检索结果-内蒙古大学图书馆

International computer Sciences and Information Technologies (CSIT)

作者： Nataliia Lutska Lidiia Vlasenko Nataliia Zaiets Vitaliy Lysenko dept. of Automation and Computer Technologies of Control Systems National University of Food Technologies Kyiv Ukraine dept. of Software Engineering and Cyber Security State University of Trade and Economics Kyiv Ukraine dept. of Automation and Robotic Systems National University of Life and Environmental Sciences of Ukraine Kyiv Ukraine

ISBN: (纸本)9798350334326

Relevant today is the digitalization of industrial enterprises, which is an evolutionary continuation of the introduction of MES/MOM. At the same time, an important role is played by the construction of mathematical models for various purposes, which are the main component of the Digital Twin development. Digital Twin provides a new philosophy for conducting enterprise production processes based on these models, which is aimed at improving the efficiency of both individual sectors and the enterprise as a whole. To increase the profit of the enterprise, it is necessary to ensure the planned productivity of technological processes, the final indicator of which is the yield of sugar. Taking into account that a significant number of material flows operate at the enterprise, only production flows with which the operator-technologist works are singled out in the work. The selected flows, based on expert assessments, were assigned weighted values of the impact on the overall performance of the sugar production. This made it possible to build a mathematical model that predicts the yield of sugar from input flows. The structure and parameters of this model are determined by machine learning methods. This is a feed-forward neural network MLP 7-23-23-1, which provides forecast accuracy with an error of less than 1%. The model can be used to model, correct, and predict the process conditions of an enterprise, which will increase the overall productivity of the sugar factory.

关键词： Productivity Biological system modeling Machine learning Predictive models Mathematical models Sugar industry Production facilities

来源：评论

学校读者我要写书评

暂无评论

Selection of Beamforming in 5G MIMO scenarios using Machine Learning approach

Selection of Beamforming in 5G MIMO scenarios using Machine ...

引用

International Conference on Electrical engineering/Electronics, computer, Telecommunications and Information Technology, ECTI-CON

作者： Douglas Henrique Silva David Augusto Ribeiro Miguel Arjona Ramí rez Renata Lopes Rosa Sushank Chaudhary Demó stenes Zegarra Rodrí guez Dept. of Computer Science Federal University of Lavras Lavras-MG Brazil Dept. of Automation Federal University of Lavras Lavras-MG Brazil Dept. of Electronic Systems Engineering University of S&#x00E3 o Paulo S&#x00E3 o Paulo Brazil Dept. of Electrical Engineering Chulalongkorn University Bangkok Thailand

In new generation networks, 5G and 6G networks, intelligent mechanisms based on artificial intelligence algorithms are playing a relevant role in the performance improvement at different network levels. In 5G networks, different techniques are used, such as MIMO systems, and its network infrastructure is utilized by diverse services, for instance, vehicular communications. Thus, the description and the tracing of a communication scenario needs a large volume of data. Because of the difficulty to implement actual 5G networks, there is a lack of datasets containing complete 5G scenarios, the data is not enough or contain imbalanced classes to properly train machine learning (ML) algorithms. In this context, we propose a method to increase the amount of data to improve the machine learning performance of some classification models, specifically Random Forest, Multilayer Perceptron, and k-Nearest Neighbors. In the experimental results of the test phase, considering the inclusion of synthetic data, Random Forest, Multilayer Perceptron and k-Nearest Neighbors reached macro F1 scores of 0.9341, 0.9241 and 0.9456, respectively, which are superior to the results obtained when training with the original data only.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fast Measurement of Impedance Calculation for Electrochemical Impedance Spectroscopy

Fast Measurement of Impedance Calculation for Electrochemica...

