检索结果-内蒙古大学图书馆

Asian control Conference

作者： Aulia Rahma Jumardi Nadana Ayzah Azis Yul Yunazwin Nazaruddin Vebi Nadhira Faculty of Industrial Technology Instrumentation and Control Master Program Institut Teknologi Bandung Bandung Indonesia Faculty of Industrial Technology Engineering Physics Doctoral Program Institut Teknologi Bandung Bandung Indonesia Department of Engineering Physics Instrumentation Control and Automation Research Group Institut Teknologi Bandung Bandung Indonesia

ISBN: (数字)9789887581598

ISBN: (纸本)9798331540845

To enhance the accuracy of vehicle localization, this research proposes a map matching system with a distinct architecture involving four key stages. Each GPS point creates a local map, and the system detects reference points within that map, subsequently calculating Euclidean distances and determining observation and transmission probabilities. The matching results yield the actual position of the vehicle on the map. The localization algorithm incorporates distance computation using a sliding window technique, observation probability based on proximity between GPS and reference points, and transmission probability to minimize errors. The study employs real-world tests in Bandung, Indonesia, demonstrating successful correction of GPS positions using the proposed method. In conclusion, this research provides a significant contribution in enhancing the accuracy of autonomous vehicle localization. By employing a probabilistic approach to observation and transmission, the method effectively corrects the vehicle's position, compensating for potential inaccuracies introduced by GPS. The utilization of a local map also proves impactful by including reference point positions, resulting in more precise outcomes. From the conducted field tests, all GPS points are accurately detected in their actual positions where there are seven GPS points do not match to vehicle trajectory, after the matching process, all point positions are successfully corrected, ensuring accurate localization by the system.

关键词： Location awareness Accuracy Computer architecture Probability Probabilistic logic Trajectory Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Intelligent sensors based on amorphous nanostructures according to achieve an optimal waste collection in Lima Peru

Intelligent sensors based on amorphous nanostructures accord...

引用

IEEE Conference on Industrial Electronics and Applications (ICIEA)

作者： J. Alan Calderón Ch. E. Benjamín Barriga G. Julio C. Tafur Alan Ccarita John Lozano Rodrigo Urbizagástegui Applied Nanophysics Institute for Physics Technical University of Ilmenau Ilmenau Germany Engineering Department Mechatronics Engineering Master Program Pontificia Universidad Católica del Perú Perú Engineering Department Mechanical Engineering Master Program Pontificia Universidad Católica del Perú Perú Engineering Department Control Engineering and Automation Master Program Mechatronic Engineering Master Program Pontificia Universidad Católica del Perú Perú Northen (Artic) Federal University Named After MV Lomonosov Arkhangelsk Russian Federation Engineering Department Engineering Electronic Section Pontificia Universidad Católica del Perú Perú

ISBN: (纸本)9781665409858

An optimal waste collection is a very complicated task in different countries. However, this task is more intricate, when there is not an organized procedure between people, government and technology. In this research it was studied and proposed strategies, to optimize the waste collection by technical suggestions, that were based on mathematical analysis and new technologies applications of sensors based on nanostructures due to this kind of sensors have good performance to measure physical variables in not simple places and conditions, such as around waste. Hence the reason, this work is prepared to contribute in the development of sensors based on nanostructures according to detect the physical variables: temperature, humidity, infrared reflection, moreover carbon dioxide (CO2) and methane (CH4) gases, which help to monitor the consequences of a not correct waste *** dependence on central and local government rules of waste management, it could be possible to find solution about organized waste collection, in which every family and walkers in streets would have the task to select the organic and inorganic garbage before the government trucks take the contents of the garbage trash cans to the landfill garbage dumps. However, many times the trash cans are not taken on time by the government trucks and garbage from them are producing gases and decomposition that causes contamination that damages health. Therefore, in this work there are proposed designed intelligent sensors, which are fixed in the trash cans due to measure physical parameters to give alarm for administrators controllers of boxes and to enhance the garbage selections from homes and streets to the main garbage landfills of the city. In other side, there will not be right solution in the waste collection, no matter the high advantage technologies, while humans could not be sensitive under this problematic. There are cleaned areas in cities, as for example touristic places, nevertheless, there

关键词： Temperature sensors Temperature measurement Waste management Gases Temperature dependence Urban areas Nanostructures

来源：评论

学校读者我要写书评

暂无评论

Design of Image-Based Autonomous Landing Instrumentation and control System for Unmanned Quadrotor Vehicles

Design of Image-Based Autonomous Landing Instrumentation and...

