检索结果-内蒙古大学图书馆

A Hybrid Feature Fusion Traffic Sign Detection Algorithm Based on YOLOv7

Computers, Materials & Continua 2024年第7期80卷 1425-1440页

作者： Bingyi Ren Juwei Zhang Tong Wang School of Mechanical Engineering Henan University of Science and TechnologyLuoyang471000China School of Information Engineering Henan University of Science and TechnologyLuoyang471000China School of Electronic Information Zhengzhou Institute of Aeronautical Industry ManagementZhengzhou450046China Henan Province New Energy Vehicle Power Electronics and Power Transmission Engineering Research Center Luoyang471000China

Autonomous driving technology has entered a period of rapid development,and traffic sign detection is one of the important *** target detection networks are difficult to adapt to scenarios where target sizes are seriously imbalanced,and traffic sign targets are small and have unclear features,which makes detection more ***,we propose aHybrid Feature Fusion Traffic Sign detection algorithmbased onYOLOv7(HFFTYOLO).First,a self-attention mechanism is incorporated at the end of the backbone network to calculate feature interactions within scales;Secondly,the cross-scale fusion part of the neck introduces a bottom-up multi-path fusion *** reuse paths at the end of the neck,paying particular attention to cross-scale fusion of highlevel *** addition,we found the appropriate channel width through a lot of experiments and reduced the superfluous *** terms of training,a newregression lossCMPDIoUis proposed,which not only considers the problem of loss degradation when the aspect ratio is the same but the width and height are different,but also enables the penalty term to dynamically change at different ***,our proposed improved method shows excellent results on the TT100K *** with the baseline model,without increasing the number of parameters and computational complexity,AP0.5 and AP increased by 2.2%and 2.7%,respectively,reaching 92.9%and 58.1%.

关键词： Small target detection YOLOv7 traffic sign detection regression loss

来源：评论

学校读者我要写书评

暂无评论

Kernel Affine Projection Algorithms Based on the Robust Mixed-norm Method 7

Kernel Affine Projection Algorithms Based on the Robust Mixe...

引用

7th IEEE International Conference on electronic information and Communication technology, ICEICT 2024

作者： Li, Guoliang Zhao, Ji Zhang, Hongbin University of Electronic Science and Technology of China School of Information and Communication Engineering Chengdu611731 China Southwest University of Science and Technology School of Information Engineering Sichuan621010 China

ISBN: (纸本)9798350384437

The kernel affine projection algorithm (KAPA) has been successfully applied in the context of time-series prediction. However, the KAPA's filtering performance can be greatly affected by non-Gaussian noise. The mixed-norm algorithm (MNA) and generalized correntropy (GC) can still achieve fast convergence speed under non-Gaussian noise. In this paper, the combination of the KAPA, MNA and GC yields the kernel affine projection robust MNA (KAPRMNA). In order to further modify the convergence rate of the KAPRMNA, applying a variable-step-size (VSS) way to the KAPRMNA yields a new VSS-KAPRMNA. In the context of time-series prediction, simulations verify that both the KAPRMNA and VSS-KAPRMNA outperform some other known kernel AP-type algorithms with respect to the convergence rate in a-stable distribution environment. © 2024 IEEE.

关键词： Consensus algorithm

来源：评论

学校读者我要写书评

暂无评论

Targeted regeneration and upcycling of spent graphite by defect‐driven tin nucleation

引用

Carbon Energy 2024年第4期6卷 91-103页

作者： Zhiheng Cheng Zhiling Luo Hao Zhang Wuxing Zhang Wang Gao Yang Zhang Long Qie Yonggang Yao Yunhui Huang Kun Kelvin Fu State Key Laboratory of Materials Processing and Die&Mould Technology School of Materials Science and EngineeringHuazhong University of Science and TechnologyWuhanChina Key Laboratory of Automobile Materials(Jilin University) Ministry of EducationDepartment of Materials Science and EngineeringJilin UniversityChangchunChina Electronic Materials Research Laboratory(Key Lab of Education Ministry) School of Electronic and Information Engineeringand Instrumental Analysis CenterXi'an Jiaotong UniversityXi'anChina Department of Mechanical Engineering University of DelawareNewarkUSA

