Graph-based approaches have been widely employed to facilitate in analyzing network flow connectivity behaviors, which aim to understand the impacts and patterns of network events. However, existing approaches suffer from lack of connectivity-behavior information and loss of network event identification. In this paper, we propose network flow connectivity graphs (NFCGs) to capture network flow behavior for modeling social behaviors from network entities. Given a set of flows, edges of a NFCG are generated by connecting pairwise hosts who communicate with each other. To preserve more information about network flows, we also embed node-ranking values and edge-weight vectors into the original NFCG. After that, a network flow connectivity behavior analysis framework is present based on NFCGs. The proposed framework consists of three modules: a graph simplification module based on diversified filtering rules, a graph feature analysis module based on quantitative or semiquantitative analysis, and a graph structure analysis module based on several graph mining methods. Furthermore, we evaluate our NFCG-based framework by using real network traffic data. The results show that NFCGs and the proposed framework can not only achieve good performance on network behavior analysis but also exhibit excellent scalability for further algorithmic implementations.
{"title":"Graph analysis of network flow connectivity behaviors","authors":"Hangyu Hu, Xuemeng Zhai, Mingda Wang, Guangmin Hu","doi":"10.3906/ELK-1808-148","DOIUrl":"https://doi.org/10.3906/ELK-1808-148","url":null,"abstract":"Graph-based approaches have been widely employed to facilitate in analyzing network flow connectivity behaviors, which aim to understand the impacts and patterns of network events. However, existing approaches suffer from lack of connectivity-behavior information and loss of network event identification. In this paper, we propose network flow connectivity graphs (NFCGs) to capture network flow behavior for modeling social behaviors from network entities. Given a set of flows, edges of a NFCG are generated by connecting pairwise hosts who communicate with each other. To preserve more information about network flows, we also embed node-ranking values and edge-weight vectors into the original NFCG. After that, a network flow connectivity behavior analysis framework is present based on NFCGs. The proposed framework consists of three modules: a graph simplification module based on diversified filtering rules, a graph feature analysis module based on quantitative or semiquantitative analysis, and a graph structure analysis module based on several graph mining methods. Furthermore, we evaluate our NFCG-based framework by using real network traffic data. The results show that NFCGs and the proposed framework can not only achieve good performance on network behavior analysis but also exhibit excellent scalability for further algorithmic implementations.","PeriodicalId":49410,"journal":{"name":"Turkish Journal of Electrical Engineering and Computer Sciences","volume":"8 1","pages":""},"PeriodicalIF":1.1,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79166484","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}
Mert Aktürk, Gökhan Gümüş, B. Sarıoǧlu, Y. D. Gökdel
In this paper, a table-top, reflective mode, laser scanning confocal microscopy system that is capable of scanning the target specimen alternately through various scanning devices and methods is proposed. We have developed a laser scanning confocal microscopy system to utilize combinations of various scanning devices and methods and to be able to characterize the optical performance of different scanners and micromirrors that are frequently used in scanning microscopy systems such as multiphoton microscopy, optical coherence tomography, or confocal microscopy. By integrating the scanner to be characterized on the same optical path with a galvanometric scan mirror, which is the conventional benchmarking scanning unit in a typical scanning microscope, we obtain two major advantages: (1) microscopy images are automatically acquired from the same location on the target specimen without having any time- consuming alignment problem and accordingly provide a high-quality optical comparison opportunity, and (2) it totally eliminates the utilization of a second scanning microscopy to benchmark the performance of the scanner-based system and considerably reduces the time spent for imaging, which is a crucial factor for a freshly excised tissue, especially under a fluorescence microscope. The system is composed of a 658 nm laser source, collimation optics, a 2D galvanometer, a 2D polymer micro-scanner, an objective lens with a numerical aperture of 0.40, a 100 μm pinhole, a PMT, a DAQ card and peripheral electronics as well as a Matlab software that simultaneously controls the system through a personal computer. Prototype of the proposed flexible LSCM system is first optically characterized using a USAF resolution target. Subsequently, we provided images of red blood and bacteria cells to demonstrate the systems’ capability for clinical diagnostics. It is reported that maximum FOV and lateral resolution of the proposed LSCM are measured to be 420 μm x 360 μm and 1 μm with galvanometer and, and 117 μm x 117 μm and 3.2 μm with the polymer scanner unit, respectively.
