检索结果-内蒙古大学图书馆

4th IEEE/ACIS International Conference on Big Data, Cloud Computing, and Data science, BCD 2019

作者： Kawata, Naotaka Kikui, Genichiro Graduate School of Computer Science and Systems Engineering Okayama Prefectural University Soja719-1197 Japan Faculty of Computer Science and Systems Engineering Okayama Prefectural University Soja719-1197 Japan

ISBN: (纸本)9781728108865

This paper proposes a method for detecting entity mentions in the given text. The method consists of two sequential labelling steps. The first sequential labelling is responsible for identifying a chunk of words (morphemes) mentioning an entity. The second sequential labelling verifies whether or not each chunk (or un-chunked word) is really an entity. The paper also investigates the relation between granularity of categories of named entities and mention detection performance. Our experimental results have shown that the second sequential labeling step for checking slightly improved recall and the eleven categories is the best granularity. © 2019 IEEE.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Privacy-preserving Continual Federated Clustering via Adaptive Resonance Theory

arXiv

引用

arXiv 2023年

作者： Masuyama, Naoki Nojima, Yusuke Toda, Yuichiro Loo, Chu Kiong Ishibuchi, Hisao Kubota, Naoyuki The Graduate School of Informatics Department of Core Informatics Osaka Metropolitan University 1-1 Gakuen-cho Naka-ku Sakai-Shi Osaka599-8531 Japan The Faculty of Environmental Life Natural Science and Technology Okayama University 3-1-1 Tsushima-Naka Kita-ku Okayama Okayamashi700-8530 Japan The Department of Artificial Intelligence Faculty of Computer Science and Information Technology Universiti Malaya Kuala Lumpur50603 Malaysia The Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China Graduate School of Systems Design Department of Mechanical Systems Engineering Tokyo Metropolitan University 6-6 Asahigaoka Hino-Shi Tokyo191-0065 Japan

With the increasing importance of data privacy protection, various privacy-preserving machine learning methods have been proposed. In the clustering domain, various algorithms with a federated learning framework (i.e., federated clustering) have been actively studied and showed high clustering performance while preserving data privacy. However, most of the base clusterers (i.e., clustering algorithms) used in existing federated clustering algorithms need to specify the number of clusters in advance. These algorithms, therefore, are unable to deal with data whose distributions are unknown or continually changing. To tackle this problem, this paper proposes a privacy-preserving continual federated clustering algorithm. In the proposed algorithm, an adaptive resonance theory-based clustering algorithm capable of continual learning is used as a base clusterer. Therefore, the proposed algorithm inherits the ability of continual learning. Experimental results with synthetic and real-world datasets show that the proposed algorithm has superior clustering performance to state-of-the-art federated clustering algorithms while realizing data privacy protection and continual learning ability. The source code is available at https://***/Masuyama-lab/FCAC. © 2023, CC BY-NC-ND.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Insect Pest Detection and Identification Method Based on Deep Learning for Realizing a Pest Control System

Insect Pest Detection and Identification Method Based on Dee...

引用

SICE Annual Conference

作者： Hiroaki Kuzuhara Hironori Takimoto Yasuhiro Sato Akihiro Kanagawa Graduate School of Computer Science and Systems Engineering Okayama Prefectural University Okayama Japan Faculty of Computer Science and Systems Engineering Okayama Prefectural University Okayama Japan JST PRESTO / Research Institute for Food and Agriculture Ryukoku University Shiga Japan

ISBN: (数字)9781728110899

ISBN: (纸本)9781728110905

Detection of insect pests in the agricultural field, which is useful in achieving smart agriculture, has attracted considerable attention. In particular, automatically monitoring the number of crop insect pests has evolved into key means of managing and optimizing agricultural resources. However, despite the fact that conventional convolutional neural network (CNN)-based approaches have yielded sufficient results for general object detection, few methods have been developed to detect and recognize small objects such as insect pests. In addition, no large dataset exists for pest detection even though CNN-based methods require a large dataset to optimize many parameters. In this study, we propose two-stage detection and identification methods for small insect pests based on CNN. We also present a region proposal network for insect pest detection using YOLOv3 and propose a re-identification method using the Xception model. To train these models, we propose a data augmentation method using image processing.

