检索结果-内蒙古大学图书馆

A Dynamic Transformer Network for Vehicle Detection

IEEE Transactions on Consumer Electronics 2025年

作者： Tian, Chunwei Liu, Kai Zhang, Bob Huang, Zhixiang Lin, Chia-Wen Zhang, David Harbin Institute of Technology School of Computer Science and Technology Harbin15001 China Macao Special Administrative Region of China PAMI Research Group University of Macau 999078 China Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Key Laboratory of Electromagnetic Environmental Sensing Hefei230601 China National Tsing Hua University Department of Electrical Engineering Institute of Communications Engineering Hsinchu Taiwan School of Data Science Shenzhen518172 China

Stable consumer electronic systems can assist traffic better. Good traffic consumer electronic systems require collaborative work between traffic algorithms and hardware. However, performance of popular traffic algorithms containing vehicle detection methods based on deep networks via learning data relation rather than learning differences in different lighting and occlusions is limited. In this paper, we present a dynamic Transformer network for vehicle detection (DTNet). DTNet utilizes a dynamic convolution to guide a deep network to dynamically generate weights to enhance adaptability of an obtained detector. Taking into relations of different information account, a mixed attention mechanism based channel attention and Transformer is exploited to strengthen relations of channels and pixels to extract more salient information for vehicle detection. To overcome the drawback of difference in an image account, a translation-variant convolution relies on spatial location information to refine obtained structural information for vehicle detection. Experimental results illustrate that our DTNet is competitive for vehicle detection. Code of the proposed DTNet can be obtained at https://***/hellloxiaotian/DTNet. © 2025 IEEE.

关键词： Dynamic convolution Hybrid Attention Mechanism Transformer Vehicle Detection

来源：评论

学校读者我要写书评

暂无评论

Improved Active Disturbance Rejection Control of Inverted Pendulum Based on Differential Flatness

Improved Active Disturbance Rejection Control of Inverted Pe...

引用

Chinese Automation Congress (CAC)

作者： Lijun Wang Jieming Li Xianzhong Chen School of Automation and Electrical Engineering University of Science and Technology Beijing Beijing China Key Laboratory of Knowledge Automation for Industrial Processes Ministry of Education University of Science and Technology Beijing Beijing China Shunde Innovation School University of Science and Technology Beijing Foshan China

Aiming at the control problem of an underdriven inverted pendulum with instability and uncertain external disturbances, a novel improved active disturbance rejection control (ADRC) method based on differential flatness is proposed. Firstly, the non-minimum phase characteristics of the inverted pendulum model are established and analyzed. A flat output is found to overcome the input-output imbalance inherent in underdriven system. Secondly, to address the limitations of the fal function, an improved extended state observer based on a new nonlinear functions is proposed. The theoretical analysis demonstrates the improved performance in terms of tracking speed and accuracy. Furthermore, based on the improved extended state observer, an ADRC method is designed for the flat inverted pendulum system, enabling precise control of the cart displacement and pendulum angle with external disturbances. Finally, simulation results show the effectiveness of the proposed observer and control strategies.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Detector development at the Back-n white neutron source

