检索结果-内蒙古大学图书馆

An Empirical Study of Super-Resolution on Low-Resolution Micro-Expression Recognition

IEEE Transactions on Affective Computing 2025年

作者： Zhou, Ling Wang, Mingpei Huang, Xiaohua Zheng, Wenming Mao, Qirong Zhao, Guoying Macau University of Science and Technology School of Computer Science and Engineering 999078 China Nanjing Institute of Technology School of International Education Oulu School Jiangsu Nanjing211167 China Southeast University Key Laboratory of Child Development and Learning Science Ministry of Education Nanjing210096 China Southeast University Research Center for Learning Science China Southeast University School of Biological Science and Medical Engineering Jiangsu Nanjing210096 China Jiangsu University School of Computer Science and Communication Engineering Jiangsu Zhenjiang212013 China University of Oulu Center for Machine Vision and Signal Analysis 90014 Finland

Micro-expression recognition (MER) in low-resolution (LR) scenarios presents an important and complex challenge, particularly for practical applications such as group MER in crowded environments. Despite considerable advancements in super-resolution (SR) techniques for enhancing the quality of LR images and videos, few study has focused on investigate SR for improving LR MER. The scarcity of investigation can be attributed to the inherent difficulty in capturing the subtle motions of micro-expressions, even in original-resolution MER samples, which becomes even more challenging in LR samples due to the loss of distinctive features. Furthermore, a lack of systematic benchmarking and thorough analysis of SR-assisted MER methods has been noted. This paper tackles these issues by conducting a series of benchmark experiments that integrate both SR and MER methods, guided by an in-depth literature survey. Specifically, we employ seven cutting-edge state-of-the-art (SOTA) MER techniques and evaluate their performance on samples generated from 22 SOTA SR techniques, thereby addressing the problem of SR in MER. Through our empirical study, we uncover the primary challenges associated with SR-assisted MER and identify avenues to tackle these challenges by leveraging recent advancements in both SR and MER methodologies. Our analysis provides insights for progressing toward more efficient SR-assisted MER. © 2010-2012 IEEE.

关键词： Optical resolving power

来源：评论

学校读者我要写书评

暂无评论

Research on Design of Auditory Cues for Passive Control Switch for Level 3 Automated Vehicles

Research on Design of Auditory Cues for Passive Control Swit...

引用

IEEE International Conference on Intelligent Transportation Engineering (ICITE)

作者： Wenying Guan Jiaming Du Xiqiao Zhang Jinyu Shi the Chief Engineer Office Changchun Urban and Rural Development Committee Changchun China School of Transportation Science and Engineering Harbin Institute of Technology Harbin China

ISBN: (数字)9798350314212

ISBN: (纸本)9798350314229

When some special situations occur in L3 autonomous vehicles, the system needs to prompt the driver to take over in an appropriate way. Firstly, set the dynamic control right cutting scene as general warning, important warning and emergency warning; secondly, according to the sound attributes, the auditory prompts are divided into three categories: Auditory icon, Earcon and Voice prompts, and 9 types of auditory prompts are designed; The SCANeRTMstudio real-time vehicle dynamics simulation system performs simulation experiments on three types of switching scenarios to obtain the driver's psychological indicators and action indicators; finally, the use of analytic hierarchy process to determine the index weights, the psychological indicators and action indicators are transformed and weighted to build hearing Prompt evaluation system to determine the optimal auditory prompt method in each scenario.

关键词： Psychology Process control Switches Auditory system Control systems Real-time systems Indexes Vehicle dynamics Autonomous vehicles Vehicles

来源：评论

学校读者我要写书评

暂无评论

Detection Welding Performance of Industrial Robot Using Machine Learning

Detection Welding Performance of Industrial Robot Using Mach...

引用

International Technical Conference o Circuits/Systems, Computers and Communications (ITC-CSCC)

作者： Onjira Duongthipthewa Koonlachat Meesublak Atsushi Takahashi Chowarit Mitsantisuk Department of Electrical Engineering Kasetsart University Bangkok Thailand National Electronics and Computer Technology Center National Science and Technology Development Agency Pathumthani Thailand Department of Information and Communications Engineering Tokyo Institute of Technology Tokyo Japan

Automated welding robots have become an essential component in manufacturing industries due to their precision and increased productivity. Furthermore, they eliminate the need for human workers to be exposed to toxic fumes and bright light during welding processes, ensuring worker safety. However, any failure in welding robots can lead to poor product quality and impact a company's credibility. Therefore, it is critical to predict the welding performance of these machines to maintain product quality. This study proposes the use of spectrogram image classification to classify the quality of welding products. Using a TM-1400 WGIII welding robot, 180 welding datasets were collected to determine the conditions of the welding robot based on different welding wire lengths. Current and voltage signals of the welding robot were studied to identify suitable input parameters and machine learning algorithms were utilized to improve the accuracy of the predictive welding quality. The experiment resulted in an accuracy of 89% based on a 70% training sets and 30% testing sets of data, indicating that spectrogram image classification is an effective technique to monitor the condition of welding robots, improve welding quality, and increase product quality control. This method can be beneficial for both small- and large-scale industries such as automotive, energy, and construction.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design of Target Tracking Ball Gear Pan-Tilt System Based on Machine Vision

Design of Target Tracking Ball Gear Pan-Tilt System Based on...

