检索结果-内蒙古大学图书馆

SSRN 2024年

作者： Yin, Xuesong Ye, Run Zhang, Cheng Zhuo, Xiaojia Huang, Lei Yan, Bin School of Automation Engineering University of Electronic Science and Technology of China Chengdu China School of Resources and Environment University of Electronic Science and Technology of China Chengdu China

The automatic docking boarding bridge is an automated device used to accurately connect the aircraft with the airport terminal building automatically, the technology focuses on the accurate identification and tracking of the moving aircraft cabin door contour. Aiming at the traditional deep learning algorithms can not accurately segment the aircraft cabin doors, the improved yolov5 model based on the attention mechanism mechanism is proposed to improve the accuracy of the segmentation of the aircraft cabin door contour, and the model consists of three parts, namely, the backbone network, the neck network and the output network. In the image preprocessing stage, in order to reduce the problem of overexposure that causes the airplane door outline to disappear and thus reduce the accuracy of segmentation results, we use real-time HDR algorithm to preprocess the image. In addition, channel and spatial attention modules are added to the yolov5 model neck network to enhance the feature extraction ability of the model, and the SIoU loss function is used to improve the improved model to be more sensitive to small changes in the target edges, so that the model can be better generalized to different sizes of targets with partial occlusion. The experimental results show that the average accuracy of the improved model reaches 97.87%, which is 1.63% higher than the original algorithm, and the size of the model is 14.5MB, which meets the requirements for segmentation of airliners' hatches © 2024, The Authors. All rights reserved.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Self-supervised Lightweight Line Segment Detector and Descriptor

Self-supervised Lightweight Line Segment Detector and Descri...

引用

2022 Chinese automation Congress, CAC 2022

作者： Huang, Jie Lu, Xin Yu, Mengfan Li, Fusheng University of Electronic Science and Technology of China Shenzhen Institute for Advanced Study Shenzhen China University of Electronic Science and Technology of China School of Automation Engineering Chengdu China

ISBN: (纸本)9781665465335

Image line segment features can be used as a complement to points for geometric computer vision tasks. Previous deep learning-based line segment feature extraction is difficult to perform real-time inference in environments with limited computational resources due to the huge model size and computational cost problems. In this paper, we introduce the joint detection and description of line segments using lightweight networks in resource-constrained environments. We use a lightweight backbone as an encoder and design a top-down architecture to fuse multi-layer features, which is split into three branches for different tasks. Moreover, thanks to the self-supervised training scheme, our model can be trained on dataset without ground-truth line segments. In the experiments, our approach achieves competitive performance with the fastest model inference speed. © 2022 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Automatic Fruit Detection Based on Robotic Vision

Automatic Fruit Detection Based on Robotic Vision

引用

Big Data & Artificial Intelligence & Software engineering (ICBASE), International Conference on

作者： Yiran Chen Rui Yao Haoran Liu Bingqi Liu Mingzhe Liu School of Data Science and Artificial Intelligence Wenzhou University of Technology Wenzhou China College of Nuclear Technology and Automation Engineering Chengdu University of Technology Chengdu China Norla Institute of Technical Physics Chengdu China

ISBN: (数字)9798331506612

ISBN: (纸本)9798331506629

Automatic fruit detection has greatly reduced labor costs and crop damage rates, contributing to the progress of agricultural modernization. It involves real-time assessment of the surrounding environment and recognition of target fruit categories. However, fruit detection faces challenges due to the similarities in shape, color, and other features among different types of fruits, as well as the impact of environmental factors such as inadequate lighting, occlusion, and background variations on recognition accuracy. This project focuses on the simulation of the robotic fruit harvesting process, which includes environmental image acquisition, image processing, and robot control. The robot utilizes its integrated camera to capture real-time images of the surrounding environment. These images are then processed on a computer, employing color recognition based on traditional algorithms. The images are segmented based on the identified color regions and subjected to object detection using YOLO v5. By discerning the presence of the target objects, the results are transmitted to the robot, which responds accordingly. The real-time performance is enhanced by filtering and narrowing down the target regions, reducing the time required for object recognition.