引用

International SoC Design Conference, ISOCC

作者： En-Chi Yang Suz-Ting Wang Kusn-Lin Liu Wen-Ho Juang Ming-Hwa Sheu How-Chiun Wu Shin-Chi Lai Dept. Electronics Engineering / Dept. Doctor’s Program of Smart Industry Technology Research and Design National Yunlin University of Science and Technology / National Formosa University Douliu Taiwan / Huwei Taiwan Dept. Doctor’s Program of Smart Industry Technology Research and Design National Formosa University Huwei Taiwan Dept. Electronics Engineering National Yunlin University of Science and Technology Douliu Taiwan Dept. Computer Science and Information Engineering National Formosa University Huwei Taiwan Dept. Natural Biotechnology Nanhua University Chiayi Taiwan Dept. Automation Engineering & Smart Machinery and Intelligent Manufacturing Research Center National Formosa University Huwei Taiwan

This paper presents a design for a fast measurement electrochemical impedance spectroscopy (EIS) system, which differs from the traditional single-frequency point calculation approach. The proposed system is capable of simultaneously measuring 23 frequency points within the frequency range of 1Hz-10KHz. Additionally, it has an impedance measurement range of 100$\omega$ - 1M$\omega$. The experimental results demonstrate that the average MRE and PAE are both below 0.4% and 1°, with conditions of R=9940 $\omega$ and C=1.02uF.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DROPO: Sim-to-Real Transfer with Offline Domain Randomization

arXiv

引用

arXiv 2022年

作者： Tiboni, Gabriele Arndt, Karol Kyrki, Ville Dept. of Control and Computer Engineering Politecnico di Torino Francesco Ferrucci Street 112 Torino10141 Italy Intelligent Robotics Group Dept. of Electrical Engineering and Automation Aalto University Maarintie 8 Espoo02150 Finland

In recent years, domain randomization over dynamics parameters has gained a lot of traction as a method for sim-to-real transfer of reinforcement learning policies in robotic manipulation;however, finding optimal randomization distributions can be difficult. In this paper, we introduce DROPO, a novel method for estimating domain randomization distributions for safe sim-to-real transfer. Unlike prior work, DROPO only requires a limited, precollected offline dataset of trajectories, and explicitly models parameter uncertainty to match real data using a likelihood-based approach. We demonstrate that DROPO is capable of recovering dynamic parameter distributions in simulation and finding a distribution capable of compensating for an unmodeled phenomenon. We also evaluate the method in two zero-shot sim-to-real transfer scenarios, showing successful domain transfer and improved performance over prior methods. Copyright © 2022, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Analysis of the wheatstone bridge radiometer performance dependence on the ambient temperature 5

Analysis of the wheatstone bridge radiometer performance dep...

引用

5th International Symposium on Instrumentation Systems, Circuits and Transducers, INSCIT 2021

作者： Segundo, Jose Taunai Dantas Dantas, Evandson Claude Seabra Catunda, Sebastian Yuri Cavalcanti Belfort, Diomadson Rodrigues Federal University of Rio Grande Do Norte PPGEEC1 Natal-RN Brazil Federal University of Rio Grande Do Norte Dept. of Computer Engineering and Automation Natal-RN Brazil Federal University of Rio Grande Do Norte Dept. of Electrical Engineering Natal-RN Brazil

ISBN: (纸本)9781728197265

In this paper it is analysed the performance dependence on the ambient temperature of the constant temperature Wheatstone Bridge architecture for a radiometer. The parameters considered in this analysis are the sensitivity, response time, and circuit power consumption. The analysis was carried out through simulations in SPICE using a developed model of a positive temperature coefficient thermoresistive sensor. The results show that the ambient temperature plays a major influence of the architecture performance evidencing as main limitation of this architecture. © 2021 IEEE.

关键词： Temperature

来源：评论

学校读者我要写书评

暂无评论

Comparative Study on the Results of Student Assessment Data Developed by SURE Model 15

Comparative Study on the Results of Student Assessment Data ...

