{"title":"Design and manufacture of electromagnetic absorber composed of boric acid-incorporated waste paper composites","authors":"","doi":"10.3906/elk-2106-21","DOIUrl":"https://doi.org/10.3906/elk-2106-21","url":null,"abstract":"","PeriodicalId":49410,"journal":{"name":"Turkish Journal of Electrical Engineering and Computer Sciences","volume":"56 1","pages":""},"PeriodicalIF":1.1,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74996338","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":"Identification and mitigation of non-line-of-sight path effect using repeater for hybrid ultra-wideband positioning and networking system","authors":"","doi":"10.3906/elk-2108-174","DOIUrl":"https://doi.org/10.3906/elk-2108-174","url":null,"abstract":"","PeriodicalId":49410,"journal":{"name":"Turkish Journal of Electrical Engineering and Computer Sciences","volume":"41 1","pages":""},"PeriodicalIF":1.1,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85755075","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":"Analyzing Probabilistic Optimal Power Flow Problem by Cubature Rules","authors":"","doi":"10.3906/elk-2108-111","DOIUrl":"https://doi.org/10.3906/elk-2108-111","url":null,"abstract":"","PeriodicalId":49410,"journal":{"name":"Turkish Journal of Electrical Engineering and Computer Sciences","volume":"64 1","pages":""},"PeriodicalIF":1.1,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82305533","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":"Modeling and evaluation of SOC-based coordinated EV charging for power management in a distribution system","authors":"","doi":"10.3906/elk-2105-100","DOIUrl":"https://doi.org/10.3906/elk-2105-100","url":null,"abstract":"","PeriodicalId":49410,"journal":{"name":"Turkish Journal of Electrical Engineering and Computer Sciences","volume":"5 1","pages":""},"PeriodicalIF":1.1,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87486011","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}
A structurally compact, semiflexible wearable antenna composed of a distinctively miniaturized electromagnetic band gap (EBG) structure is presented in this work. Designed for body-centric applications in the 5.8 GHz band, the design draws heavily from a novel planar geometry realized on Rogers RT/duroid 5880 laminate with a compact physical footprint spanning lateral dimensions of 0.6 λ 0 × 0.06 λ 0 . Incorporating a 2×2 EBG structure at the rear of the proposed design ensures sufficient isolation between the body and the antenna, doing away with the performance degradation associated with high permittivity of the tissue layer. The peculiar antenna geometry allows for reduced backward radiation and low specific absorption rate (SAR). With the inclusion of EBG, the gain of the antenna undergoes a considerable increase to 7.2 dBi with more than 95% reduction in SAR value. In addition, the front-to-back ratio also amplified to 13 dB. A rigorous analysis detailing the structural robustness is reported for varied bend angle configurations of the proposed antenna. To assess the suitability of the proposed design as a body-worn antenna, an experimental investigation is carried out on different parts of the body. Experimental findings are congruent with computationally obtained results, validating the applicability of the novel antenna structure for body-worn applications.