The recycling of spent batteries has become increasingly important owing to their wide applications,abundant raw material supply,and sustainable *** with the degraded cathode,spent anode graphite often has a relatively intact structure with few defects after long ***,most spent graphite is simply burned or discarded due to its limited value and inferior performance on using conventional recycling methods that are complex,have low efficiency,and fail in performance ***,we propose a fast,efficient,and“intelligent”strategy to regenerate and upcycle spent graphite based on defect‐driven targeted *** Sn as a nanoscale healant,we used rapid heating(~50 ms)to enable dynamic Sn droplets to automatically nucleate around the surface defects on the graphite upon cooling owing to strong binding to the defects(~5.84 eV/atom),thus simultaneously achieving Sn dispersion and graphite *** a result,the regenerated graphite showed enhanced capacity and cycle stability(458.9 mAh g^(−1) at 0.2 A g^(−1) after 100 cycles),superior to those of commercial *** from the self‐adaption of Sn dispersion,spent graphite with different degrees of defects can be regenerated to similar structures and *** analysis indicates that targeted regeneration and upcycling have significantly lower energy consumption(~99%reduction)and near‐zero CO_(2) emission,and yield much higher profit than hydrometallurgy,which opens a new avenue for direct upcycling of spend graphite in an efficient,green,and profitable manner for sustainable battery manufacture.

关键词： battery recycling spent graphite targeted regeneration upcycling graphite

来源：评论

学校读者我要写书评

暂无评论

Leveraging the Potential of Large Language Models

引用

Informatica (Slovenia) 2024年第8期48卷 1-16页

作者： Prasad, Shreya Gupta, Himank Ghosh, Arup Department of Software Systems School of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu Vellore India Department of Computer Science and Information Technology Graceland University LamoniIA United States

This study focuses on enhancing Natural Language Processing (NLP) in generative AI chatbots through the utilization of advanced pre-trained models. We assessed five distinct Large Language Models (LLMs): TRANSFORMER MODEL, FALCON 7B, LAMINI-FLAN-T5-783M, LLAMA-2-7B, and LLAMA-2-13B to identify the most effective one. Our findings revealed that the LLAMA Model excels in comprehending user queries and delivering precise responses during conversations. The article elucidates the methodology employed to evaluate and select various models for our chatbot. Through rigorous testing, we determined that the LLAMA-2-13B model exhibits enhanced response time and accuracy. Additionally, we employed tools such as Facebook Artificial Intelligence Similarity Search (FAISS) and experimented with user interfaces like Streamlit and Chainlit to enhance the chatbot's user-friendliness. The research underscores the significance of selecting the appropriate model for crafting efficient chatbots. Ultimately, the LLAMA-13B model emerged as the standout performer, showcasing superior performance. Benchmark assessments, including HellaSwag and WinoGrande, which gauge common sense reasoning, were employed to evaluate our chatbot's capabilities. The study concludes that LLAMA-based models hold significant promise for the development of innovative and user-friendly chatbots in the future. Povzetek: Študija se osredotoča na izboljšanje obdelave naravnega jezika (NLP) v generativnih AI klepetalnicah z uporabo naprednih vnaprej usposobljenih modelov. Analizirali so pet modelov: TRANSFORMER MODEL, FALCON 7B, LAMINI-FLAN-T5-783M, LLAMA-2-7B in LLAMA-2-13B. Model LLAMA-13B se je izkazal kot najboljši z vrhunskimi rezultati na testih HellaSwag in WinoGrande. Raziskava uporablja orodja, kot je FAISS, in uporabniške vmesnike, kot sta Streamlit in Chainlit za izboljšanje uporabniške izkušnje. © 2024 Slovene Society Informatika. 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

FlowerAction: a federated deep learning framework for video-based human action recognition

引用

Journal of Ambient Intelligence and Humanized Computing 2025年第2期16卷 459-470页

作者： Dinh, Thi Quynh Khanh Tran, Thanh-Hai Tran, Trung-Kien Le, Thi-Lan School of Electrical and Electronic Engineering International Research Insitute MICA Hanoi University of Science and Technology Hanoi100000 Viet Nam Information Technology Institute Academy of Military Science and Technology Hanoi100000 Viet Nam

Federated learning (FL) is a security paradigm using low-resource devices to contribute to the training without sharing local data;hence, it is very suitable for practical applications with strict privacy requirements. Although some FL frameworks have been developed to facilitate specific tasks, they are limited to applications that require real and big data, such as human action videos. In this paper, we introduce FlowerAction, a novel framework for human action recognition, built on top of the Flower framework to connect its existing internal functions, including model communication and aggregation algorithms, with our external components (e.g., dataset, models, specific utilities). To the best of our knowledge, this is the first framework of FL for video-based action recognition. Our experimental results on some datasets show that the FlowerAction framework operates properly, helping researchers approach FL with less effort and conduct federated training benchmarks quickly. Furthermore, our analysis results that show performances in terms of top-k accuracy and communication cost of different FL algorithms could give instructive suggestions for selecting and deploying a deep model for FL-based action recognition in the future. Source code is available at https://***/quynhkhanh96/flower-action. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Exponential Synchronization for Mobile Robotic Formation: A Hybrid Dynamic Event-Triggered Intermittent Control Method

