检索结果-内蒙古大学图书馆

An Improved YOLOv5s-Based Smoke Detection System for Outdoor Parking Lots

Computers, Materials & Continua 2024年第8期80卷 3333-3349页

作者： Ruobing Zuo Xiaohan Huang Xuguo Jiao Zhenyong Zhang State Key Laboratory of Public Big Data College of Computer Science and TechnologyGuizhou UniversityGuiyang550025China School of Information and Control Engineering Qingdao University of TechnologyQingdao266520China State Key Laboratory of Industrial Control Technology College of Control Science and EngineeringZhejiang UniversityHangzhou310027China Key Laboratory of Computing Power Network and Information Security Ministry of EducationQilu University of Technology(Shandong Academy of Sciences)Jinan250353China Text Computing&Cognitive Intelligence Engineering Research Center of National Education Ministry Guizhou UniversityGuiyang550025China

In the rapidly evolving urban landscape,outdoor parking lots have become an indispensable part of the city’s transportation *** growth of parking lots has raised the likelihood of spontaneous vehicle combus-tion,a significant safety hazard,making smoke detection an essential preventative ***,the complex environment of outdoor parking lots presents additional challenges for smoke detection,which necessitates the development of more advanced and reliable smoke detection *** paper addresses this concern and presents a novel smoke detection technique designed for the demanding environment of outdoor parking ***,we develop a novel dataset to fill the gap,as there is a lack of publicly available *** dataset encompasses a wide range of smoke and fire scenarios,enhanced with data augmentation to ensure robustness against diverse outdoor ***,we utilize an optimized YOLOv5s model,integrated with the Squeeze-and-Excitation Network(SENet)attention mechanism,to significantly improve detection accuracy while maintaining real-time processing ***,this paper implements an outdoor smoke detection system that is capable of accurately localizing and alerting in real time,enhancing the effectiveness and reliability of emergency *** show that the system has a high accuracy in terms of detecting smoke incidents in outdoor scenarios.

关键词： YOLOv5s smoke detection deep learning SENet

来源：评论

学校读者我要写书评

暂无评论

A First Look at LLM-powered Smartphones 39

A First Look at LLM-powered Smartphones

引用

39th ACM/IEEE International Conference on Automated Software Engineering Workshops, ASEW 2024

作者： Wu, Liangxuan Zhao, Yanjie Wang, Chao Liu, Tianming Wang, Haoyu Huazhong University of Science and Technology Wuhan China Huazhong University of Science and Technology Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering China

ISBN: (纸本)9798400712494

The integration of Large Language Models (LLMs) into edge devices such as smartphones represents a significant leap in mobile technology, promising enhanced user experiences and novel functionalities. This paper presents a first look at LLM-powered smartphones, addressing four key aspects: the current market landscape, core functions enabled by integrated LLMs, potential security risks, and user perceptions. The findings reveal a rapidly evolving market with major manufacturers competing to integrate LLMs, innovative features that improve user interaction, significant security challenges, and mixed user perceptions that balance enthusiasm for new capabilities with privacy concerns. This study contributes to understanding LLM integration in mobile devices and its implications for users, manufacturers, and the broader technological landscape. © 2024 ACM.

关键词： Smartphones

来源：评论

学校读者我要写书评

暂无评论

A Novel Global-Local Representations Network for Speech Steganalysis 5

A Novel Global-Local Representations Network for Speech Steg...

引用

5th International Conference on Artificial Intelligence and Pattern Recognition, AIPR 2022

作者： Xu, Shulong Tian, Hui Quan, Hanyu Lu, Jing College of Computer Science and Technology Xiamen Key Laboratory of Data Security and Blockchain Technology Fujian Key Laboratory of Big Data Intelligence and Security National Huaqiao University China

ISBN: (纸本)9781450396899

With the popularity of the internet and the development of network services, Steganography based on speech stream has become a research hotspot in information hiding. To improve the detection performance of steganalysis of multiple steganography methods, in this paper, we proposed the Global-Local Representations Network (GLRN), which consists of a Global Correlation Extraction (GCE) module and a Local Correlation Enhancement (LCE) module. Firstly, considering the inter-class differences of different coding elements, the GCE module is used to capture the global correlation of different coding elements by using multi-channel modeling. Then, we realize that the process of global correlation extraction suffers from the loss of detailed information, so the LCE module is used to capture local correlations to complement the global features. The experiments show that the GLRN achieves the start-of-art detection performance. © 2022 ACM.

