binary classification, named FuzzyCSampling, which aims to increase model performance by ensembling fuzzy c-means clustering and data sampling solutions. This article compares the proposed approaches’ results not only to the base model built on an imbalanced dataset but also to the previously presented state-of-the-art solutions undersampling, SMOTE oversampling, and Borderline Smote Oversampling. The model evaluation metrics for the comparison are accuracy, roc_auc score, precision, recall and F1-score. We evaluated the success of the brand-new proposed method on three different datasets having different imbalanced ratios and for three different machine learning algorithms (k-nearest neighbors algorithm, support vector machines and random forest). According to the experiments, FuzzyCSampling is an effective way to improve the model performance in the case of imbalanced datasets.","PeriodicalId":49410,"journal":{"name":"Turkish Journal of Electrical Engineering and Computer Sciences","volume":"11 1","pages":""},"PeriodicalIF":1.1,"publicationDate":"2023-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139198658","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
: High-dimensional feature vectors entail computational cost and computational complexity. However, a successful classification can be obtained with an optimally sized feature vector consisting of distinctive features. With the widespread use of the internet and mobile devices, the need for systems with low computational costs is increasing day by day. In this study, starting from the idea that each motor imagery is represented as a subject-specific pattern in the brain, we propose a new and practical method that can generate a low-dimensional feature vector based on wavelet transform. The feature vector is obtained from the correlation between each trial and each class average. To investigate the effect of possible temporal shifts in the trial signals, the proposed method is analyzed with signal segments with different starting points and lengths. The effect of these signal segments on classification is shown. The proposed feature extraction approach is tested on two different datasets and the classification results are presented in comparison with previous studies. With the method proposed in this study, much lower-dimensional feature vectors are obtained compared to previous studies and very satisfactory results are obtained. It is observed that EEG signals related to motor imagery in the brain have a subject-specific pattern, and this pattern is successfully classified with a feature vector consisting of only 1 feature per class.
{"title":"A practical low-dimensional feature vector generation method based on wavelet transform for psychophysiological signals","authors":"Erdem Erkan, Yasemin Erkan","doi":"10.55730/1300-0632.4041","DOIUrl":"https://doi.org/10.55730/1300-0632.4041","url":null,"abstract":": High-dimensional feature vectors entail computational cost and computational complexity. However, a successful classification can be obtained with an optimally sized feature vector consisting of distinctive features. With the widespread use of the internet and mobile devices, the need for systems with low computational costs is increasing day by day. In this study, starting from the idea that each motor imagery is represented as a subject-specific pattern in the brain, we propose a new and practical method that can generate a low-dimensional feature vector based on wavelet transform. The feature vector is obtained from the correlation between each trial and each class average. To investigate the effect of possible temporal shifts in the trial signals, the proposed method is analyzed with signal segments with different starting points and lengths. The effect of these signal segments on classification is shown. The proposed feature extraction approach is tested on two different datasets and the classification results are presented in comparison with previous studies. With the method proposed in this study, much lower-dimensional feature vectors are obtained compared to previous studies and very satisfactory results are obtained. It is observed that EEG signals related to motor imagery in the brain have a subject-specific pattern, and this pattern is successfully classified with a feature vector consisting of only 1 feature per class.","PeriodicalId":49410,"journal":{"name":"Turkish Journal of Electrical Engineering and Computer Sciences","volume":"1 1","pages":""},"PeriodicalIF":1.1,"publicationDate":"2023-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139199285","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Merve Mollahasanoglu, Hakki Mollahasanoglu, H. Okumus
: In this study, the aim is to evaluate three-phase (3 ϕ ) AC/DC neutral point-clamped (NPC) power factor-corrected (PFC) multilevel converter performance for electric vehicle (EV) fast chargers. Power factor correction for EV fast chargers is very important in terms of efficient power usage and charger compatibility with the grid. Multilevel converters improve charging efficiency, reduce voltage stresses on components, minimize electromagnetic interference, and support high power capabilities. For this reason, multilevel converters with the PFC feature contribute to the reliable and effective operation of the fast-charging infrastructure. Rectifier analysis is tested with extensive simulations using a new modified carrier-based level-shifted pulse-width modulation (PWM) technique. The results obtained are in accordance with international standards. The proposed PWM technique provides low voltage regulation, low total harmonic distortion input current, unit input power factor, and a well-regulated DC bus voltage for the NPC rectifier in fast charging systems, and the system has high efficiency. In addition, the modulation method eliminates the need for an additional PFC circuit. The system demonstrates remarkable success in addressing critical parameters such as capacitor voltage balance. This modified carrier-based PWM is highly successful for NPC rectifiers designed for DC fast chargers, rated for power up to 300 kW. The simulation results of the DC fast charger system demonstrate the validity and flexibility of the proposed carrier-based level-shifted PWM method