引用

Control Engineering and Robotics (ISCER), International Symposium on

作者： Weichong Gu Tingbo Huang Lei Zhao Zhilin Wu Zhihui Zhou School of Mechanical Engineering Nanjing University of Science and Technology Nanjing China Research & Development Centre Jiangsu Airship Co Ltd. Taizhou China

The trend of intelligent and unmanned industries benefited from the rapid development of information technology is more and more obvious. The unmanned combat platform has become a new combat force in anti-terrorism operations, relying on sensor, machine vision, communication, information fusion and other technologies. A design scheme of pan-tilt target tracking system based on machine vision is proposed here for the visual perception requirements of unmanned combat platform. A combination of YOLOv4-tiny and DeepSORT is used to identify and track personnel with cameras mounted on ball gears. When the target moves to the edge of view, the position information will be sent to the control circuit through serial communication, and the camera will be adjusted with the PID control algorithm to keep the target in the center of view. The experimental results showed that this system can achieve target tracking effectively in real time and the tracking success rate can reach 80% by optimizing with K-Means++ algorithm and PID controller.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Estimation of Anomalous Portion in Gray Cast Iron using Non-contacting Electromagnetic Sensor

Estimation of Anomalous Portion in Gray Cast Iron using Non-...

引用

2023 IEEE International Magnetic Conference - Short Papers, INTERMAG Short Papers 2023

作者： Mio, Syunsuke Kawada, Kohei Okumura, Yukihisa Gotoh, Yuji Oita University Faculty of Science and Technology Department of Innovative Engineering 700 Dannoharu Oita870-1192 Japan Oita University Graduate School of Engineering 700 Dannoharu Oita870-1192 Japan Materials Analysis & Evaluation Team Kubota Corporation Research & Development Headquarters Materials & Castings Center Japan

ISBN: (纸本)9798350338362

The gray cast iron is used in pulleys for power transmission in industrial machinery, etc., since its excellent wear resistance and castability. However, this cast iron material may become brittle during the manufacturing process. In the brittle cast iron, the ferrite content is increased and the pearlite content is decreased. The electromagnetic properties in the cast iron are affected by the proportions of these components. In this paper, an electromagnetic sensor that detects the brittleness of the cast iron from changes in electromagnetic properties within the cast iron is proposed. The electromagnetic FEM analysis using a play model method and the verification experiment show that the brittle cast iron is discriminated from the difference in hysteresis magnetic curve and conductivity between brittle and normal cast iron. © 2023 IEEE.

关键词： Hysteresis

来源：评论

学校读者我要写书评

暂无评论

On the Upper Bound of Non-Thermal Fusion Reactivity with Fixed Total Energy

arXiv

引用

arXiv 2023年

作者： Xie, Huasheng Wang, Xueyun Hebei Key Laboratory of Compact Fusion Langfang065001 China ENN Science and Technology Development Co. Ltd. Langfang065001 China

Fusion reactivity represents the integration of fusion cross-sections and the velocity distributions of two reactants. In this study, we investigate the upper bound of fusion reactivity for a non-thermal reactant coexisting with a thermal Maxwellian background reactant while maintaining a constant total energy. Our optimization approach involves fine-tuning the velocity distribution of the non-thermal reactant. We employ both Lagrange multiplier and Monte Carlo methods to analyze Deuterium-Tritium (D-T) and Proton-Boron11 (p-B11) fusion scenarios. Our findings demonstrate that, within the relevant range of fusion energy, the maximum fusion reactivity can often surpass that of the conventional Maxwellian-Maxwellian reactants case by a substantial margin, ranging from 50% to 300%. These enhancements are accompanied by distinctive distribution functions for the non-thermal reactant, characterized by one or multiple beams. These results not only establish an upper limit for fusion reactivity but also provide valuable insights into augmenting fusion reactivity through non-thermal fusion, which holds particular significance in the realm of fusion energy research. © 2023, CC0.