关键词： Steganography

来源：评论

学校读者我要写书评

暂无评论

From Global to Hybrid: A Review of Supervised Deep Learning for 2D Image Feature Representation

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年第6期6卷 1540-1560页

作者： Dong, Xinyu Wang, Qi Deng, Hongyu Yang, Zhenguo Ruan, Weijian Liu, Wu Lei, Liang Wu, Xue Tian, Youliang Guizhou University State Key Laboratory of Public Big Data College of computer science Guiyang550025 China Guangdong University of Technology Guangzhou510006 China Chinese Academy of Sciences Shenzhen Institute of Advanced Technology Shenzhen518000 China AI Research of *** Beijing100101 China

Computer vision is the science that aims to enable computers to emulate human visual perception, and it encompasses various techniques and methods for extracting and interpreting information from two-dimensional images. Supervised deep 2D image feature representation is a fundamental problem in computer vision that applies deep learning techniques to extract and process information from a given 2D image under supervised settings. The goal is to obtain a feature vector that can be utilized for various downstream computer vision applications. The quality of supervised deep 2D image feature representation algorithms directly affects the performance of downstream applications. However, most of the existing vision research only explores supervised deep 2D image feature representation for specific subtasks. Therefore, a comprehensive discussion on this topic is needed. In this paper, we propose a taxonomy of supervised deep 2D image feature representation methods based on four categories: global representation, region representation, hash representation, and hybrid representation, and we introduce their typical approaches. Furthermore, we perform a comparative analysis of the representative methods on three fundamental tasks: image classification, object detection, and semantic segmentation, as well as other common tasks. We also discuss the limitations of supervised deep 2D image feature representation and investigate future directions in image representation to facilitate the advancement of computer vision through image representation. © 2020 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Moth-flame optimization for critical node detection 3

Moth-flame optimization for critical node detection

引用

3rd International Conference on Machine Vision, Automatic Identification, and Detection, MVAID 2024

作者： Zhao, Xuehua Chen, Dengfeng Shenzhen Institute of Information Technology Guangdong Shenzhen518172 China State Key Laboratory of Public Big Data Guizhou University Guiyang Guizhou550025 China

ISBN: (纸本)9781510681880

The critical node detection (CND) is after removing these critical nodes of a given number, there is the least network connectivity on a predefined measure for the residual network. The CND arouses great attention for its extensive practical applications, however, the CND is still computationally challenging until now. In this paper, we present an improved moth-flame optimization for CND, in which opposition-based learning and fast population evolution strategy are implemented to generate solutions with diversity and accelerate the convergence, and hybrid Gaussian evolution method helps the proposed algorithm to get rid of local optima traps and enhance its exploration ability. In our experiments, the performance of proposed algorithm is evaluated on the synthetic networks and real-world networks, and we also make comparisons with other algorithms. The experimental results illustrate that the proposed algorithm outperforms other current algorithms. © 2024 SPIE.

关键词： Premixed flames

来源：评论

学校读者我要写书评

暂无评论

Efficient and Verifiable Multi-server Framework for Secure Information Classification and Storage 20th

Efficient and Verifiable Multi-server Framework for Secure...

引用

20th International Conference on Information security and Cryptology, Inscrypt 2024

作者： Guo, Ziqing Wang, Yaohui Jin, Xuanyu Wang, Xiuhua He, Yuanyuan Dai, Yueyue Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)9789819647330

With the rapid development of digital technology, the complexity and diversity of data sources present significant security and privacy challenges. To address these issues, this paper proposes an efficient and verifiable Multi-Server Framework for Secure Information Classification and Storage (MSF-SCS). The framework distributes sensitive data across multiple servers, proposing an opening authority to manage classified information and a semi-honest sanitizer to ensure strong authentication while preserving user anonymity. We formalize the security model of our scheme and prove that it satisfies the no-read rule, no-write rule, and unforgeability. We instantiate the scheme and conduct comprehensive experimental evaluations, which demonstrate that MSF-SCS significantly outperforms traditional architectures in terms of scalability and efficiency, making it particularly suitable for industries with stringent data protection requirements. Future work will focus on further improving the system’s security while maintaining its high performance. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

IntML-KNN: A Few-Shot Radio Frequency Fingerprint Identification Scheme for Lora Devices

引用

IEEE Signal Processing Letters 2025年 32卷 2259-2263页

作者： Cao, Xin Tan, Weijie Gao, Qiangqiang Hu, Zhilong Li, Chunguo Guizhou University College of Computer Science and Technology Guiyang550025 China Guizhou University State Key Laboratory of Public Big Data College of Computer Science and Technology Guiyang550025 China Advanced Cryptography and System Security Key Laboratory of Sichuan Province Chengdu610025 China Ministry of Industry and Information Technology Laboratory of Cryptograph Application Technology Innovation and Testing Verification Beijing100015 China Southeast University School of Information Science and Engineering Nanjing210096 China

Deep learning (DL) is widely used in radio frequency fingerprint identification (RFFI). However, in few-shot case, traditional DL-based RFFI need to construct auxiliary dataset to realize radio frequency fingerprint identification. To address this issue, we propose a few-shot RFFI (FS-RFFI) method based on interpolating metric learning and KNN (IntML-KNN). Specifically, the method first extends the dataset with data augmentation, and CutMix interpolation. Secondly, combining with metric learning to enhance the generalization capacity of the model. Finally, KNN algorithm is designed to realize device classification and detection. The proposed IntML-KNN method is verified on the commercial available LoRa dataset. The experimental results indicate that the proposed scheme exhibits strong classification and generalization performance in FS-RFFI. Meanwhile, the recognition rate of the proposed IntML-KNN reaches 97.00% with only 10% samples. © 1994-2012 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

A potential game-based outsourcing computation framework for multiple calculators