{"title":"New modified carrier-based level-shifted PWM control for NPC rectifiers considered for implementation in EV fast chargers","authors":"Merve Mollahasanoglu, Hakki Mollahasanoglu, H. Okumus","doi":"10.55730/1300-0632.4046","DOIUrl":"https://doi.org/10.55730/1300-0632.4046","url":null,"abstract":": In this study, the aim is to evaluate three-phase (3 ϕ ) AC/DC neutral point-clamped (NPC) power factor-corrected (PFC) multilevel converter performance for electric vehicle (EV) fast chargers. Power factor correction for EV fast chargers is very important in terms of efficient power usage and charger compatibility with the grid. Multilevel converters improve charging efficiency, reduce voltage stresses on components, minimize electromagnetic interference, and support high power capabilities. For this reason, multilevel converters with the PFC feature contribute to the reliable and effective operation of the fast-charging infrastructure. Rectifier analysis is tested with extensive simulations using a new modified carrier-based level-shifted pulse-width modulation (PWM) technique. The results obtained are in accordance with international standards. The proposed PWM technique provides low voltage regulation, low total harmonic distortion input current, unit input power factor, and a well-regulated DC bus voltage for the NPC rectifier in fast charging systems, and the system has high efficiency. In addition, the modulation method eliminates the need for an additional PFC circuit. The system demonstrates remarkable success in addressing critical parameters such as capacitor voltage balance. This modified carrier-based PWM is highly successful for NPC rectifiers designed for DC fast chargers, rated for power up to 300 kW. The simulation results of the DC fast charger system demonstrate the validity and flexibility of the proposed carrier-based level-shifted PWM method","PeriodicalId":49410,"journal":{"name":"Turkish Journal of Electrical Engineering and Computer Sciences","volume":"1 1","pages":""},"PeriodicalIF":1.1,"publicationDate":"2023-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139198358","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A novel computing scheme based on pattern matching for identification of nephron loss and chronic kidney disease stage","authors":"Rehan Ahmad, Basant Mohanty","doi":"10.55730/1300-0632.4045","DOIUrl":"https://doi.org/10.55730/1300-0632.4045","url":null,"abstract":"","PeriodicalId":49410,"journal":{"name":"Turkish Journal of Electrical Engineering and Computer Sciences","volume":"85 1","pages":""},"PeriodicalIF":1.1,"publicationDate":"2023-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139200574","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Muhammed Said Zengin, Berk Utku Yeni̇sey, Mucahid Kutlu
: Stance detection has garnered considerable attention from researchers due to its broad range of applications, including fact-checking and social computing. While state-of-the-art stance detection models are usually based on supervised machine learning methods, their effectiveness is heavily reliant on the quality of training data. This problem is more prevalent in stance detection task because the stance of a text is intimately tied to the target under consideration. While numerous datasets exist for stance detection, determining their suitability for a specific target can be challenging. In this work, we focus on Turkish stance detection and explore the impact of training data on the model performance. In particular, we fine-tune BERT model with various datasets and assess their performance when the test data is the same/different compared to the training data in terms of target and domain. In addition, given the scarcity of resources for Turkish stance detection, we investigate i) whether we can use existing datasets in other languages in a cross-lingual setup, and ii) the effectiveness of data augmentation with simple automatic labeling methods. In order to conduct our experiments, we also create new Turkish stance detection datasets for various targets in different domains. In our comprehensive experiments, our findings are as follows. 1) Using training data with multiple targets in the same domain yields high performance as the model is able to learn more characteristics of expressing stance with additional data. 2) The domain of the training data plays a crucial role in achieving high performance. 3) Automatically generated data enhances performance when combined with manually annotated data. 4) Training solely on Turkish data outperforms training with the combination of Turkish and English data. Overall, our study points out the importance of creating Turkish annotated datasets for different domains to achieve high performance in stance detection.