关键词： Velocity distribution

来源：评论

学校读者我要写书评

暂无评论

HvNCX, a prime candidate gene for the novel qualitative locus qS7.1 associated with salinity tolerance in barley (vol 136, 9, 2023)

引用

THEORETICAL AND APPLIED GENETICS 2023年第4期136卷 9页

作者： Zhu, J. Yangzhou University Key Laboratory of Plant Functional Genomics of the Ministry of Education / Jiangsu Key Laboratory of Crop Genomics and Molecular Breeding/ Jiangsu Co-Innovation Center for Modern Production Technology of Grain Crops/ Institutes of Agricultural Science and Technology Development Yangzhou China (GRID:grid.268415.c) University of Tasmania Tasmanian Institute of Agriculture Prospect Australia (GRID:grid.1009.8) (ISNI:0000 0004 1936 826X) Yangzhou University Key Laboratory of Plant Functional Genomics of the Ministry of Education / Jiangsu Key Laboratory of Crop Genomics and Molecular Breeding/ Jiangsu Co-Innovation Center for Modern Production Technology of Grain Crops/ Institutes of Agricultural Science and Technology Development Yangzhou China (GRID:grid.268415.c) University of Tasmania Tasmanian Institute of Agriculture Prospect Australia (GRID:grid.1009.8) (ISNI:0000 0004 1936 826X) University of Tasmania Tasmanian Institute of Agriculture Prospect Australia (GRID:grid.1009.8) (ISNI:0000 0004 1936 826X) Foshan University International Research Centre for Environmental Membrane Biology Foshan China (GRID:grid.443369.f) (ISNI:0000 0001 2331 8060) University of Western Australia School of Biological Sciences Perth Australia (GRID:grid.1012.2) (ISNI:0000 0004 1936 7910)

Key MessageA major QTL (qS7.1) for salinity damage score and Na+ exclusion was identified on chromosome 7H from a barley population derived from a cross between a cultivated variety and a wild accession. qS7.1 was fine-mapped to a 2.46 Mb physical interval and HvNCX encoding a sodium/calcium exchanger is most likely the candidate *** salinity is one of the major abiotic stresses affecting crop yield. Developing salinity-tolerant varieties is critical for minimizing economic penalties caused by salinity and providing solutions for global food security. Many genes/QTL for salt tolerance have been reported in barley, but only a few of them have been cloned. In this study, a total of 163 doubled haploid lines from a cross between a cultivated barley variety Franklin and a wild barley accession TAM407227 were used to map QTL for salinity tolerance. Four significant QTL were identified for salinity damage scores. One (qS2.1) was located on 2H, determining 7.5% of the phenotypic variation. Two (qS5.1 and qS5.2) were located on 5H, determining 5.3–11.7% of the phenotypic variation. The most significant QTL was found on 7H, explaining 27.8% of the phenotypic variation. Two QTL for Na+ content in leaves under salinity stress were detected on chromosomes 1H (qNa1.1) and 7H(qNa7.1). qS7.1 was fine-mapped to a 2.46 Mb physical interval using F4 recombinant inbred lines. This region contains 23 high-confidence genes, with HvNCX which encodes a sodium/calcium exchanger being most likely the candidate gene. HvNCX was highly induced by salinity stress and showed a greater expression level in the sensitive parent. Multiple nucleotide substitutions and deletions/insertions in the promoter sequence of HvNCX were found between the two parents. cDNA sequencing of the HvNCX revealed that the difference between the two parents is conferred by a single Ala77/Pro77 amino acid substitution, which is located on the transmembrane domain. These findings open new prospects for imp

关键词： Plants (botany)

来源：评论

学校读者我要写书评

暂无评论

Management of face masks driven by the COVID-19 pandemic, possible implications and proposed policies: A household perspective

World Development Sustainability

引用

World development Sustainability 2023年 3卷

作者： Douti, Nang Biyogue Amuah, Ebenezer Ebo Yahans Acheampong, Emmanuel Dankwa, Paul Kazapoe, Raymond Webrah Agyemang, Edna Pambour Department of Environmental Science C. K. Tedam University of Technology and Applied Sciences Navrongo Ghana Department of Environmental Science Kwame Nkrumah University of Science and Technology Kumasi Ghana Department of Geological Engineering University for Development Studies Tamale Ghana Department of Geography and Resource Development University of Ghana Accra Ghana

