检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Xiong, Zheli Lian, Defu Chen, Enhong Chen, Gang Cheng, Xiaomin The School of Data Science University of Science and Technology of China Anhui Hefei230000 China The Anhui Province Key Laboratory of Big Data Analysis and Application School of Computer Science and Technology University of Science and Technology of China Anhui Hefei230000 China The Yangtze River Delta Information Intelligence Innovation Research Institute China

The estimation of origin-destination (OD) matrices is a crucial aspect of Intelligent Transport Systems (ITS). It involves adjusting an initial OD matrix by regressing the current observations like traffic counts of road sections (e.g., using least squares). However, the OD estimation problem lacks sufficient constraints and is mathematically underdetermined. To alleviate this problem, some researchers incorporate a prior OD matrix as a target in the regression to provide more structural constraints. However, this approach is highly dependent on the existing prior matrix, which may be outdated. Others add structural constraints through sensor data, such as vehicle trajectory and speed, which can reflect more current structural constraints in real-time. Our proposed method integrates deep learning and numerical optimization algorithms to infer matrix structure and guide numerical optimization. This approach combines the advantages of both deep learning and numerical optimization algorithms. The neural network(NN) learns to infer structural constraints from probe traffic flows, eliminating dependence on prior information and providing real-time performance. Additionally, due to the generalization capability of NN, this method is economical in engineering. We conducted tests to demonstrate the good generalization performance of our method on a large-scale synthetic dataset. Subsequently, we verified the stability of our method on real traffic data. Our experiments provided confirmation of the benefits of combining NN and numerical *** Codes I.2.1 Copyright © 2023, The Authors. All rights reserved.

关键词： Statistical tests

来源：评论

学校读者我要写书评

暂无评论

NM-LinkNet: Cloud Detection from Remote Sensing Images with Non-local Operation and Multi-scale Feature Aggregation 7th

NM-LinkNet: Cloud Detection from Remote Sensing Images with ...

引用

7th International Symposium of Space Optical Instruments and applications, ISSOIA 2022

作者： Jie, Yongshi Yue, Anzhi Wang, Naijian Wang, Yan Xu, Xuejie Ding, Ding Tan, Wei He, Hongyan Xing, Kun Beijing Institute of Space Mechanics and Electricity China Academy of Space Technology Beijing China Aerospace Information Research Institute Chinese Academy of Sciences Beijing China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Xian China Bureau of Geophysical Prospecting INC. China National Petroleum Corporation Hebei Province Zhuozhou China Department of Engineering Physics Tsinghua University Beijing China Powerleader Computer Systems Co. Ltd Guangdong Province Shenzhen China

ISBN: (纸本)9789819940974

Cloud detection is an important preprocessing process in remote sensing applications. Cloud detection methods have developed from traditional methods to deep learning methods which are widely used at present. However, current cloud detection methods still have limitations in the detection of thin clouds and broken clouds, mainly because the thin clouds are sparsely distributed and the size of broken clouds is relatively small. To solve the above difficult problems, this paper proposes a cloud detection network NM-LinkNet, which combines non-local operation and multi-scale feature aggregation, to improve the detection ability of thin clouds and broken clouds. Based on LinkNet50, NM-LinkNet uses non-local operation to obtain the long-distance context information of sparse distributed thin clouds to enhance the features of thin clouds. The multi-scale feature aggregation module designed in this paper is used to extract the features of clouds of different scales to improve the detection ability of small broken clouds. The experimental results on SPARCS dataset show that the IoU and F1 of NM-LinkNet proposed in this paper reach 87.50% and 93.33% respectively, which exceeds the other five mainstream deep learning methods in quantitative data and visualization results. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Remote sensing

来源：评论

学校读者我要写书评

暂无评论

Requirement of Production Simulation of DC Distribution Network Containing High Renewable Energy 37

Requirement of Production Simulation of DC Distribution Netw...

引用

37th Youth Academic Annual Conference of Chinese Association of Automation, YAC 2022

作者： Li, Man Zhang, Yi Li, Yan Li, Xiaoxue Fan, Bo Li, Lifeng Li, Yanmei Hu, Yuan National Research Center for Rehabilitation and Technical Aids Testing Department Beijing China China Academy of Industrial Internet Big Data Department Beijing China China Electric Power Research Institute Artificial Intelligence Department Beijing China Beijing Aerospace Data Stock Company General Manager of Key Account Division Beijing China General Headquarters Chengdu Aerospace Science & Industry Big Data Institute Ltd chengdu China National Research Center for Rehabilitation and Technical Aids AI Application Research Department Beijing China Kunlun Digital Technology Co. Ltd Business Department Beijing China

