检索结果-内蒙古大学图书馆

IEEE International Conference on Consumer elec.ronics-Taiwan (ICCE-TW)

作者： Antônio M.C. Pereira Mateus O. Silva Andrey R. R. Bessa José E.B.S. Linhares Diego A. Amoedo Edma V.C.U. Mattos Agemilson P. Silva Allan C. Brito Ruan J.S. Belem Rômulo S.F. Jean A.O. Nunes Madson R. Lemos Maura R.A. Costa Waldir S.S. Celso B. Carvalho Federal University of Amazonas and Center for R&D in Elec. and Inf. Tech. (UFAM/CETELI) AM Brazil ENVISION/TPV Group Technology Limited AM Brazil INDT Institute for Technological Development AM Brazil

ISBN: (数字)9798350386844

ISBN: (纸本)9798350386851

In this work, conducted by three partners — UFAM/CETELI, INDT, and Envision (TPV Group) — we present a system comprising machine learning microservices for predicting defects in industrial assets at the ENVISION factory. Data collected through sensors installed in the factory’s industrial assets are processed by machine learning models to generate predictions of failures and machine stops, which are then displayed to the user through a front end.

关键词： Microservice architectures Machine learning Predictive models Data models Sensor systems Production facilities Sensors

来源：评论

学校读者我要写书评

暂无评论

Asset Administration Shell in Manufacturing: Case Study in Manaus Industrial Complex

Asset Administration Shell in Manufacturing: Case Study in M...

引用

IEEE International Conference on Consumer elec.ronics-Taiwan (ICCE-TW)

作者： José E.B.S. Linhares Gustavo M. Torres Matheus S. Uchôa Adriel V. Santos Myke D.M. Valadão Diego A. Amoedo Maria Regina Araújo Souza Edma V. C.U. Mattos Antônio M.C. Pereira Agemilson P. Silva Allan C. Brito Allan R. A. Silva Rômulo S.F. Jean A. O. Nunes Madson R. Lemos Maura R. A. Costa Waldir S.S. Júnior Celso B. Carvalho Federal University of Amazonas and Center for R&D in Elec. and Inf. Tech. (UFAM/CETELI) Amazon Brazil ENVISION/TPV Group Technology Limited Amazon Brazil INDT Institute for Technological Development Amazon Brazil

ISBN: (数字)9798350386844

ISBN: (纸本)9798350386851

In this work, conducted by three partners, UFAM/CETELI, INDT and Envision (TPV Group), we present a system for modeling and sensing data acquired from various machines, including both legacy and modern types, in industrial environments. This approach involves monitoring the on-off state of machines to gather inf.rmation about their operation on the production line. The results show the successful implementation of the system, highlighting its potential application in predictive maintenance solutions within the context of Industry 4.0.

关键词： Solid modeling Vacuum systems Pumps Production Predictive models Data models Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Architecture for Industrial Asset Sensing using LoRaWAN and Acquisition Microservice

Architecture for Industrial Asset Sensing using LoRaWAN and ...

引用

IEEE International Conference on Consumer elec.ronics-Taiwan (ICCE-TW)

作者： Andrey R. R. Bessa José E. B.S. Linhares Matheus S. Uchôa Adriel V. Dos Santos Diego A. Amoedo Maria R. A. Souza Edma V.C.U. Mattos Antônio M. C. Pereira Agemilson P. Silva Allan C. Brito Rômulo S.F. Jean A. O. Nunes Madson R. Lemos Maura R. A. Costa Waldir S.S. Junior Celso B. Carvalho Federal University of Amazonas and Center for R&D in Elec. and Inf. Tech. (UFAM/CETELI) Amazonas Brazil ENVISION/TPV Group Technology Limited Amazonas Brazil INDT Institute for Technological Development Amazonas Brazil

ISBN: (数字)9798350386844

ISBN: (纸本)9798350386851

This paper, conducted by three partners, UFAM/CETELI, INDT and Envision (TPV Group), presents a data collection architecture with WISE-2410 and ITE11LI sensors, focusing on LoRaWAN configurations, and distance tests. The architecture integrates LoRa radio, MQTT, and microservices with an ITG201 outdoor gateway. Results show accurate network setup, reliable reconnections, strong signal levels, improved device stability, and transmission efficiency. The study demonstrates a robust framework for reliable data collection in diverse applications.