关键词： YOLO Image recognition Accuracy Image color analysis Target recognition Lighting Laser feedback Real-time systems Computational efficiency Laser beams

来源：评论

学校读者我要写书评

暂无评论

Practical Prescribed-Time Bipartite Time-Varying Formation Control for Multiagent Systems With Adaptive Self-Triggered

引用

IEEE Transactions on automation Science and engineering 2025年 22卷 16838-16850页

作者： Shuxing Xuan Hongjing Liang Tieshan Li Chenguang Yang School of Automation Engineering University of Electronic Science and Technology of China Chengdu China Department of Computer Science University of Liverpool Liverpool U.K.

This paper investigates the problem of practical prescribed-time fuzzy bipartite time-varying formation control for nonlinear multiagent systems. To achieve practical prescribed-time control, a bounded and continuous prescribed-time evolution function is constructed, and a new stability lemma is derived, proving that the proposed controller avoids singularities and ensures synchronization errors converge to a neighborhood independent of initial conditions within the prescribed time. Considering cooperative-competitive interactions among the agents, a fuzzy bipartite time-varying formation controller is designed to achieve formation control within a specified time while keeping all closed-loop signals bounded. Furthermore, to reduce communication costs, an adaptive self-triggered mechanism is introduced. This mechanism maps the prescribed time to a dynamic triggering function, enabling the controller to adjust triggering conditions based on the user-defined convergence time, thereby balancing speed and communication costs. Finally, the effectiveness of the proposed method is validated through a simulation case involving five uncrewed ground *** to Practitioners—This study addresses the formation control problem in nonlinear multiagent systems and proposes a practical prescribed-time bipartite formation control strategy, particularly suited for complex cooperative and competitive relationships. Traditional methods often face issues related to communication overhead and dynamic uncertainties, while the proposed approach significantly optimizes system performance by introducing a prescribed-time evolution function and an adaptive self-triggered mechanism, particularly in scenarios with limited communication resources. The self-triggered mechanism enables the system to adaptively adjust the triggering conditions based on the user-defined convergence time, thereby ensuring rapid convergence while reducing unnecessary communication. This approach is particularly

关键词： Convergence Formation control Multi-agent systems Time-varying systems Costs System performance automation Vehicle dynamics Training Topology

来源：评论

学校读者我要写书评

暂无评论

DPAL-BERT:A Faster and Lighter Question Answering Model

引用

Computer Modeling in engineering & Sciences 2024年第10期141卷 771-786页

作者： Lirong Yin Lei Wang Zhuohang Cai Siyu Lu Ruiyang Wang Ahmed AlSanad Salman A.AlQahtani Xiaobing Chen Zhengtong Yin Xiaolu Li Wenfeng Zheng Department of Geography and Anthropology Louisiana State UniversityBaton RougeLA 70803USA School of Automation University of Electronic Science and Technology of ChinaChengdu610054China College of Computer and Information Sciences King Saud UniversityRiyadh11574Saudi Arabia School of Electrical and Computer Engineering Louisiana State UniversityBaton RougeLA 70803USA College of Resources and Environmental Engineering Guizhou UniversityGuiyang550025China School of Geographical Sciences Southwest UniversityChongqing400715China

Recent advancements in natural language processing have given rise to numerous pre-training language models in question-answering ***,with the constant evolution of algorithms,data,and computing power,the increasing size and complexity of these models have led to increased training costs and reduced *** study aims to minimize the inference time of such models while maintaining computational *** also proposes a novel Distillation model for PAL-BERT(DPAL-BERT),specifically,employs knowledge distillation,using the PAL-BERT model as the teacher model to train two student models:DPAL-BERT-Bi and *** research enhances the dataset through techniques such as masking,replacement,and n-gram sampling to optimize knowledge *** experimental results showed that the distilled models greatly outperform models trained from *** addition,although the distilled models exhibit a slight decrease in performance compared to PAL-BERT,they significantly reduce inference time to just 0.25%of the *** demonstrates the effectiveness of the proposed approach in balancing model performance and efficiency.

