检索结果-内蒙古大学图书馆

3rd EAI International Conference on Artificial Intelligence for Communications and Networks, AICON 2021

作者： Zhang, YunLing Guo, Pei Liu, Pengyu Li, Yaoyao Chen, Shanji Research and Development Center of Transport Industry of Spatial Information Application and Disaster Prevention and Mitigation Technology Beijing100097 China China Highway Engineering Consultants Corporation Beijing100097 China Faculty of Information Technology Beijing University of Technology Beijing100124 China Beijing Laboratory of Advanced Information Networks Beijing100124 China Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing University of Technology Beijing100124 China School of Physics and Electronic Information Qinghai Nationalities University Xining810007 China

ISBN: (纸本)9783030901950

Highway slope disasters show obvious stage characteristics before the occurrence, and cracks are the early symptoms of most highway slope disasters. Computer vision is widely used in crack detection because of its advantages of high efficiency and low cost. In view of the shortage of traditional crack actual area calculation methods and poor effect, this paper proposes a slope crack pixel level segmentation method based on deep convolutional neural network, so as to generate accurate segmentation of crack morphology. Then, according to the binary segmentation mask, the checkerboard mapping method is proposed to calculate the actual crack area. Finally, the effectiveness and superiority of the proposed checkerboard mapping method are verified and evaluated with a self-made data set of highway crack image. The experimental results show that this method can effectively detect the actual crack area, and the relative error is small. The calculated results can be used as a reference for slope disaster warning. © 2021, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Cyclic Learning: Bridging Image-level Labels and Nuclei Instance Segmentation

arXiv

引用

arXiv 2023年

作者： Zhou, Yang Wu, Yongjian Wang, Zihua Wei, Bingzheng Lai, Maode Shou, Jianzhong Fan, Yubo Xu, Yan School of Biological Science and Medical Engineering State Key Laboratory of Software Development Environment Key Laboratory of Biomechanics and Mechanobiology of Ministry of Education Beijing Advanced Innovation Center for Biomedical Engineering Beihang University Beijing100191 China Xiaomi Corporation Beijing100085 China Department of Pathology School of Medicine Zhejiang University Zhejiang Provincial Key Laboratory of Disease Proteomics and Alibaba Zhejiang University Joint Research Center of Future Digital Healthcare Hangzhou310053 China Department of Urology National Cancer Center National Clinical Research Center for Cancer Cancer Hospital Chinese Academy of Medical Sciences Peking Union Medical College Chaoyang District Beijing100021 China

Nuclei instance segmentation on histopathology images is of great clinical value for disease analysis. Generally, fully-supervised algorithms for this task require pixel-wise manual annotations, which is especially time-consuming and laborious for the high nuclei density. To alleviate the annotation burden, we seek to solve the problem through image-level weakly supervised learning, which is underexplored for nuclei instance segmentation. Compared with most existing methods using other weak annotations (scribble, point, etc.) for nuclei instance segmentation, our method is more labor-saving. The obstacle to using image-level annotations in nuclei instance segmentation is the lack of adequate location information, leading to severe nuclei omission or overlaps. In this paper, we propose a novel image-level weakly supervised method, called cyclic learning, to solve this problem. Cyclic learning comprises a front-end classification task and a back-end semi-supervised instance segmentation task to benefit from multi-task learning (MTL). We utilize a deep learning classifier with interpretability as the front-end to convert image-level labels to sets of high-confidence pseudo masks and establish a semi-supervised architecture as the back-end to conduct nuclei instance segmentation under the supervision of these pseudo masks. Most importantly, cyclic learning is designed to circularly share knowledge between the front-end classifier and the back-end semi-supervised part, which allows the whole system to fully extract the underlying information from image-level labels and converge to a better optimum. Experiments on three datasets demonstrate the good generality of our method, which outperforms other image-level weakly supervised methods for nuclei instance segmentation, and achieves comparable performance to fully-supervised methods. Copyright © 2023, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Nucleus-aware Self-supervised Pretraining Using Unpaired Image-to-image Translation for Histopathology Images

arXiv

引用

arXiv 2023年

作者： Song, Zhiyun Du, Penghui Yan, Junpeng Li, Kailu Shou, Jianzhong Lai, Maode Fan, Yubo Xu, Yan The School of Biological Science and Medical Engineering State Key Laboratory of Software Development Environment Key Laboratory of Biomechanics and Mechanobiology of Ministry of Education Research Institute of Beihang University in Shenzhen Beijing Advanced Innovation Center for Biomedical Engineering Beihang University Beijing100191 China The Department of Urology National Cancer Center National Clinical Research Center for Cancer Cancer Hospital Chinese Academy of Medical Sciences Peking Union Medical College Chaoyang District Beijing100021 China The Department of Pathology School of Medicine Zhejiang University Zhejiang Provincial Key Lab Disease Proteomics Alibaba-Zhejiang University Joint Research Center of Future Healthcare Hangzhou310053 China