引用

Information Technology International Seminar (ITIS)

作者： Ihsan M. Fauzan Faqihza Mukhlish Aditya Prayoga Robby Azhari Ahmad Instrumentation and Control Master Program Faculty of Industrial Technology Institut Teknologi Bandung Engineering Physics Research Group and Center for Instrumentation Technology and Automation Institut Teknologi Bandung Engineering Department PT. Sas Aero Sishan

ISBN: (数字)9798331521295

ISBN: (纸本)9798331521301

The study designs an instrumentation and control system for autonomous quadrotor landing using a visual marker as the landing target. For landing process, the marker used as a landing target is an embedded ArUco marker, capable for detection for both long range and close-range detection. Position of the quadrotor relative from the ArUco marker is estimated using Perspective-N-Point pose estimation. The estimation errors compared to actual measurements are under 20 cm, which is less than the distance between ArUco border and its center. To keep camera for facing downward during the flight, the 2 axis inertially stabilization platform (ISP). The designed ISP can maintain the camera orientation even when quadrotor angle has changed. The landing control system is made for two different scenarios. First scenario is for landing with Global Positioning System (GPS) support, and the second scenario is without GPS support. The landing control system in GPS support scenario uses velocity setpoint to control the quadrotor while in without GPS support scenario, control system uses angle-thrust setpoint to control quadrotor. Quadrotor landing control system can attempt landing on top of the ArUco marker in both scenarios. The trajectory Mean Average Error (MAE) of x and y coordinates and radius of the landing process is (0.108, 0.326, 0.359) m for GPS support scenario and (0.301, 0.251, 0.436) m for without GPS support scenario.

关键词： Seminars Visualization Instruments Pose estimation Process control control systems Cameras Trajectory Quadrotors Global Positioning System

来源：评论

学校读者我要写书评

暂无评论

Biophotogrammetry model of respiratory motion analysis applied to children

Biophotogrammetry model of respiratory motion analysis appli...

引用

Annual International Conference of the IEEE engineering in Medicine and Biology Society (EMBC)

作者： W. L. Ripka D. da V. Ricieri L. Ulbricht E. B. Neves A. M. W Stadnik E. F. R. Romaneli Electrical Engineering and Industrial Computing Program Federal University of Technology Paraná Brazil Physical Education Department Federal University of Paraná Brazil Master Program in Biomedical Engineering Physical Education Federal University of Technology Paraná Brazil Control and Automation Engineering Federal University of Technology Paraná Brazil

This study aimed to test a protocol of measurements based on Biophotogrammetry to Analysis of Respiratory Mechanics (BARM) in healthy children. Seventeen normal spirometric children (six male and 11 female) were tested. Their performed maneuvers of forced inspiratory vital capacity were recorded in the supine position. The images were acquired by a digital camera, laterally placed to the trunk. Surface markers allowed that the files, exported to CorelDraw® software, were processed by irregular trapezoids paths. Compartments were defined in the thoracic (TX), abdominal (AB) and the chest wall (CW). They were defined at the end of an inspiration and expiration, both maximum, controlled by a digital spirometer. The result showed that the measured areas at the inspiratory and expiratory periods were statistically different (p

关键词： Muscles Educational institutions Lungs Member and Geographic Activities Board committees Biological system modeling Pediatrics Surface treatment

来源：评论

学校读者我要写书评

暂无评论

Comparison Performance on SOTA Deep Learning Models for Coffee Beans Grading Inspection

Comparison Performance on SOTA Deep Learning Models for Coff...

引用

Asian control Conference

作者： Achmad Norman Firdaus Amalia Rakhmawati Vebi Nadhira Suprijanto Endang Juliastuti Gema Nuran Utomo Ayu Gareta Risangtuni Master Program on Instrumentation and Control Faculty of Industrial Technology Bandung Institute of Technology Bandung Indonesia Graduate Program on Engineering Physics Faculty of Industrial Technology Bandung Institute of Technology Bandung Indonesia Instrumentation Control and Automation Research Group Faculty of Industrial Technology Bandung Institute of Technology Bandung Indonesia