ISBN: (纸本)9781665465366

Renewable energy power generation connected to the DC distribution network, converter station capacity, renewable energy installed capacity and renewable energy operation mode are the primary factors that affect the maximum consumption of renewable energy. Unreasonable converter station capacity and renewable energy installed capacity planning and configuration will result in excessive renewable energy installed capacity, resulting in abandonment of wind and light, or too small installed capacity to make the converter station with full using. The renewable energy power generation operation mode strategy directly affects the DC distribution network transmission capacity and the regulation capacity of the energy storage station, which in turn affects the consumption of renewable energy power generation. The paper studies relevant time series modeling methods of wind and PV power generation, and proposes the technical requirements for optimizing the power generation operation mode considering the hybrid of multiple types of renewable energy and the DC distribution network, so as to achieve maximum consumption renewable energy, and to ensure that the power of renewable energy can be 'controlled and consumed'', and ultimately ensure the stable operation and safe of renewable energy and the DC distribution network. The paper results will provide support for the future planning of the local consumption of a high proportion of renewable energy, and will effectively guide the planning and design of renewable energy and DC distribution networks. © 2022 IEEE.

关键词： Electric power distribution

来源：评论

学校读者我要写书评

暂无评论

Gradient Alignment Improves Test-Time Adaptation for Medical Image Segmentation

arXiv

引用

arXiv 2024年

作者： Chen, Ziyang Ye, Yiwen Pan, Yongsheng Xia, Yong National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer Science and Engineering Northwestern Polytechnical University Xi’an China Research & Development Institute of Northwestern Polytechnical University in Shenzhen Shenzhen China Ningbo Institute of Northwestern Polytechnical University Ningbo China

Although recent years have witnessed significant advancements in medical image segmentation, the pervasive issue of domain shift among medical images from diverse centres hinders the effective deployment of pre-trained models. Many Test-time Adaptation (TTA) methods have been proposed to address this issue by fine-tuning pre-trained models with test data during inference. These methods, however, often suffer from less-satisfactory optimization due to suboptimal optimization direction (dictated by the gradient) and fixed step-size (predicated on the learning rate). In this paper, we propose the Gradient alignment-based Test-time adaptation (GraTa) method to improve both the gradient direction and learning rate in the optimization procedure. Unlike conventional TTA methods, which primarily optimize the pseudo gradient derived from a self-supervised objective, our method incorporates an auxiliary gradient with the pseudo one to facilitate gradient alignment. Such gradient alignment enables the model to excavate the similarities between different gradients and correct the gradient direction to approximate the empirical gradient related to the current segmentation task. Additionally, we design a dynamic learning rate based on the cosine similarity between the pseudo and auxiliary gradients, thereby empowering the adaptive fine-tuning of pre-trained models on diverse test data. Extensive experiments establish the effectiveness of the proposed gradient alignment and dynamic learning rate and substantiate the superiority of our GraTa method over other state-of-the-art TTA methods on a benchmark medical image segmentation task. Copyright © 2024, The Authors. All rights reserved.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

A Lightweight CNN-Transformer Network with Agent Attention Mechanism for 3D Whole Heart Segmentation

A Lightweight CNN-Transformer Network with Agent Attention M...

引用

Pattern Recognition and Artificial Intelligence (PRAI), International Conference on

作者： Jiatong Li Yifan Wang Dianrong Du Hengfei Cui National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Northwestern Polytechnical University Xi'an China Research & Development Institute of Northwestern Polytechnical University in Shenzhen Shenzhen China Chongqing Innovation Center Northwestern Polytechnical University Chongqing China

ISBN: (数字)9798350350890

ISBN: (纸本)9798350350906

In recent years, heart diseases have become one of the major global health issues, emphasizing the importance of 3D whole heart segmentation technology for accurate and efficient treatment. Currently, 3D whole heart segmentation algorithms often combine Transformer technologies with 3D Convolutional Neural Networks (3D CNNs), leveraging the self-attention mechanism of Transformers for global information modeling and 3D CNNs for capturing local contextual information. However, the high computational complexity of Transformers leads to huge computational resource wastage. To address this issue, this work proposes a novel whole heart segmentation algorithm named AgentTransBTS, based on an improved 3D Agent Attention mechanism and the TransBTS framework. This algorithm utilizes TransBTS as the baseline model, capitalizing on its deep feature extraction and information integration capabilities to capture global dependencies in images. To reduce computational complexity without sacrificing the model's expressive power, an enhanced 3D Agent Attention mechanism is introduced. Comprehensive experiments were conducted on the Multi-Modality Whole Heart Segmentation (MM-WHS) 2017 dataset to evaluate the proposed algorithm. The experimental results demonstrate that our proposed method achieved an average Dice coefficient of 91.9% on the CT dataset and 79.9% on the MRI dataset of the MM-WHS 2017 challenge. Furthermore, our algorithm's FLOPs are 217G, representing an approximate 9.2% improvement in computational efficiency compared to the baseline network.

