检索结果-南通市图书馆

Science in One Health 2022年第1期1卷 6-8页

作者： Zhen-Hui Lu Ming Yang Chen-Hui Pan Pei-Yong Zheng Shun-Xian Zhang Longhua Hospital Shanghai University of Traditional Chinese MedicineShanghai 200032China

Despite the advent of new diagnostics,drugs and regimens,multi-drug resistant pulmonary tuberculosis(MDRPTB)remains a global health *** has a long treatment cycle,low cure rate and heavy disease *** such as demographics,disease characteristics,lung imaging,biomarkers,therapeutic schedule and adherence to medications are associated with MDR-PTB ***,thus far,the majority of existing studies have focused on predicting treatment outcomes through static single-scale or low dimensional ***,multi-modal deep learning based on dynamic data for multiple dimensions can provide a deeper understanding of personalized treatment plans to aid in the clinical management of patients.

关键词： MDR-PTB multi-modal Deep learning Prognosis

Prospects on mangrove knowledge services in the smart era: From plant atlas to knowledge graphs

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Science China Earth Sciences 2025年第1期68卷 111-127页

作者： Zhi-Wei HOU Wenlong JING Cheng-Zhi QIN Ji YANG Qing XIA Xiaoling YIN Key Laboratory of Guangdong for Utilization of Remote Sensing and Geographical Information System Guangdong Open Laboratory of Geospatial Information Technology and Application Guangzhou Institute of Geography Guangdong Academy of Sciences Southern Marine Science and Engineering Guangdong Laboratory (Guangzhou) State Key Laboratory of Resources and Environmental Information System Institute of Geographic Sciences and Natural Resources ResearchChinese Academy of Sciences College of Resources and Environment University of Chinese Academy of Sciences School of Traffic & Transportation Engineering Changsha University of Science and Technology

Mangroves are crucial to the ecological security of the Earth and human well-being. Their management, conservation, and restoration are of great importance and necessitate the support of spatio-temporal information and multidisciplinary knowledge such as biology and ecology. Traditional knowledge services such as plant atlas provide illustrated textual knowledge of mangroves. However, this kind of service is oriented to information retrieval and is incapable of effectively mining and utilizing fragmented knowledge from multi-source heterogeneous data, facing the problem of “massive data, rare knowledge”. Knowledge graphs are capable of extracting, organizing, and fusing the knowledge contained in massive data into semantic networks that can be understood and computed by computers. They provide a solution for the realization of intelligent knowledge services. Focusing on the urgent need for mangrove knowledge acquisition, formal representation, and intelligent services, this paper proposes a research prospect on mangrove knowledge graphs and knowledge services. We first analyze the similarities and differences between various domain-specific concepts of Tupu. On this basis, we define the mangrove knowledge graph as a large-scale knowledge base that integrates multi-disciplinary knowledge and spatio-temporal information with mangrove ecosystems as the core. Then, we propose a research framework for mangrove knowledge services that can realize the transformation from multi-modal data to intelligent knowledge services, including multiple research levels such as ubiquitous data sensing and aggregation, knowledge organization and graph construction, and intelligent mangrove knowledge services. Subsequently, the methods and workflow for constructing mangrove knowledge graphs are introduced. Finally, we discuss the challenges and possible future directions of mangrove knowledge services in the smart era, including the construction of a mangrove knowledge system that integra

关键词： Mangrove Tupu Knowledge graph multi-modal Knowledge service

multi-state supernetworks:recent progress and prospects

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Journal of Traffic and Transportation Engineering(English Edition) 2014年第1期1卷 13-27页

作者： Feixiong Liao Theo Arentze Harry Timmermans Urban Planning Group Eindhoven University of TechnologyEindhovenNorth BrabontNetherlands

Supernetworks have long been adopted to address multi-dimensional choice problems, which are thorny to solve for classic singular networks. Originated from combining transport mode and route choice into a multi-modal network, supernetworks have been extended into multi-state networks to include activity-travel scheduling, centered around activity-based models of travel demand. A key feature of the network extensions is that multiple choice facets pertaining to conducting a full activity program can be modeled in a consistent and integrative fashion. Thus, interdependencies and constraints between related choice facets can be readily captured. Given this advantage of integrity, the modeling of supernetwork has become an emerging topic in transportation research. This paper summarizes the recent progress in modeling multi-state supernetworks and discusses future prospects.