引用

15th International Scientific-Technical Conference on Actual Problems of Electronic Instrument engineering, APEIE 2021

作者： Senden, Delgermaa Shambaljamts, Tsooj Tudevdagva, Uranchimeg Reva, Ivan L. Mongolian University of Science and Technology Department of Mechanical Science Ulaanbaatar Mongolia Chemnitz University of Technology Computer Sceince Faculty Chemnitz Germany Novosibirsk State Technical University Faculty of Automation and Computer Engineering Dept. of Data Security Novosibirsk Russia

ISBN: (纸本)9781665434089

The Mongolian University of Science and Technology collects information (data) related to teaching methods and learning environment using a brief questionnaire from each student each semester. The data collected via questionnaires should be used for analysis of education activities, as well as development of policy level measures directed to improve education quality and teaching methods. However, as was observed by teachers, there is still an insufficiency in development of collected data and actions taken based on the results. In order to conduct comparative study within the framework of this issue, one module was taught by the same teacher (Theoretical mechanics 2) and other three different subjects (Mathematics 1, Information Technology 1, Theoretical Mechanics 1) were chosen, which are selected by most of the students, and ultimately processed the results with the use of the SURE model of structure-based evaluation. In this article, a total of 66681 evaluation data were provided by students who completed general education courses, professional foundation courses and other specialized courses at three schools (School of Industrial Technology, School of Mechanical engineering and Transportation, School of Information and Telecommunication Technology) under the MUST, and these data were processed with the use of evaluation model mentioned above and the results were compared with the outcomes of previous study. © 2021 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Discrete-time Sliding Mode Control with Second-Order Decoupled Disturbance Compensator to Improve the Stability and Robustness

Discrete-time Sliding Mode Control with Second-Order Decoupl...

引用

International Conference on Control, automation and Systems ( ICCAS)

作者： Dae-Young Yang Tae-Ho Oh Young-Seok Kim Tae-Hoon Kim Sang-Hoon Lee Dong-Il “Dan” Cho ASRI/ISRC Dept. of Electrical and Computer Engineering Seoul National University Seoul Korea RS Automation Co. Ltd Gyeonggi-do Korea

This paper presents a design method for the discrete-time sliding mode control (DSMC) with a second-order decoupled disturbance compensator (DDC). A DSMC with DDC has been widely used for industrial servo systems. The method has asymptotic convergence properties in the systems with slowly-varying disturbance and parametric uncertainty. The DDC can be modeled as a disturbance observer (DOB) with a first-order Q-filter structure. However, when the difference between the nominal plant model and the actual plant is large, this first-order Q-filter does not sufficiently minimize the effects of model uncertainties, which hinder applying a high DDC gain. Hence, high gains for high performance cannot be used. In this paper, a DSMC with a second-order DDC is developed to improve the system stability and robustness. The proposed method minimizes the effects of model uncertainties and increases the stability margin. As a result, high gains can be used for high performance. The developed method is applied to industrial servo systems and experimental results show enhanced stability performance, when compared to the DSMC with first-order DDC.

关键词： Asymptotic stability Uncertainty Design methodology Cutoff frequency Stability analysis Robustness Disturbance observers

来源：评论

学校读者我要写书评

暂无评论

MeWEHV: Mel and Wave Embeddings for Human Voice Tasks

arXiv

引用

arXiv 2022年

作者： Carofilis, Andrés Fernández-Robles, Laura Alegre, Enrique Fidalgo, Eduardo Dept. of Electrical Systems and Automation Engineering School of Industrial Computer and Aerospace Engineering Universidad de León León24007 Spain Researcher at INCIBE Spanish National Cybersecurity Institute León Spain Dept. of Mechanical Computer and Aerospace Engineering Universidad de León Spain