Self-supervised pretraining attempts to enhance model performance by obtaining effective features from unlabeled data, and has demonstrated its effectiveness in the field of histopathology images. Despite its success, few works concentrate on the extraction of nucleus-level information, which is essential for pathologic analysis. In this work, we propose a novel nucleus-aware self-supervised pretraining framework for histopathology images. The framework aims to capture the nuclear morphology and distribution information through unpaired image-to-image translation between histopathology images and pseudo mask images. The generation process is modulated by both conditional and stochastic style representations, ensuring the reality and diversity of the generated histopathology images for pretraining. Further, an instance segmentation guided strategy is employed to capture instance-level information. The experiments on 7 datasets show that the proposed pretraining method outperforms supervised ones on Kather classification, multiple instance learning, and 5 dense-prediction tasks with the transfer learning protocol, and yields superior results than other self-supervised approaches on 8 semi-supervised tasks. Our project is publicly available at https://***/zhiyuns/UNITPathSSL. Copyright © 2023, The Authors. All rights reserved.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Differences in the Composition of Archidendron Clypearia at Different Harvest Periods and Spectrum–Effect Relationship and Structure–Activity Analysis of Antioxidant Components

SSRN

引用

SSRN 2022年

作者： Ji, Wenduo Li, Zhichao Gu, Lixia Zou, Xuezhe Wu, Jialin Zhang, Shu Deng, Hong The Center for Drug Research and Development Guangdong Pharmaceutical University Guangdong Guangzhou510006 China Guangdong Provincial Key Laboratory of Advanced Drug Delivery Systems Guangdong Pharmaceutical University Guangdong Guangzhou510006 China Guangdong Provincial Engineering Center of Topical Precise Drug Delivery System Department of Pharmaceutics Guangdong Pharmaceutical University Guangdong Guangzhou510006 China

Archidendron clypearia, a specialty plant in Southeast Asia, is expected to be developed as a natural antioxidant due to its rich polyphenolic compounds. In this study, the ultra-performance liquid chromatography (UPLC) fingerprints of 16 different harvest period batches of A. clypearia were evaluated using hierarchical clustering analysis (HCA), principal component analysis (PCA), and partial least squares discrimination analysis (PLS-DA). The antioxidant activities of 70% aqueous ethanol extracts from the above 16 batches of samples were assessed using diphenyl picryl hydrazyl (DPPH), 2,2-azinobis-(3-ethylbenzothiazoline-6-sulfonic acid) (ABTS) and ferric reducing antioxidant assay (FRAP). The spectrum–effect relationship between UPLC fingerprints and antioxidant activity of A. clypearia was evaluated to screen for the antioxidant activity of substances based on three chemometrics, i.e., orthogonal partial least squares analysis (OPLS), gray correlation analysis (GRA), and bivariate correlation analysis (BCA). The results revealed that P7 (ethyl gallate), P14 (5,3',4',5'-tetrahydroxyflavan-7-gallate), P16 (quercitrin), P15 and P18 (7,3’-O-di-gallyoltricetiflavan /7,4’-O-di-galloyltricetiflavan) were the main changing components between different harvest periods and P3 (gallic acid), P6, P7, P8 (3,5,3',4',5'-pentahydroxyflavan-7-gallate), P9, P13, P14, P15, P17 and P18 played an essential role in the antioxidant effects of A. clypearia . Six monomer components and a pair of isomonomer mixtures were also isolated to verify the antioxidant activity combined with structure-activity analysis by density functional theory (DFT) calculations. Our results prove the potential of A. clypearia as an antioxidant for some common and unique components, and at the same time provides a reference for the selection and utilization of A. clypearia . © 2022, The Authors. All rights reserved.