ISBN: (数字)9789887581598

ISBN: (纸本)9798331540845

Several coffee producers rely on manual inspection for quality control, which is prone to inconsistencies and time consumption. Recent studies have proposed Comparison performance on State-of-The-Art (SOTA). Deep learning models were investigated as part of the proposed intelligent computer vision for faster and more reliable coffee bean grading. Performance Deep learning models, i.e., MobileNetV3Small, ResNet50, EfficientNetV2L, and DenseNet201, were evaluated to grade the quality of coffee beans that followed a grading procedure based on Indonesian National Standard (SNI) 01-2907-2008. A specific tray was designed to position coffee beans evenly without overlap for sample preparation, which consist of about 500–600 coffee beans. The process of capturing images is conducted systematically, focusing on each type of coffee bean defect individually. For comparison of SOTA models, five classes of coffee bean defects, With 1053 beans per class, the total dataset comprises 5265 beans. This dataset was divided into 10% for testing and 90% for training. Within the training data, 12% was reserved for validation. The result from this paper shows that MobileNetV3Small achieves the highest accuracy (99.43%) with minimal memory and parameters. Its efficient design allows for robust feature extraction, crucial for distinguishing subtle defect features. While larger models like ResNet50 and EfficientNetV2L also perform well, they exhibit higher memory and parameters.

关键词： Deep learning Training Accuracy Computational modeling Training data Inspection Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Adversarially Robust Reinforcement Learning for Urban Traffic Signal control

Adversarially Robust Reinforcement Learning for Urban Traffi...

引用

International Conference on Technology, Informatics, Management, engineering, and Environment (TIME-E)

作者： Muhammad Shafly Hamzah Endra Joelianto Herman Yoseph Sutarto Adiyana Putri Instrumentation and Control Master Program Institut Teknologi Bandung Bandung Indonesia Instrumentation Control and Automation Research Group Institut Teknologi Bandung Bandung Indonesia Department of Intelligent System PT. Pusat Riset Energi Bandung Indonesia Doctoral Program of Engineering Physics Institut Teknologi Bandung Bandung Indonesia

ISBN: (数字)9798350364750

ISBN: (纸本)9798350364767

Urban traffic congestion presents critical challenges, resulting in delays, environmental pollution, and significant economic costs. While traditional traffic control methods, such as fixed-time and adaptive systems, have been widely implemented, they often fail in unpredictable conditions, particularly when confronted with noisy or inaccurate data. This research proposes a robust reinforcement learning (RL) solution for traffic signal control using the RADIAL-DQN (Robust Adversarial Loss DQN) algorithm. Integrating adversarial training enhances the system's robustness to real-world uncertainties. Evaluations conducted using a SUMO traffic simulation show that the robust agent produced an increase of only 60.71% in queue length under a projected gradient descent (PGD) adversarial attack, outperforming standard RL agents, which experienced an 89% increase. These results demonstrate the potential of robust RL to improve both the reliability and scalability of urban traffic control systems.

关键词： Training Adaptive systems Uncertainty Scalability Urban areas Traffic control Robustness Standards Traffic congestion Testing

来源：评论

学校读者我要写书评

暂无评论

Design of a fractional order PI controller for steam pressure in the steam drum of a bagasse fired boiler

引用

IFAC Proceedings Volumes 2014年第3期47卷 1337-1342页

作者： R. Rivas-Perez F. Castillo-Garcia J. Sotomayor-Moriano V. Feliu-Batlle Master Program in Control Engineering and Automation Pontificia Universidad Católica del Perú Lima Peru Havana Polytechnic University CUJAE Habana Cuba (Tel: 537-266-3285 Escuela Técnica Superior de Ingenieros Industriales Universidad de Castilla-La Mancha Ciudad Real Spain

This paper proposes a fractional-order PI controller for controlling the steam pressure in the steam drum of a bagasse fired boiler. The dynamics behavior of this process was experimentally identified. This identification procedure yielded an equivalent third order plus time delay model, and showed wide process static gain variations. We therefore propose a new methodology for the design of fractional-order robust controllers for this class of processes. It was shown that the attained controllers significantly outperformed the robustness achieved with current PI controllers.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Verification of relationship between heart rate and body movement for fatigue estimation

Verification of relationship between heart rate and body mov...