引用

Radiation Detection Technology and Methods 2023年第2期7卷 171-191页

作者： Fan Ruirui Li Qiang Bao Jie Li Yang Liu Rong Jiang Wei Ren Jie Zhang Qiwei Cao Ping Gu Minhao Ren Zhizhou Yi Han Tang Jingyu An Qi Bai Haofan Bai Jiangbo Chen Qiping Chen Yonghao Chen Zhen Cui Zengqi Fan Anchuan Feng Changqing Feng Fanzhen Gao Keqing Han Changcai Han Zijie He Guozhu He Yongcheng Hong Yang Hu Yiwei Huang Hanxiong Jia Weihua Jiang Haoyu Jiang Zhijie Jin Zhengyao Kang Ling Li Bo Li Chao Li Gong Li Jiawen Li Xiao Liu Jie Liu Shubin Luan Guangyuan Ning Changjun Qi Binbin Ruan Xichao Song Zhaohui Sun Kang Tan Zhixin Tang Shengda Wang Pengcheng Wang Zhaohui Wen Zhongwei Wu Xiaoguang Wu Xuan Xie Likun Yang Yiwei Yu Yongji Zhang Guohui Zhang Linhao Zhang Mohan Zhang Xianpeng Zhang Yuliang Zhang Yue Zhang Zhiyong Zhao Maoyuan Zhou Luping Zhou Zhihao Zhu Kejun The CSNS Back-n Collaboration Institute of High Energy Physics CASBeijing 100049People’s Republic of China Spallation Neutron Source Science Center Dongguan 523803People’s Republic of China State Key Laboratory of Particle Detection and Electronics Beijing 100049People’s Republic of China Key Laboratory of Nuclear Data China Institute of Atomic EnergyBeijing 102413People’s Republic of China Institute of Nuclear Physics and Chemistry China Academy of Engineering PhysicsMianyang 621900People’s Republic of China Department of Modern Physics University of Science and Technology of ChinaHefei 230026People’s Republic of China State Key Laboratory of Particle Detection and Electronics Hefei 230026People’s Republic of China State Key Laboratory of Nuclear Physics and Technology School of PhysicsPeking UniversityBeijing 100871People’s Republic of China USTC archaeometry lab University of Science and Technology of ChinaHefei 230026People’s Republic of China Northwest Institute of Nuclear Technology Xi’an 710024People’s Republic of China University of Chinese Academy of Sciences Beijing 100049People’s Republic of China 不详

Purpose Back-n is a white neutron beamline at China spallation neutron source,which was established in the year of *** is a powerful facility for nuclear data measurement,neutron detector calibration,and radiation effect *** A series of detectors were built for different experiments,including beam monitoring,beam profile measurement,neutron induced secondaries(fission fragments,light charged particles and gamma)cross section measurement,and neutron resonance radiography,etc.A common digitization electronics and a cluster-based DAQ were developed for these detector *** detectors have been employed at Back-n and serviced for experiments from the beginning of the beamline *** and conclusion As an overview of detectors of Back-n,the details of the detector design and the experiment performing are described in this *** developing systems,e.g.,MTPC and B-MCP,are also included.

关键词： White neutron source Beam diagnostics Fission fragment Charged particle Gamma Neutron resonance radiography

来源：评论

学校读者我要写书评

暂无评论

Visible Light Positioning Method for Indoor Line-of-Sight Scene Based on Time Series Coding

Visible Light Positioning Method for Indoor Line-of-Sight Sc...

引用

IEEE International Conference on data Science in Cyberspace (DSC)

作者： Yonghao Yu Yongde Guo Dawei Zhao Kexue Fu Yongwei Tang Qinyuan Wang Faculty of Data Science City University of Macau China Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center(National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computer Networks Jinan China School of Mechanical Engineering Key Laboratory of High Efficiency and Clean Mechanical Manufacture Ministry of Education Shandong University Jinan China

ISBN: (数字)9798350391367

ISBN: (纸本)9798350391374

Existing indoor visible light positioning methods, such as those based on fingerprint database algorithms, are complex to construct and consume significant resources. In response to this issue, the text proposes an end-to-end indoor visible light positioning method that samples continuous signals at a small number of random coordinate positions in indoor environments. Through a deep learning method based on attention mechanism, a nonlinear mapping between the received signal and spatial position coordinates is constructed, and the time series properties in the received signal are encoded as a feature in the data. The method is further improved by combining residual networks to improve accuracy. Through simulation experiments, it has been verified that the deep learning based localization method described in this article can achieve sub meter level accuracy on small sample datasets, and it has been proven that time series features have a significant impact on localization accuracy in indoor visible light positioning algorithms based on deep learning.

