Pub Date : 2024-07-09DOI: 10.23919/comex.2024XBL0064
Shin-Ichi Yamamoto;Hiroto Ado;Ryuya Seki
When reflector antennas with a beam waveguide feeding system are used in an array configuration, the transmission phase of each reflector antenna must be known and corrected. In this paper, we propose a method in which a reflector plate is placed in the center hole of the main reflector, the reflected phase at the primary radiator horn is measured, and half of the measured phase is used as the transmission phase of the beam waveguide feeding system. The proposed method was verified by calculation, measurement using a simple model with the same path length, and measurement using an actual reflector antenna, and its effectiveness was confirmed.
{"title":"Phase Measurement and Adjustment of Reflector Antenna with Beam Waveguide Feeds","authors":"Shin-Ichi Yamamoto;Hiroto Ado;Ryuya Seki","doi":"10.23919/comex.2024XBL0064","DOIUrl":"https://doi.org/10.23919/comex.2024XBL0064","url":null,"abstract":"When reflector antennas with a beam waveguide feeding system are used in an array configuration, the transmission phase of each reflector antenna must be known and corrected. In this paper, we propose a method in which a reflector plate is placed in the center hole of the main reflector, the reflected phase at the primary radiator horn is measured, and half of the measured phase is used as the transmission phase of the beam waveguide feeding system. The proposed method was verified by calculation, measurement using a simple model with the same path length, and measurement using an actual reflector antenna, and its effectiveness was confirmed.","PeriodicalId":54101,"journal":{"name":"IEICE Communications Express","volume":"13 9","pages":"367-370"},"PeriodicalIF":0.3,"publicationDate":"2024-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10591716","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142091033","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-09DOI: 10.23919/comex.2024XBL0098
Kai Ikuta;Yuta Ito;Moriya Nakamura
We investigated a nonlinear equalizer based on reservoir computing (RC) with tapped-delay lines for compensating for linear and nonlinear waveform distortion caused by, e.g., chromatic dispersion and self-phase modulation. We evaluated and compared the equalization performance of RC systems with and without tapped-delay lines by numerical simulation, while varying the parameters and the transmission distance. The proposed equalizer construction enables the use of RC with a shorter time-constant than that used for conventional RC-based nonlinear equalizers.
{"title":"Optical Nonlinearity Mitigation Using Reservoir Computing with Tapped-Delay Lines","authors":"Kai Ikuta;Yuta Ito;Moriya Nakamura","doi":"10.23919/comex.2024XBL0098","DOIUrl":"https://doi.org/10.23919/comex.2024XBL0098","url":null,"abstract":"We investigated a nonlinear equalizer based on reservoir computing (RC) with tapped-delay lines for compensating for linear and nonlinear waveform distortion caused by, e.g., chromatic dispersion and self-phase modulation. We evaluated and compared the equalization performance of RC systems with and without tapped-delay lines by numerical simulation, while varying the parameters and the transmission distance. The proposed equalizer construction enables the use of RC with a shorter time-constant than that used for conventional RC-based nonlinear equalizers.","PeriodicalId":54101,"journal":{"name":"IEICE Communications Express","volume":"13 9","pages":"384-388"},"PeriodicalIF":0.3,"publicationDate":"2024-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10591710","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142091061","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
As machine learning research in the networking field has become more active in recent years, the demand for network traffic datasets has increased. On the other hand, the amount and types of publicly available network traffic datasets are scarce as training datasets for machine learning. Therefore, we focus on the generative adversarial network (GAN) as a data generation model, aiming to use generated rather than publicly available training datasets. However, existing GANs have difficulty generating sufficiently diverse network traffic to improve generalization ability while representing variations across weekdays, weekends, and date. This study proposes a new layers inserted into the conditional GAN model with the functions of expanding dimensionality of time-series traffic data and embedding temporal position information. Experimental results show that the model with the proposed layers inserted generated diverse network traffic data that represents temporal features.
近年来,网络领域的机器学习研究日趋活跃,对网络流量数据集的需求也随之增加。另一方面,作为机器学习的训练数据集,公开可用的网络流量数据集的数量和类型都很少。因此,我们将生成式对抗网络(GAN)作为数据生成模型,旨在使用生成的而非公开可用的训练数据集。然而,现有的生成式对抗网络难以生成足够多样化的网络流量,从而在代表工作日、周末和日期变化的同时提高泛化能力。本研究提出在条件 GAN 模型中插入一个新层,其功能是扩展时间序列流量数据的维度并嵌入时间位置信息。实验结果表明,插入了所建议的层的模型生成了代表时间特征的多样化网络流量数据。
{"title":"Proposal of Temporal Feature Layers for Network Traffic Dataset Generation Using C-GAN","authors":"Yukito Onodera;Erina Takeshita;Tomoya Kosugi;Satoshi Suzuki","doi":"10.23919/comex.2024XBL0062","DOIUrl":"https://doi.org/10.23919/comex.2024XBL0062","url":null,"abstract":"As machine learning research in the networking field has become more active in recent years, the demand for network traffic datasets has increased. On the other hand, the amount and types of publicly available network traffic datasets are scarce as training datasets for machine learning. Therefore, we focus on the generative adversarial network (GAN) as a data generation model, aiming to use generated rather than publicly available training datasets. However, existing GANs have difficulty generating sufficiently diverse network traffic to improve generalization ability while representing variations across weekdays, weekends, and date. This study proposes a new layers inserted into the conditional GAN model with the functions of expanding dimensionality of time-series traffic data and embedding temporal position information. Experimental results show that the model with the proposed layers inserted generated diverse network traffic data that represents temporal features.","PeriodicalId":54101,"journal":{"name":"IEICE Communications Express","volume":"13 8","pages":"319-322"},"PeriodicalIF":0.3,"publicationDate":"2024-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10554803","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141973490","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Comparing the bandwidths of a crossed spherical helix antenna (XSHA) and conventional antennas is challenging owing to significant change in the radiation efficiency with respect to frequency even at low voltage standing wave ratio (VSWR). Thus, two types of evaluation were performed in this work to demonstrate the wideband property of XSHA. First, the antennas were assumed to be made of a perfect conductor and were compared regarding only the VSWR bandwidth. Next, we compared the bandwidth at radiation efficiency of lossy antennas based on the generalized effective fractional bandwidth $(B_{e}). B_{e}$