Poor management of infectious waste in households poses severe health and environmental threats. This study was conducted in the Kassena-Nankana East Municipality of Ghana to assess the management of waste face masks/PPEs used in the prevention of the spread of the COVID-19 pandemic at the household level. Information was elicited from 150 households and two (2) institutions in charge of waste management to elicit information on the generation, management practices, and challenges in handling waste face masks/PPEs in the area. The study estimates that about 107,322 face masks are used daily in the area. Also, the rate of awareness of COVID-19 was strongly related (p = 0.002) to the generated volume of PPEs wasted. The need for face masks/PPEs as protection against COVID-19 largely influenced the rate of PPE waste generation (p = 0.005). However, the study found that 56% of households faced challenges in handling waste PPEs. Among them, 47% burned PPEs separately, 16% burned them with regular waste, and 27% discarded them with household waste. Improved waste management practices are needed to address these issues. Although there was no significant statistical association between age, gender, or occupation and awareness of face masks, there were some observed differences in awareness levels. The odds of respondents aged 18–25 being aware of face masks were 1.273 times greater than those aged 35 and older, while the odds of respondents aged 26–34 being aware of face masks were 2.181 times greater than those aged 35 and older. However, these differences may not be statistically significant. It is recommended that enhancing waste management procedures and educating people on the proper disposal of waste PPEs will be effective in the management of waste PPEs. © 2023 The Author(s)

关键词： COVID-19 Ghana Households Management and challenges PPEs Waste face masks

来源：评论

学校读者我要写书评

暂无评论

HILS Validation of Integral Super Twisting Sliding Mode Control for Induction Motor Drive with Thermal Model Coupling

HILS Validation of Integral Super Twisting Sliding Mode Cont...

引用

International Conference on Power Electronics (ICPE)

作者： Hamza AhmadA Irfan Sami Trung-Kien Vu Dong-Hyun Lim Ki-Bum Park Korea Advanced Institute of Science and Technology (KAIST) South Korea Research & Development Department Milim Syscon Co. Ltd. South Korea

The PI control scheme is widely adapted for speed control of induction motor. The major drawback of PI control scheme is lack of robustness to external and internal parameters. This paper proposes a robust control technique for Induction Machines (IM), known as Integral Super Twisting Sliding Mode Control (ISTSMC), which combines the advantages of Super Twisting Sliding Mode Control (STSMC) and Integral Sliding Mode Control (ISMC) to eliminate chattering and improve the robustness and convergence of IM torque and speed. The power losses thermal stresses of semiconductor junctions are also evaluated in the IM drive plant model, where the thermal model of switching elements is incorporated. The control algorithm is tested in real-time using a high-fidelity hardware-in-the-loop (HIL) simulator comprising of Typhoon-HIL 604 and Imperix B-Box RCP 3.0 , which accounts for communication delays and allows for wide test coverage. The proposed ISTSMC controller is built in a rapid-control prototyping device and is interfaced with the HIL. The results shows that the ISTSMC increases the robustness of the system without adding further losses or thermal stress to the system and thus demonstrate the reliability of the control algorithm during full system operation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Industry 4.0 Application in Manufacturing for Real-Time Monitoring and Control

引用

Journal of Dynamics, Monitoring and Diagnostics 2022年第3期1卷 176-187页

作者： Debasish Mishra Ashok Priyadarshi Sarthak M Das Sristi Shree Abhinav Gupta Surjya K Pal Debashish Chakravarty Advanced Technology Development Centre Indian Institute of Technology KharagpurKharagpurWest Bengal 721302India Mathematics and Computing Birla Institute of Technology MesraRanchiJharkhand 835215India Information Technology Birla Institute of Technology MesraRanchiJharkhand 835215India Computer Science and Engineering Birla Institute of Technology MesraRanchiJharkhand 835215India Electronics and Communication Engineering Birla Institute of Technology MesraRanchiJharkhand 835215India Department of Mechanical Engineering Indian Institute of Technology KharagpurKharagpurWest Bengal 721302India Department of Mining Engineering Indian Institute of Technology KharagpurKharagpurWest Bengal 721302India

Modern manufacturing aims to reduce downtime and track process anomalies to make profitable business *** ideology is strengthened by Industry 4.0,which aims to continuously monitor high-value manufacturing *** article builds upon the Industry 4.0 concept to improve the efficiency of manufacturing *** major contribution is a framework for continuous monitoring and feedback-based control in the friction stir welding(FSW)*** consists of a CNC manufacturing machine,sensors,edge,cloud systems,and deep neural networks,all working cohesively in real *** edge device,located near the FSW machine,consists of a neural network that receives sensory information and predicts weld quality in real *** addresses time-critical manufacturing *** receives the sensory data if weld quality is poor,and a second neural network predicts the new set of welding parameters that are sent as feedback to the welding *** experiments are conducted for training the neural *** framework successfully tracks process quality and improves the welding by controlling it in real *** system enables faster monitoring and control achieved in less than 1 *** framework is validated through several experiments.

关键词： cloud edge deep neural networks friction stir welding Industry 4.0 internet of things machine learning manufacturing process control process monitoring signal processing

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：