关键词： Location awareness Deep learning Meters Training Accuracy Attention mechanisms Time series analysis Training data Encoding data models

来源：评论

学校读者我要写书评

暂无评论

Computer-Automated Design of Self-Aligned Multi-Ball Pitch Artifact with High Precision

SSRN

引用

SSRN 2024年

作者： Zhu, Hongjun Liu, Binghong Zhou, Sen Zhang, Xiaoyan Xin, Liu Chen, Kuo Qian, Ying School of Software Engineering Chongqing University of Posts and Telecommunications Chongqing400065 China Chongqing Engineering Research Center of Software Quality Assurance Testing and Assessment Chongqing400065 China College of Mechanical and Vehicle Engineering Chongqing University Chongqing400044 China Chongqing Academy of Metrology and Quality Inspection Chongqing401121 China School of Engineering Computer and Mathematical Sciences Auckland University of Technology Auckland1010 New Zealand Key Laboratory of Big Data Intelligent Computing Chongqing University of Posts and Telecommunications Chongqing400065 China

This study presents a computational methodology for developing a multi-ball system that automatically aligns during assembly processes. The contributions of this work are threefold: Firstly, a comprehensive error analysis of the multi-ball system is performed. It is found that temperature and pressure-induced deformations should not be ignored when micrometer-level precision is required. Secondly, a novel process flow for designing the multi-ball pitch artifact is introduced, which enables optimization decision-making. Lastly, a series of experiments are conducted on standard bearing balls (grade G20). The resulting artifact meets the Class 1 standards. It is reasonable to assume that, by using balls of grade G3 precision, the multi-ball artifact can achieve accuracy at the sub-micrometer level. © 2024, The Authors. All rights reserved.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Generating Targeted Universal Adversarial Perturbation against Automatic Speech Recognition via Phoneme Tailoring

Generating Targeted Universal Adversarial Perturbation again...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Yujun Zhang Yanqu Chen Jiakai Wang Jin Hu Renshuai Tao Xianglong Liu State Key Laboratory of Complex & Critical Software Environment Beihang University China School of Computer Science and Engineering Beihang University China College of Computer Science Beijing University of Technology China Zhongguancun Laboratory China School of Computer and Information Technology Beijing Jiaotong University China Institute of Data Space Hefei Comprehensive National Science Center China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

There is a growing concern about adversarial attacks against automatic speech recognition (ASR) systems. Although research into targeted universal adversarial examples (AEs) has progressed, current methods are constrained by inefficient exploitation of audio features, demonstrating insufficient attack ability and robustness in the physical world. To solve this problem, we propose a phoneme-tailored attack (PTA) to improve the quality of the generated AEs. Specifically, to improve attack ability, we propose a Diverse Audio Composition Enrichment method, which enhances the utilization of audio features through phoneme-level slicing and recombination. To adapt AEs to complex environments, we propose a Natural Noise Pattern Guidance method to align AEs with natural noise patterns to improve their robustness. Experiments show that our method achieves an average accuracy of more than 72.34% and 98% with and without a norm constraint, and also demonstrates excellent performance in terms of generalization across datasets and resilience to MP3 compression.

关键词： Accuracy Target recognition Perturbation methods Noise Robustness Acoustics Speech processing Digital audio players Automatic speech recognition Resilience

来源：评论

学校读者我要写书评

暂无评论

On the noise robustness of in-context learning for text generation 24

On the noise robustness of in-context learning for text gene...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Hongfu Gao Feipeng Zhang Wenyu Jiang Jun Shu Feng Zheng Hongxin Wei Department of Statistics and Data Science Southern University of Science and Technology and School of Economics and Finance Xi'an Jiaotong University School of Economics and Finance Xi'an Jiaotong University Department of Statistics and Data Science Southern University of Science and Technology and National Key Laboratory for Novel Software Technology Nanjing University School of Mathematics and Statistics Xi'an Jiaotong University Department of Computer Science and Engineering Southern University of Science and Technology Department of Statistics and Data Science Southern University of Science and Technology