关键词： Heart Image segmentation Solid modeling Three-dimensional displays Attention mechanisms Computational modeling Magnetic resonance imaging Transformers Computational complexity Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

Tackling the Incomplete Annotation Issue in Universal Lesion Detection Task By Exploratory Training

arXiv

引用

arXiv 2023年

作者： Bai, Xiaoyu Ma, Benteng Li, Changyang Xia, Yong National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer Science and Engineering Northwestern Poly-technical University Xi’an710072 China Sydney Polytechnic Institute NSW2000 Australia

Universal lesion detection (ULD) has great value for daily clinical practice as it aims to detect various types of lesions in multiple organs on medical images. Deep learning methods have shown promising results, but demanding substantial volumes of annotated data for effective training. Nevertheless, annotating medical images is costly and requires specialized knowledge. Additionally, the diverse forms and contrasts of objects in medical images make fully annotation even more challenging, resulting in incomplete annotations. Directly training ULD detectors on such datasets can yield suboptimal results. Pseudo-label-based methods examine the data in the training set and mine unlabelled objects for retraining, which have shown to be effective to tackle this issue. Presently, top-performing methods rely on a dynamic label-mining mechanism, operating at the mini-batch level. However, the model’s performance varies at different iterations, leading to inconsistencies in the quality of the mined labels during training. This inconsistency limits their potential for performance enhancement. Inspired by the observation that deep models learn concepts with increasing complexity, we introduce an innovative exploratory training strategy to assess the reliability of mined lesions over time. Specifically, we introduce a teacher-student detection model as the basis, where the teacher model’s predictions are combined with incomplete annotations to train the student model. On top of that, we design a prediction bank to record all high-confidence predictions. Each sample is trained several times, allowing us to get a sequence of records for each sample. If a prediction consistently appears in the record sequence, it is likely to be a true object, otherwise it may just a noise. This serves as a crucial criterion for selecting reliable mined lesions for subsequent retraining. Our experimental results substantiate that the proposed framework surpasses state-of-the-art methods on two med

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Fast extraction of winter wheat planting area in Huang-Huai-Hai Plain using high-resolution satellite imagery on a cloud computing platform

引用

International Journal of Agricultural and Biological Engineering 2022年第1期15卷 241-250页

作者： Dongyan Zhang Mengru Zhang Fenfang Lin Zhenggao Pan Fei Jiang Liang He Hang Yang Ning Jin National Engineering Research Center for Agro-Ecological Big Data Analysis&Application Anhui UniversityHefei 230601China Key Laboratory of Geospatial Technology for Middle and Lower Yellow River Regions(Henan University) Ministry of EducationKaifeng 475004HenanChina School of Informatics and Engineering Suzhou UniversitySuzhou 234000AnhuiChina National Meteorological Center Beijing 100081China Aerospace Information Research Institute Chinese Academy of ScienceBeijing 100101China

To extract regional winter wheat planting area using higher-resolution satellite imagery still faces many challenges due to large data size and long processing time in traditional remote sensing *** Earth Engine(GEE),a cloud computing analysis platform based on global geospatial analysis,provides a new opportunity for rapid analysis of remote sensing *** this study,high-quality Landsat-8 imagery was used to extract the winter wheat planting area from the Huang-Huai-Hai Plain in *** random forest algorithm was used to identify and map the winter wheat sown in 2019 and harvested in 2020,and Sentinel-2 imagery was used to verify the *** spectral indices,texture,and terrain features of the image were derived,and their contribution to the classification accuracy of winter wheat was evaluated by *** the top nine features were selected to form an optimal feature *** the set of thirty-four features and the optimized feature subset as the input variables of the random forest classifier,the results show that the accuracy difference between the two feature classification schemes is small,but the classification effect of all feature sets is slightly better than the optimal feature *** overall classification accuracy of sample plots verification was 86%-95%,the Kappa coefficient was between 0.7 and 0.85,and the percentage error of the total area was 5.42%.The research demonstrates a reliable method for mapping a wide range of winter wheat planting area,and provides a good prospect for exploring the precise mapping of other crops,which is of great significance to crop monitoring and agricultural development.

