检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Zheng, Xin Peng, Ziang Cao, Yuan Shan, Hongming Zhang, Junping Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai200433 China Department of Aeronautics and Astronautics Fudan University Shanghai200433 China Institute of Science and Technology for Brain-inspired Intelligence Fudan University Shanghai200433 China

Video prediction, predicting future frames from the previous ones, has broad applications such as autonomous driving and weather forecasting. Existing state-of-the-art methods typically focus on extracting either spatial, temporal, or spatiotemporal features from videos. Different feature focuses, resulting from different network architectures, may make the resultant models excel at some video prediction tasks but perform poorly on others. Towards a more generic video prediction solution, we explicitly model these features in a unified encoder-decoder framework and propose a simple alternating Mixer (SIAM). The novelty of SIAM lies in the design of dimension alternating mixing (DaMi) blocks, which can model spatial, temporal, and spatiotemporal features through alternating the dimensions of the feature maps. Extensive experimental results demonstrate the superior performance of the proposed SIAM on four benchmark video datasets covering both synthetic and real-world scenarios. Copyright © 2023, The Authors. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Interactive Prototype Learning and Self-Learning for Few-Shot Medical image Segmentation

SSRN

引用

SSRN 2024年

作者： Song, Yuhui Xu, Chenchu Wang, Boyan Du, Xiuquan Chen, Jie Zhang, Yanping Li, Shuo School of Computer Science and Technology Anhui University Hefei230601 China Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Anhui University Hefei230601 China Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei230051 China Department of Computer Science and Technology Tsinghua University Beijing100084 China School of Engineering Case Western Reserve University Cleveland44106 United States

Few-shot learning alleviates the heavy dependence of medical image segmentation tasks on large-scale labeled data, but it shows a strong performance gap when dealing with new targets and new tasks compared with traditional deep learning. Existing few-shot medical image segmentation models mainly realize segmentation by learning the semantic class knowledge of a few known (support) samples and extending it to unknown (query) samples. However, the neglect of the differences between known and unknown samples leads to a certain deviation in the transfer of class knowledge, and the trained model tends to overfit the class knowledge of training classes, which greatly reduces the segmentation and generalization performance of few-shot model. In this work, we propose an interactive prototype learning and self-learning network to alleviate the above problems. Specifically, we propose an interactive prototype learning network to promote feature consistency between support images and query images to improve the accuracy of prototype metric learning. In addition, to avoid overfitting the training class knowledge and reduce the over-dependence of query segmentation on the class knowledge, we introduce a query features-guided self-learning network to achieve the finer segmentation of query images through its rich feature information. Our model obtained the competitive segmentation results on three multi-organ and multi-modal public datasets that show a substantial improvement in generalization ability. © 2024, The Authors. All rights reserved.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Lane marking detection algorithm based on high-precision map and multisensor fusion

Lane marking detection algorithm based on high-precision map...

引用

作者： Yao, Haichang Chen, Chen Liu, Shangdong Li, Kui Ji, Yimu Huang, Guangyan Wang, Ruchuan School of Computer Science Nanjing University of Posts and Telecommunications Nanjing China School of Computer and Software Nanjing Institute of Industry Technology Nanjing China Industrial Software Engineering Technology Research and Development Center of Jiangsu Education Department Nanjing Institute of Industry Technology Nanjing China Jiangsu HPC and Intelligent Processing Engineer Research Center Nanjing China Institute of High Performance Computing and Bigdata Nanjing University of Posts and Telecommunications Nanjing China School of Information Technology Deakin University Melbourne Australia

In case of sharp road illumination changes, bad weather such as rain, snow or fog, wear or missing of the lane marking, the reflective water stain on the road surface, the shadow obstruction of the tree, and mixed lane markings and other signs, missing detection or wrong detection will occur for the traditional lane marking detection algorithm. In this manuscript, a lane marking detection algorithm based on high-precision map and multisensor fusion is proposed. The basic principle of the algorithm is to use the centimeter-level high-precision positioning combined with high-precision map data to complete the detection of lane markings. In the process of generating high-precision maps or in the uncovered areas of high-precision maps, LIDAR (LIght Detection And Ranging) is used to estimate the curvature of the road to assist in lane marking detection. The experimental results show that the algorithm has lower false detection rate in case of bad road conditions, and the algorithm is robust. © 2020 John Wiley & Sons, Ltd.