{"title":"Multiscanning mode laser scanning confocal microscopy system","authors":"Mert Aktürk, Gökhan Gümüş, B. Sarıoǧlu, Y. D. Gökdel","doi":"10.3906/ELK-1807-268","DOIUrl":"https://doi.org/10.3906/ELK-1807-268","url":null,"abstract":"In this paper, a table-top, reflective mode, laser scanning confocal microscopy system that is capable of scanning the target specimen alternately through various scanning devices and methods is proposed. We have developed a laser scanning confocal microscopy system to utilize combinations of various scanning devices and methods and to be able to characterize the optical performance of different scanners and micromirrors that are frequently used in scanning microscopy systems such as multiphoton microscopy, optical coherence tomography, or confocal microscopy. By integrating the scanner to be characterized on the same optical path with a galvanometric scan mirror, which is the conventional benchmarking scanning unit in a typical scanning microscope, we obtain two major advantages: (1) microscopy images are automatically acquired from the same location on the target specimen without having any time- consuming alignment problem and accordingly provide a high-quality optical comparison opportunity, and (2) it totally eliminates the utilization of a second scanning microscopy to benchmark the performance of the scanner-based system and considerably reduces the time spent for imaging, which is a crucial factor for a freshly excised tissue, especially under a fluorescence microscope. The system is composed of a 658 nm laser source, collimation optics, a 2D galvanometer, a 2D polymer micro-scanner, an objective lens with a numerical aperture of 0.40, a 100 μm pinhole, a PMT, a DAQ card and peripheral electronics as well as a Matlab software that simultaneously controls the system through a personal computer. Prototype of the proposed flexible LSCM system is first optically characterized using a USAF resolution target. Subsequently, we provided images of red blood and bacteria cells to demonstrate the systems’ capability for clinical diagnostics. It is reported that maximum FOV and lateral resolution of the proposed LSCM are measured to be 420 μm x 360 μm and 1 μm with galvanometer and, and 117 μm x 117 μm and 3.2 μm with the polymer scanner unit, respectively.","PeriodicalId":49410,"journal":{"name":"Turkish Journal of Electrical Engineering and Computer Sciences","volume":"148 1","pages":""},"PeriodicalIF":1.1,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75717158","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}
I. Aryanian, A. Ahmadi, Mehdi Rabbani, Sina Hassibi, M. Karimipour
Two main factors limiting the reflectarray bandwidth are different phase slopes versus the frequency at every point on the aperture and the phase limitation of comprising elements at different frequencies. Considering these two factors, a novel design method is proposed to implement a dual-band, dual-polarized reflectarray antenna in X and Ku bands. An optimization algorithm is adopted to find the optimum phase for each unit cell on the reflectarray aperture. The best geometrical parameters of the phasing elements are suggested based on the phase variation of the element versus frequency and the element position with respect to the antenna feed. Many different classes of phasing elements with identical base structures are investigated to provide a lookup table for the optimization algorithm. The optimum phases are obtained so that two collimated beams are realized within the frequencies of 10.95 GHz to 11.7 GHz and 14 GHz to 14.5 GHz with vertical and horizontal polarizations, respectively. From the experimental results, the peak directivity of 27.1 dBi and 30.6 dBi, aperture efficiency of 42% and 67%, and cross-polarization level of less than –15 dB and –20 dB were obtained in the lower and upper bands, respectively.