{"title":"Robust and efficient EBG-backed wearable antenna for ISM applications","authors":"H. Shahid, Y. Amin, H. Tenhunen","doi":"10.3906/elk-2101-54","DOIUrl":"https://doi.org/10.3906/elk-2101-54","url":null,"abstract":"A structurally compact, semiflexible wearable antenna composed of a distinctively miniaturized electromagnetic band gap (EBG) structure is presented in this work. Designed for body-centric applications in the 5.8 GHz band, the design draws heavily from a novel planar geometry realized on Rogers RT/duroid 5880 laminate with a compact physical footprint spanning lateral dimensions of 0.6 λ 0 × 0.06 λ 0 . Incorporating a 2×2 EBG structure at the rear of the proposed design ensures sufficient isolation between the body and the antenna, doing away with the performance degradation associated with high permittivity of the tissue layer. The peculiar antenna geometry allows for reduced backward radiation and low specific absorption rate (SAR). With the inclusion of EBG, the gain of the antenna undergoes a considerable increase to 7.2 dBi with more than 95% reduction in SAR value. In addition, the front-to-back ratio also amplified to 13 dB. A rigorous analysis detailing the structural robustness is reported for varied bend angle configurations of the proposed antenna. To assess the suitability of the proposed design as a body-worn antenna, an experimental investigation is carried out on different parts of the body. Experimental findings are congruent with computationally obtained results, validating the applicability of the novel antenna structure for body-worn applications.","PeriodicalId":49410,"journal":{"name":"Turkish Journal of Electrical Engineering and Computer Sciences","volume":"39 1","pages":""},"PeriodicalIF":1.1,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79290538","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":"Event-related microblog retrieval in Turkish","authors":"","doi":"10.3906/elk-2108-167","DOIUrl":"https://doi.org/10.3906/elk-2108-167","url":null,"abstract":"","PeriodicalId":49410,"journal":{"name":"Turkish Journal of Electrical Engineering and Computer Sciences","volume":"126 1","pages":""},"PeriodicalIF":1.1,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84952000","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 new classification method for encrypted internet traffic using machine learning","authors":"","doi":"10.3906/elk-2011-31","DOIUrl":"https://doi.org/10.3906/elk-2011-31","url":null,"abstract":"","PeriodicalId":49410,"journal":{"name":"Turkish Journal of Electrical Engineering and Computer Sciences","volume":"15 1","pages":""},"PeriodicalIF":1.1,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89139563","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}
The meaningful performance of convolutional neural network (CNN) has enabled the solution of various state-of-the-art problems. Although CNNs achieve satisfactory results in computer-vision problems, they still have some difficulties. As the designed CNN models are deepened to achieve much better accuracy, computational cost and complexity increase. It is significant to train CNNs with suitable topology and training hyperparameters that include initial learning rate, minibatch size, epoch number, filter size, number of filters, etc. because the initialization of hyperparameters affects classification results. On the other hand, it is not possible to make a definite inference for the hyperparameter initialization and there is uncertainty. This study is carried out to model uncertainty using fuzzy inference system (FIS). The designed fuzzy model provides estimation of classification result depending on CNN topology and training hyperparameters. GoogleNet and Inceptionv3 that contain inception-modules, ShuffleNet that contains shuffleblocks, DenseNet201 that contains dense-blocks, EfficientNet, ResNet18, ResNet50, ResNet101, and MobileNetv2 that contain residual-blocks, and InceptionResNetv2 that includes both inception-modules and residual-blocks were evaluated as CNN models. Test sample dataset was obtained by training CNN models with various training hyperparameter combinations. CNN models were trained on Animal Diagnostics Lab (ADL) which is a histopathological dataset includes healthy and inflamed kidney, lung, and spleen images. A new FIS tree model that is more computationally efficient and easier to understand than a single FIS was designed and classification accuracy prediction of CNN models depending on hyperparameter combinations was performed. The best, the worst, and the average classification accuracies obtained with CNN models that use best training hyperparameter set are 97.70%, 93.60%, and 96.30%, respectively. Moreover, Cifar10 and Cifar100 benchmark datasets were experimented to reveal true capability and limitations of the proposed approach. Experimental results indicate that the designed FIS tree model provides a successful hyperparameter evaluation mechanism with an average RMSE value of 1.2652.
