检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Qi, Zhaoshuai Pang, Jingqi Hao, Yifeng Zhang, Yanning College of Computer Science Northwestern Polytechnical University Xi’an710072 China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology China

We construct constraints from consistency between estimated parameters from different spheres, termed inter-sphere consistency. It facilitates more flexible calibration using only two spheres, which has been considere... 详细信息

关键词： Spheres

来源：评论

学校读者我要写书评

暂无评论

Integrated Optimization of Autonomous Intersection Management for Connected and Automated Vehicle

Integrated Optimization of Autonomous Intersection Managemen...

引用

2022世界交通运输大会(WTC2022)

作者： Hui Hua Zhanbo Sun School of Transportation and Logistics Southwest Jiaotong University National Engineering Laboratory of Integrated Transportation Big Data Application Technology

With the development of Connected and Automated Vehicles(CAVs),wireless communication,smart sensor and other technologies,Autonomous Intersection Management(AIM) is more appropriate than the conventional signal intersection *** this work,a bi-level dynamic programming is proposed into signal-free intersection management,where the optimal control problem for controlling vehicle acceleration and deceleration is embedded in the scheduling problem as a *** a centralized control framework,information of CAVs can be *** control center predicts status and potential conflicts of all vehicles,finely analyzes and puts forward acceleration/deceleration strategies to vehicles,to avoid the potential collision and guide the trajectories of subsequent *** proposed method is tested by simulation and numerical experiment,compared with First-come-first-service(FCFS) *** show that the proposed optimization framework perform is better than FCFS in different measurements,and the average travel time can be reduced by up to 35 %.

关键词： CAV and road transport Bi-level programming Dynamic programming(DP) Signal-free intersection management

来源：评论

学校读者我要写书评

暂无评论

Framework for Fuzzy Temporal Association Rule Mining Based on Density Clustering Optimization

Framework for Fuzzy Temporal Association Rule Mining Based o...

引用

6th International Conference on Intelligent Computing and Signal Processing (ICSP)

作者： Yang Cao Pengzhi Ma School of Computer Science and Engineering Shenyang Jianzhu University(SJZU) Liaoning Province Big Data Management and Analysis Laboratory of Urban Construction Shenyang Branch of National Special Computer Engineering Technology Research Center Shenyang China

ISBN: (数字)9798350376548

ISBN: (纸本)9798350376555

This paper proposes a framework for fuzzy temporal association rule mining based on density clustering optimization, aimed at improving the fuzzification of continuous attributes and enhancing the efficiency of mining temporal association rules. The first part of the framework effectively handles continuous attribute data and reduces data redundancy by adopting a density peak clustering algorithm and designing an optimized membership function. The second part introduces a fuzzy list ranking structure combined with item lifespan to mine fuzzy temporal association rules. Experimental results demonstrate that the framework exhibits superior performance in mining fuzzy temporal association rules and outperforms advanced algorithms in handling continuous attributes.

关键词： Fuzzy sets Systematics Redundancy Memory management Signal processing algorithms Clustering algorithms Signal processing Association rule learning Optimization Sorting

来源：评论

学校读者我要写书评

暂无评论

Improved YOLOv5 with Transformer for Large Scene Military Vehicle Detection on SAR Image 7

Improved YOLOv5 with Transformer for Large Scene Military Ve...

引用

7th International Conference on Image, Vision and Computing, ICIVC 2022

作者： Sun, Yi Wang, Wenna Zhang, Qianyu Ni, Han Zhang, Xiuwei Big Data Application Technology National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Xi'an710072 China Northwestern Polytechnical University School of Cybersecurity Xi'an710072 China Northwestern Polytechnical University School of Computer Science Xi'an710072 China

ISBN: (数字)9781665467346

ISBN: (纸本)9781665467346

With the development of SAR technology, large scene object detection on SAR images has attracted more and more attention. Exiting large scene object detection is mainly based on the CNN network, which limits the obtaining of global context information. On the other hand, due to the high acquisition cost of SAR images, there are no existing public datasets in military vehicle detection. To solve these problems, we adopt the Transformer module to construct the neck block based on YOLOv5. This design can gain global context information, and also has better performance for small objects detection. Furthermore, to achieve the detection of large-scale military ground vehicles, we construct a dataset based on the MSTAR dataset, named LSGVOD. Extensive experiments have been conducted on LSGVOD, and experimental results show that the proposed method greatly improves detection accuracy. Compared to other methods, it achieves the best accuracy with 93.3% mAP. © 2022 IEEE.