ISBN: (纸本)9798331314385

Large language models (LLMs) have shown impressive performance on downstream tasks by in-context learning (ICL), which heavily relies on the quality of demonstrations selected from a large set of annotated examples. Recent works claim that in-context learning is robust to noisy demonstrations in text classification. In this work, we show that, on text generation tasks, noisy annotations significantly hurt the performance of in-context learning. To circumvent the issue, we propose a simple and effective approach called Local Perplexity Ranking (LPR), which replaces the "noisy" candidates with their nearest neighbors that are more likely to be clean. Our method is motivated by analyzing the perplexity deviation caused by noisy labels and decomposing perplexity into inherent perplexity and matching perplexity. Our key idea behind LPR is thus to decouple the matching perplexity by performing the ranking among the neighbors in semantic space. Our approach can prevent the selected demonstrations from including mismatched input-label pairs while preserving the effectiveness of the original selection methods. Extensive experiments demonstrate the effectiveness of LPR, improving the EM score by up to 18.75 on common benchmarks with noisy annotations. Our code is available at https://***/ml-stat-Sustech/Local-Perplexity-Ranking

关键词：

来源：评论

学校读者我要写书评

暂无评论

Joint Timing and Frequency Synchronization for Coherent Optical SEFDM Systems

Joint Timing and Frequency Synchronization for Coherent Opti...

引用

Asia Communications and Photonics Conference and Exhibition (ACP)

作者： Jinze Shi Xinwei Du Shuai Liu Qian Wang Changyuan Yu Guangdong Provincial Key Laboratory of Interdisciplinary Research and Application for Data Science BNU-HKBU United International College Zhuhai China College of Information Engineering Zhejiang University of Technology Hangzhou China Department of Electronic and Information Engineering Photonics Research Institute The Hong Kong Polytechnic University Hung Hom Hong Kong

In this paper, we propose a joint timing and frequency synchronization algorithm for spectrally efficient frequency-division multiplexing (SEFDM) systems by utilizing a training symbol composed of a conjugate symmetric sequence. The timing metric is designed to be the multiplication of two timing metrics which aims to reduce the amplitude of sidelobes, thus ensuring the timing synchronization performance. In addition, according to the phase relationship between the four halves in the designed training symbol, we then derive a closed form expression of the the carrier frequency offset (CFO) estimate. Simulation results verify the superior timing and frequency synchronization accuracy of the proposed method compared with the existing synchronization algorithms.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Vector Magnetic Field Sensor Based on Etched Seven-Core Fiber Helical Long-Period Grating with Magnetic Fluid

Vector Magnetic Field Sensor Based on Etched Seven-Core Fibe...

引用

Conference on Lasers and Electro-Optics (CLEO)

作者： Siyu Chen Chen Jiang Yuehe Zhao Yuehui Ma Chengbo Mou Yunqi Liu The Key Laboratory of Specialty Fiber Optics and Optical Access Networks Joint International Research Laboratory of Specialty Fiber Optics and Advanced Communication Shanghai Institute for Advanced Communication and Data Science Shanghai University Shanghai China Advanced Photonic Technology Lab College of Electronic and Optical Engineering & College of Flexible Electronics (Future Technology) Nanjing University of Posts and Telecommunications Nanjing China Institute of Logistics Science and Engineering Shanghai Maritime University Shanghai China

We demonstrated a vector magnetic field sensor utilizing an etched seven-core fiber helical long-period grating, showcasing a high-sensitivity response of up to 10.8 nm/mT within magnetic field intensity measurement r... 详细信息

ISBN: (纸本)9798350369311

关键词： Optical fibers Optical fiber sensors Magnetic field measurement Measurement by laser beam Magnetic liquids Lasers and electrooptics Fiber gratings Vectors Magnetic fields Laser applications