关键词： Roads and streets

来源：评论

学校读者我要写书评

暂无评论

Back to the Future: Challenges of Sparse and Irregular Medical image Time Series

Back to the Future: Challenges of Sparse and Irregular M...

引用

Workshop on Longitudinal Disease Tracking and Modeling with Medical images and Data, LDTM 2024, 5th International Workshop on Multiscale Multimodal Medical Imaging, MMMI 2024, 1st Workshop on Machine Learning for Multimodal/-sensor Healthcare Data, ML4MHD2024 and Workshop on Multimodal Learning and Fusion Across Scales for Clinical Decision Support, ML-CDS 2024 held in conjunction with the 27th International Conference on Medical image Computing and computer Assisted Intervention, MICCAI 2024

作者： Disch, Nico Albert Peretzke, Robin Roy, Saikat Ulrich, Constantin Zimmerer, David Stiefelhagen, Rainer Kleesiek, Jens Maier-Hein, Klaus Division of Medical Image Computing German Cancer Research Center Heidelberg Germany HIDSS4Health - Helmholtz Information and Data Science School for Health Karlsruhe Heidelberg Germany Faculty of Mathematics and Computer Science University of Heidelberg Heidelberg Germany Pattern Analysis and Learning Group Department of Radiation Oncology Heidelberg University Hospital Heidelberg Germany Karlsruhe Institute of Technology Karlsruhe Germany University Hospital Essen Essen Germany University Hospital Essen West German Cancer Center Essen Essen Germany Medical Faculty Heidelberg University of Heidelberg Heidelberg Germany

ISBN: (纸本)9783031845246

In longitudinal medical image analysis, most work focuses on regularly sampled images, or on tasks like regression or classification. However, in the clinical context, images are frequently generated irregularly due to factors such as cost constraints. This work tackles the problem of irregularly sampled longitudinal medical imaging by evaluating methods in segmentation and reconstruction tasks. We examine the reconstruction for real-life MRI from patients with Alzheimer’s Disease (AD), where the model predicts future MRI scans from an arbitrary number of input images sampled at irregular intervals. However, experiments show that most models cannot surpass the performance of using an image from the same patient at a different time point as a baseline. Therefore, we conducted experiments on a synthetic dataset to better isolate effects in temporal learning. These experiments offer insights into model behavior and serve as a benchmark for validating models’ longitudinal learning capability, thus providing a straightforward method to assess temporal understanding in a controlled environment. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Neurodegenerative diseases

来源：评论

学校读者我要写书评

暂无评论

Advanced functional nanofibers:strategies to improve performance and expand functions

引用

Frontiers of Optoelectronics 2022年第4期15卷 125-143页

作者： Xinyu Chen Honghao Cao Yue He Qili Zhou Zhangcheng Li Wen Wang Yu He Guangming Tao Chong Hou School of Optical and Electronic Information Huazhong University of Science and TechnologyWuhan 430074China Wuhan National Laboratory for Optoelectronics Huazhong University of Science and TechnologyWuhan 430074China State Key Laboratory of Materials Processing and Die and Mould Technology School of Materials Science and EngineeringHuazhong University of Science and TechnologyWuhan 430074China Research Institute of Huazhong University of Science and Technology in Shenzhen Shenzhen 518063China Department of Electrical Engineering and Computer Science Massachusetts Institute of TechnologyCambridge 02139USA