关键词： Synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

Renin-angiotensin system inhibitors prescriptions in Chinese hospitalized chronic kidney disease patients

引用

World Journal of Clinical Cases 2024年第17期12卷 3061-3075页

作者： Chun Zhang Zhi-Yu Duan Sa-Sa Nie Zhou Zhang Xin-Ru Guo Chao-Yang Zhang Jing Dong Guang-Yan Cai Department of Nephrology The First Medical CentreChinese PLA General HospitalBeijing 100853China School of Medicine Nankai UniversityTianjin 300071China National Engineering Laboratory for Medical Big Data Application Technology Chinese PLA General HospitalBeijing 100853China

BACKGROUND Many guidelines have recommended renin-angiotensin system inhibitors(RASI)as the first-line treatment for patients with chronic kidney disease(CKD).We studied RASI prescription trends from 2010 to 2019,and analyzed the characteristics associated with RASI prescription in Chinese hospitalized CKD *** To study the prescription of renin angiotensin system inhibitors in hospitalized patients with CKD in *** It was retrospectively,cross-sectional reviewed RASI prescriptions in hospitalized CKD patients in China from 2010 to *** prescribing trends were analyzed from 2010 to 2019,and bivariate and multivariate logistic regression analyses were conducted to identify characteristics associated with RASI *** A total of 35090 CKD patients were included,with 10043(28.6%)RASI *** these patients,18919(53.9%)met the criteria for RASI treatments based on the 2012 kidney disease:Improving global outcomes *** these,7246(38.3%)patients received RASI *** prescriptions showed an initial rapid increase from 2011 to 2012,reached its peak around 2015 and 2016,and then exhibited a subsequent slight decreasing *** bivariate and multivariate analyses showed that several characteristics,including the male gender,age less than 60-year-old,nephrology department admission,lower CKD stage,history of hypertension or diabetes,proteinuria,glomerulonephritis as the CKD etiology,and non-acute kidney injury were associated with RASI *** The frequency of RASI prescriptions showed an initial increase but a slight decreasing trend in more recent *** patients with certain characteristics such as elderly age,advanced disease stage,surgery department admission,or acute kidney injury were less likely to receive RASI *** the application of RASI in hospitalized CKD patients is *** actual clinical practice needs to be *** development of related research

关键词： Chronic kidney disease Renin-angiotensin system inhibitors Prescriptions Adherence

来源：评论

学校读者我要写书评

暂无评论

A Cooperative Truck Platooning Approach on Ramp Merging Area of Highway in Mixed Traffic

A Cooperative Truck Platooning Approach on Ramp Merging Area...

引用

International Conference on Transportation Information and Safety (ICTIS)

作者： Xiao Sang Linhan Bai Tao Zhou Fangfang Zheng School of Transportation and Logistics National Engineering Laboratory of Integrated Transportation Big Data Application Technology National United Engineering Laboratory of Integrated and Intelligent Transportation Southwest Jiaotong University Chengdu China Jiangsu Railway Group Nanjing China

Truck platooning has emerged as a promising solution for improving traffic efficiency on highways. This paper proposes an optimization model for connected automated trucks (CATs) that addresses the trajectory optimization problem for CATs as human-driven trucks (HDTs) merge onto highways from on-ramps in a mixed traffic scenario. To maximize the speed of the mixed traffic system, we propose a mixed integer programming (MIP) model based on a rolling horizon algorithm. The algorithm optimizes CATs’ trajectories iteratively, taking into account real-time updates on their driving state, and guides HDTs to follow the trajectories of CATs. The numerical experiments demonstrate that the increasing number of HDTs on the on-ramp negatively impacts the overall system performance, leading to higher traffic delay and reduced system stability. Furthermore, accounting for the stochastic behavior of HDTs can lead to increased instability in the system. Finally, we show that the objective function that comprehensively considers the system speed and platooning time effectively minimizes the delay of all vehicles.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Simulation Method to Play with Porosity and Particle Size Distribution for Characterizing Porous Media

arXiv

引用

arXiv 2024年

作者： Wang, Yuhe National & Local Joint Engineering Laboratory for Big Data Analysis and Computing Technology Beijing100190 China Institute for Scientific Computation Texas A&M University College StationTX77843 United States

This note presents a simulation method for investigating the relationship between porosity and particle size distribution in porous media characterization. The method simulates particle packing based on particle size distributions, incorporating descent and collision rules to mimic the natural deposition process while minimizing boundary-induced porosity distortions. By systematically varying the mean particle size and standard deviation, multiple packed structures are generated, and their corresponding porosities are calculated. This approach offers a flexible and scalable tool for exploring the impact of particle size distribution on porosity, providing both qualitative and quantitative insights into porous media properties. © 2024, CC BY.