关键词： Deep learning Insects Process control Object detection Pest control Agriculture Proposals

来源：评论

学校读者我要写书评

暂无评论

Relationship between number of annotations and accuracy in segmentation of the erector spinae muscle using Bayesian U-Net in torso CT images

Relationship between number of annotations and accuracy in s...

引用

International Forum on Medical Imaging in Asia 2021, IFMIA 2021

作者： Wakamatsu, Yuichi Kamiya, Naoki Zhou, Xiangrong Hara, Takeshi Fujita, Hiroshi Department of Media Informatics Graduate School of Information Science and Technology Aichi Prefectural University 1522-3 Ibaragabasama Nagakute-shi Aichi480-1198 Japan Department of Information Systems Graduate School of Information Science and Technology Aichi Prefectural University 1522-3 Ibaragabasama Nagakute-shi Aichi480-1198 Japan Department of Electrical Electronic and Computer Engineering Faculty of Engineering Gifu University 1-1 Yanagido Gifu-shi Gifu501-1193 Japan

ISBN: (数字)9781510644212

ISBN: (纸本)9781510644205

Supervised learning for image segmentation requires annotated images. However, image annotation has the problem that it is time-consuming. This problem is particularly significant in the erector spinae muscle segmentation due to the large size of the muscle. Therefore, this study considers the relationship between the number of annotated images used for training and segmentation accuracy of the erector spinae muscle in torso CT images. We use Bayesian U-Net, which has shown high accuracy in thigh muscle segmentation, for the segmentation of the erector spinae muscle. In the network training, we limit the number of slices for each case and the number of cases to 100%, 50%, 25%, and 10%. In the experiment, we use 30 torso CT images, including 6 cases for the test dataset. Experimental results are evaluated by the mean Dice value of the test dataset. Using 100% of the slices per case, the segmentation accuracy with 100%, 50%, 25%, and 10% of the cases was 0.934, 0.927, 0.926, and 0.890, respectively. On the other hand, using 100% of the cases, the segmentation accuracy with 100%, 50%, 25%, and 10% of the slices per case was 0.934, 0.934, 0.933, and 0.931, respectively. Furthermore, the segmentation accuracy with 100% of the cases and 10% of the slices per case was higher than that of the previous method. We showed that it is feasible to achieve high segmentation accuracy with a limited number of annotated images by selecting several slices from a limited number of cases for training. © 2021 SPIE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

A Compact Low Power AI Module Mounted on Drone for Plant Monitor System 8

A Compact Low Power AI Module Mounted on Drone for Plant Mon...

引用

8th IIAI International Congress on Advanced Applied Informatics, IIAI-AAI 2019

作者： Kobayashi, Tomoki Yokogawa, Tomoyuki Igawa, Nao Sato, Yoichiro Fujii, Satoshi Arimoto, Kazutami Graduate School of Computer Science and Systems Engineering Okayama Prefectural University Soja Okayama Japan Faculty of Computer Science and System Engineering Okayama Prefectural University Soja Okayama Japan Information and Communication Systems Engineering National Institute of Technology Okinawa College Nago Okinawa Japan

This paper describes the compact and low power AI DNN discriminator which is mounted on the small drone like a hobby type. By adopting this AI module, the effective plant monitoring system using the drone has been ach... 详细信息

ISBN: (纸本)9781728126272

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Dual-Band Concurrent Low Noise LNA

Dual-Band Concurrent Low Noise LNA

引用

IEEE International Workshop on Radio-Frequency Integration Technology (RFIT)

作者： Yuito Sawayama Takayuki Morishita Kiyotaka Komoku Nobuyuki Itoh Graduate School of Computer Science and Systems Engineering Okayama Prefectural University Soja Japan

ISBN: (数字)9781728165066

ISBN: (纸本)9781728165073

This paper presents 1.66/3.26 GHz dual-band concurrent LNA with low NF. Proposed LNA incorporates notch filter matching circuit and mutual induction matching circuit on input and output side to improve NF. The measured S 11 ,S 22 ,S 21 and NF were -7.11 dB, -8.41 dB, 12.5 dB, and 1.91 dB at 1.66 GHz and -7.52 dB, -16.0 dB, 9.02 dB and 3.25 dB at 3.26 GHz, respectively. IP1dB exhibits -10.3/-4.7 dBm at 1.66/3.26 GHz. The power consumption is 20.5 mW from a 1.8 V supply voltage. The proposed LNA is designed by using the TSMC-180 nm CMOS process.