{"title":"The Analysis and Optimization of CNN Hyperparameters with Fuzzy Tree Model for Image Classification","authors":"K. Uyar, Sakir Tasdemir, Ilker Ali Özkan","doi":"10.3906/elk-2107-130","DOIUrl":"https://doi.org/10.3906/elk-2107-130","url":null,"abstract":"The meaningful performance of convolutional neural network (CNN) has enabled the solution of various state-of-the-art problems. Although CNNs achieve satisfactory results in computer-vision problems, they still have some difficulties. As the designed CNN models are deepened to achieve much better accuracy, computational cost and complexity increase. It is significant to train CNNs with suitable topology and training hyperparameters that include initial learning rate, minibatch size, epoch number, filter size, number of filters, etc. because the initialization of hyperparameters affects classification results. On the other hand, it is not possible to make a definite inference for the hyperparameter initialization and there is uncertainty. This study is carried out to model uncertainty using fuzzy inference system (FIS). The designed fuzzy model provides estimation of classification result depending on CNN topology and training hyperparameters. GoogleNet and Inceptionv3 that contain inception-modules, ShuffleNet that contains shuffleblocks, DenseNet201 that contains dense-blocks, EfficientNet, ResNet18, ResNet50, ResNet101, and MobileNetv2 that contain residual-blocks, and InceptionResNetv2 that includes both inception-modules and residual-blocks were evaluated as CNN models. Test sample dataset was obtained by training CNN models with various training hyperparameter combinations. CNN models were trained on Animal Diagnostics Lab (ADL) which is a histopathological dataset includes healthy and inflamed kidney, lung, and spleen images. A new FIS tree model that is more computationally efficient and easier to understand than a single FIS was designed and classification accuracy prediction of CNN models depending on hyperparameter combinations was performed. The best, the worst, and the average classification accuracies obtained with CNN models that use best training hyperparameter set are 97.70%, 93.60%, and 96.30%, respectively. Moreover, Cifar10 and Cifar100 benchmark datasets were experimented to reveal true capability and limitations of the proposed approach. Experimental results indicate that the designed FIS tree model provides a successful hyperparameter evaluation mechanism with an average RMSE value of 1.2652.","PeriodicalId":49410,"journal":{"name":"Turkish Journal of Electrical Engineering and Computer Sciences","volume":"62 1","pages":""},"PeriodicalIF":1.1,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77907693","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}
An intrusion detection system is an automated monitoring tool that analyzes network traffic and detects malicious activities by looking out either for known patterns of attacks or for an anomaly. In this study, intrusion detection and classification performances of different deep learning based systems are examined. For this purpose, 24 deep neural networks with four different architectures are trained and evaluated on CICIDS2017 dataset. Furthermore, the best performing model is utilized to inspect raw network traffic features and rank them with respect to their contributions to success rates. By selecting features with respect to their ranks, sets of varying size from 3 to 77 are assessed in terms of classification accuracy and time efficiency. The results show that recurrent neural networks with a certain level of complexity can achieve comparable success rates with state-of-the-art systems using a small feature set of size 9; while the average time required to classify a test sample is halved compared to the complete set.
{"title":"Performance analysis and feature selection for network-based intrusion detection with deep learning","authors":"Serhat Caner, N. Erdogmus, Y. M. Erten","doi":"10.3906/elk-2104-50","DOIUrl":"https://doi.org/10.3906/elk-2104-50","url":null,"abstract":"An intrusion detection system is an automated monitoring tool that analyzes network traffic and detects malicious activities by looking out either for known patterns of attacks or for an anomaly. In this study, intrusion detection and classification performances of different deep learning based systems are examined. For this purpose, 24 deep neural networks with four different architectures are trained and evaluated on CICIDS2017 dataset. Furthermore, the best performing model is utilized to inspect raw network traffic features and rank them with respect to their contributions to success rates. By selecting features with respect to their ranks, sets of varying size from 3 to 77 are assessed in terms of classification accuracy and time efficiency. The results show that recurrent neural networks with a certain level of complexity can achieve comparable success rates with state-of-the-art systems using a small feature set of size 9; while the average time required to classify a test sample is halved compared to the complete set.","PeriodicalId":49410,"journal":{"name":"Turkish Journal of Electrical Engineering and Computer Sciences","volume":"7 1","pages":""},"PeriodicalIF":1.1,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85250775","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：