A recent trend in speech processing is the use of embeddings created through machine learning models trained on a specific task with large datasets. By leveraging the knowledge already acquired, these models can be reused in new tasks where the amount of available data is small. This paper proposes a pipeline to create a new model, called Mel and Wave Embeddings for Human Voice Tasks (MeWEHV), capable of generating robust embeddings for speech processing. MeWEHV combines the embeddings generated by a pre-trained raw audio waveform encoder model, and deep features extracted from Mel Frequency Cepstral Coefficients (MFCCs) using Convolutional Neural Networks (CNNs). We evaluate the performance of MeWEHV on three tasks: speaker, language, and accent identification. For the first one, we use the VoxCeleb1 dataset and present YouSpeakers204, a new and publicly available dataset for English speaker identification that contains 19607 audio clips from 204 persons speaking in six different accents, allowing other researchers to work with a very balanced dataset, and to create new models that are robust to multiple accents. For evaluating the language identification task, we use the VoxForge and Common Language datasets. Finally, for accent identification, we use the Latin American Spanish Corpora (LASC) and Common Voice datasets. Our approach allows a significant increase in the performance of state-of-the-art models on all the tested datasets, with a low additional computational cost. © 2022, CC BY-NC-ND.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Innovative Competency-Based Electrical engineering Curriculum 54

Innovative Competency-Based Electrical Engineering Curriculu...

引用

54th IEEE Frontiers in Education Conference, FIE 2024

作者： Rehder, Gustavo P. Serrano, Ariana L. C. Grimoni, José B. Brandão, Anarosa A. F. Silva, Magno M. T. Moriya, Henrique T. Panazio, Cristiano M. Barbero, Edson Alayo, Marco I. Gianesi, Irineu G. N. Seabra, Antonio C. Universidade de São Paulo Electronic Systems Department The Escola Politécnica São Paulo Brazil Universidade de São Paulo Electric Automation and Energy Dept. The Escola Politécnica São Paulo Brazil Universidade de São Paulo Computer Engineering and Digital Systems Department The Escola Politécnica São Paulo Brazil Universidade de São Paulo Telecommunications and Control Dept. The Escola Politécnica São Paulo Brazil Á lvares Penteado School of Commerce Foundation São Paulo Brazil Instituto Mauá de Tecnologia São Paulo Brazil

ISBN: (纸本)9798350351507

The Electrical engineering undergraduate program of the Escola Politécnica of the Universidade de São Paulo has created an alternative innovative curriculum path for its freshmen students in 2024. The Competency-based Path emphasizes the development of competencies and skills for the unprecedented technological advancements that necessitate a holistic education for future electrical engineers, preparing them with practical skills for real-world challenges. The program was designed using an innovative methodology and centers around semester-long or year-long integrative projects. These projects bridge the gap between theory and practice, as students deal with real-world challenges while fostering social responsibility. © 2024 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Local Topology Inference of Mobile Robotic Networks under Formation Control

arXiv

引用

arXiv 2022年

作者： Li, Yushan He, Jianping Cai, Lin Guan, Xinping The Dept. of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai China The Dept. of Electrical and Computer Engineering University of Victoria BC Canada

The interaction topology is critical for efficient cooperation of mobile robotic networks (MRNs). We focus on the local topology inference problem of MRNs under formation control, where an inference robot with limited observation range can manoeuvre among the formation robots. This problem faces new challenges brought by the highly coupled influence of unobservable formation robots, inaccessible formation inputs, and unknown interaction range. The novel idea here is to advocate a range-shrink strategy to perfectly avoid the influence of unobservable robots while filtering the input. To that end, we develop consecutive algorithms to determine a feasible constant robot subset from the changing robot set within the observation range, and estimate the formation input and the interaction range. Then, an ordinary least squares based local topology estimator is designed with the previously inferred information. Resorting to the concentration measure, we prove the convergence rate and accuracy of the proposed estimator, taking the estimation errors of previous steps into account. Extensions on nonidentical observation slots and more complicated scenarios are also analyzed. Comprehensive simulation tests and method comparisons corroborate the theoretical findings. Copyright © 2022, The Authors. All rights reserved.

关键词： Topology

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：