检索结果-内蒙古大学图书馆

42nd Chinese Control Conference, CCC 2023

作者： Yang, Guanci Wang, Xiaoyuan Zhu, Dongying Li, Yang Guizhou University Key Laboratory of Advanced Manufacturing Technology of the Ministry of Education Guiyang550025 China School of Mechanical Engineering Guizhou University Guiyang550025 China Guizhou University State Key Laboratory of Public Big Data Guiyang550025 China

ISBN: (纸本)9789887581543

Focusing on the poor real-time performance of 3D semantic mapping using RGB-D cameras in indoor environments, this paper investigates the Real-time Dense 3D Semantic Mapping (RD3DSM) using RGB-D camera. Firstly, a lightweight semantic point cloud acquisition algorithm based on keyframe is designed, which is used to segment scene images and obtain the semantic point cloud real-timely. Secondly, to address the loss of inter-frame tracking in the semantic mapping process, ORB-SLAM3 system is employed as the underlying architecture of the visual 3D semantic mapping system to provide stable camera pose. Thirdly, an information fusion mechanism of the visual 3D semantic mapping system is designed, and the OctoMap 3D scene reconstruction module is adopted to implement dense 3D map representation with semantic information, and then a visual 3D semantic mapping algorithm based on ORB-SLAM3 is proposed. Finally, the designed RD3DSM system is integrated into a robot platform. The tests were conducted on the TUM dataset and natural indoor scenes. The results show the effectiveness and real-time performance of the RD3DSM system. © 2023 Technical Committee on Control Theory, Chinese Association of Automation.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

An Efficient Blockchain-Based Certificateless Anonymous Authentication Scheme for VANETs

An Efficient Blockchain-Based Certificateless Anonymous Auth...

引用

2023 International Conference on Networking and Network Applications, NaNA 2023

作者： Bi, Changbing Tian, Youliang Li, Ta Wu, Shihong Zhou, Hua Guizhou University State Key Laboratory of Public Big Data Guiyang550025 China College of Computer Science and Technology Guizhou University Guiyang550025 China Guizhou University Guizhou Province Key Laboratory of Cryptography and Block Chain Technology Guiyang550025 China Institute of Cryptography & Data Security Guizhou University Guiyang550025 China College of Big Data and Information Engineering Guizhou University Guiyang550025 China

ISBN: (纸本)9798350327380

Vehicle ad-hoc networks (VANETs) play a critical role in providing security and privacy protection for intelligent transportation systems. However, the limited network bandwidth and computing capacity within VANETs have resulted in existing authentication schemes having excessive computational overhead, which cannot meet the low-latency communication requirements of VANETs. To tackle these problems, we propose an efficient blockchain-based certificateless anonymous authentication scheme for VANETs. Firstly, we propose a novel signature scheme without bilinear pairing to reduce the computational overhead in VANETs. Secondly, we utilize blockchain to facilitate trusted information sharing. Thirdly, we provide privacy-preserving through the use of anonymous keys, and enable tracing of vehicle identities in the event of malicious behavior. Finally, security analysis and simulation experiments demonstrate that our proposed scheme has lower communication and computational overhead, while satisfying various security requirements for VANETs, such as anonymity, unlinkability, and traceability. © 2023 IEEE.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

ReconBoost: Boosting Can Achieve Modality Reconcilement 41

ReconBoost: Boosting Can Achieve Modality Reconcilement

引用

41st International Conference on Machine Learning, ICML 2024

作者： Hua, Cong Xu, Qianqian Bao, Shilong Yang, Zhiyong Huang, Qingming Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China

This paper explores a novel multi-modal alternating learning paradigm pursuing a reconciliation between the exploitation of uni-modal features and the exploration of cross-modal interactions. This is motivated by the fact that current paradigms of multi-modal learning tend to explore multi-modal features simultaneously. The resulting gradient prohibits further exploitation of the features in the weak modality, leading to modality competition, where the dominant modality overpowers the learning process. To address this issue, we study the modality-alternating learning paradigm to achieve reconcilement. Specifically, we propose a new method called ReconBoost to update a fixed modality each time. Herein, the learning objective is dynamically adjusted with a reconcilement regularization against competition with the historical models. By choosing a KL-based reconcilement, we show that the proposed method resembles Friedman's Gradient-Boosting (GB) algorithm, where the updated learner can correct errors made by others and help enhance the overall performance. The major difference with the classic GB is that we only preserve the newest model for each modality to avoid overfitting caused by ensembling strong learners. Furthermore, we propose a memory consolidation scheme and a global rectification scheme to make this strategy more effective. Experiments over six multi-modal benchmarks speak to the efficacy of the method. We release the code at https://***/huacong/ReconBoost. Copyright 2024 by the author(s)

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

DGN-MEF: A DenseNet-Based Multi-Exposure Image Fusion Framework using Adaptive Gabor convolution 43

DGN-MEF: A DenseNet-Based Multi-Exposure Image Fusion Framew...