{"title":"Design and fabrication of a dual-polarized, dual-band reflectarray using optimal phase distribution","authors":"I. Aryanian, A. Ahmadi, Mehdi Rabbani, Sina Hassibi, M. Karimipour","doi":"10.3906/ELK-1807-324","DOIUrl":"https://doi.org/10.3906/ELK-1807-324","url":null,"abstract":"Two main factors limiting the reflectarray bandwidth are different phase slopes versus the frequency at every point on the aperture and the phase limitation of comprising elements at different frequencies. Considering these two factors, a novel design method is proposed to implement a dual-band, dual-polarized reflectarray antenna in X and Ku bands. An optimization algorithm is adopted to find the optimum phase for each unit cell on the reflectarray aperture. The best geometrical parameters of the phasing elements are suggested based on the phase variation of the element versus frequency and the element position with respect to the antenna feed. Many different classes of phasing elements with identical base structures are investigated to provide a lookup table for the optimization algorithm. The optimum phases are obtained so that two collimated beams are realized within the frequencies of 10.95 GHz to 11.7 GHz and 14 GHz to 14.5 GHz with vertical and horizontal polarizations, respectively. From the experimental results, the peak directivity of 27.1 dBi and 30.6 dBi, aperture efficiency of 42% and 67%, and cross-polarization level of less than –15 dB and –20 dB were obtained in the lower and upper bands, respectively.","PeriodicalId":49410,"journal":{"name":"Turkish Journal of Electrical Engineering and Computer Sciences","volume":"58 1","pages":""},"PeriodicalIF":1.1,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78271310","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 study, we propose a new approach that can be used as a kernel-like function for support vector machines (SVMs) in order to get nonlinear classification surfaces. We combined polyhedral conic functions (PCFs) with the SVM method. To get nonlinear classification surfaces, kernel functions are used with SVMs. However, the parameter selection of the kernel function affects the classification accuracy. Generally, in order to get successful classifiers which can predict unknown data accurately, best parameters are explored with the grid search method which is computationally expensive. We solved this problem with the proposed method. There is no need to optimize any parameter in the proposed method. We tested the proposed method on three publicly available datasets. Next, the classification accuracies of the proposed method were compared with the linear, radial basis function (RBF), Pearson universal kernel (PUK), and polynomial kernel SVMs. The results are competitive with those of the other methods.
{"title":"Polyhedral conic kernel-like functions for SVMs","authors":"Gurkan Ozturk, Emre Çimen","doi":"10.3906/ELK-1806-45","DOIUrl":"https://doi.org/10.3906/ELK-1806-45","url":null,"abstract":"In this study, we propose a new approach that can be used as a kernel-like function for support vector machines (SVMs) in order to get nonlinear classification surfaces. We combined polyhedral conic functions (PCFs) with the SVM method. To get nonlinear classification surfaces, kernel functions are used with SVMs. However, the parameter selection of the kernel function affects the classification accuracy. Generally, in order to get successful classifiers which can predict unknown data accurately, best parameters are explored with the grid search method which is computationally expensive. We solved this problem with the proposed method. There is no need to optimize any parameter in the proposed method. We tested the proposed method on three publicly available datasets. Next, the classification accuracies of the proposed method were compared with the linear, radial basis function (RBF), Pearson universal kernel (PUK), and polynomial kernel SVMs. The results are competitive with those of the other methods.","PeriodicalId":49410,"journal":{"name":"Turkish Journal of Electrical Engineering and Computer Sciences","volume":"70 1","pages":""},"PeriodicalIF":1.1,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76633326","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}
Data centers are becoming the main backbone of and centralized repository for all cloud-accessible services in on-demand cloud computing environments. In particular, virtual data centers (VDCs) facilitate the virtualization of all data center resources such as computing, memory, storage, and networking equipment as a single unit. It is necessary to use the data center efficiently to improve its profitability. The essential factor that significantly influences efficiency is the average number of VDC requests serviced by the infrastructure provider, and the optimal allocation of requests improves the acceptance rate. In existing VDC request embedding algorithms, data center performance factors such as resource utilization rate and energy consumption are not taken into consideration. This motivated us to design a strategy for improving the resource utilization rate without increasing the energy consumption. We propose novel VDC embedding methods based on row-epitaxial and batched greedy algorithms inspired by bioinformatics. These algorithms embed new requests into the VDC while reembedding previously allocated requests. Reembedding is done to consolidate the available resources in the VDC resource pool. The experimental testbed results show that our algorithms boost the data center objectives of high resource utilization (by improving the request acceptance rate), low energy consumption, and short VDC request scheduling delay, leading to an appreciable return on investment.