关键词： Density functional theory

来源：评论

学校读者我要写书评

暂无评论

A new pixel structure for OLEDoS micro-display

A new pixel structure for OLEDoS micro-display

引用

International Conference on Display Technology, ICDT 2019

作者： Guo, Aiying Ran, Feng Zhang, Jianhua Microelectronic Research and Development Center Shanghai China Key Laboratory of Advanced Display and System Applications Ministry of Education Shanghai China

ISBN: (纸本)9781510896161

In this paper, we propose a new pixel structure for the organic Light Emitting Diode (OLED) 0.65 inch SVGA resolution micro-display with 8 bit gray level. The proposed pixel structure is composed of 4 MOSFETS and one capacitor to integrate the pixel structure in the restricted pixel area ( 9um 9um ) using 0.18um technology. The simulation result shows that the maximum error of emission current occurs at high gray level. Author Keywords © 2019, John Wiley and Sons Inc. All rights reserved.

关键词： MOSFET devices

来源：评论

学校读者我要写书评

暂无评论

Role of the immune microenvironment in bone,cartilage,and soft tissue regeneration:from mechanism to therapeuticopportunity

引用

Military Medical research 2023年第4期10卷 499-528页

作者： Yuan Xiong Bo‑Bin Mi Ze Lin Yi‑Qiang Hu Le Yu Kang‑Kang Zha Adriana CPanayi Tao Yu Lang Chen Zhen‑Ping Liu Anish Patel Qian Feng Shuan‑Hu Zhou Guo‑Hui Liu Department of Orthopedics Union HospitalTongji Medical CollegeHuazhong University of Science and TechnologyWuhan 430022China Hubei Province Key Laboratory of Oral and Maxillofacial Development and Regeneration Wuhan 430022China Department of Chemical and Biomolecular Engineering Ohio UniversityAthensOH 45701USA Key Laboratory of Biorheological Science and Technology Ministry of Education College of BioengineeringChongqing UniversityShapingbaChongqing 400044China Department of Plastic Surgery Brigham and Women’s HospitalHarvard Medical SchoolBostonMA 02152USA Department of Orthopaedics Ruijin HospitalShanghai Jiao Tong University School of MedicineShanghai 200025China Department of Physics Center for Hybrid Nanostructure(CHyN)University of HamburgHamburg 22761Germany Joint Laboratory of Optofluidic Technology and System National Center for International Research on Green OptoelectronicsSouth China Academy of Advanced OptoelectronicsSouth China Normal UniversityGuangzhou 510006China Skeletal Biology Laboratory Department of Orthopedic SurgeryBrigham and Women’s HospitalHarvard Medical SchoolBostonMA 02120USA Harvard Stem Cell Institute Harvard UniversityCambridgeMA 02138USA.

Bone,cartilage,and soft tissue regeneration is a complex spatiotemporal process recruiting a variety of cell types,whose activity and interplay must be precisely mediated for effective healing *** extensive strides have been made in the understanding of the immune microenvironment processes governing bone,cartilage,and soft tissue regeneration,effective clinical translation of these mechanisms remains a *** of the immune microenvironment is increasingly becoming a favorable target for bone,cartilage,and soft tissue regeneration;therefore,an in-depth understanding of the communication between immune cells and functional tissue cells would be ***,we review the regulatory role of the immune microenvironment in the promotion and maintenance of stem cell states in the context of bone,cartilage,and soft tissue repair and *** discuss the roles of various immune cell subsets in bone,cartilage,and soft tissue repair and regeneration processes and introduce novel strategies,for example,biomaterial-targeting of immune cell activity,aimed at regulating *** the mechanisms of the crosstalk between the immune microenvironment and regeneration pathways may shed light on new therapeutic opportunities for enhancing bone,cartilage,and soft tissue regeneration through regulation of the immune microenvironment.