Nanofbers have a wide range of applications in many felds such as energy generation and storage,environmental sensing and treatment,biomedical and health,thanks to their large specifc surface area,excellent fexibility,and superior mechanical *** the expansion of application felds and the upgrade of application requirements,there is an inevitable trend of improving the performance and functions of *** the past few decades,numerous studies have demonstrated how nanofbers can be adapted to more complex needs through modifcations of their structures,materials,and ***,it is necessary to systematically review the feld of nanofbers in which new ideas and technologies are *** we summarize the recent advanced strategies to improve the performances and expand the functions of *** frst introduce the common methods of preparing nanofbers,then summarize the advances in the feld of nanofbers,especially up-to-date strategies for further enhancing their *** classify these strategies into three categories:design of nanofber structures,tuning of nanofber materials,and improvement of nanofbers ***,the optimization methods,materials,application areas,and fabrication methods are summarized,and existing challenges and future research directions are *** hope this review can provide useful guidance for subsequent related work.

关键词： Functional nanofber Nanofber fabrication Nanofber structure Nanofber materials Nanofber assembly

来源：评论

学校读者我要写书评

暂无评论

Iterative Random Training Sampling Convolutional Neural Network for Hyperspectral image Classification

引用

IEEE Transactions on Geoscience and Remote Sensing 2023年 61卷

作者： Chang, Chein-I Liang, Chia-Chen Hu, Peter Fuming University of Maryland Remote Sensing Signal and Image Processing Laboratory Department of Computer Science and Electrical Engineering BaltimoreMD21250 United States National Cheng Kung University Department of Electrical Engineering Tainan70101 Taiwan Providence University Department of Computer Science and Information Management Taichung02912 Taiwan University of Maryland School of Medicine R. A. Cowley Shock Trauma Center Shock Trauma Anesthesia Organized Research Center Department of Anesthesia BaltimoreMD21201 United States

Convolutional neural network (CNN) has received considerable interest in hyperspectral image classification (HSIC) lately due to its excellent spectral-spatial feature extraction capability. To improve CNN, many approaches have been directed at exploring the infrastructure of its network by introducing different paradigms. This article takes a rather different approach by developing an iterative CNN that extends a CNN by including a feedback system to repeatedly process the same CNN in an iterative manner. Its idea is to take advantage of a recently developed iterative training sampling spectral-spatial classification (IRTS-SSC) that allows CNN to update its spatial information of classification maps through a feedback spatial fil- tering system via IRTS. The resulting CNN is called iterative random training sampling CNN (IRTS-CNN) with several unique features. First, IRTS-CNN combines CNN and IRTS-SSC into one paradigm, an architecture that has never been investigated in the past. Second, it implements a series of spatial filters to capture spatial information of classified data samples and further feeds this information back via an iterative process to expand the current input data cube for the next iteration. Third, it utilizes the expanded data cube to randomly reselect training samples and then to reimplement CNN iteratively. Last but not least, IRTS-CNN provides a general framework that can implement any arbitrary CNN as an initial classifier to improve its performance through an iterative process. Extensive experiments are conducted to demonstrate that IRTS-CNN indeed significantly improves CNN, specifically when only a small size of limited training samples is used. © 1980-2012 IEEE.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

科学研究的第五范式——以智能驱动的材料设计为例

引用

Engineering 2023年第5期24卷 126-137,I0003,I0004页

作者： Can Leng Zhuo Tang Yi-Ge Zhou Zean Tian Wei-Qing Huang Jie Liu Keqin Li Kenli Li Science and Technology on Parallel and Distributed Processing Laboratory National University of Defense TechnologyChangsha 410073China Laboratory of Software Engineering for Complex Systems National University of Defense TechnologyChangsha 410073China National Supercomputing Center in Changsha Changsha 410082China College of Computer Science and Electronic Engineering Hunan UniversityChangsha 410082China Institute of Chemical Biology and Nanomedicine State Key Laboratory of Chemo/Biosensing and ChemometricsCollege of Chemistry and Chemical EngineeringHunan UniversityChangsha 410082China Department of Applied Physics School of Physics and ElectronicsHunan UniversityChangsha 410082China Department of Computer Science State University of New YorkNew PaltzNY 12561USA

