检索结果-内蒙古大学图书馆

Communication, Image and Signal Processing (CCISP), International Conference on

作者： Shuaihua Yang Caixia Zheng College of Information Science and Technology Northeast Normal University Changchun China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun China

Left ventricle (LV) segmentation in echocardiography is of paramount significance in cardiac function analysis. Recently, semi-supervised segmentation has garnered considerable attention due to its potential mitigation of labeling costs. Despite this, most semi-supervised methodologies tend to overlook the specialized anatomical priors specific to echocardiography, often yielding suboptimal outcomes. Simultaneously, atlas priors have been validated on other organs and imaging modalities. However, their direct application in echocardiography is fraught with challenges, primarily attributed to the indistinct boundaries of the LV and the presence of fan-shaped image edges, which impede atlas image registration. This paper presents a new method of semi-supervised segmentation using multi-atlas fusion, named SS- MAF, which is designed to incorporate atlas priors tailored for echocardiography while circumventing the intricate image registration process in traditional atlas-based methods. The SS-MAF comprises two components: a Multi-Task Learning (MTL) module and a Multi-Atlas Fusion (MAF) module. The MTL module serves precise landmark localization and segmentation estimation. The MAF module is primarily focused on the generation of probabilistic atlases, utilizing annotated atlas data with the guidance of key landmarks to facilitate the automatic annotation of unlabeled data, avoiding the traditional image-level registration, thus enhancing the performance of the MTL module. Our SS- MAF is rigorously evaluated on the publicly available CAMUS dataset, with results demonstrating its superiority over other state-of-the-art semi-supervised segmentation techniques in echocardiography.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Prompting Large Language Models with Answer Heuristics for Knowledge-Based Visual Question Answering

Prompting Large Language Models with Answer Heuristics for K...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Zhenwei Shao Zhou Yu Meng Wang Jun Yu Key Laboratory of Complex Systems Modeling and Simulation School of Computer Science and Technology Hangzhou Dianzi University China School of Computer Science and Information Engineering Hefei University of Technology China

Knowledge-based visual question answering (VQA) requires external knowledge beyond the image to answer the question. Early studies retrieve required knowledge from explicit knowledge bases (KBs), which often introduces irrelevant information to the question, hence restricting the performance of their models. Recent works have sought to use a large language model (i.e., GPT-3 [3]) as an implicit knowledge engine to acquire the necessary knowledge for answering. Despite the encouraging results achieved by these methods, we argue that they have not fully activated the capacity of GPT-3 as the provided input information is insufficient. In this paper, we present Prophet-a conceptually simple framework designed to $prompt$ GPT-3 with answer heuristics for knowledge-based VQA. Specifically, we first train a vanilla VQA model on a specific knowledge-based VQA dataset without external knowledge. After that, we extract two types of complementary answer heuristics from the model: answer candidates and answer-aware examples. Finally, the two types of answer heuristics are encoded into the prompts to enable GPT-3 to better comprehend the task thus enhancing its capacity. Prophet significantly outperforms all existing state-of-the-art methods on two challenging knowledge-based VQA datasets, OK-VQA and A-OKVQA, delivering 61.1% and 55.7% accuracies on their testing sets, respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Changes of composition and antibiotic resistance of fecal coliform bacteria in municipal wastewater treatment plant

引用

Journal of Environmental sciences 2024年第12期146卷 241-250页

作者： Luoyao Wen Yunwei Cui Luodong Huang Chunzhong Wei Gangan Wang Junya Zhang Yanbo Jiang Yuansong Wei Peihong Shen State Key Joint Laboratory of Environmental Simulation and Pollution Control Research Center for Eco-Environmental SciencesChinese Academy of SciencesBeijing 100085China College of Life Science and Technology Guangxi UniversityNanning 530005China Nanning Engineering&Technology Research Center for Water Safety Guangxi Beitou Environmental Protection&Water Group Co.LTD.Nanning 530025China Department of Isotope Biogeochemistry Helmholtz Centre for Environmental Research–UFZLeipzig 04318Germany University of Chinese Academy of Sciences Beijing 100049China International Graduate School at Shenzhen Tsinghua UniversityShenzhen 518055China