数据中心正在成为按需云计算环境中所有云访问服务的主要支柱和集中存储库。特别是vdc (virtual data centers)，可以将所有数据中心的计算、内存、存储、网络设备等资源虚拟化为一个整体。为了提高数据中心的盈利能力，必须有效地利用数据中心。影响效率的关键因素是基础设施提供商服务的VDC请求的平均数量，请求的优化分配可以提高接收率。现有的VDC请求嵌入算法没有考虑资源利用率、能耗等数据中心性能因素。这促使我们设计一种在不增加能源消耗的情况下提高资源利用率的策略。基于生物信息学的启发，我们提出了基于行外延和批处理贪婪算法的新型VDC嵌入方法。这些算法将新请求嵌入到VDC中，同时重新嵌入以前分配的请求。重嵌是为了整合VDC资源池中的可用资源。实验测试结果表明，我们的算法提高了数据中心的目标，即高资源利用率(通过提高请求接受率)、低能耗和短VDC请求调度延迟，从而获得可观的投资回报。
{"title":"Efficient virtual data center request embedding based on row-epitaxial and batched greedy algorithms","authors":"S. Balakrishnan, Surendran Doraiswamy","doi":"10.3906/ELK-1802-166","DOIUrl":"https://doi.org/10.3906/ELK-1802-166","url":null,"abstract":"Data centers are becoming the main backbone of and centralized repository for all cloud-accessible services in on-demand cloud computing environments. In particular, virtual data centers (VDCs) facilitate the virtualization of all data center resources such as computing, memory, storage, and networking equipment as a single unit. It is necessary to use the data center efficiently to improve its profitability. The essential factor that significantly influences efficiency is the average number of VDC requests serviced by the infrastructure provider, and the optimal allocation of requests improves the acceptance rate. In existing VDC request embedding algorithms, data center performance factors such as resource utilization rate and energy consumption are not taken into consideration. This motivated us to design a strategy for improving the resource utilization rate without increasing the energy consumption. We propose novel VDC embedding methods based on row-epitaxial and batched greedy algorithms inspired by bioinformatics. These algorithms embed new requests into the VDC while reembedding previously allocated requests. Reembedding is done to consolidate the available resources in the VDC resource pool. The experimental testbed results show that our algorithms boost the data center objectives of high resource utilization (by improving the request acceptance rate), low energy consumption, and short VDC request scheduling delay, leading to an appreciable return on investment.","PeriodicalId":49410,"journal":{"name":"Turkish Journal of Electrical Engineering and Computer Sciences","volume":"60 1","pages":""},"PeriodicalIF":1.1,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77231187","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}
System dynamics (SD) is a simulation-based approach for analyzing feedback-rich systems. An ideal SD modeling cycle requires evaluating the qualitative pattern characteristics of a large set of time series model output for testing, validation, scenario analysis, and policy analysis purposes. This traditionally requires expert judgement, which limits the extent of experimentation due to time constraints. Although time series recognition approaches can help to automate such an evaluation, utilization of them has been limited to a hidden Markov model classifier, namely the Indirect Structure Testing Software (ISTS) algorithm. Despite being used within several automated model-analysis tools, ISTS has several shortcomings. In that respect, we propose an interpretable time series classification algorithm for the SD field, which also addresses the shortcomings of ISTS. Our approach, which can highlight the regions of a certain time series that are influential in the class assignment, is an extension of the symbolic multivariate time series approach with the use of a local importance measure. We compare the performance of the proposed approach against both ISTS and nearest-neighbor (NN) classifiers. Our experiments on a SD-specific application show that the proposed approach outperforms ISTS as well as conventional NN classifiers on both noisy and nonnoisy datasets. Additionally, its class assignments are interpretable as opposed to the other approaches considered in the experiments.