关键词： Wireless communication Wireless sensor networks Microservice architectures LoRaWAN Data collection Logic gates Sensors

来源：评论

学校读者我要写书评

暂无评论

FusTP-FL: Enhancing Differential Federated Learning through Personalized Layers and Data Transformation

FusTP-FL: Enhancing Differential Federated Learning through ...

引用

IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom)

作者： Xiong Yan Kedong Yan Chanying Huang Dan Yin Shan Xiao School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China School of Comp. Science & Engineering Nanjing Univ. of Science & Technology Nanjing China School of Elec. & Inf. Engineering Beijing Univ. of Civil Engineering & Architecture Beijing China Fiberhome Comm. Tech. Co. Wuhan China

ISBN: (数字)9798331506209

ISBN: (纸本)9798331506216

Federated Learning enables multiple clients to collaboratively train a model without sharing their individual data, thereby protecting local data privacy. However, attackers, such as untrusted servers, can still compromise the privacy of clients’ local training data through various inf.rence attacks. One feasible approach to protect client privacy during training is the incorporation of differential privacy. Nevertheless, achieving an ideal level of privacy protection with differential privacy often degrades the model’s performance, significantly reducing its accuracy. To enhance model accuracy while minimizing the additional client heterogeneity introduced by differential privacy, this paper proposes a method that integrates personalized layers and data transformations, FusTP-FL. The core of our FusTP-FL is the incorporation of personalized layers and personalized data transformations within the client’s local training model, which further reduces client heterogeneity and improves model accuracy. We evaluated the model’s accuracy on six common datasets; experimental results demonstrate that the proposed FusTP-FL effectively enhances model accuracy across two different differential privacy modes (CDP and LDP), increasing it by up to 45%. Furthermore, we show that compared to PRIVATEFL, our method achieves lower client heterogeneity.

关键词： Training Differential privacy Privacy Accuracy Federated learning Computational modeling Training data Data models Servers Security

来源：评论

学校读者我要写书评

暂无评论

Detection of stator turns short-circuit during sensorless operation by means of the Direct Flux Control technique 12

Detection of stator turns short-circuit during sensorless op...

引用

12th AEIT International Annual Conference, AEIT 2020

作者： Grasso, Emanuele Palmieri, Marco Corti, Fabio Nienhaus, Matthias Cupertino, Francesco Grasso, Francesco University of Saarland Laboratory of Actuation Technology Saarbrücken Germany Politecnico di Bari Dept. Elec. and Inf. Engineering Bari Italy University of Florence Dept. of Information Engineering Firenze Italy

ISBN: (纸本)9788887237474

In the field of sensorless control techniques for Permanent Magnet Synchronous machines, many solutions have been proposed that are based on the exploitation of the machine anisotropies. Among them, the Direct Flux Control (DFC) technique allows sensorless operation by measuring the star-point voltage of the machine. Given the high signal to noise ratio of the DFC measurements, such technique can be potentially used not only for sensorless operation but also for condition monitoring and fault detection. In this work, after a brief introduction on the technique, an analysis of the effects of stator inter-turns short-circuit fault on the DFC measurements is presented in order to provide a better insight on the capability of DFC as fault detector. Simulation results are finally shown and discussed. © 2020 AEIT.

关键词： Fault detection

来源：评论

学校读者我要写书评

暂无评论

Reinf.rcement Causal Structure Learning on Order Graph

arXiv

引用

arXiv 2022年

作者： Yang, Dezhi Yu, Guoxian Wang, Jun Wu, Zhengtian Guo, Maozu School of Software Shandong University Jinan China SDU-NTU Joint Centre for AI Research Shandong University Jinan China School of Electronic and Information Engineering Suzhou University of Science and Technology Suzhou China College of Elec. & Inf. Eng. Beijing University of Civil Engineering and Architecture Beijing China

