检索结果-内蒙古大学图书馆

2024 International Conference on Computer Application and Information Security, ICCAIS 2024

作者： Hu, Junzhu Lu, Ying Xu, Quanyuan Li, Caiyi Wang, Mingyang Zhou, Hao Yang, Peidong Jiang, Feng College of Big Data and Intelligent Engineering Southwest Forestry University Kunming650024 China Key Laboratory of Forestry and Ecological Big Data State Forestry Administration on Southwest Forestry University Kunming650024 China Qujing Tobacco Company Qujing655000 China

ISBN: (纸本)9781510689312

To address the challenges of vehicle attribute recognition in traffic management, intelligent parking systems, and road surveillance, this paper proposes an algorithm that integrates the Squeeze-and-Excitation (SE) attention mechanism into ResNet34. The SE mechanism is added after each BasicBlock, with a total of 16 SE modules incorporated to train the network. The optimal model is achieved after 100 iterations. The SE mechanism enhances the network’s ability to focus on key features by adaptively adjusting the importance of features across channels, thereby improving the effectiveness of feature representation. This dynamic adjustment allows the model to better adapt to complex and varying image structures, demonstrating strong adaptability in vehicle attribute recognition tasks. Experimental results show a significant improvement in recognition accuracy, with the enhanced ResNet34 model achieving a 5.1% increase in vehicle attribute recognition accuracy compared to the original ResNet34. The proposed algorithm effectively improves recognition performance, offering valuable technical support for the application of intelligent transportation systems. © The Authors.

关键词： Highway administration

来源：评论

学校读者我要写书评

暂无评论

Remote Image Acquisition System Based on STM32 for Spodoptera frugiperda 5

Remote Image Acquisition System Based on STM32 for Spodopter...

引用

5th IEEE Advanced Information Management, Communicates, Electronic and Automation Control Conference, IMCEC 2022

作者： Chang, Jumei Xu, Quanyuan Lu, Ying Zhang, Hanrui College of Big Data and Intelligent Engineering Southwest Forestry University Kunming China Southwest Forestry University Key Laboratory of Forestry and Ecological Big Data State Forestry Administration China

ISBN: (纸本)9781665479677

To enable remote image acquisition and wireless transmission for field sex lure monitoring of Spodoptera frugiperda, the design consists of a CPU processor module, power supply module, image acquisition module, 4G wireless network transmission module, and external SRAM module. The system employs the STM32F407 control core, the OV2640 camera for image acquisition, the JPEG algorithm to compress and decode the image data collected by the camera, and automatically restore the image collected at the monitoring point, the EC20 as a 4G wireless communication network for image data transmission, and the transmission of real-time image data to the server side of the upper computer to achieve human-computer interaction and real-time interaction of system daemons. The experimental results show that the system achieves remote image acquisition of grassland moths and reliably transmits the collected image data to the server side of the upper computer via a 4G wireless network, allowing the monitor to view images of grassland moth monitoring points collected by the system in real-time and save the collected image data locally. This system accomplishes the automation and intelligence of the grassland moth monitoring system, prepares the data for subsequent grassland moth research, and has a broad application promise for grassland moth population monitoring. © 2022 IEEE.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Assisted diagnosis of breast cancer based on federated learning and improved DenseNet 5

Assisted diagnosis of breast cancer based on federated learn...

引用

5th International Conference on Computer Vision and data Mining, ICCVDM 2024

作者： Huang, Shan Xiang, Hexia Li, Jingjie Sun, Yongkai Duan, Xiaodong College of Computer Science and Engineering Dalian Minzu University Dalian116600 China State Ethnic Affairs Commission Key Laboratory of Big Data Applied Technology Dalian Minzu University Dalian116600 China