{"title":"Classification of generic system dynamics model outputs via supervised time series pattern discovery","authors":"Mert Edali, M. Baydogan, Gönenç Yücel","doi":"10.3906/ELK-1711-394","DOIUrl":"https://doi.org/10.3906/ELK-1711-394","url":null,"abstract":"System dynamics (SD) is a simulation-based approach for analyzing feedback-rich systems. An ideal SD modeling cycle requires evaluating the qualitative pattern characteristics of a large set of time series model output for testing, validation, scenario analysis, and policy analysis purposes. This traditionally requires expert judgement, which limits the extent of experimentation due to time constraints. Although time series recognition approaches can help to automate such an evaluation, utilization of them has been limited to a hidden Markov model classifier, namely the Indirect Structure Testing Software (ISTS) algorithm. Despite being used within several automated model-analysis tools, ISTS has several shortcomings. In that respect, we propose an interpretable time series classification algorithm for the SD field, which also addresses the shortcomings of ISTS. Our approach, which can highlight the regions of a certain time series that are influential in the class assignment, is an extension of the symbolic multivariate time series approach with the use of a local importance measure. We compare the performance of the proposed approach against both ISTS and nearest-neighbor (NN) classifiers. Our experiments on a SD-specific application show that the proposed approach outperforms ISTS as well as conventional NN classifiers on both noisy and nonnoisy datasets. Additionally, its class assignments are interpretable as opposed to the other approaches considered in the experiments.","PeriodicalId":49410,"journal":{"name":"Turkish Journal of Electrical Engineering and Computer Sciences","volume":"5 1","pages":""},"PeriodicalIF":1.1,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87400927","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 consider a variant of the extended target tracking (ETT) problem, namely the multiel- lipsoidal ETT problem. In multiellipsoidal ETT, target extent is represented by multiple ellipses, which correspond to the origin of the measurements on the target surface. The problem involves estimating the target’s kinematic state and solving the association problem between the measurements and the ellipses. We cast the problem in a sequential Monte Carlo (SMC) framework and investigate different marginalization strategies to find an efficient particle filter. Under the known extent assumption, we define association variables to find the correct association between the measurements and the ellipses; hence, the posterior involves both discrete and continuous random variables. By expressing the measurement likelihood as a mixture of Gaussians we derive and employ a marginalized particle filter for the independent association variables without sampling the discrete states. We compare the performance of the method with its alternatives and illustrate the gain in nonstandard marginalization.
{"title":"Multiellipsoidal extended target tracking with known extent using sequential Monte Carlo framework","authors":"S. Kara, Emre Özkan","doi":"10.3906/ELK-1811-52","DOIUrl":"https://doi.org/10.3906/ELK-1811-52","url":null,"abstract":"In this paper, we consider a variant of the extended target tracking (ETT) problem, namely the multiel- lipsoidal ETT problem. In multiellipsoidal ETT, target extent is represented by multiple ellipses, which correspond to the origin of the measurements on the target surface. The problem involves estimating the target’s kinematic state and solving the association problem between the measurements and the ellipses. We cast the problem in a sequential Monte Carlo (SMC) framework and investigate different marginalization strategies to find an efficient particle filter. Under the known extent assumption, we define association variables to find the correct association between the measurements and the ellipses; hence, the posterior involves both discrete and continuous random variables. By expressing the measurement likelihood as a mixture of Gaussians we derive and employ a marginalized particle filter for the independent association variables without sampling the discrete states. We compare the performance of the method with its alternatives and illustrate the gain in nonstandard marginalization.","PeriodicalId":49410,"journal":{"name":"Turkish Journal of Electrical Engineering and Computer Sciences","volume":"14 1","pages":""},"PeriodicalIF":1.1,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81859840","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 the present study, a new strategy of analysis was used to determine the optimal interval of a single-phase resistive load to operate a fixed-speed wind turbine. The essence of this optimal range is to enable the generator to have stable voltages and current balances, large power, and an acceptable frequency range, and also mitigate generator overheating. The generator windings and excitation capacitances were prepared according to the C-2C connection scheme with suitable values of excitation capacitances. The admittance matrix of the system was based on positive and negative sequence generator voltages and was calculated by symmetrical components theory. The generator performance was found through optimization of the determinant admittance matrix magnitude. Moreover, balanced position of the generator can be achieved near the maximum load power. Consequently, the best interval of resistive load of the generator (1.5 kW) was found around 2% voltage unbalance factor. The appropriate optimal load was approximately ±6% of the perfect balance resistive load value.