关键词： Google Earth Engine regional scale winter wheat rapid mapping

来源：评论

学校读者我要写书评

暂无评论

Machine Reading Comprehension of High-Tech Industry Policies: A New dataset and Chinese Pre-Trained Language Model

Machine Reading Comprehension of High-Tech Industry Policies...

引用

2021 IEEE Conference on Telecommunications, Optics and Computer Science, TOCS 2021

作者： Zeng, Changchang Li, Shaobo Chen, Bin Chengdu Institute of Computer Application in Chinese Academy of Sciences University of Chinese Academy of Sciences Chengdu China Guizhou University State Key Laboratory of Public Big Data Guiyang China Chongqing Research Institute of HIT Harbin Institute of Technology Shenzhen China

ISBN: (纸本)9781665424981

Machine reading comprehension (MRC) is a challenging research hotspot in the field of Artificial Intelligence (AI). It can be applied to many scenarios, such as intelligent question answering, intelligent document retrieval, and so on. In this article, we focus on the machine reading comprehension of high-Tech industry policy texts in China. First, we create a cloze style machine reading comprehension dataset of Chinese high-Tech industrial policies. Next, we propose a new pre-Training objective named multi-segment ordering discriminator, and we also use domain-specific dictionary to improve the MLM pre-Training process. Finally, on our dataset, we trained a new pre-Trained language model for machine reading comprehension of Chinese industrial policies. Experiment results show that our pre-Trained language model surpasses existing models such as BERT and RoBERTa in the new dataset. © 2021 IEEE.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Predicting the Transportation Activities of Construction Waste Hauling Trucks: An Input-Output Hidden Markov Approach

arXiv

引用

arXiv 2023年

作者： Yang, Hongtai Lei, Boyi Han, Ke Liu, Luna School of Transportation and Logistics National Engineering Laboratory of Integrated Transportation Big Data Application Technology National United Engineering Laboratory of Integrated and Intelligent Transportation Institute of System Science and Engineering Southwest Jiaotong University Chengdu611756 China

Construction waste hauling trucks (CWHTs), as one of the most commonly seen heavy-duty vehicles in major cities around the globe, are usually subject to a series of regulations and spatial-temporal access restrictions because they not only produce significant NOx and PM emissions but also causes on-road fugitive dust. The timely and accurate prediction of CWHTs’ destinations and dwell times play a key role in effective environmental management. To address this challenge, we propose a prediction method based on an interpretable activity-based model, input-output hidden Markov model (IOHMM), and validate it on 300 CWHTs in Chengdu, China. Contextual factors are considered in the model to improve its prediction power. Results show that the IOHMM outperforms several baseline models, including Markov chains, linear regression, and long short-term memory. Factors influencing the predictability of CWHTs’ transportation activities are also explored using linear regression models. Results suggest the proposed model holds promise in assisting authorities by predicting the upcoming transportation activities of CWHTs and administering intervention in a timely and effective manner. Copyright © 2023, The Authors. All rights reserved.

关键词： Trucks

来源：评论

学校读者我要写书评

暂无评论

ZuantuSet: A Collection of Historical Chinese Visualizations and Illustrations 25

ZuantuSet: A Collection of Historical Chinese Visualizations...

引用

2025 CHI Conference on Human Factors in Computing Systems, CHI 2025

作者： Mei, Xiyao Zhang, Yu Yang, Chaofan Shi, Rui Yuan, Xiaoru Peking University Beijing China University of Oxford Oxford United Kingdom National Key Laboratory of General Artificial Intelligence School of Intelligence Science and Technology Peking University China Department of Computer Science University of Oxford United Kingdom Center for Research on Ancient Chinese History Peking University China National Engineering Laboratory for Big Data Analysis and Application Peking University China PKU-WUHAN Institute for Artificial Intelligence China

ISBN: (纸本)9798400713941

Historical visualizations are a valuable resource for studying the history of visualization and inspecting the cultural context where they were created. When investigating historical visualizations, it is essential to consider contributions from different cultural frameworks to gain a comprehensive understanding. While there is extensive research on historical visualizations within the European cultural framework, this work shifts the focus to ancient China, a cultural context that remains underexplored by visualization researchers. To this aim, we propose a semi-automatic pipeline to collect, extract, and label historical Chinese visualizations. Through the pipeline, we curate ZuantuSet, a dataset with over 71K visualizations and 108K illustrations. We analyze distinctive design patterns of historical Chinese visualizations and their potential causes within the context of Chinese history and culture. We illustrate potential usage scenarios for this dataset, summarize the unique challenges and solutions associated with collecting historical Chinese visualizations, and outline future research directions. © 2025 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： data labeling dataset digital humanities historical visualization

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：