The dynamics of the composition and antibiotic resistance of the fecal coliform bacteria(FCB)in a typical wastewater treatment plant(WWTP)were investigated concerning the seasonal *** showed that WWTP could remove the FCB concentration by 3∼5 logs within the effluent of 10^(4)∼10^(5)CFU/L,but the antibiotic resistant rate of FCB species increased significantly after *** dominant FCB changed from Escherichia coli in the influent(∼73.0%)to Klebsiella pneumoniae in the effluent(∼53.3%)after WWTP,where the Escherichia coli was removed the most,while Klebsiella pneumoniae was the most *** secondary tank removed the most of FCB(by 3∼4 logs)compared to other processes,but increased all the concerned antibiotic resistant *** potential super bugs of FCB community showing resistance to all the target antibiotics were selected in the biological treatment unit of *** FCB showed the highest multiple antibiotic resistance(92.9%)in total which even increased to 100%in the *** has the highest antibiotic resistant rate in FCB,with a multiple antibiotic resistance rate of 98.4%.These indicated that the Klebsiella pneumoniae not just Escherichia coli should be specially emphasized after WWTP concerning the health risk associated with FCB community.

关键词： Fecal coliform bacteria Antibiotic resistance Wastewater treatment plant Antibiotic resistant bacteria Multiple antibiotic resistance

来源：评论

学校读者我要写书评

暂无评论

Acceptor-acceptor-type conjugated polymer semiconductors

引用

Journal of Energy Chemistry 2021年第8期30卷 364-387,I0008页

作者： Dunshuai Qu Ting Qi Hui Huang School of Chemical Sciences University of Chinese Academy of Sciences100049 BeijingChina College of Materials Science and Opto-Electronic Technology&Center of Materials Science and Optoelectronics Engineering&CAS Center for Excellence in Topological Quantum Computation&CAS Key Laboratory of Vacuum Physic University of Chinese Academy of Sciences100049 BeijingChina

The rapid development of electronic devices such as organic field-effect transistors(OFETs)and solar cells makes the research and development of electronic transport materials *** acceptor-acceptortype(AàA-type)conjugated n-type polymer semiconductors have caught much attention due to the outstanding advantages on excellent electron-accepting capabilities,the precise adjustment of energy levels and the mass production at low fabrication *** article systematically reviews the polymerization methods of AàA-type polymers and the recent advancements applied in OFETs and polymer solar cells(PSCs).The analyses of the synthesis and the relationship between device performances and polymer molecular structures may provide a constructive guidance for the further development of highperformance n-type polymer materials.

关键词： Acceptor-acceptor-type(A-A-type) polymers Organic field-effect transistors(OFETs) Polymer solar cells(PSCs) Polymerization n-Type semiconductors

来源：评论

学校读者我要写书评

暂无评论

Comprehensive understanding of microplastics in compost: Ecological risks and degradation mechanisms

引用

science of the Total Environment 2025年 958卷 178104页

作者： Dong, Dazhuang Gao, Wenjing Li, Lele Liu, Yuxin Dai, Yaodan State Key Laboratory of Water Environment Simulation School of Environment Beijing Normal University Beijing100875 China Department of Earth and Space Science University of Science and Technology of China Anhui Hefei230026 China School of Resources and Environmental Engineering Hefei University of Technology Hefei230009 China

The introduction of microplastics (MPs) into soil ecosystems via compost application has emerged as a critical environmental concern. However, the ecological risks and degradation behavior of MPs in compost remain insufficiently understood. This review addresses these gaps by synthesizing recent findings on MPs in composting systems, focusing on their sources, impacts on compost quality, ecological risks, and degradation mechanisms. MP sources vary significantly across compost matrices-domestic waste, sludge, and agricultural waste‑leading to differences in their types and quantities. MPs adversely impact compost quality by disrupting its physical structure and impairing fertility, aeration, and water retention. Furthermore, their persistence after compost application can result in long-term environmental accumulation, posing risks to soil ecosystems and biological health. This review also explores the aging and degradation of MPs during composting, a complex process influenced by physical, chemical, and biological mechanisms. Finally, we propose future research directions, emphasizing the development of standardized methodologies to assess MP behavior in compost and strategies to mitigate associated risks. These insights contribute to advancing sustainable waste management and environmental protection practices. © 2024 Elsevier B.V.