关键词： Immune microenvironment Regeneration Cell-cell interaction Tissue engineering Biomaterials

来源：评论

学校读者我要写书评

暂无评论

Hybrid RAG-empowered Multi-modal LLM for Secure Data Management in Internet of Medical Things: A Diffusion-based Contract Approach

arXiv

引用

arXiv 2024年

作者： Su, Cheng Wen, Jinbo Kang, Jiawen Wang, Yonghua Su, Yuanjia Pan, Hudan Zhong, Zishao Hossain, M. Shamim School of Automation The GuangdongHongKong-Macao Joint Laboratory for Smart Discrete Manufacturing Guangdong University of Technology Guangzhou510006 China College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing210016 China School of Automation The Guangdong Basic Research Center of Excellence for Ecological Security and Green Development Key Laboratory for City Cluster Environmental Safety Green Development The Ministry of Education Guangdong University of Technology Guangzhou510006 China School of Automation The Key Laboratory of Intelligent Detection and IoT in Manufacturing Ministry of Education Guangdong University of Technology Guangzhou510006 China School of Automation Key Laboratory of Intelligent Information Processing and System Integration of IoT Ministry of Education Guangdong University of Technology Guangzhou510006 China Guangzhou University of Traditional Chinese Medicine State Key Laboratory of Traditional Chinese Medicine Syndrome The Second Affiliated Hospital of Guangzhou University of Chinese Medicine Chinese Medicine Guangdong Laboratory Hengqin 519000 China Second Affiliated Hospital of Guangzhou University of Chinese Medicine Chinese Medicine Guangdong Laboratory Hengqin 519000 China Department of Software Engineering College of Computer and Information Sciences King Saud University Riyadh12372 Saudi Arabia

Secure data management and effective data sharing have become paramount in the rapidly evolving healthcare landscape, especially with the growing integration of the Internet of Medical Things (IoMT). The rise of generative artificial intelligence has further elevated Multi-modal Large Language Models (MLLMs) as essential tools for managing and optimizing healthcare data in IoMT. MLLMs can support multi-modal inputs and generate diverse types of content by leveraging large-scale training on vast amounts of multi-modal data. However, critical challenges persist in developing medical MLLMs, including security and freshness issues of healthcare data, affecting the output quality of MLLMs. To this end, in this paper, we propose a hybrid Retrieval-Augmented Generation (RAG)-empowered medical MLLM framework for healthcare data management. This framework leverages a hierarchical cross-chain architecture to facilitate secure data training. Moreover, it enhances the output quality of MLLMs through hybrid RAG, which employs multi-modal metrics to filter various unimodal RAG results and incorporates these retrieval results as additional inputs to MLLMs. Additionally, we employ age of information to indirectly evaluate the data freshness impact of MLLMs and utilize contract theory to incentivize healthcare data holders to share their fresh data, mitigating information asymmetry during data sharing. Finally, we utilize a generative diffusion model-based deep reinforcement learning algorithm to identify the optimal contract for efficient data sharing. Numerical results demonstrate the effectiveness of the proposed schemes, which achieve secure and efficient healthcare data management. Copyright © 2024, The Authors. All rights reserved.

关键词： Information management

来源：评论

学校读者我要写书评

暂无评论

Integer Programming Approach to the Data Traffic Paths Recovering Problem 19th

Integer Programming Approach to the Data Traffic Paths Recov...

引用

19th International Conference on Mathematical Optimization Theory and Operations research, MOTOR 2020

作者： Vasilyev, Igor Zhang, Dong Ren, Jie Matrosov Institute for System Dynamics and Control Theory of Siberian Branch of Russian Academy of Sciences Irkutsk Russia Algorithm and Technology Development Department Global Technical Service Department Huawei Technologies Co. Ltd. Dongguan China Moscow Advanced Software Technology Lab Huawei Russian Research Institute Moscow Russia

ISBN: (纸本)9783030499877

In this paper, we propose a novel approach to recovering path relationships in communication networks. The path relationship is one of the key input data which is necessary for network operation and maintenance. We have a continuous network transformation, upgrades, expansions, service allocations, thus the network physical topology and paths relationship are permanently changing with high frequency. Our approach is aimed at recovering the path relationships through flow information of each arc in the network. Getting the flow information is not a big technical problem and its control is included in the basic toolbox for network monitoring. We consider two scenarios which lead us to integer linear programs. The both of them minimize the flow deviation, where in the first one we look for a directed spanning tree (r-arborescence) and, in the second one—more general origin/destination paths (OD-paths). We propose mixed integer linear programming formulations for both problems. Their feature is that they contain the non-polynomial number of constraints which are considered implicitly by the cutting planes approach. The preliminary computation results showed that the large-scale instances of the first scenario can easily be solved. At the same time, the optimal solutions of second scenario problems can be found only on small- and medium-size instances, which inspires for the further research. © 2020, Springer Nature Switzerland AG.