引用

Digital Communications and Networks 2022年第5期8卷 654-663页

作者： Duo Zhang Youliang Tian Linjie Wang State Key Laboratory of Public Big Data College of Computer Science and TechnologyGuizhou UniversityGuiyang550025China School of Mathematics and Statistics Guizhou UniversityGuiyang550025China

Outsourcing computation enables a computationally weak client to outsource the computation of a function f to a more powerful but untrusted *** traditional outsourcing computation model forbids communication between players,but it has little *** on the game theory,this paper establishes an outsourcing computation model which is more in line with the actual ***,we construct a structural mapping relationship between security outsourcing computation and the optimization ***,by designing the individual potential function and the global potential function,the individual goal is consistent with the global goal to ensure the correctness of the calculation ***,in the information exchange environment between calculators,we construct a Zero-determinant strategy to ensure that the calculator chooses the strategy according to the predetermined target.

关键词： Outsourcing computation Game theory Potential function Zero-determinant strategy Information exchange

来源：评论

学校读者我要写书评

暂无评论

Modulating perovskite crystallization and band alignment using coplanar molecules for high-performance indoor photovoltaics

引用

Journal of Energy Chemistry 2024年第11期98卷 383-390页

作者： Qu Yang Shuhan Fan Haozhe Zhang Zhenhuang Su Xingyu Gao Hui Shen Mingkui Wang Xiu Gong College of Physics &Guizhou Province Key Laboratory for Photoelectrics Technology and ApplicationGuizhou UniversityGuiyang 550025GuizhouChina State Key Laboratory of Public Big Data Guizhou UniversityGuiyang 550025GuizhouChina Shanghai Synchrotron Radiation Facility(SSRF) Shanghai Advanced Research InstituteChinese Academy of SciencesShanghai 201204China Wuhan National Laboratory for Optoelectronics School of Optical and Electronic InformationHuazhong University of Science and TechnologyWuhan 430074HubeiChina

The proper bandgap and exceptional photostability enable CsPbI_(3) as a potential candidate for indoor photovoltaics(IPVs),but indoor power conversion efficiency(PCE) is impeded by serious nonradiative recombination stemming from challenges in incomplete DMAPbI_(3) conversion and lattice structure ***,the coplanar symmetric structu re of hexyl sulfide(HS) is employed to functionalize the CsPbI_(3) layer for fabricating highly efficient *** hydrogen bond between HS and DMAI promotes the conversion of DMAPbI_(3) to CsPbI_(3),while the copianar symmetric structure enhances crystalline ***,surface sulfidation during HS-induced growth results in the in situ formation of PbS,spontaneously creating a CsPbI_(3) N-P homojunction to enhance band alignment and carrier *** a result,the CsPbI_(3)&HS devices achieve an impressive indoor PCE of 39.90%(P_(in):334.6 μW cm^(-2),P_(out):133.5 μW cm^(-2)) under LED@2968 K,1062 lux,and maintain over 90% initial PCE for 800 h at ^(3)0% air ambient humidity.

关键词： Perovskite indoor photovoltaics CsPbI_(3) Coplanar symmetric structure molecules Crystallization kinetics Hydrogen bond N-P homojunction

来源：评论

学校读者我要写书评

暂无评论

Knowledge Distillation Facilitates the Lightweight and Efficient Plant Diseases Detection Model

引用

Plant Phenomics 2023年第3期5卷 501-519页

作者： Qianding Huang Xingcai Wu Qi Wang Xinyu Dong Yongbin Qin Xue Wu Yangyang Gao Gefei Hao State Key Laboratory of Public Big Data College of Computer Science and TechnologyGuizhou UniversityGuiyang 550025China Text Computing&Cognitive Intelligence Engineering Research Center of National Education Ministry Guizhou UniversityGuiyang 550025China National Key Laboratory of Green Pesticide Guizhou UniversityGuiyang 550025China

Plant disease diagnosis in time can inhibit the spread of the disease and prevent a large-scale drop in production,which benefits food *** detection-based plant disease diagnosis methods have attracted widespread attention due to their accuracy in classifying and locating ***,existing methods are still limited to single crop disease *** importantly,the existing model has a large number of parameters,which is not conducive to deploying it to agricultural mobile ***,reducing the number of model parameters tends to cause a decrease in model *** solve these problems,we propose a plant disease detection method based on knowledge distillation to achieve a lightweight and efficient diagnosis of multiple diseases across multiple *** detail,we design 2 strategies to build 4 different lightweight models as student models:the YOLOR-Light-v1,YOLOR-Light-v2,Mobile-YOLOR-v1,and Mobile-YOLOR-v2 models,and adopt the YOLOR model as the teacher *** develop a multistage knowledge distillation method to improve lightweight model performance,achieving 60.4%mAP@.5 in the PlantDoc dataset with small model parameters,outperforming existing ***,the multistage knowledge distillation technique can make the model lighter while maintaining high *** only that,the technique can be extended to other tasks,such as image classification and image segmentation,to obtain automated plant disease diagnostic models with a wider range of lightweight applicability in smart *** code is available at https://***/QDH/MSKD.

关键词： Plant diagnosis image

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：