关键词： DPAL-BERT question answering systems knowledge distillation model compression BERT Bi-directional long short-term memory(BiLSTM) knowledge information transfer PAL-BERT training efficiency natural language processing

来源：评论

学校读者我要写书评

暂无评论

Multi-Dimensional Hybrid Quantitative Analysis of Teaching Evaluation by Big Data technology: A Case Study on Chinese Universities

Multi-Dimensional Hybrid Quantitative Analysis of Teaching E...

引用

Electronic Communications, Internet of Things and Big Data (ICEIB), International Conference on

作者： Laiying Long Yingzi Wen Fei Li Muhao Zhang College of Nuclear Technology and Automation Engineering Chengdu University of Technology Chengdu China Department of Physics Universitat Politècnica de Catalunya Barcelona Spain

ISBN: (数字)9798350360721

ISBN: (纸本)9798350360738

Students' feedback is adopted as a common method of evaluating teaching quality, which is crucial in monitoring teaching quality in colleges and universities. However, various factors such as area, gender, and age of the students can influence the model, content, and subjective bias of teaching quality evaluation. Therefore, we conducted a questionnaire survey for students at 90 universities in China and analyzed the data using Tableau and SPSS. The current teaching evaluation system lacks model diversity, discipline specificity, and objective standardization. Thus, improvement considering the relationship between students' cognition, attitude, and participation is proposed to provide a significant reference on the higher education reform system based on the result.

关键词： Surveys Statistical analysis Education Evaluation models Standardization Receivers Big Data

来源：评论

学校读者我要写书评

暂无评论

Independently tunable dual-wavelength symmetry-protected bound states in the continuum via metasurface 5

Independently tunable dual-wavelength symmetry-protected bou...

引用

5th International Conference on Material Chemistry and Composite Materials, MCCM 2024

作者： Luo, Xin Ha, Yingli Zhang, Fei Pu, Mingbo Guo, Yinghui Luo, Xiangang Institute of Optics and Electronics Chinese Academy of Sciences Chengdu 610209 China School of Automation Engineering University of Electronic Science and Technology of China Chengdu 610054 China National Key Laboratory of Optical Field Manipulation Science and Technology Chinese Academy of Sciences Chengdu 610209 China College of Materials Science and Opto-Electronic Technology University of Chinese Academy of Sciences Beijing 100049 China

Symmetry-protected bound states in the continuum (SP-BICs) have attracted considerable attention in the realm of nanophotonics, primarily due to their infinite quality (Q) factor and remarkable ability to confine fields. However, while most of the current research realizes multiple high-Q quasi-SP-BIC resonances, these lack independent tunability, thereby significantly limiting their utility in multi-wavelength lasers with independent control. In this work, we introduce symmetry-broken in an all-dielectric metasurface to achieve dual quasi-SP-BICs with independent tunability. An analysis conducted through near-field distributions and multipole decomposition reveals that the excited dual quasi-SP-BICs are predominantly influenced by the magnetic dipole. Furthermore, the dual quasi-SP-BICs can be independently controlled by varying the magnitude of the periods in both the x- and y-directions, respectively. Our research lays the groundwork for the development of independently adjustable multiple SP-BIC metasurfaces, thereby enabling their application in a variety of fields, such as lasers, nonlinear optics, and biosensing. © Published under licence by IOP Publishing Ltd.

关键词： Optical bistability

来源：评论

学校读者我要写书评

暂无评论

Transition Stability Phase Portrait Analysis and Pi-Based Improved Control of Grid-Forming Converter

SSRN

引用

SSRN 2023年

作者： Xing, Yankai Zhang, Guangdou Yang, Kai Li, Jian Cai, Dongsheng Bamisile, Olusola Huang, Qi University of Electronic Science and Technology of China Chengdu China College of Nuclear Technology and Automation Engineering Chengdu University of Technology Chengdu China Southwest University of Science and Technology Mianyang China

For power stability requirements, the controller of a converter in renewable power system should not only has ability to face the traditional faults in the grid but also to stabilize with different working modes, i.e., islanding or grid-connected modes. Furthermore, the existence GFM power modulation control loop has been proven as an instability reason when Voltage Source Converter (VSC) transitioning is operated from islanded to grid-connected mode and power flows from the converter to the gird. Since the active power and reactive power modulation loop in GFM have the coupling effect for each other to provide the reference voltage and frequency, which can lead to instability phenomenon in transition process. Thus, the PI-based voltage direct control in power modulation scheme is analyzed by design-oriented to prove its advantage in this application scenario. The advanced approach based on this principle is proposed to taking more dynamics in tuning process in order to obtain more robustness. Deep Reinforcement Learning (DRL) method (DDPG) is selected to accomplish the optimization task. The test results show that the proposed control approach along with its optimal parameters has ability to deal with the transition process to keep stability in low SCR grid and grid fault condition. © 2023, The Authors. All rights reserved.