{"title":"Exploring the impact of training datasets on Turkish stance detection","authors":"Muhammed Said Zengin, Berk Utku Yeni̇sey, Mucahid Kutlu","doi":"10.55730/1300-0632.4043","DOIUrl":"https://doi.org/10.55730/1300-0632.4043","url":null,"abstract":": Stance detection has garnered considerable attention from researchers due to its broad range of applications, including fact-checking and social computing. While state-of-the-art stance detection models are usually based on supervised machine learning methods, their effectiveness is heavily reliant on the quality of training data. This problem is more prevalent in stance detection task because the stance of a text is intimately tied to the target under consideration. While numerous datasets exist for stance detection, determining their suitability for a specific target can be challenging. In this work, we focus on Turkish stance detection and explore the impact of training data on the model performance. In particular, we fine-tune BERT model with various datasets and assess their performance when the test data is the same/different compared to the training data in terms of target and domain. In addition, given the scarcity of resources for Turkish stance detection, we investigate i) whether we can use existing datasets in other languages in a cross-lingual setup, and ii) the effectiveness of data augmentation with simple automatic labeling methods. In order to conduct our experiments, we also create new Turkish stance detection datasets for various targets in different domains. In our comprehensive experiments, our findings are as follows. 1) Using training data with multiple targets in the same domain yields high performance as the model is able to learn more characteristics of expressing stance with additional data. 2) The domain of the training data plays a crucial role in achieving high performance. 3) Automatically generated data enhances performance when combined with manually annotated data. 4) Training solely on Turkish data outperforms training with the combination of Turkish and English data. Overall, our study points out the importance of creating Turkish annotated datasets for different domains to achieve high performance in stance detection.","PeriodicalId":49410,"journal":{"name":"Turkish Journal of Electrical Engineering and Computer Sciences","volume":"202 ","pages":""},"PeriodicalIF":1.1,"publicationDate":"2023-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139202753","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Machine learning based bioinformatics analysis of intron usage alterations and metabolic regulation in adipose browning","authors":"Hamza Umut Karakurt, Pinar Pi̇r","doi":"10.55730/1300-0632.4049","DOIUrl":"https://doi.org/10.55730/1300-0632.4049","url":null,"abstract":"","PeriodicalId":49410,"journal":{"name":"Turkish Journal of Electrical Engineering and Computer Sciences","volume":"81 8","pages":""},"PeriodicalIF":1.1,"publicationDate":"2023-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139206359","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Amin Shamsi, A. Ganjovi, Amirabbas Shayegani Akmal
: In this work, using a lumped RC circuit model which is based on transmission line modeling (TLM) method, the charge transfer in a solid insulating system encapsulating a gaseous void of submillimeter dimensions is evaluated. Here, both the dielectric material and gaseous void are considered simultaneously as a transmission line. The transmission line includes the capacitive and resistance elements and, the obtained circuit equations were coupled with the continuity and kinetic energy equations for charged species along with Poisson’s equation. These equations are solved via 4th order Runge-Kutta method and, the electric field and potential, density of all the charged species, discharge current and electron temperature are calculated in the gaseous media. Hence, the discharge propagation in the gaseous void and its mutual influences on dielectric medium are described. The partially penetration of electrons in the avalanche head into the anode dielectric bulk is shown, and it is observed that their movements towards the electrodes are much faster than ions. Besides, the total transferred charge particles at both the avalanche and streamer phases in the void is calculated. Besides, it was found that, the electrons temperature distribution completely influenced by electric field in the gaseous void. In addition, the effects of voids thickness and their location on the discharge current are examined. It is shown that, at the higher void thicknesses and for the cavities locating in the electrodes adjacent, the magnitude of discharge current increases
{"title":"Charge transfer evaluation in solid insulating materials encapsulating the gaseous voids of submillimeter dimensions using transmission line method","authors":"Amin Shamsi, A. Ganjovi, Amirabbas Shayegani Akmal","doi":"10.55730/1300-0632.4040","DOIUrl":"https://doi.org/10.55730/1300-0632.4040","url":null,"abstract":": In this work, using a lumped RC circuit model which is based on transmission line modeling (TLM) method, the charge transfer in a solid insulating system encapsulating a gaseous void of submillimeter dimensions is evaluated. Here, both the dielectric material and gaseous void are considered simultaneously as a transmission line. The transmission line includes the capacitive and resistance elements and, the obtained circuit equations were coupled with the continuity and kinetic energy equations for charged species along with Poisson’s equation. These equations are solved via 4th order Runge-Kutta method and, the electric field and potential, density of all the charged species, discharge current and electron temperature are calculated in the gaseous media. Hence, the discharge propagation in the gaseous void and its mutual influences on dielectric medium are described. The partially penetration of electrons in the avalanche head into the anode dielectric bulk is shown, and it is observed that their movements towards the electrodes are much faster than ions. Besides, the total transferred charge particles at both the avalanche and streamer phases in the void is calculated. Besides, it was found that, the electrons temperature distribution completely influenced by electric field in the gaseous void. In addition, the effects of voids thickness and their location on the discharge current are examined. It is shown that, at the higher void thicknesses and for the cavities locating in the electrodes adjacent, the magnitude of discharge current increases","PeriodicalId":49410,"journal":{"name":"Turkish Journal of Electrical Engineering and Computer Sciences","volume":"1 1","pages":""},"PeriodicalIF":1.1,"publicationDate":"2023-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139207855","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Feature selection optimization with filtering and wrapper methods: two disease classification cases","authors":"Serhat Ati̇k, Tuǧba Dalyan","doi":"10.55730/1300-0632.4050","DOIUrl":"https://doi.org/10.55730/1300-0632.4050","url":null,"abstract":"","PeriodicalId":49410,"journal":{"name":"Turkish Journal of Electrical Engineering and Computer Sciences","volume":" 30","pages":""},"PeriodicalIF":1.1,"publicationDate":"2023-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139197708","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：