科学正在进入一个新时代——第五范式——它被认为是知识整合到不同领域的主要特征,是基于无所不在的机器学习系统的计算社区中智能驱动的工作。在此,我们通过在天河一号超级计算机系统上构建的催化材料专门设计的典型平台案例,生动地... 详细信息

科学正在进入一个新时代——第五范式——它被认为是知识整合到不同领域的主要特征,是基于无所不在的机器学习系统的计算社区中智能驱动的工作。在此,我们通过在天河一号超级计算机系统上构建的催化材料专门设计的典型平台案例,生动地阐明了第五范式的本质,旨在促进第五范式在其他领域的培养。第五范式平台主要包括模型自动构建(原始数据提取)、指纹自动构建(神经网络特征选择)以及跨学科知识串联的重复迭代(“火山图”)。与分解一起进行的是对迭代中实现的体系结构的性能评估。通过讨论,第五范式的智能驱动平台可以极大地简化和改进研究中极其繁琐和具有挑战性的工作,并通过补偿机器学习中缺少样本和替代一些由于计算资源不足而导致的数值计算来实现数值计算与机器学习之间的相互反馈,从而加速探索过程。在数据驱动的学科中,跨学科专家的协同作用和对动态数据需求的急剧增长仍然是一个挑战。我们相信,对第五范式平台的一瞥可以为其在其他领域的应用铺平道路。

关键词：机器学习自动构建天河一号数据驱动神经网络动态数据知识整合科学研究

来源：评论

学校读者我要写书评

暂无评论

Automated Detection of Epileptic Spikes and Seizures Incorporating a Novel Spatial Clustering Prior

Automated Detection of Epileptic Spikes and Seizures Incorpo...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Dong, Hanyang Sheng, Shurong Wang, Xiongfei Gao, Jia-Hong Sun, Yi Yang, Wanli Xiao, Kuntao Teng, Pengfei Luan, Guoming Lv, Zhao Anhui University School of Artificial Intelligence Hefei230601 China Hefei Comprehensive National Science Center Anhui Province Key Laboratory of Biomedical Imaging and Intelligent Processing Institute of Artificial Intelligence Hefei230088 China Sanbo Brain Hospital Capital Medical University Beijing Key Laboratory of Epilepsy Department of Neurosurgery Beijing China Peking University McGovern Institute for Brain Research Beijing China Peking University Center for Mri Research Academy for Advanced Interdisciplinary Studies Beijing China Peking University Beijing City Key Lab for Medical Physics and Engineering Institute of Heavy Ion Physics School of Physics Beijing China Anhui University Anhui Province Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Hefei230601 China

ISBN: (纸本)9798350386226

A Magnetoencephalography (MEG) time-series recording consists of multi-channel signals collected by superconducting sensors, with each signal's intensity reflecting magnetic field changes over time at the sensor location. Automating epileptic MEG spike detection significantly reduces manual assessment time and effort, yielding substantial clinical benefits. Existing research addresses MEG spike detection by encoding neural network inputs with signals from all channel within a time segment, followed by classification. However, these methods overlook simultaneous spiking occurred from nearby sensors. We introduce a simple yet effective paradigm that first clusters MEG channels based on their sensor's spatial position. Next, a novel convolutional input module is designed to integrate the spatial clustering and temporal changes of the signals. This module is fed into a custom MEEG-ResNet3D developed by the authors, which learns to extract relevant features and classify the input as a spike clip or not. Our method achieves an F1 score of 94.73% on a large real-world MEG dataset Sanbo-CMR collected from two centers, outperforming state-of-the-art approaches by 1.85%. Moreover, it demonstrates efficacy and stability in the Electroencephalographic (EEG) seizure detection task, yielding an improved weighted F1 score of 1.4% compared to current state-of-the-art techniques evaluated on TUSZ, whch is the largest EEG seizure dataset. © 2024 IEEE.