关键词： Integer programming

来源：评论

学校读者我要写书评

暂无评论

Correction to: Influence of sustained mild dehydration on thermoregulatory and cognitive functions during prolonged moderate exercise

引用

European journal of applied physiology 2024年第12期124卷 2024 Oct 9页

作者： Hironori Watanabe Yuma Kadokura Taisuke Sugi Kiyoshi Saito Kei Nagashima Institute for Energy and Environmental System Sustainable Energy & Environmental Society Open Innovation Research Organization Waseda University 3-4-1 Okubo Shinjuku-ku Tokyo 1698555 Japan. Advanced Research Center for Human Sciences Waseda University 2-579-15 Mikajima Tokorozawa Saitama 3591192 Japan. Body Temperature and Fluid Laboratory Faculty of Human Sciences Waseda University 2-579-15 Mikajima Tokorozawa Saitama 3591192 Japan. Infrastructure Systems Research & Development Center Toshiba Infrastructure Systems & Solutions Corporation Kawasaki Kanagawa 2129595 Japan. Department of Applied Mechanics and Aerospace Engineering School of Fundamental Science and Engineering Waseda University 3-4-1 Okubo Shinjuku-ku Tokyo 1698555 Japan. Institute for Energy and Environmental System Sustainable Energy & Environmental Society Open Innovation Research Organization Waseda University 3-4-1 Okubo Shinjuku-ku Tokyo 1698555 Japan. k-nagashima@waseda.jp. Body Temperature and Fluid Laboratory Faculty of Human Sciences Waseda University 2-579-15 Mikajima Tokorozawa Saitama 3591192 Japan. k-nagashima@waseda.jp.

来源：评论

学校读者我要写书评

暂无评论

An in-situ defect passivation through a green anti-solvent approach for high-efficiency and stable perovskite solar cells

引用

Science Bulletin 2021年第14期66卷 1419-1428,M0004页

作者： Chang Liu Lei Huang Xianyong Zhou Xingzhu Wang Jianxi Yao Zhike Liu Shengzhong Frank Liu Wanli Ma Baomin Xu Academy for Advanced Interdisciplinary Studies Southern University of Science and TechnologyShenzhen 518055China Department of Materials Science and Engineering and Shenzhen Engineering Research and Development Center for Flexible Solar Cells Southern University of Science and TechnologyShenzhen 518055China Key Laboratory of Energy Conversion and Storage Technologies(Southern University of Science and Technology) Ministry of EducationShenzhen 518055China Guangdong-Hong Kong-Macao Joint Laboratory for Photonic-Thermal-Electrical Energy Materials and Devices Southern University of Science and TechnologyShenzhen 518055China State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources North China Electric Power UniversityBeijing 102206China Key Laboratory of Applied Surface and Colloid Chemistry(Ministry of Education) Shaanxi Key Laboratory for Advanced Energy DevicesShaanxi Engineering Laborartory for Advanced Energy TechnologySchool of Materials Science and EngineeringShaanxi Normal UniversityXi’an 710119China Institute of Functional Nano&Soft Materials Jiangsu Key Laboratory for Carbon-Based Functional Materials&DevicesJoint International Research Laboratory of Carbon-Based Functional Materials and DevicesSoochow UniversitySuzhou 215123China

Surface and grain boundary defects in halide perovskite solar cells are highly detrimental,reducing efficiencies and *** halide anion and organic cation defects usually aggravate ion diffusion and material degradation on the surfaces and at the grain boundaries of perovskite *** this study,we employ an in-situ green method utilizing nontoxic cetyltrimethylammonium chloride(CTAC)and isopropanol(IPA)as anti-solvents to effectively passivate both surface and grain boundary defects in hybrid *** vacancies can be readily passivated by the chloride group due to its high electronegativity,and cation defects can be synchronously passivated by the more stable cetyltrimethylammonium *** results show that the charge trap density was significantly reduced,while the carrier recombination lifetime was markedly *** a result,the power conversion efficiency of the cell can reach 23.4%with this in-situ green *** addition,the device retains 85%of its original power conversion efficiency after 600 h of operation under illumination,showing that the stability of perovskite solar cells is improved with this in-situ passivation *** work may provide a green and effective route to improve both the stability and efficiency of perovskite solar cells.

关键词： Perovskite solar cells In-situ defect passivation Green anti-solvent

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：