关键词： supernetwork multi-modal multi-state activity-based models

Fusing Geometrical and Visual Information via Superpoints for the Semantic Segmentation of 3D Road Scenes

在线全文

学校读者我要写书评

暂无评论

Tsinghua Science and Technology 2020年第4期25卷 498-507页

作者： Liuyuan Deng Ming Yang Zhidong Liang Yuesheng He Chunxiang Wang the Department of Automation Shanghai Jiao Tong UniversityShanghai 200240China the Key Laboratory of System Control and Information Processing Ministry of Education of ChinaShanghai 200240China the Research Institute of Robotics Shanghai Jiao Tong UniversityShanghai 200240China

This paper addresses the problem of the semantic segmentation of large-scale 3D road scenes by incorporating the complementary advantages of point clouds and *** make full use of geometrical and visual information,this paper extracts 3D geometric features from a point cloud using a deep neural network for 3D semantic segmentation and extracts 2D visual features from images using a Convolutional Neural Network(CNN)for 2D semantic *** order to bridge the features of the two modalities,this paper uses superpoints as an intermediate representation to connect the 2D features with the 3D features.A superpoint-based pooling method is proposed to fuse the features from the two different modalities for joint *** evaluate the approach,the paper generates 3D scenes from the Virtual KITTI *** results of the experiments demonstrate that the proposed approach is capable of segmenting large-scale 3D road scenes based on the compact and semantically homogeneous superpoints,and that it achieves considerable improvements over the 2D image and 3D point cloud semantic segmentation methods.

关键词： scene understanding point cloud semantic segmentation multi-modal information fusion deep learning

RGBT tracking via reliable feature configuration

在线全文

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2022年第4期65卷 128-140页

作者： Zhengzheng TU Wenli PAN Yunsheng DUAN Jin TANG Chenglong LI Anhui Provincial Key Laboratory of multimodal Cognitive Computation School of Computer Science and Technology Anhui University Network Information Center Anhui University

There is an increasing interest in RGBT tracking recently because of the complementary benefits of RGB and thermal infrared data. However, the reliability of each modality will change over time quite possibly, and the modality with bad reliability will disturb tracking performance. Thus, we propose a novel reliability-based feature configuration approach in the correlation filter framework for robust RGBT tracking. Specifically, we configure a feature set based on RGB, thermal, and RGBT data. To measure the reliabilities of different feature configurations, we equip each feature configuration with a tracker and design a guideline judging whether the tracker is reliable. We use the tracker with the best reliability for *** results show that the proposed tracker achieves promising performance against other RGBT tracking methods.

关键词： RGBT tracking multi-modal multi-modal Reliability guideline reliability guideline Feature configuration feature configuration correlation filter Correlation filter

同方期刊数据库

PVSS:A Progressive Vehicle Search System for Video Surveillance Networks

在线全文

学校读者我要写书评

暂无评论

Journal of Computer Science & Technology 2019年第3期34卷 634-644页

作者： Xin-Chen Liu Wu Liu Hua-Dong Ma Shuang-Qun Li Beijing Key Laboratory of Intelligent Telecommunication Software and multimedia Beijing University of Posts and TelecommunicationsBeijing 100876China

This paper is focused on the task of searching for a specific vehicle that appears in the surveillance *** methods usually assume the vehicle images are well cropped from the surveillance videos,and then use visual attributes,like colors and types,or license plate numbers to match the target vehicle in the image ***,a complete vehicle search system should consider the problems of vehicle detection,representation,indexing,storage,matching,and so ***,it is very difficult for attribute-based search to accurately find the same vehicle due to intra-instance changes in different cameras and the extremely uncertain ***,the license plates may be mis-recognized in surveillance scenes due to the low resolution and *** this paper,a progressive vehicle search system,named as PVSS,is designed to solve the above *** is constituted of three modules:the crawler,the indexer,and the *** vehicle crawler aims to detect and track vehicles in surveillance videos and transfer the captured vehicle images,metadata and contextual information to the server or *** multi-grained attributes,such as the visual features and license plate fingerprints,are extracted and indexed by the vehicle *** last,a query triplet with an input vehicle image,the time range,and the spatial scope is taken as the input by the vehicle *** target vehicle will be searched in the database by a progressive *** experiments on the public dataset from a real surveillance net work validate the effec tiveness of PVSS.

关键词： multi-modal data analysis progressive search system vehicle search video surveillance network

A new optimization algorithm applied in electromagnetics——Maxwell's equations derived optimization (MEDO)

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2020年第10期63卷 19-41页

作者： Donglin SU Lilin LI Shunchuan YANG Bing LI Guangzhi CHEN Hui XU School of Electronics and Information Engineering Beihang University Research Institute for Frontier Science Beihang University MIIT Key Laboratory of E3 for Smart System and Equipment Beihang University EMC Technology Institute Beihang University Shenyuan Honors Colledge Beihang University

In this paper, a novel global optimization algorithm, named as Maxwell’s equations derived optimization(MEDO), is proposed. Using the Maxwell’s equations to analyse the behaviors of the timevarying current, the Ampere force is obtained from Fleming’s left hand rule. MEDO introduces an ‘Ampere force’ term, which is derived from Maxwell’s equations and is rigorous in physics, to drive the variables to the global optimal solution in the search space. In addition, introducing ‘gravity’ to MEDO can increase the stability of the optimizations. 11 classical benchmarks are tested, and results show that MEDO can always converge to numerical optimal solutions. To evaluate the proposed MEDO in solving the electromagnetic problems, four practical engineering applications are considered including the linear antenna array synthesis,frequency selected surface optimization, numerical dispersion reduction for finite-difference method, and parameters extraction of typical waveform. These examples are significant in electromagnetics, but tough to be solved because of their high dimensionality and strong nonlinearity. Numerical results show that MEDO can outperform several classic optimization methods, like wind driven optimization(WDO) and particle swarm optimization(PSO). Therefore, the electromagnetics-inspired MEDO is robust and of great potential in solving the electromagnetic optimization problems.