关键词： Magnetoencephalography

来源：评论

学校读者我要写书评

暂无评论

Use of Sun-Induced Chlorophyll Fluorescence in Linear and Non-Linear Light Use Efficiency Models for Remote Estimation of Photosynthesis

SSRN

引用

SSRN 2023年

作者： Pilar Cendrero-Mateo, MaPi Van Wittenberghe, Shari Laparra, Valero Rascher, Uwe Papuga, Shirley Anne Ponce-Campos, Guillermo Moreno, Jose Image Processing Laboratory University of Valencia Valencia Spain Institute of Bio- and Geosciences Plant Science Forschungszentrum Jülich GmbH Jülich Germany Department of Environmental Science and Geology Wayne State University DetroitMI United States The University of Arizona School of Natural Resources and Environment TucsonAZ United States

In this study, different linear and non-linear light-use efficiency (LUE) models were used to evaluate the contribution of Sun-induced chlorophyll fluorescence (SIF) for the remote estimation of plant photosynthesis. Coincident measurements of net plant photosynthesis (Anet), optical vegetation indices (i.e., Red edge index and photochemical reflectance index (PRI) among others), photochemical quantum yield (ΦPSII), and SIF were made at leaf level once a week in a wheat field under different nitrogen treatments. In LUE models, three key variables explain the seasonal variability of photosynthesis;these are the fraction of absorbed photosynthetically active radiation (fAPAR), LUE, and a correction factor related to meteorological conditions that limit LUE. In this study, the Red edge index was highly correlated with fAPAR (R2>0.70, p-value © 2023, The Authors. All rights reserved.

关键词： Photosynthesis

来源：评论

学校读者我要写书评

暂无评论

Evaluating edge artificial intelligence-driven supply chain management platforms using collaborative large-scale fuzzy information fusion

引用

Applied Soft Computing 2024年 159卷

作者： Zhang, Chao Zhang, Jingjing Sangaiah, Arun Kumar Li, Deyu Li, Wentao School of Computer and Information Technology Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education Shanxi University Taiyuan Shanxi030006 China International Graduate Institute of Artificial Intelligence National Yunlin University of Science and Technology Yunlin Taiwan Department of Electrical and Computer Engineering Lebanese American University Byblos Lebanon College of Artificial Intelligence Southwest University Chongqing400715 China

The rapid development of edge artificial intelligence (AI) has brought about revolutionary changes in supply chain management (SCM). It not only provides real-time data processing capabilities but also accelerates the decision-making process, injecting more innovative elements into SCM. In this context, SCM platforms require new technological developments and effective evaluations, as they collectively drive the efficient coordination of complex business processes. SCM platforms enable the seamless coordination of various supply chain elements, facilitating streamlined operations and enhanced decision-making processes. The evaluation of these platforms not only serves to validate their performance and effectiveness, but also contributes to continual improvements in design and application, and addressing the evolving demands within the realms of global commerce and dynamic market conditions. The ongoing assessment and enhancement of SCM platforms play a crucial role in optimizing resource allocation, improving production efficiency, and fostering adaptability to changing market dynamics. However, the acquisition of assessment data often introduces imprecise data. Additionally, the large-scale nature and bounded rationality of decision-makers (DMs) significantly impact the evaluation of SCM platforms. This article aims to explore a collaborative large-scale information fusion approach and provide a robust fuzzy framework for evaluating SCM platforms. This approach employs a combination of spherical fuzzy sets (SFSs), large-scale group decision-making (LSGDM), behavioral theories and three-way decisions (TWD) to thoroughly explore collaborative large-scale information fusion and its practical application in assessing SCM platforms. It introduces an innovative spherical fuzzy (SF) LSGDM technique and integrates TWD with the inclusion of prospect theory (PT) and regret theory (RT) to mitigate potential decision risks. The developed collaborative large-scale information f

关键词： Supply chain management

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：