Learning directed acyclic graph (DAG) that describes the causality of observed data is a very challenging but important task. Due to the limited quantity and quality of observed data, and non-identifiability of causal graph, it is almost impossible to inf.r a single precise DAG. Some methods approximate the posterior distribution of DAGs to explore the DAG space via Markov chain Monte Carlo (MCMC), but the DAG space is over the nature of super-exponential growth, accurately characterizing the whole distribution over DAGs is very intractable. In this paper, we propose Reinf.rcement Causal Structure Learning on Order Graph (RCL-OG) that uses order graph instead of MCMC to model different DAG topological orderings and to reduce the problem size. RCL-OG first defines reinf.rcement learning with a new reward mechanism to approximate the posterior distribution of orderings in an efficacy way, and uses deep Q-learning to update and transfer rewards between nodes. Next, it obtains the probability transition model of nodes on order graph, and computes the posterior probability of different orderings. In this way, we can sample on this model to obtain the ordering with high probability. Experiments on synthetic and benchmark datasets show that RCL-OG provides accurate posterior probability approximation and achieves better results than competitive causal discovery algorithms. Copyright © 2022, The Authors. All rights reserved.

关键词： Reinf.rcement learning

来源：评论

学校读者我要写书评

暂无评论

Stabilization of THz waves using chaos supremacy

Stabilization of THz waves using chaos supremacy

引用

2023 International Conference on Smart-Green technology in elec.rical and inf.rmation Systems, ICSGTEIS 2023

作者： Kuwashima, Fumiyoshi Jarrahi, Mona Cakmakyapan, Semih Wada, Kenji Haraguchi, Masanobu Kawakami, Yuki Moriyasu, Takeshi Morikawa, Osamu Kurihara, Kazuyoshi Kitahara, Hideaki Furuya, Takashi Nakajima, Makoto Tani, Masahiko Fukui University of Technology Dep. of Electr. and Electron. Eng. Fukui Japan Ucla Electrical and Computer Eng. Los AngelesCA90095 United States Osaka Metropolitan University Dep. of Physics and Electronics Osaka Japan Tokushima Univ. Industrial and Social Science Grad. Sch. of Tech. Tokushima Japan Fukui Col. Natl. Inst. of Tech. Dep. of Elec. and Inf. Eng. Fukui Japan University of Fukui Faculty of Engineering Fukui Japan Japan Coast Guard Academy Liberal Arts Kure Japan University. of Fukui School of Education Fukui Japan FIR-UF University of Fukui Fukui Japan Osaka Univ. Inst. of Laser Engineering Osaka Japan

ISBN: (纸本)9798350382822

We apply the chaos supremacy of laser chaos system to the high stabilization of THz waves. Stability was demonstrated by down converting the optical beats between laser longitudinal modes in the THz domain to the radio frequency domain and comparing a conventional free running CW laser diode to a chaotically oscillating laser diode. Because of their exceptional stability, chaotically oscillating lasers are attractive options for optical pump sources in terahertz time-domain spectroscopy systems. © 2023 IEEE.

关键词： Stabilization

来源：评论

学校读者我要写书评

暂无评论

Automated Mura Defect Detection System on LCD Displays using Random Forest Classifier

Automated Mura Defect Detection System on LCD Displays using...

引用

IEEE International Conference on Consumer elec.ronics (ICCE)

作者： Gustavo M. Torres Adriana S. Souza David A. O. Ferreira Luiz C. S. G. Júnior Kethilen Y. Ouchi Myke D. M. Valadão Mateus O. Silva Victor L. G. Cavalcante Edma V. C. U Mattos Antônio M. C. Pereira Caio F. S. Cruz Agemilson P. Silva Ruan J. S. Belem André S. Costa Lucas G. C. Evangelista Wilson C. C. Junior Ricardo G. Paula Thiago B. Bezerra Waldir S. S. Júnior Celso B. Carvalho Federal University of Amazonas and Center for R&D in Elec. and Inf. Tech. (UFAM/CETELI) AM-Brazil ENVISION/TPV Group Technology Limited AM-Brazil ICTS Institute Center of Development Research in Software Technology AM-Brazil