关键词： Reactive power

来源：评论

学校读者我要写书评

暂无评论

Modeling, Computation and Analysis of Gaussian-Based Probability Density Function and Conflict Potential Field for Cooperative Overtaking

Modeling, Computation and Analysis of Gaussian-Based Probabi...

引用

Chinese automation Congress (CAC)

作者： Wen He Menglin Lv Yong Chen Jinlong Hao Mingjie Liu Yuhao Jiang School of Automation Engineering University of Electronic Science and Technology of China Chengdu China School of Automation Chongqing University of Posts and Telecommunications Chongqing China School of Automation Engineering University of Electronic Science and Technology Chengdu China Chongqing Chang'an Automobile Corp Chengdu China College of Mechanical and Vehicle Engineering Chongqing University Chongqing China

ISBN: (数字)9798350368604

ISBN: (纸本)9798350368611

The collaborative overtaking framework presents significant potential for advancing road traffic safety and operational efficiency in intelligent transportation systems. By enabling instantaneous communication among roadway infrastructure, proximate vehicles, and other traffic entities, the framework facilitates the seamless exchange of critical information. Recognized for its superior performance, it is poised to play a pivotal role in the evolution of next-generation Advanced Driver Assistance Systems (ADAS), particularly with the proliferation of 5G communication technologies. This paper examines fundamental challenges associated with the modeling, computation, and analysis of Gaussian-based probability density functions and conflict potential fields, applying these methodologies to coordinated overtaking systems. Specifically, a Gaussian-based conflict potential field model is introduced alongside a risk assessment methodology designed to enhance overtaking safety by evaluating collision risks through vehicle-to-vehicle communication. Empirical experiments further substantiate the efficacy of the proposed approach, demonstrating notable performance improvements under dynamic and unpredictable driving conditions.

关键词： Analytical models Systematics Computational modeling Roads Vehicular ad hoc networks Collaboration Probability density function Road traffic Vehicle dynamics Testing

来源：评论

学校读者我要写书评

暂无评论

An Improved Chaotic Gwo-Lgbm Hybrid Algorithm for Emotion Recognition

SSRN

引用

SSRN 2024年

作者： Wei, Daohong Chen, Dongyi Huang, Zhiqi Li, Minsen School of Automation Engineering University of Electronic Science and Technology of China Chengdu611731 China School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu611731 China

In order to address the challenges associated with the unbalanced search abilities and low search accuracy of the Gray Wolf Optimization (GWO) algorithm, we propose an enhanced version termed the Improved Chaotic Gray Wolf Optimization Algorithm (ICGWO) based on cubic mapping. Initially, the population positions of gray wolves were perturbed to expedite the convergence speed. Subsequently, a nonlinear convergence factor was introduced to enhance both search ability and efficiency. Finally, within the algorithm, a dynamic inertia-weighting strategy was implemented to improve convergence speed and solution accuracy. Experimental simulations encompassing 23 classical test functions demonstrate that the ICGWO algorithm exhibits superior convergence speed, solution accuracy, and stability compared to other swarm intelligence optimization algorithms and certain enhanced GWO algorithms. In comparison to GWO, utilizing the ICGWO method for hyperparameter optimization within the Light Gradient Boosting Machine (LightGBM) for emotional recognition led to notable enhancements in average accuracy and F1 score by 7.29% and 3.92% respectively for valence, and 4.33% and 3.23% respectively for arousal. Additionally, the standard deviation of the IGWO was less than one-tenth of the standard deviation of GWO in both conditions. These results underscore the strong optimization capabilities and high stability of the ICGWO algorithm. © 2024, The Authors. All rights reserved.

关键词： Machine learning

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：