关键词： Impedance matching Dual band Inductors Notch filters Frequency measurement Receivers Equivalent circuits

来源：评论

学校读者我要写书评

暂无评论

On chip synthesis of Au nanoparticles by microwave heating

IEEJ Transactions on Electronics, Information and Systems

引用

IEEJ Transactions on Electronics, Information and systems 2020年第4期140卷 471-475页

作者： Takeuchi, Masaya Kishihara, Mitsuyoshi Fukuoka, Takao Yamaguchi, Akinobu Utsumi, Yuichi Laboratory of Advanced Science and Technology for Industry University of Hyogo 3-1-2 Koto Kamigori-cho Ako-gun Hyogo678-1205 Japan Faculty of Computer Science and System Engineering Okayama Prefectural University 111 Kuboki Soja-shi Okayama719-1197 Japan Graduate School of Engineering Kyoto University Bldg. C3 Kyoto Daigaku Katsura Nishikyo-ku Kyoto615-8540 Japan

We demonstrate the on-chip synthesis of Au nanoparticles achieved by a microwave-induced reaction in a microfluidic channel. The chip structure consists of a waveguide and a microchannel through the inside of the waveguide. A post-wall waveguide, which configures the metallic post on the side wall continuously, is utilized to confine microwave fields. It allows to insert a solution inside the waveguide by microchannel passing between the metallic posts. In order to realize a miniaturization of the chip, the 24.125 GHz industrial, scientific, and medical (ISM) band is utilized instead of the commonly used 2.45 GHz ISM band. When pure water is heated in the microchannel under the microwave input power of 3.0 W, it has been confirmed that the temperature increases to 70℃. In this paper, this chip is adopted to synthesis Au nanoparticles via microwave-induced reaction. After the irradiation of the microwave power 3.0 W and the irradiation time 5 min, we have observed absorbance and dynamic light scattering of the reactant, and the results indicated generation of Au nanoparticles. This microwave synthesis system allows us to achieve automatic and fast selective synthesis of nanoparticles in the solution. © 2020 The Institute of Electrical Engineers of Japan.

关键词： Gold nanoparticles

来源：评论

学校读者我要写书评

暂无评论

A Study of 24 GHz 3D-Striped Inductor VCO with Gradually Changed Metal Width of Inductor

A Study of 24 GHz 3D-Striped Inductor VCO with Gradually Cha...

引用

IEEE International Workshop on Radio-Frequency Integration Technology (RFIT)

作者： Tsukasa Yuki Takayuki Morishita Kiyotaka Komoku Nobuyuki Itoh Graduate School of Computer Science and Systems Engineering Okayama Prefectural University Soja Japan

ISBN: (数字)9781728165066

ISBN: (纸本)9781728165073

The phase noise characteristics of the 24-GHz 3D-striped inductor VCO with gradually changed metal width of inductor has been investigated. In the high frequency region such as beyond 20-GHz, the striped inductor VCO ensure to obtain lower phase noise compare than normal inductor VCO, and the optimum metal fixed width is existing. In this work, we focused on the striped inductor which metal width changed gradually from inner to outer to consider current crowding effect. In concretely, one is the inner metal finger is the widest and the outer metal finger is the narrowest, and the other is vice versa, the inner metal finger is the narrowest and the outer metal width is the widest. The measurement results of VCOs with the constant fixed finger width inductor, the outer-widest width, and the inner-widest width all exhibit approximately -103 dBc/Hz minimum phase noise at 1-MHz offset from 24 GHz oscillation frequency, but the current consumption at achieving the lowest phase noise are 10.9 mA, 11.6 mA, 9.2 mA, respectively. This result shows that the VCO which adopted the striped inductor with metal width change gradually from inner-wide to outer-narrow shows the lowest current consumption. The process technology in this work is TSMC-180 nm CMOS.