Mura on LCD displays are challenging visual defects to detect, due to uneven brightness of the panel. So, automatic detection of mura defects on TVs and monitors is an important application to ensure the quality of LCDs manufactured in elec.ronic product factories. In this work, conducted by three partners, called UFAM/CETELI, Envision (TPV Group) and ICTS, we propose an automated mura defect detection system on LCD displays that are based on similarities of the histograms and a machine learning (ML) algorithm called random forest. For comparison with the proposed method, we use one of the most popular methods of ML called k-Nearest Neighbors (k-NN). The experimental results show a detection rate above 99%, and processing time of 27 milliseconds per image, highlighting as contributions of our proposal, the high accuracy and reduced processing time, which allows the use of our solution in real production processes of LCD monitors.

关键词： Visualization TV Machine learning algorithms Shape Liquid crystal displays Production facilities Visual databases

来源：评论

学校读者我要写书评

暂无评论

Automated Bright Pixel Detection System on LCD Displays

Automated Bright Pixel Detection System on LCD Displays

引用

IEEE International Conference on Consumer elec.ronics (ICCE)

作者： Mateus O. Silva David A. O. Ferreira Kethilen Y. Ouchi Gustavo M. Torres Edma V.C. Urtiga Mattos Antônio M. C. Pereira Luciana R. Costa Victor L. G. Cavalcante Caio F.S. Cruz Agemilson P. Silva Ruan J.S. Belem Anderson S. Jesus Wilson C.C. Junior Ricardo G. Paula Thiago B. Bezerra Waldir S. S. Júnior Celso B. Carvalho Federal University of Amazonas and Center for R&D in Elec. and Inf. Tech. (UFAM/CETELI) AM Brazil ENVISION/TPV Group Technology Limited AM Brazil ICTS Institute Center of Development Research in Software Technology AM Brazil

Bright pixel defect occurs in LCDs when a transistor of a subpixel remains bright. Bright pixels reduce the quality of manufactured devices, negatively impacting companies looking to meet an increasingly demanding market. In this wokr, conducted by three partners, called UFAM/CETELI, Envision (TPV Group) and ICTS, we propose an automated bright pixel defect detection system on LCD displays, which works in conjunction with two proposed methods, the quartile-based method and the standard-based method to identify bright pixels in LCDs. The proposals obtained as best result 100% of accuracy and between 0.397s and 0.193s of average processing time per image. The results of high accuracy and reduced processing time demonstrate the contribution of our proposal, being possible to use it in the detection of bright pixels in real production lines that use LCDs on TVs or monitors.

关键词： TV Conferences Distributed databases Production Companies Liquid crystal displays Proposals

来源：评论

学校读者我要写书评

暂无评论

Stable THz wave out put power using laser chaos

Stable THz wave out put power using laser chaos

引用

International Conference on inf.ared and Millimeter Waves

作者： Fumiyoshi Kuwashima Mona Jarrahi Semih Cakmakyapan Kenji Wada Masanobu Haraguchi Yuki Kawakami Takeshi Moriyasu Osamu Morikawa Kazuyoshi Kurihara Hideaki Kitahara Takashi Furuya Makoto Nakajima Masahiko Tani Dep. of Electr. and Electron. Eng. Fukui University of Technology Fukui Japan Electrical and Computer Eng. UCLA Los Angeles CA USA Dep. of Physics and Electronics Osaka Metropolitan University Osaka Japan Dep. of Elec. and Inf. Eng. Natl. Inst. of Tech. Fukui Col. Fukui Japan Faculty of Engineering University of Fukui Fukui Japan Chair of Liberal Arts Japan Coast Guard Academy Kure Japan School of Education University. of Fukui Fukui Japan FIR-UF University of Fukui Fukui Japan Inst. of Laser Engineering Osaka Univ. Osaka Japan

We generate stable optical beats using laser chaos. This optical beat is converted to THz waves through the photoconductive antenna. The output of the THz wave was roughly estimated by comparison with the output of th... 详细信息

ISBN: (数字)9798350370324

ISBN: (纸本)9798350370331

关键词： Chaos Power lasers Laser stability Laser excitation Antennas Oscillators

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：