ISBN: (纸本)9781510682863

Breast cancer is one of the common cancers worldwide, and how to identify breast cancer as early as possible plays an important role in its later diagnosis and treatment. However, relying only on data from a single organisation can limit the ability of trained neural networks to meet the performance demands of medical diagnostic services, and centralised learning that collects data from decentralised organisations can lead to privacy leakage. To address the above challenges, this paper proposes an assisted diagnosis model for breast cancer combining federated learning and improved DenseNet. Specifically, in contrast to mainstream centralised learning, this paper introduces federated learning to integrate multiparty data and effectively prevent privacy leakage. Each client sends the local model to the central server for aggregation, and then the global model obtained from the aggregation is sent to each client for training, thus achieving collaborative training of neural network models. In addition, in order to enhance the ability to capture feature information, this paper incorporates a Dynamic Convolution module into the densely connected network to improve the diagnostic accuracy without significantly increasing the size of the network model. The experimental results show that the proposed method has better diagnostic performance in breast cancer diagnosis compared with other methods. © 2024 SPIE.

关键词： Information leakage

来源：评论

学校读者我要写书评

暂无评论

Dual-view Label and Feature Supervision Network for Semi-supervised Medical Image Segmentation 24

Dual-view Label and Feature Supervision Network for Semi-sup...

引用

7th International Conference on Signal Processing and Machine Learning, SPML 2024

作者： Zhou, Zhen Li, Zuoyong Wang, Zhengyuan Teng, Shenghua Wang, Tao College of Electronic and Information Engineering Shandong University of Science and Technology Qingdao China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control School of Computer and Big Data Minjiang University Fuzhou China

ISBN: (纸本)9798400717192

Semi-supervised learning has garnered significant attention, particularly in medical image segmentation, owing to its capacity to leverage a large number of unlabeled data and a limited amount of labeled data to improve performance. However, most existing semi-supervised segmentation methods exhibit shortcomings in supervising unlabeled data, both in the label space due to potential noise in pseudo-labels, and the feature space due to indistinct class boundaries. To address the issues above, we propose Dual-view Label and Feature Supervision Network, termed DLFS-Net, to enhance label and feature supervision for unlabeled data. Our approach is based on a dual-view learning strategy that incorporates two modules: the Confidence Fusion Supervision Module (CFS) and the Dual-view Prototype Learning Module (DPL). Specifically, the CFS module generates weight matrices to integrate complementary information from two model outputs, producing more accurate pseudo-labels in the label space. The DPL module reduces intra-class variations in the feature space from two different views through prototype learning to generate clear class boundaries. Experiments on the LA and Pancreas-CT datasets demonstrate that our framework show solid gains (e.g.,1.76% Dice and 2.37% Jaccard improvement on Pancreas-CT dataset with 20% labeled data) compared with the state-of-the-art methods. © 2024 ACM.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Federated Intelligence for Intelligent Vehicles

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2024年第5期9卷 1-5页

作者： Zhang, Weishan Zhang, Baoyu Jia, Xiaofeng Qi, Hongwei Qin, Rui Li, Juanjuan Tian, Yonglin Liang, Xiaolong Wang, Fei-Yue School of China University of Petroleum Qingdao China Department of Data Management Big Data Centre Beijing Beijing China Technology Company Beijing China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing China Faculty of Innovation Engineering Macau University of Science and Technology Macao China State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China

This letter is a brief summary of a series of IEEE TIV's decentralized and hybrid workshops (DHWs) on Federated Intelligence for Intelligent Vehicles. The discussed results are: 1) Different scales of large models (LMs) can be federated and deployed on IVs, and three types of federated collaboration between large and small models can be adopted for IVs. 2) Federated fine-tuning of LMs is beneficial for IVs data security. 3) The sustainability of IVs can be improved through optimizing existing models and continuous learning using federated intelligence. 4) LM-enhanced knowledge can make IVs smarter. IEEE

关键词： Intelligent vehicle highway systems

来源：评论

学校读者我要写书评

暂无评论

An Ultra-Wideband Cascaded Power Amplifier for Military Individual Radio 7

An Ultra-Wideband Cascaded Power Amplifier for Military Indi...