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2024年 1-10页

作者： Chang, Zhenyu Guo, Ying Zong, Guangdeng Qi, Wenhai Zhao, Xudong School of Control Science and Engineering Tiangong University Tianjin China School of Computer Science Beijing University of Posts and Telecommunications Beijing China School of Engineering Qufu Normal University Rizhao China Faculty of Electronic Information and Electrical Engineering Dalian University of Technology Dalian China

To address the formation tracking issue of mobile robotic systems, this paper constructs a novel hybrid dynamic event-triggered intermittent control strategy, which can achieve the exponential synchronization of the systems. Considering the limited control resources, the intermittent control method is introduced into the distributed control strategy to save resources, and the existing intermittent control model is reconstructed to describe the system model better. A hybrid dynamic event-triggered mechanism is developed by combining the dynamic event-triggered method with the time sampling strategy, eliminating the Zeno phenomenon. The control time sequences in the developed intermittent control strategy are automatically selected by the hybrid dynamic event-triggered sequences, rather than artificially designed in advance, which reduces a certain degree of design complexity. The developed control strategy effectively saves control resources while alleviating the burden of network communication. Sufficient conditions for achieving exponential synchronization formation tracking are provided, and the exponential convergence of the formation error is demonstrated through the proposed lemma. Finally, a control task of multi-mobile robots formation is presented to verify the effectiveness of the theoretical analysis. IEEE

关键词： Synchronization

来源：评论

学校读者我要写书评

暂无评论

Game Theoretic Resource Allocation for information Freshness in Mobile Edge Computing 29

Game Theoretic Resource Allocation for Information Freshness...

引用

29th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2023

作者： Gu, Jingjing Zhang, Di Bao, Hongcheng Xing, Weiwei Zheng, Xindong Shao, Xun Beijing Jiaotong University School of Software Engineering China Fudan University School of Information Science and Technology China Toyohashi University of Technology Department of Electrical and Electronic Information Engineering Japan

ISBN: (纸本)9798350330717

Age of information (AoI) is an important metric used to quantify the freshness of data. By utilizing resources of the edge server near the source nodes, mobile edge computing (MEC) can speed up the processing of information updates and ensure data freshness. However, the resources of the edge server are usually limited, so it is necessary to study the resource allocation strategy to ensure data freshness and optimize the profit of the edge server. In this paper, we propose a game-theoretic approach for resource allocation in mobile edge computing to guarantee information freshness. First, with the purpose of ensuring information freshness, we formalize the problem as minimizing the computational cost of source nodes and maximizing the profit of the edge server. Then, we introduce a two-stage dynamic game model to simulate the competitive process. We further transform the resource allocation problem into a knapsack problem and propose an iterative resource allocation algorithm based on dynamic programming. Experimental results show that the proposed algorithm can obtain a Nash equilibrium and maximize the profit of the edge server while ensuring information freshness. © 2023 IEEE.

关键词： Age of information mobile edge computing resource allocation two-stage game

来源：评论

学校读者我要写书评

暂无评论

OFDM with Generalized Cascade Index Modulation for Secure Communications

引用

China Communications 2024年第10期21卷 210-225页

作者： Hu Zeng Jin Xiaopin Yao Yudong Chen Fangjiong Wan Dehuan Liu Yun College of Information Science and Technology Zhongkai University of Agriculture and EngineeringGuangzhou 510225China College of Information Engineering China Jiliang UniversityHangzhou 310018China Department Electrical and Computer Engineering Stevens Institute of Technology HobokenNJ 07030USA School of Electronic and Information Engineering South China University of TechnologyGuangzhou 510641China Center for Data Science and Artificial Intelligence Guangdong University of FinanceGuangzhou 510521China

Cascade index modulation(CIM) is a recently proposed improvement of orthogonal frequency division multiplexing with index modulation(OFDM-IM) and achieves better error *** CIM, at least two different IM operations construct a super IM operation or achieve new functionality. First, we propose a OFDM with generalized CIM(OFDM-GCIM) scheme to achieve a joint IM of subcarrier selection and multiple-mode(MM)permutations by using a multilevel digital ***, two schemes, called double CIM(D-CIM) and multiple-layer CIM(M-CIM), are proposed for secure communication, which combine new IM operation for disrupting the original order of bits and symbols with conventional OFDM-IM, to protect the legitimate users from eavesdropping in the wireless communications. A subcarrier-wise maximum likelihood(ML) detector and a low complexity log-likelihood ratio(LLR) detector are proposed for the legitimate users. A tight upper bound on the bit error rate(BER) of the proposed OFDM-GCIM, D-CIM and MCIM at the legitimate users are derived in closed form by employing the ML criteria detection. Computer simulations and numerical results show that the proposed OFDM-GCIM achieves superior error performance than OFDM-IM, and the error performance at the eavesdroppers demonstrates the security of D-CIM and M-CIM.