引用

IEEE International Conference on Industrial Informatics (INDIN)

作者： Jinhua She Hitoshi Nakamura Junya Imani Yasuhiro Ohyama Hiroshi Hashimoto Min Wu School of Information Science and Engineering Hunan Engineering Laboratory for Advanced Control and Intelligent Automation Changsha China School of Computer Science Tokyo University of Technology Hachioji Japan Graduate School of Bionics Tokyo University of Technology Hachioji Japan Master Program of Innovation for Design and Engineering Advanced Institute of Industrial Technology Japan

It is an urgent need to find an objective way to estimate the degree of fatigue of employees. In this study, we designed a monitoring and estimation system for the degree of fatigue. This paper explains a long-term pedaling experiment that we use it to explore the possibility to use only the time sequence data of head movement during pedaling to estimate the fatigue. While we show the possibility for this through experimental data, it is clear that we need to collect more data to establish an estimation method.

关键词： Fatigue Heart rate Estimation Educational institutions Monitoring Correlation Electronic mail

来源：评论

学校读者我要写书评

暂无评论

Quantification of C02 emission reductions from energy efficiency actions and solar photovoltaic generation at the Federal Institute of Education, Science, and Technology of Goiás

Renewable Energy and Power Quality Journal

引用

Renewable Energy and Power Quality Journal 2021年 19卷 45-50页

作者： Vidal, M.A. Faria, A.F. Stach, A.H.M. Netou, D.P. Pinto, L.S. Pinlio, A.G. Domingues, E.G. Master’s Program in Technology of Sustainable Process Federal Institute of Education Science and Technology Goias-Cainpuj Rua 75. n°46 - Centro Goiania - GO74055-110 Brazil Electiical Engineering Control and Automation Engineering Program Federal Institute of Education Science and Technology Goias-Cainpuj Rua 75. n°46 - Centro Goiania - GO74055-110 Brazil NeXT - Nucleus of Experimental and Technological Studies Federal Institute of Education Science and Technology Goias-Cainpuj Rua 75. n°46 - Centro Goiania - GO74055-110 Brazil

In 2016. die Brazilian Agency of Electric Energy-launched a public call for research and development projects to reduce barriers to implementing energy efficiency projects and own electricity generation. One objective of this public call was to encourage pilot projects at the Brazilian public higher education institutions. In this context, the Federal Institute of Education. Science, and Technology of Goias has approved the research project, entided "Energy efficiency and mini generation ai the Federal Institute of Education. Science, and Technology - IFG." The project consists of implementing energy efficiency actions and installing photovoltaic distributed generation (mini generation) in twelve of the fourteen IFG campuses. The main objective of this work is to quantify the C0;emission reductions from die project through the methodologies used by the United Nations Framework Climate Change Convention for projects under the Clean Development Mechanism The emission reductions over the project lifetime was estimated at approximately 37,400 iC’O- equivalent, evidencing the environmental benefit to be provided by the referred project. © 2021, European Association for the Development of Renewable Energy, Environment and Power Quality (EA4EPQ). All rights reserved.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Synthetic series of electricity generation through a photovoltaic system by using different panel temperature models

Renewable Energy and Power Quality Journal

引用

Renewable Energy and Power Quality Journal 2021年 19卷 39-44页

作者： Stach, A.H.M. Neto, D.P. Vidal, M.A. Souto, O.C.N. Silva, S.B. Domingues, E.G. Master’s Program in Sustainable Process Technology Federal Institute of Education Science and Technology of Goiás Brazil Rua 75 nº46-Centro Goiânia-GO74055-110 Brazil Electrical Engineering/Control and Automation Engineering Program Federal Institute of Education Science and Technology of Goiás Brazil Rua 75 nº46-Centro Goiânia-GO74055-110 Brazil NeXT-Nucleus of Experimental and Technological Studies Federal Institute of Education Science and Technology of Goiás Brazil Rua 75 nº46-Centro Goiânia-GO74055-110 Brazil

The electric energy produced by photovoltaic systems is a function of several variables that present random behavior, such as solar irradiance, ambient temperature, wind speed, and relative humidity. Several models describe the energy produced by these systems, which reflect the various factors that influence the generation and how significant these influences are. In this way, the present work aims to compare some panel temperature models and the electrical energy produced from a photovoltaic system located in the Midwest of Brazil. The applied methodology aims to evaluate the expected averages and standard deviations of the monthly synthetic series of generated energy to identify the main random variables that influence the electric generation. The results indicate the model that best describes the physical system concerning the randomness of the variables involved, the photovoltaic technology, the location, and the measurement period. © 2021, European Association for the Development of Renewable Energy, Environment and Power Quality (EA4EPQ). All rights reserved.

关键词： Stochastic models

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：