引用

7th IEEE International Conference on Electronic Information and Communication Technology, ICEICT 2024

作者： Gao, Fei Nan, Jingchang Fan, Hongji Wang, Cong Tang, Panpan Li, Zhaoqi Liaoning Technical University Liaoning Key Laboratory of Radio Frequency and Big Data for Intelligent Applications Huludao China Southeast University Nanjing China Harbin Institute of Technology Department of Microwave Engineering Harbin China

ISBN: (纸本)9798350384437

In recent years, there has been a tremendous interest in military individual radio in wireless communication. To obtain sufficient operating distance and long standby time, the output power and efficiency of power amplifiers have become the research focus by some of the research teams. GaN has higher electron mobility and forbidden bandwidth than other materials. Nowadays, GaN has become the mainstream key technology for radio frequency (RF) power amplifiers in 5G communication systems. In this work, a 500MHz~2500MHz GaN-based HEMT wideband cascaded power amplifier was designed. The output power of the driver amplifier is 36.6dBm ± 0.5dB, the input return loss is 20%, the DC power consumption is 10 dB, input voltage standing wave ratio © 2024 IEEE.

关键词： Gallium nitride

来源：评论

学校读者我要写书评

暂无评论

An improved teaching-learning optimization algorithm based on fully informed search 4

An improved teaching-learning optimization algorithm based o...

引用

4th International Symposium on Computer Technology and Information Science, ISCTIS 2024

作者： Wu, Xiao Jiang, Xinghe Li, Shaobo Zhou, Yanqiu Guizhou University School of Mechanical Engineering Guiyang China Guizhou University State Key Laboratory of Public Big Data Guiyang China Guizhou University Jiangnan Institute of Mechanical and Electrical Design Guiyang China

ISBN: (纸本)9798350354560

As an advanced version of the Rao algorithm, the fully informed search algorithm (FISA) exhibits exceptional global search capabilities. However, its slow convergence rate somewhat limits its applicability in solving real-world problems. In contrast, the teaching-learning-based optimization (TLBO) algorithm is renowned for its rapid convergence but is highly susceptible to local optima entrapment. To capitalize on the robust global search prowess of FISA and the swift convergence characteristic of TLBO, while addressing optimization challenges, this study introduces an innovative proactive hybrid algorithm termed FISTLBO. Comparative experiments are conducted on the CEC2022 benchmark suite comprising 20-dimensional test functions, pitting the FISTLBO algorithm against six classical algorithms. The results demonstrate that the FISTLBO algorithm not only achieves superior consistency and stability in benchmark function outcomes but also outperforms other comparative algorithms, securing the top rank in the Friedman rank sum test. Consequently, the proposed FISTLBO algorithm proves to be an effective solution for intricate optimization problems. © 2024 IEEE.

关键词： Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Image Denoising Method Based on Channel Compression and Split-Attention Mechanism 5

Image Denoising Method Based on Channel Compression and Spli...

引用

5th International Conference on Computer engineering and Intelligent Control, ICCEIC 2024

作者： Sun, Hao Qiao, Xiaoyan School of Computer Science and Technology Shandong Technology and Business University Technology and Evaluation Shandong Engineering Research Center Yantai Key Laboratory of Big Data Modeling and Intelligent Computing Immersion Shandong Yantai China

ISBN: (纸本)9798331507992

In the image restoration task, how to make full use of spatial and channel feature information to improve the reconstruction quality of the model without significantly increasing the computational complexity is an important research issue. To address this challenge, this paper proposes a CS module (Channel Compression and Split-Attention) specifically for optimizing image denoising tasks. The module first compresses the features through a preliminary convolution operation, then introduces the split attention convolution mechanism to split the features by channel and dynamically weight them, thereby enhancing the model's adaptive attention to different feature channels and improving feature expression capabilities. Through experiments on multiple image denoising datasets, the results show that the CS module significantly improves the image reconstruction quality, especially in terms of peak signal-to-noise ratio (PSNR). At the same time, the introduction of the CS module does not lead to a significant increase in computational complexity, maintaining a high computational efficiency, which verifies the practicality and superiority of the module in image denoising tasks. © 2024 IEEE.