引用

43rd Chinese Control Conference, CCC 2024

作者： Zhang, Mei Jin, Ye Zhu, Jinhui South China University of Technology School of Automation Science and Engineering Guangzhou510641 China South China University of Technology School of Software Engineering Guangzhou510006 China Key Laboratory of Big Data and Intelligent Robot Ministry of Education Guangzhou510006 China

ISBN: (纸本)9789887581581

Multi-exposure image fusion is a cost-effective method to improve the dynamic range of images. For the problems of inadequate detail extraction in bright and dark areas and the over simplicity of existing fusion rules by current deep learning multi-exposure image fusion algorithms, we propose a DenseNet-based framework using adaptive Gabor convolution. Building on the Dense network architecture, we design an adaptive Gabor convolution module, which the parameters of the Gabor filter can be updated along with the network, enhancing the ability of Gabor to extract image features. Additionally, a cross-domain aggregation attention module is proposed, which effectively aggregates and enhances information. Comparing our method with seven advanced methods on the multi-exposure image fusion benchmark dataset, the subjective and objective evaluations outperform the other methods, proving the effectiveness and superiority of our method. The experiments of different exposure images fusion demonstrate the good generalization performance of our method. © 2024 Technical Committee on Control Theory, Chinese Association of Automation.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Plausible Heterogeneous Graph k-Anonymization for Social Networks

引用

Tsinghua Science and Technology 2022年第6期27卷 912-924页

作者： Kaiyang Li Ling Tian Xu Zheng Bei Hui School of Computer Science and Engineering University of Electronic Science and Technology of ChinaChengdu 611731China School of Information and Software Engineering University of Electronic Science and Technology of ChinaChengdu 610054China Trusted Cloud Computing and Big Data Key Laboratory of Sichuan Province Chengdu 610000China

The inefficient utilization of ubiquitous graph data with combinatorial structures necessitates graph embedding methods,aiming at learning a continuous vector space for the graph which is amenable to be adopted in traditional machine learning algorithms in favor of vector *** embedding methods build an important bridge between social network analysis and data analytics as social networks naturally generate an unprecedented volume of graph data *** social network data not only bring benefit for public health,disaster response,commercial promotion,and many other applications,but also give birth to threats that jeopardize each individual’s privacy and ***,most existing works in publishing social graph embedding data only focus on preserving social graph structure with less attention paid to the privacy issues inherited from social *** be specific,attackers can infer the presence of a sensitive relationship between two individuals by training a predictive model with the exposed social network *** this paper,we propose a novel link-privacy preserved graph embedding framework using adversarial learning,which can reduce adversary’s prediction accuracy on sensitive links while persevering sufficient non-sensitive information such as graph topology and node attributes in graph *** experiments are conducted to evaluate the proposed framework using ground truth social network datasets.

关键词： social network graph embedding privacy preservation adversarial learning

来源：评论

学校读者我要写书评

暂无评论

A Novel 3D Medical Image Segmentation Model Using Improved SAM

A Novel 3D Medical Image Segmentation Model Using Improved S...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Kuang, Yuansen Ma, Xitong Zhao, Jing Wang, Guangchen Zeng, Yijie Liu, Song Key Laboratory of Computing Power Network and Information Security Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Jinan China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computer Networks Jinan China