关键词： electromagnetic theory heuristic optimization high-dimensionality Maxwell's equations multi-modal

Recent advances in deep learning based sentiment analysis

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Science China(Technological Sciences) 2020年第10期63卷 1947-1970页

作者： YUAN JianHua WU Yang LU Xin ZHAO YanYan QIN Bing LIU Ting Research Center for Social Computing and Information Retrieval Harbin Institute of TechnologyHarbin 150001China Pengcheng Lab Shenzhen 518066China

Sentiment analysis is one of the most popular research areas in natural language *** is extremely useful in many applications,such as social media monitoring and *** application of deep learning based methods has dramatically changed the research strategies and improved the performance of many traditional sentiment analysis tasks,such as sentiment classification and aspect based sentiment ***,it also pushed the boundary of various sentiment analysis task,including sentiment classification of different text granularities and in different application scenarios,implicit sentiment analysis,multimodal sentiment analysis and generation of sentiment-bearing *** this paper,we give a brief introduction to the recent advance of the deep learning-based methods in these sentiment analysis tasks,including summarizing the approaches and analyzing the *** survey can be well suited for the researchers studying in this field as well as the researchers entering the field.

关键词： coarse-grained fine-grained implicit multi-modal generation

Leveraging foundation and large language models in medical artificial intelligence

在线全文

学校读者我要写书评

暂无评论

中华医学杂志(英文版) 2024年第21期137卷 2529-2539页

作者： Wong Io Nam Monteiro Olivia Baptista-Hon Daniel T. Wang Kai Lu Wenyang Sun Zhuo Nie Sheng Yin Yun Institute for AI in Medicine Faculty of Medicine Macau University of Science and Technology Macau Special Administrative Region China Department of Big Data and Biomedical AI College of Future Technology Peking University Beijing China Institute for Advanced Study on Eye Health and Diseases Wenzhou Medical University Wenzhou Zhejiang China Department of Ophthalmology The Third People’s Hospital of Changzhou Changzhou Jiangsu China Division of Nephrology National Clinical Research Center for Kidney Disease State Key Laboratory of Organ Failure Research Nanfang Hospital Southern Medical University Guangzhou Guangdong China Faculty of Health and Wellness Faculty of Business City University of Macau Macau Special Administrative Region China

Recent advancements in the field of medical artificial intelligence (AI) have led to the widespread adoption of foundational and large language models. This review paper explores their applications within medical AI, introducing a novel classification framework that categorizes them as disease-specific, general-domain, and multi-modal models. The paper also addresses key challenges such as data acquisition and augmentation, including issues related to data volume, annotation, multi-modal fusion, and privacy concerns. Additionally, it discusses the evaluation, validation, limitations, and regulation of medical AI models, emphasizing their transformative potential in healthcare. The importance of continuous improvement, data security, standardized evaluations, and collaborative approaches is highlighted to ensure the responsible and effective integration of AI into clinical applications.

关键词： Artificial intelligence Foundation model Large language model multi-modal Data security Medical AI Segment-anchoring model ChatGPT Disease-specific model General-domain model Data privacy Hallucination Data annotation

Numerical Study on the Effect of Current Profiles on Vortex-Induced Vibrations in a Top-Tension Riser

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Journal of Marine Science and Application 2017年第4期16卷 473-479页

作者： Bowen Fu Lu Zou Decheng Wan State Key Laboratory of Ocean Engineering School of Naval Architecture Ocean and Civil Engineering Shanghai Jiao Tong UniversityCollaborative Innovation Center for Advanced Ship and Deep-Sea Exploration Shanghai 200240 China

In this paper, numerical simulations of vortex-induced vibrations in a vertical top-tension riser with a length-to-diameter ratio of 500 using our in-house code viv-FOAM-SJTU are presented. The time-dependent hydrodynamic forces on two-dimensional strips are obtained by solving the Navier-Stokes equations, which are, in turn, integrated into a finite-element structural model to obtain the riser deflections. The riser is discretized into 80 elements with its two ends set as pinned and 20 strips are located equidistant along the risers. Flow and structure are coupled by hydrodynamic forces and structural displacements. In order to study the effects of the shear rate, of the current profiles on the vortex-induced vibrations in the riser, vibrations, with varying shear rates, in both the in-line and cross-flow directions, are simulated. In addition to the time domain analysis, spectral analysis was conducted in both the temporal and spatial domains. multi-mode vibration characteristics were observed in the riser. The relationship between dominant vibration mode number and the shear rate of current profiles is discussed. In general, the overall vibrations in the riser pipe include contributions from several modes and each mode persists over a range of shear rates. Moreover, the results suggest that with a larger shear rate the position of the maximum in-line time-averaged displacement will move closer to the end where the largest velocity is located.

关键词： risers vortex-induced vibration multi-modal vibration strip theory computational fluid dynamics fluid-structure interaction