关键词： Porosity

来源：评论

学校读者我要写书评

暂无评论

The Vcg Pricing Policy with Unit Reserve Prices for Ride-Sourcing is 3/4-Individual Compatibility

SSRN

引用

SSRN 2024年

作者： Li, Ruijie Chen, Haiyuan Liu, Xiaobo Zhang, Kenan School of Transportation and Logistics Southwest Jiaotong University Sichuan Chengdu611756 China National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University Sichuan Chengdu611756 China Switzerland

We consider a customized pricing and matching strategy for ride-sourcing services in which drivers and riders disclose their willingness to pay (WTP) per unit distance and willingness to accept (WTA) per unit distance, respectively. The platform then matches drivers and riders based on their reports to maximize the total social welfare. While this strategy is motivated to promote transparency, fair pricing, and participant satisfaction, it faces a particular challenge to ensure riders and drivers truthfully report their valuations, which are considered private information. To encourage truthful reports, we implement the Vickrey-Clarke-Groves pricing policy augmented with unit reserve prices, referred to as VCG-URP. For the riders, the reserve price is set as the minimum WTP per unit distance, while for the drivers, it is the maximum WTA per unit distance. We demonstrate that VCG-URP ensures that riders provide truthful valuations. However, it does not guarantee the same level of honesty from drivers in reporting their valuations. While drivers cannot enhance their utility by overstating their unit WTA, they may benefit from understating it. These theoretical results are confirmed by numerical experiments with several additional findings: i) although the underreporting strategy of the drivers theoretically has an opportunity to achieve a higher utility, it always leads to a decrease in expected utility over randomly generated matching scenarios;ii) the introduction of reserve prices has larger impacts on riders than drivers and benefits the platform in excluding less profitable trips;and iii) the performance of VCG-URP is reasonably robust towards the market density, while the VCG price is less applied when the market becomes sparse, mainly due to the loss of substitutability among participants. All these findings bring valuable insights into ride-sourcing services in practice. © 2024, The Authors. All rights reserved.

关键词： Costs

来源：评论

学校读者我要写书评

暂无评论

Coordinate Attention Based 3D-CNN Using Ghost Multi-Scale for Diagnosing Alzheimer’s Disease

Coordinate Attention Based 3D-CNN Using Ghost Multi-Scale fo...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Xiaolu Lin Pinya Lu Jie Pan Hongqin Yang Xuemei Ding Fujian Provincial Engineering Research Center for Public Service Big Data Mining and Application Fujian Provincial University Engineering Research Center for Big Data Analysis and Application Fujian Normal University Fuzhou China Xiamen Jingyi Zhikang Technology Co. Ltd Xiamen China Fujian Provincial Key Laboratory for Photonics Technology Key Laboratory of OptoElectronic Science and Technology for Medicine of Ministry of Education Fujian Normal University Fuzhou China School of Computing Engineering and Intelligent Systems Ulster University Derry-Londonderry NI UK

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Alzheimer's disease (AD) is a neurodegenerative disease and mild cognitive impairment (MCI) is the early stage of AD. Previous studies have predominantly focused on binary classification using 3 dimensional - convolutional neural network (3D-CNN) for AD diagnosis, with limited progress in multi-classification. Moreover, the current 3D-CNNs often adopt a single-scale architecture with massive parameters growth. Additionally, obtaining precise location information of brain imaging data is crucial for improving the classification accuracy with 3D-CNN. Hence, we propose a multi-scale 3D-CNN based on coordinate attention mechanism to marvelously capture and integrate 3D features with fewer parameters, improving the accuracy of AD diagnosis. A total of 447 cognitively normal (CN), 512 MCI, and 358 AD sMRI images from the Alzheimer's Disease Neuroimaging Initiative datasets are used for multi-class classification task, yielding a classification accuracy of 92.8%. The model merely involves 2.41 M parameters and achieves the best classification results with the least number of parameters when compared to other representative CNN architectures including ResNet 18, ResNet 34, ConvNeXt tiny, and VGG 11. Through the ablation experiment, the addition of attention mechanism and the multi-scale classification enhances the classification performance by 4.5% and 1.5%, respectively. Furthermore, our model outperforms the other six existing studies in terms of accuracy for classifying AD vs. MCI vs. CN. Overall, this study underscores the efficacy of our approach for AD diagnosis, showcasing its utility in diagnosing AD patients and providing novel insights for diagnosing other neurological disorder diseases.

关键词： Neuroimaging Accuracy Attention mechanisms Three-dimensional displays Resonance Convolutional neural networks Alzheimer's disease

来源：评论

学校读者我要写书评

暂无评论

Reservoir Static Property Estimation Using Nearest-Neighbor Neural Network

arXiv

引用

arXiv 2024年

This note presents an approach for estimating the spatial distribution of static properties in reservoir modeling using a nearest-neighbor neural network. The method leverages the strengths of neural networks in approximating complex, non-linear functions, particularly for tasks involving spatial interpolation. It incorporates a nearest-neighbor algorithm to capture local spatial relationships between data points and introduces randomization to quantify the uncertainty inherent in the interpolation process. This approach addresses the limitations of traditional geostatistical methods, such as Inverse Distance Weighting (IDW) and Kriging, which often fail to model the complex non-linear dependencies in reservoir data. By integrating spatial proximity and uncertainty quantification, the proposed method can improve the accuracy of static property predictions like porosity and permeability. © 2024, CC BY-NC-SA.

关键词： Interpolation

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：