ISBN: (纸本)9781665410205

3D medical image segmentation is an essential task in the medical image field, which aims to segment organs or tumours into different labels. A number of issues exist with the current 3D medical image segmentation task: existing models cannot simultaneously obtain the space correlation and depth correlation of 3D slices;previous models suffer from local detail loss of positional embedding in 3D images;previous approaches often have blurring of boundaries in segmenting 3D images. To solve these shortcomings, we propose a 3D medical image segmentation model named TPM-SAM. In our model, we design a twinchannel image encoder to simultaneously capture the space correlation and depth correlation of 3D slices through a multi-head attention mechanism and improved adapters. Furthermore, we design a prompt encoding generator, which divides the volumetric image into small blocks and better captures the local detail information. In addition, we introduce a multi-layer aggregation decoder by employing U-Net with multi-level skip connection to solve the blurring of boundaries in processing 3D images. Finally, we experimented and evaluated our model on KiTS21 and LiTS17 datasets to compare with other baseline models. © 2024 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

CCAC: Contrastive Learning with Channel Attention and Contour Loss for Brain Image Registration

CCAC: Contrastive Learning with Channel Attention and Contou...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Zhang, Ying Shi, Dantong Wang, Jiaqi Xiang, Jinhai Zhang, Wen Huazhong Agricultural University College of Informatics Wuhan China Agricultural Bioinformatics Key Laboratory of Hubei Province Hubei Engineering Technology Research Center of Agricultural Big Data Key Laboratory of Smart Farming for Agricultural Animals Ministry of Agriculture Wuhan China

ISBN: (纸本)9798350337488

In medical image analysis, image registration plays a key role in establishing the deformation field between image pairs. A good deformation model is essential for high-quality estimates. However, most existing approaches still face great challenges in extracting better image features and generating detailed information on deformation fields. In this paper, we present a brain image registration model based on contrastive learning with channel attention and contour loss (CCAC). To integrate lower-level features more effectively, we propose a channel attention-based skip connection to obtain weight information of features at different encoder layers. To enhance the feature consistency of semantics in different stages, we then introduce multi-stage contrastive learning to capture semantics at different stages. Moreover, in order to reduce the influence caused by the disparities of inter-image gray value in registered images, contour feature loss is employed. Both qualitative and quantitative experiments on the popular LPBA40 dataset demonstrate that our method can achieve much better performance than the baseline methods. © 2023 IEEE.

关键词： Brain MR image Channel attention Contour features Medical image registration Multistage contrastive learning

来源：评论

学校读者我要写书评

暂无评论

Design of cloud platform for niche monitoring of forest pests based on Internet of Things 22

Design of cloud platform for niche monitoring of forest pest...

引用

5th International Conference on Information Management and Management Science, IMMS 2022

作者： Fan, Min Lu, Ying Xu, Quanyuan Yang, Peidong College of Big Data and Intelligent Engineering Southwest Forestry University China College of Big Data and Intelligent Engineering Southwest Forestry University China and Key Laboratory of Forest Ecology Big Data National Forestry and Grassland Administration Southwest Forestry University China Qujing Tobacco Company of Yunnan Province China

ISBN: (纸本)9781450396721

In view of the frequent occurrence of dangerous forest diseases and insect pests in China, which have caused varying degrees of damage to forest resources and ecological environment, this study designed a niche monitoring system for forest diseases and insect pests based on STM32 and the Internet of Things. The design uses STM32 as the data acquisition terminal and repeater, and transmits data to the cloud via the Internet through the W5500 module, realizing remote monitoring of the host computer's webpage. Through this monitoring system, users can understand the environmental information and historical conditions that have a greater impact on forest diseases and insect pests in the deployment area of the system at any time, including carbon dioxide concentration, oxygen concentration, soil pH, temperature and humidity, light intensity, etc., collected by the system The terminal can adapt to about 20 kinds of sensors, and can easily and comprehensively monitor and manage different forest niches. This study provides a basis for forest pest monitoring, which can efficiently and timely provide forest ecological environment information and reduce the consumption of human and material resources. It is of great significance to the scientific management of forest workers. © 2022 ACM.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Solidification modes and delta-ferrite of two types of 316L stainless steels:a combination of as-cast microstructure and HT-CLSM research

引用

Journal of Iron and Steel Research International 2025年第2期32卷 426-436页

作者： Yang Wang Chao Chen Xiao-yu Yang Zheng-rui Zhang Jian Wang Zhou Li Lei Chen Wang-zhong Mu College of Materials Science and Engineering Taiyuan University of TechnologyTaiyuan 030024ShanxiChina Department of Materials Science and Engineering KTH Royal Institute of TechnologyStockholm 10044Sweden College of Artificial Intelligence and Big Data for Medical Sciences Shandong First Medical University and Shandong Academy of Medical SciencesJinan 250117ShandongChina College of Mechanical Engineering Taiyuan University of TechnologyTaiyuan 030024ShanxiChina Key Laboratory of Electromagnetic Processing of Materials(Ministry of Education) Northeastern UniversityShenyang 110819LiaoningChina