来源：评论

学校读者我要写书评

暂无评论

Back-n white neutron source at CSNS and its applications

引用

Nuclear Science and Techniques 2021年第1期32卷 95-104页

作者： Jing-Yu Tang Qi An Jiang-Bo Bai Jie Bao Yu Bao Ping Cao Hao-Lei Chen Qi-Ping Chen Yong-Hao Chen Zhen Chen Zeng-Qi Cui Rui-Rui Fan Chang-Qing Feng Ke-Qing Gao Xiao-Long Gao Min-Hao Gu Chang-Cai Han Zi-Jie Han Guo-Zhu He Yong-Cheng He Yang Hong Yi-Wei Hu Han-Xiong Huang Xi-Ru Huang Hao-Yu Jiang Wei Jiang Zhi-Jie Jiang Han-Tao Jing Ling Kang Bo Li Chao Li Jia-Wen Li Qiang Li Xiao Li Yang Li Jie Liu Rong Liu Shu-Bin Liu Xing-Yan Liu Ze Long Guang-Yuan Luan Chang-Jun Ning Meng-Chen Niu Bin-Bin Qi Jie Ren Zhi-Zhou Ren Xi-Chao Ruan Zhao-Hui Song Kang Sun Zhi-Jia Sun Zhi-Xin Tan Xin-Yi Tang Bin-Bin Tian Li-Jiao Wang Peng-Cheng Wang Zhao-Hui Wang Zhong-Wei Wen Xiao-Guang Wu Xuan Wu Li-Kun Xie Xiao-Yun Yang Yi-Wei Yang Han Yi Li Yu Tao Yu Yong-Ji Yu Guo-Hui Zhang Lin-Hao Zhang Qi-Wei Zhang Xian-Peng Zhang Yu-Liang Zhang Zhi-Yong Zhang Lu-Ping Zhou Zhi-Hao Zhou Ke-Jun Zhu 无 State Key Laboratory of Particle Detection and Electronics Institute of High Energy PhysicsChinese Academy of SciencesBeijing 100049China Department of Modern Physics University of Science and Technology of ChinaHefei 230026China Institute of Nuclear Physics and Chemistry China Academy of Engineering PhysicsMianyang 621900China Key Laboratory of Nuclear Data China Institute of Atomic EnergyBeijing 102413China Institute of High Energy Physics Chinese Academy of SciencesBeijing 100049China Spallation Neutron Source Science Center Dongguan 523803China State Key Laboratory of Nuclear Physics and Technology School of PhysicsPeking UniversityBeijing 100871China Northwest Institute of Nuclear Technology Xi’an 710024China University of Chinese Academy of Sciences Beijing 100049China Department of Engineering and Applied Physics University of Science and Technology of ChinaHefei 230026China State Key Laboratory of Particle Detection and Electronics University of Science and Technology of ChinaHefei 230026China The CSNS Back-n Collaboration

Back-streaming neutrons from the spallation target of the China Spallation Neutron Source(CSNS)that emit through the incoming proton channel were exploited to build a white neutron beam facility(the so-called Back-n white neutron source),which was completed in March *** Back-n neutron beam is very intense,at approximately 29107 n/cm2/s at 55 m from the target,and has a nominal proton beam with a power of 100 kW in the CSNS-I phase and a kinetic energy of 1.6 GeV and a thick tungsten target in multiple slices with modest moderation from the cooling water through the *** addition,the excellent energy spectrum spanning from 0.5 eV to 200 MeV,and a good time resolution related tothe time-of-flight measurements make it a typical white neutron source for nuclear data measurements;its overall performance is among that of the best white neutron sources in the *** with advanced spectrometers,detectors,and application utilities,the Back-n facility can serve wide applications,with a focus on neutron-induced cross-sectional *** article presents an overview of the neutron beam characteristics,the experimental setups,and the ongoing applications at Backn.

关键词： White neutron source Nuclear data measurements Experimental setups Neutron applications

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：