{"title":"Optimal range of loading for operating a fixed-speed wind turbine using a self-excited induction generator","authors":"Nassim A. Iqteit, Gül Kurt, B. Çakır","doi":"10.3906/ELK-1708-20","DOIUrl":"https://doi.org/10.3906/ELK-1708-20","url":null,"abstract":"In the present study, a new strategy of analysis was used to determine the optimal interval of a single-phase resistive load to operate a fixed-speed wind turbine. The essence of this optimal range is to enable the generator to have stable voltages and current balances, large power, and an acceptable frequency range, and also mitigate generator overheating. The generator windings and excitation capacitances were prepared according to the C-2C connection scheme with suitable values of excitation capacitances. The admittance matrix of the system was based on positive and negative sequence generator voltages and was calculated by symmetrical components theory. The generator performance was found through optimization of the determinant admittance matrix magnitude. Moreover, balanced position of the generator can be achieved near the maximum load power. Consequently, the best interval of resistive load of the generator (1.5 kW) was found around 2% voltage unbalance factor. The appropriate optimal load was approximately ±6% of the perfect balance resistive load value.","PeriodicalId":49410,"journal":{"name":"Turkish Journal of Electrical Engineering and Computer Sciences","volume":"1 1","pages":""},"PeriodicalIF":1.1,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89675571","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 recent years, author gender identification has gained considerable attention in the fields of information retrieval and computational linguistics. In this paper, we employ and evaluate different learning approaches based on machine learning (ML) and neural network language models to address the problem of author gender identification. First, several ML classifiers are applied to the features obtained by bag-of-words. Secondly, datasets are represented by a low-dimensional real-valued vector using Word2vec, GloVe, and Doc2vec, which are on par with ML classifiers in terms of accuracy. Lastly, neural networks architectures, the convolution neural network and recurrent neural network, are trained and their associated performances are assessed. A variety of experiments are successfully conducted. Different issues, such as the effects of the number of dimensions, training architecture type, and corpus size, are considered. The main contribution of the study is to identify author gender by applying word embeddings and deep learning architectures to the Turkish language.
{"title":"A comparative study of author gender identification","authors":"Tuğba Yıldız","doi":"10.3906/ELK-1806-185","DOIUrl":"https://doi.org/10.3906/ELK-1806-185","url":null,"abstract":"In recent years, author gender identification has gained considerable attention in the fields of information retrieval and computational linguistics. In this paper, we employ and evaluate different learning approaches based on machine learning (ML) and neural network language models to address the problem of author gender identification. First, several ML classifiers are applied to the features obtained by bag-of-words. Secondly, datasets are represented by a low-dimensional real-valued vector using Word2vec, GloVe, and Doc2vec, which are on par with ML classifiers in terms of accuracy. Lastly, neural networks architectures, the convolution neural network and recurrent neural network, are trained and their associated performances are assessed. A variety of experiments are successfully conducted. Different issues, such as the effects of the number of dimensions, training architecture type, and corpus size, are considered. The main contribution of the study is to identify author gender by applying word embeddings and deep learning architectures to the Turkish language.","PeriodicalId":49410,"journal":{"name":"Turkish Journal of Electrical Engineering and Computer Sciences","volume":"9 1","pages":""},"PeriodicalIF":1.1,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77643135","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}
This paper presents a discontinuous space vector modulation technique for unbalanced two-phase three-leg inverters. This technique is based on the shift-angle and generalized modulation algorithm obtained for generating the unbalanced two-phase output voltage. Furthermore, the discontinuous switching sequence intends to improve the commutations of power switching devices in each inverter leg that achieves a minimum number of switching state changes in one sampling cycle. Therefore, the switch commutations can be reduced by one-third in one main period. The step- by-step procedure of the modulation algorithm for easy implementation in a digital control platform is discussed. The performance of the developed modulation technique is verified through both simulation and experimental results in a nonunity power factor balanced two-phase load and asymmetrical two-phase induction motor drive.
{"title":"A generalized switching function-based discontinuous space vector modulation technique for unbalanced two-phase three-leg inverters","authors":"W. Srirattanawichaikul","doi":"10.3906/ELK-1806-214","DOIUrl":"https://doi.org/10.3906/ELK-1806-214","url":null,"abstract":"This paper presents a discontinuous space vector modulation technique for unbalanced two-phase three-leg inverters. This technique is based on the shift-angle and generalized modulation algorithm obtained for generating the unbalanced two-phase output voltage. Furthermore, the discontinuous switching sequence intends to improve the commutations of power switching devices in each inverter leg that achieves a minimum number of switching state changes in one sampling cycle. Therefore, the switch commutations can be reduced by one-third in one main period. The step- by-step procedure of the modulation algorithm for easy implementation in a digital control platform is discussed. The performance of the developed modulation technique is verified through both simulation and experimental results in a nonunity power factor balanced two-phase load and asymmetrical two-phase induction motor drive.","PeriodicalId":49410,"journal":{"name":"Turkish Journal of Electrical Engineering and Computer Sciences","volume":"36 1","pages":""},"PeriodicalIF":1.1,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76446728","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：