In 316L austenitic stainless steel,the presence of ferrite phase severely affects the non-magnetic properties.316L austenitic stainless steel with low-alloy type(L-316L)and high-alloy type(H-316L)has been *** microstructure and solidification kinetics of the two as-cast grades were in situ observed by high temperature confocal laser scanning microscopy(HT-CLSM).There are significant differences in the as-cast microstructures of the two 316L stainless steel *** L-316L steel,ferrite morphology appears as the short rods with a ferrite content of 6.98%,forming a dual-phase microstructure consisting of austenite and ***,in H-316L steel,the ferrite appears as discontinuous network structures with a content of 4.41%,forming a microstructure composed of austenite and sigma(σ)*** alloying elements in H-316L steel exhibit a complex distribution,with Ni and Mo enriching at the austenite grain ***-CLSM experiments provide the real-time observation of the solidification processes of both 316L specimens and reveal distinct solidification modes:L-316L steel solidifies in an FA mode,whereas H-316L steel solidifies in an AF *** differences result in ferrite and austenite predominantly serving as the nucleation and growth phases,*** solidification mode observed by experiments is similar to the thermodynamic calculation *** L-316L steel solidified in the FA mode and showed minimal element segregation,which lead to a direct transformation of ferrite to austenite phase(δ→γ)during phase transformation after ***,the H-316L steel solidified in the AF mode and showed severe element segregation,which lead to Mo enrichment at grain boundaries and transformation of ferrite into sigma and austenite phases through the eutectoid reaction(δ→σ+γ).

关键词： 316L austenitic stainless steel As-cast microstructure High-temperature confocal laser scanning microscopy Solidification mode Ferrite Characterization

来源：评论

学校读者我要写书评

暂无评论

Surface-enhanced Raman scattering on nanomaterials for cancer and pathogens diagnosis

引用

Nano Research 2025年第2期18卷 650-674页

作者： Jingjing Wu Baohong Zhang Lei Xu Yanyu Zhao Tao Chen Jie Lin Anran Li School of Engineering Medicine Beihang UniversityBeijing 100191China Key Laboratory of Big Data-Based Precision Medicine Ministry of Industry and Information Technology of the People’s Republic of ChinaBeihang UniversityBeijing 100191China School of Optics and Photonics Beijing Institute of TechnologyBeijing 100089China Shanxi Lu'an Taihang Lubricant Technology Co. Ltd.Changzhi 046204China Cixi Institute of Biomedical Engineering Ningbo Institute of Materials Technology and EngineeringChinese Academy of SciencesNingbo 315201China

Surface-enhanced Raman scattering(SERS)is a non-invasive spectroscopic technique that provides specific chemical fingerprint information for biomarkers in cancer and pathogen ***,the SERS strategies are limited by the non-specific interactions between substrates and co-existing substances in biological matrices and the challenges of obtaining molecular fingerprint information from the complex vibrational *** recent years,the rapid development of novel substrates with high SERS activity has opened up new opportunities for their applications in cancer and pathogen *** aim of this review is to present the recent progress and perspectives of novel SERS-based substrates for cancer and pathogen diagnostic ***,we will introduce recently developed SERS-active nanomaterials and discuss the influencing factors of the SERS ***,the advantages of SERS in the diagnosis of cancer and pathogens will be ***,we will review the latest breakthroughs in cancer and pathogen detection research with SERS technology,as well as the new opportunities for SERS applications brought about by artificial intelligence(Al)*** addition,the novel microfluidic-SERS platforms for cancer and pathogens diagnosis will also be ***,we will summarize the challenges and future perspectives of SERS technology in the field of early cancer diagnosis and rapid pathogen *** is highly expected that this review could benefit a comprehensive understanding of the research status of the SERS-active nanomaterials and arouse the research enthusiasm for them,leading to accelerated clinical translation of SERS technology in cancer and pathogen diagnosis.

关键词： surface-enhanced Raman scattering(SERS) SERS-active nanomaterials cancer and pathogen diagnosis artificial intelligence(Al)technology

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：