关键词： Inductors Metals Fingers Voltage-controlled oscillators Phase noise Resistance Proximity effects

来源：评论

学校读者我要写书评

暂无评论

Design and Structural Optimization of Thiadiazole Derivatives with Potent GLS1 Inhibitory Activity

SSRN

引用

SSRN 2023年

作者： Okada, Takuya Yamabe, Kaho Jo, Michiko Sakajiri, Yuko Shibata, Tomokazu Sawada, Ryusuke Yamanishi, Yoshihiro Kanayama, Daisuke Mori, Hisashi Mizuguchi, Mineyuki Obita, Takayuki Nabeshima, Yuko Koizumi, Keiichi Toyooka, Naoki Faculty of Engineering University of Toyama Toyama930-8555 Japan Graduate School of Pharma-Medical Sciences University of Toyama Toyama930-8555 Japan Graduate School of Science and Engineering University of Toyama Toyama930-8555 Japan Division of Presymptomatic Disease Institute of Natural Medicine University of Toyama Toyama930‑0194 Japan Department of Bioscience and Bioinformatics Faculty of Computer Science and Systems Engineering Kyushu Institute of Technology Fukuoka804-8550 Japan Graduate School of Informatics Nagoya University Chikusa Nagoya464-8602 Japan Department of Pharmacology Okayama University Graduate School of Medicine Dentistry and Pharmaceutical Sciences Okayama700-8558 Japan Department of Molecular Neuroscience Faculty of Medicine University of Toyama Toyama930-0194 Japan Research Center for Pre-Disease Science University of Toyama Toyama930-0194 Japan Faculty of Pharmaceutical Sciences University of Toyama Toyama930-0194 Japan

GLS1 is an attractive target not only as anticancer agents but also as candidates for various potential pharmaceutical applications such as anti-aging and anti-obesity treatments. We performed docking simulations based on the complex crystal structure of GLS1 and its inhibitor CB-839 and found that compound A bearing a thiadiazole skeleton exhibits GLS1 inhibition. Furthermore, we synthesized 27 thiadiazole derivatives in an effort to obtain a more potent GLS1 inhibitor. Among the synthesized derivatives, 4d showed more potent GLS1 inhibitory activity (IC50 of 46.7 µM) than known GLS1 inhibitor DON and A. Therefore, 4d is a very promising novel GLS1 inhibitor. © 2023, The Authors. All rights reserved.

关键词： Structural optimization

来源：评论

学校读者我要写书评

暂无评论

K-Band Low Phase Noise Inductive Coupled VCO

K-Band Low Phase Noise Inductive Coupled VCO

引用

Asia-Pacific Conference on Microwave

作者： Naoki Tajima Kiyotaka Komoku Takayuki Morishita Nobuyuki Itoh Graduate School of Computer Science and Systems Engineering Okayama Prefectural University 111 Kuboki Soja Japan Okayama Prefectural University 111 Kuboki Soja Japan

ISBN: (数字)9781728169620

ISBN: (纸本)9781728169637

A low phase noise inductive coupled voltagecontrolled oscillator has been investigated and demonstrated in this paper. It is found in this work that to improve the phase noise of the inductive coupled VCO, high coupling coefficient and low parasitic resistance of inductors are essential, moreover, in the case of the parasitic resistance ratio between drain-side inductor and gate-side inductor, R G /R D , is low, the phase noise is improved. To confirm them, four transformers which have different coupling coefficient and different R G /R D ratio were designed and VCOs which adopted these four transformer were designed, fabricated, and measured. In the measurement result, difference of the phase noise was obtained due to difference of the coupling coefficient and the parasitic resistance ratio. The measurement results showed the VCO using inductor of M4 vs M6+M5+M3 exhibited the minimum phase noise since the inductor of M4 vs M6+M5+M3 has lower R G /R D and higher coupling coefficient. The measured phase noise of that VCO exhibited -103.3 dBc/Hz at 1 MHz offset from 23.5 GHz oscillation frequency with the power consumption of 19.8 mW. The process technology used in this work is TSMC- 180 nm CMOS.

关键词： Phase noise Couplings Resistance Phase measurement Voltage-controlled oscillators Electrical resistance measurement Inductors

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：