关键词： Restoration

来源：评论

学校读者我要写书评

暂无评论

Research on Weld Detection Based on Weighted Feature Fusion Network 23

Research on Weld Detection Based on Weighted Feature Fusion ...

引用

15th International Conference on Digital Image Processing, ICDIP 2023

作者： Wang, Mengxue Ma, Xing Mu, Chunyang Hou, Bing College of Electronic and Information Engineering North Minzu University Yinchuan China The Key Laboratory of Intelligent Information and Big Data Processing North Minzu University Yinchuan China

ISBN: (纸本)9798400708237

Weld seam grinding is a crucial process for welding cast products. Not only are the polished welds more attractive and durable, but they also have superior stress effects. However, the workplace is harsh and can significantly impact health. The first task for automated weld grinding is weld detection. This paper, a pyramid feature fusion network (YOLOv5-BiCA) learning model with embedded coordinate attention as a weighting condition that fully utilizes the shallow and deep network information. An online data augmentation strategy employing Mosaic+Mixup is proposed to address the problem of insufficient sample size. We use Focal Loss to enhance the classification function and increase the positive influence of positive samples on the loss function during the training process to address the problem of an imbalance between positive and negative sample. Our proposed YOLOv5-BiCA performs better in weld detection, mAP improves by 3.5%, and recall improves by 7.97%, according to experimental results based on homegrown datasets. © 2023 ACM.

关键词： Welds

来源：评论

学校读者我要写书评

暂无评论

A preliminary study on the volcanic intrusive complex type beryllium metallogenic belt from the southeast coast of China

引用

Science China Earth Sciences 2022年第8期65卷 1586-1600页

作者： Can RAO Rucheng WANG Fuyuan WU Xudong CHE Xiaofeng LI Qi WANG Zhiqi ZHANG Runqiu WU Key Laboratory of Geoscience Big Data and Deep Resource of Zhejiang Province School of Earth SciencesZhejiang UniversityHangzhou310027China State Key Laboratory for Mineral Deposits Research School of Earth Sciences and EngineeringNanjing UniversityNanjing210023China State Key Laboratory of Lithosphere Evolution Institute of Geology and GeophysicsChinese Academy of SciencesBeijing100029China

Beryllium(Be)is one of the unsubstitutable key metals in strategic emerging industries and national defense industries,mainly originating from volcanogenic Be ***,volcanogenic Be deposits have become important research objects of key metal deposits,with a focus on their occurrence,metallogenic mechanism,and resource *** the southeast coast of China,the Late Mesozoic volcanic intrusive complex has a good Be metallogenic background,and strong Be mineralization occurs in some *** geological investigation and analyses of samples from Southeast Zhejiang as well as Northeast and Southeast Fujian indicate that Be mineralization in the southeast coast of China is closely related to the hydrothermal processes in the volcanic intrusive *** Southeast Zhejiang,Be ore in the Qingtian area mainly occurs in granite porphyry,with the Be content reaching 939 ppm,while strong Be mineralization from Zhangji rhyolite porphyry in the Pingyang area contains up to 11400 ppm *** Xiapu County,Northeastern Fujian,the Dawan Be deposit is characterized by constituents of helvite and *** Pinghe County,Southeastern Fujian,the Fulishi Be ore is a quartz vein beryl-type *** results suggest that the volcanic intrusive complex area in the southeast coast of China has a wide range of Be mineralization and better Be metallogenic potential,and it is expected to become an important Be metallogenic belt in ***,we should thoroughly investigate the Be resources of granite porphyry,rhyolite porphyry,quartz porphyry,and quartz vein in this volcanic rock area,which can provide a theoretical basis for the exploration and guiding prospecting of volcanic intrusive complex Be deposits.

关键词： Volcanogenic Be deposit Beryllium resources Be-bearing minerals Beryllium metallogenic belt Southeast coast of China

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：