关键词： Compost Degradation mechanisms Ecological risks Influencing factors Microplastics

来源：评论

学校读者我要写书评

暂无评论

Skeleton-based Action Recognition with Non-linear Dependency Modeling and Hilbert-Schmidt Independence Criterion

arXiv

引用

arXiv 2024年

作者： Chen, Haipeng Yang, Yuheng Lyu, Yingda College of Computer Science and Technology Jilin University China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University China Public Computer Education and Research Center Jilin University China

Human skeleton-based action recognition has long been an indispensable aspect of artificial intelligence. Current state-of-the-art methods tend to consider only the dependencies between connected skeletal joints, limiting their ability to capture non-linear dependencies between physically distant joints. Moreover, most existing approaches distinguish action classes by estimating the probability density of motion representations, yet the high-dimensional nature of human motions invokes inherent difficulties in accomplishing such measurements. In this paper, we seek to tackle these challenges from two directions: (1) We propose a novel dependency refinement approach that explicitly models dependencies between any pair of joints, effectively transcending the limitations imposed by joint distance. (2) We further propose a framework that utilizes the Hilbert-Schmidt Independence Criterion to differentiate action classes without being affected by data dimensionality, and mathematically derive learning objectives guaranteeing precise recognition. Empirically, our approach sets the state-of-the-art performance on NTU RGB+D, NTU RGB+D 120, and Northwestern-UCLA datasets. © 2024, CC BY-SA.

关键词： Probability density function

来源：评论

学校读者我要写书评

暂无评论

Quantum Circuits for the Heat Equation with Physical Boundary Conditions Via Schrödingerisation

SSRN

引用

SSRN 2024年

作者： Jin, Shi Liu, Nana Yu, Yue School of Mathematical Sciences Institute of Natural Sciences MOE-LSC Shanghai Jiao Tong University Shanghai200240 China University of Michigan Shanghai Jiao Tong University Joint Institute Shanghai200240 China School of Mathematics and Computational Science Hunan Key Laboratory for Computation and Simulation in Science and Engineering Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education National Center for Applied Mathematics in Hunan Xiangtan University Hunan Xiangtan411105 China

This paper explores the explicit design of quantum circuits for quantum simulation of partial differential equations (PDEs) with physical boundary conditions. These equations and/or their discretized forms usually do not evolve via unitary dynamics, thus are not suitable for quantum simulation. Boundary conditions (either time-dependent or independent) make the problem more difficult. To tackle this challenge, the Schrödingerisation method can be employed, which converts linear partial and ordinary differential equations with non-unitary dynamics into systems of Schrödinger-type equations, via the so-called warped phase transformation that maps the equation into one higher dimension. Despite advancements in Schrödingerisation techniques, the explicit implementation of quantum circuits for solving general PDEs, especially with physical boundary conditions, remains underdeveloped. We present two methods for handling the inhomogeneous terms arising from time-dependent physical boundary conditions. One approach utilizes Duhamel's principle to express the solution in integral form and employs linear combination of unitaries (LCU) for coherent state preparation. Another method applies an augmentation to transform the inhomogeneous problem into a homogeneous one. We then apply the quantum simulation technique from [CJL23] to transform the resulting non-autonomous system to an autonomous system in one higher dimension. We provide detailed implementations of these two methods and conduct a comprehensive complexity analysis in terms of queries to the time evolution input oracle. © 2024, The Authors. All rights reserved.

关键词： Boundary conditions

来源：评论

学校读者我要写书评

暂无评论

WGAN-GP_Glu: A semi-supervised model based on double generator-Wasserstein GAN with gradient penalty algorithm for glutarylation site identification

引用

Computers in Biology and Medicine 2025年 184卷 109328-109328页

作者： Ning, Qiao Qi, Zedong Information Science and Technology Dalian Maritime University Liaoning Dalian China The School of Artificial Intelligence and Computer Science Jiangnan University Wuxi China Neusoft Education Technology Group Dalian China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun130012 China

As an important post-translational modification, glutarylation plays a crucial role in a variety of cellular functions. Recently, diverse computational methods for glutarylation site identification have been proposed. However, the class imbalance problem due to data noise and uncertainty of non-glutarylation sites remains a great challenge. In this article, we propose a novel semi-supervised learning algorithm, called WGAN-GP_Glu, for identifying reliable non-glutarylation lysine sites from those without glutarylation annotation. WGAN-GP_Glu method is a multi-module framework algorithm, which mainly includes a reliable negative sample selection module, a deep feature extraction module, and a glutarylation site prediction module. In reliable negative sample selection module, we design an improved method of Wasserstein GAN with Gradient Penalty (WGAN-GP), named ReliableWGAN-GP, including three parts, two generators G1, G2 and a discriminator D, which can select reliable non-glutarylation samples from a great number of unlabeled samples. Generator G1 is utilized to generate noise data from unlabeled samples. For generator G2, both the positive sample and the noise data are used as inputs to improve the discriminant capability of discriminator D. Then, convolutional neural network and bidirectional long short-term memory network combined with attention mechanism are utilized to extract deep features for glutarylation samples and reliable non-glutarylation samples. Finally, a glutarylation site prediction module based on the three-layer fully connected layer is designed to make class predictions for samples. The sensitivity, specificity, accuracy and Matthew correlation coefficient of WGAN-GP_Glu on the independent test data set reach 90.58 %, 95.82 %, 94.44 % and 0.8645, respectively, which surpassed the existing methods for glutarylation sites prediction. Therefore, WGAN-GP_Glu can serve as a powerful tool in identifying glutarylation sites and the ReliableWGAN-GP algo