关键词： cascade index modulation low-complexity detector maximum likelihood OFDM physical layer security

来源：评论

学校读者我要写书评

暂无评论

Potassium ion pre‑intercalated MnO_(2)for aqueous multivalent ion batteries

引用

Frontiers of Optoelectronics 2023年第4期16卷 81-89页

作者： Zikang Xu Ruiqi Ren Hang Ren Jingyuan Zhang Jinyao Yang Jiawen Qiu Yizhou Zhang Guoyin Zhu Liang Huang Shengyang Dong School of Environmental Science and Engineering School of Chemistry and Materials ScienceNanjing University of Information Science and TechnologyNanjing 210044China Wuhan National Laboratory for Optoelectronics School of Optical and Electronic InformationHuazhong University of Science and TechnologyWuhan 430074China

Manganese dioxide(MnO_(2)),as a cathode material for multivalent ion(such as Mg^(2+)and Al^(3+))storage,is investigated due to its high initial ***,during multivalent ion insertion/extraction,the crystal structure of MnO_(2)partially collapses,leading to fast capacity decay in few charge/discharge ***,through pre-intercalating potassium-ion(K+)intoδ-MnO_(2),we synthesize a potassium ion pre-intercalated MnO_(2),K_(0.21)MnO_(2)·0.31H_(2)O(KMO),as a reliable cathode material for multivalent ion *** as-prepared KMO exhibits a high reversible capacity of 185 mAh/g at 1 A/g,with considerable rate performance and improved cycling stability in 1 mol/L MgSO_(4)*** addition,we observe that aluminum-ion(Al^(3+))can also insert into a KMO *** work provides a valid method for modifcation of manganesebased oxides for aqueous multivalent ion batteries.

关键词： Aqueous batteries Multivalent ion batteries Magnesium ion Aluminum ion MnO_(2)

来源：评论

学校读者我要写书评

暂无评论

Thermoelectric enhancement of p-type Si_(80)Ge_(20) alloy via co-compositing of dual oxides:Respective regulation for power factor and thermal conductivity byβ-Ga_(2)O_(3) and SiO_(2) aerogel powders

引用

Journal of Advanced Ceramics 2023年第2期12卷 228-241页

作者： Huajun LAI Ying PENG Mengfei WANG Runze SHI Junliang CHEN Chengyan LIU Yifeng WANG Lei MIAO Haiqiao WEI Key Laboratory of Information Material Ministry of EducationGuangxi Key Laboratory of Information MaterialSchool of Materials Science and EngineeringGuilin University of Electronic TechnologyGuilin 541004China Guangxi Key Laboratory of Precision Navigation Technology and Application School of Information and CommunicationGuilin University of Electronic TechnologyGuilin 541004China School of Physical Science and Technology Guangxi UniversityNanning 530004China College of Materials Science and Engineering Nanjing Tech UniversityNanjing 210009China State Key Laboratory of Engines Tianjin UniversityTianjin 300072China

Si-based thermoelectric(TE)materials are exhibiting remarkable perspectives in self-energized applications with their special ***,the relatively high total thermal conductivity(κ)prevents their TE ***,a strategy of co-compositing dual oxides was implemented for enhancing the TE properties of p-type Si_(80)Ge_(20) *** Ga2O_(3) was demonstrated to enhance the power factor(PF)due to the crystallization-induced effect of produced Ga by decomposition on SiGe *** with compositing SiO_(2) aerogel(a-SiO_(2))powder,not only introduced the fine amorphous inclusions and decreased the grain size of host matrix,but also various nano morphologies were formed,i.e.,nano inclusions,precipitations,twin boundaries(TBs),and *** with the eutectic Ge,hierarchical scattering centers impeded the phonon transport comprehensively(decreasing the phonon group velocity(a v)and relaxation time)for reducing the lattice-induced thermal conductivity(lκ).As a result,a minimumκof 2.38 W·m^(−1)·K^(−1) was achieved,which is significantly dropped by 32.6%in contrast with that of the pristine ***,a maximal dimensionless figure of merit(ZT)of 0.9 was achieved at 600℃,which is better than those of most corresponding oxide-composited Si-based bulks.

关键词： thermoelectric(TE)materials SiGe Ga_(2)O_(3) SiO_(2)aerogel(a-SiO_(2)) average velocity of sound hierarchical scattering

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：