关键词： Gallium nitride

来源：评论

学校读者我要写书评

暂无评论

Troublemaker Learning for Low-Light Image Enhancement

arXiv

引用

arXiv 2024年

作者： Song, Yinghao Cao, Zhiyuan Xiang, Wanhong Long, Sifan Ge, Hongwei Liang, Yanchun Yang, Bo Wu, Chunguo College of Computer Science and Technology Jilin University Jilin China Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education Jilin University Jilin China YGSOFT INC Dalian University of Technology China

Low-light image enhancement (LLIE) restores the color and brightness of underexposed images. Supervised methods suffer from high costs in collecting low/normal-light image pairs. Unsupervised methods invest substantial effort in crafting complex loss functions. We address these two challenges through the proposed TroubleMaker Learning (TML) strategy, which employs normal-light images as inputs for training. TML is simple: we first dim the input and then increase its brightness. TML is based on two core components. First, the troublemaker model (TM) constructs pseudo low-light images from normal images to relieve the cost of pairwise data. Second, the predicting model (PM) enhances the brightness of pseudo low-light images. Additionally, we incorporate an enhancing model (EM) to further improve the visual performance of PM outputs. Moreover, in LLIE tasks, characterizing global element correlations is important because more information on the same object can be captured. CNN cannot achieve this well, and self-attention has high time complexity. Accordingly, we propose Global Dynamic Convolution (GDC) with O(n) time complexity, which essentially imitates the partial calculation process of self-attention to formulate elementwise correlations. Based on the GDC module, we build the UGDC model. Extensive quantitative and qualitative experiments demonstrate that UGDC trained with TML can achieve competitive performance against state-of-the-art approaches on public datasets. The code is available at https://***/Rainbowman0/TML LLIE. Copyright © 2024, The Authors. All rights reserved.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Lattice Boltzmann simulation reveals supercritical bifurcation in flow mode transitions of power-law fluids in the four-roll mill

arXiv

引用

arXiv 2025年

作者： Yu, Yuan Jiang, Xiao Gu, Qingqing Lin, Chuandong Zhu, Qingyong Yuan, Hai-Zhuan School of Mathematics and Computational Science Xiangtan University Xiangtan411105 China National Center for Applied Mathematics in Hunan Xiangtan411105 China Hunan Key Laboratory for Computation and Simulation in Science and Engineering Xiangtan University Xiangtan411105 China School of Energy and Power Engineering University of Shanghai for Science and Technology Shanghai200093 China Sino-French Institute of Nuclear Engineering and Technology Sun Yat-sen University Zhuhai519082 China School of Aeronautics and Astronautics Sun Yat-sen University Shenzhen518107 China

The four-roll mill has been traditionally viewed as a device generating simple extensional flow with a central stagnation point. Our systematic investigation using a two-relaxation-time regularized lattice Boltzmann (TRT-RLB) model reveals unexpected richness in the flow physics, identifying two previously unreported supercritical bifurcation modes: a quadrifoliate vortex mode featuring four symmetrical counter-rotating vortices, and a dumbbell-shaped quad-vortex mode where vortices detach from but remain symmetric about the stagnation point. The numerical framework, representing the first successful extension of TRT-RLB method to power-law fluid dynamics, enables comprehensive mapping of flow characteristics across Reynolds numbers (1 ≤ Re ≤ 50), power-law indices (0.7 ≤ n ≤ 1.3), and geometric configurations. The transition from quadrifoliate vortex mode exhibits distinct pathways depending on the power-law index: at relatively small n, the flow undergoes a direct supercritical bifurcation to simple extensional flow, while at relatively large n, it evolves through an intermediate dumbbell-shaped state. Among geometric parameters, the roller radius r emerges as the dominant factor controlling bifurcation points and vortex dimensions, whereas the roller-container gap δ exerts minimal influence on flow regimes. The transitions between flow modes can be precisely characterized through the evolution of vortex dimensions and velocity gradients at the stagnation point, providing quantitative criteria for flow regime identification. These findings enrich our fundamental understanding of bifurcation phenomena in extensional devices and provide quantitative guidelines for achieving desired flow patterns in four-roll mill applications. Copyright © 2025, The Authors. All rights reserved.

关键词： Vortex flow

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：