检索结果-内蒙古大学图书馆

SSRN 2024年

作者： Guo, Xinyu Sun, Hongkun Wang, Weigang College of Statistics and Mathematics Zhejiang Gongshang University Hangzhou310018 China Collaborative Innovation Center of Statistical Data Engineering Technology and Application Zhejiang Gongshang University Hangzhou China

Accurately extracting lesions from medical images is a fundamental but challenging problem in medical image analysis. In recent years, methods based on convolutional neural networks and Transformer have achieved great success in the medical image segmentation field. Combining the powerful perception of local information by CNNs and the efficient capture of global context by Transformer is crucial for medical image segmentation. However, most current models do not fully utilize the interactive guidance of both, and only achieve local-global information fusion through cascading or parallel means. Therefore, based on an encoder-decoder architecture, we propose a novel alternate encoder dual-decoding CNN-Transformer network, AD2Former, with two attractive designs: 1) We propose alternating learning encoder can achieve real-time interaction between local and global information, allowing both to mutually guide learning. 2) We propose a novel dual decoding form. The unique way of dual-branch independent decoding and refusion. To efficiently fuse different feature information from two sub-decoders during decoding, we introduce a channel attention module to reduce redundant feature information. Driven by these two designs, AD2Former demonstrates strong capture ability for target regions and fuzzy boundaries. Experiments on multi-organ segmentation and skin lesion segmentation datasets also demonstrate the effectiveness and superiority of AD2Former. © 2024, The Authors. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Attribute Enhanced Graph Attention Networks for Session-based Recommendation 11

Attribute Enhanced Graph Attention Networks for Session-base...

引用

11th International Conference on Advanced Cloud and Big data, CBD 2023

作者： Xu, Yidan Wang, Ning Wu, Jiaqi Xu, Shuai Li, Bohan Nanjing University of Aeronautics and Astronautics Nanjing China Collaborative Innovation Center of Novel Software Technology and Industrialization Nanjing China Natl. Engineering Laboratory for Integrated Aero-Space-Ground Ocean Big Data Application Technology Xi'an China

ISBN: (纸本)9798350345346

Session-based recommendation (SBR) aims to predict the next item that the anonymous users will interact with based on their short behavior sequence. However, most of the current approaches towards SBR only focus on modeling users' interest preferences based on a series of items, ignoring extra item attributes, i.e., the brand attribute. This paper proposes a novel approach, called the Attribute Enhanced Graph Attention Networks for Session-based Recommendation (AGSR), using the brand attribute to better model user preferences. Specifically, (i) AGSR constructs the session graph of the current session to capture the user's session-level item embedding;(ii) AGSR constructs the brand global graph to capture the brand-level item embedding and brand embedding;(iii) Based on the learned node embeddings, AGSR apply attention layers to extract users' interest and brand preferences. Finally, AGSR makes the recommendation based on item features and user interest and brand preferences, so as to provide better recommendations. Extensive experiments on three real-world datasets demonstrate the effectiveness of our approach. © 2023 IEEE.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Progress and prospects of data-driven stock price forecasting research

引用

International Journal of Cognitive Computing in engineering 2023年第1期4卷 100-108页

作者： Zhao, Chuanjun Wu, Meiling Liu, Jingfeng Duan, Zening li, Jie Shen, Lihua Shangguan, Xuekui Liu, Donghang Wang, Yanjie School of Information Shanxi University of Finance and Economics Shanxi Taiyuan030006 China School of Journalism and Mass Communication University of Wisconsin-Madison MadisonWI53706 United States Financial Innovation and Big Data Statistical Analysis Laboratory Shanxi University of Finance and Economics Shanxi Taiyuan030006 China Shanxi Information Technology Application Innovation Engineering Research Center Shanxi Taiyuan030006 China

With the rapid development of social economy and the continuous improvement of stock market, stock investment has become more and more widely concerned. Stock price prediction has become an important research direction in the field of cognitive computing in engineering. data-driven stock price forecasting aims to predict future stock price trends based on historical values and textual data, which can effectively help people reduce risks and improve returns in the process of stock investment. The article reviews the literature on stock price forecasting methods, and classifies stock price forecasting methods from two different perspectives of model and feature. According to different model angles, the existing stock price prediction methods can be divided into statistical analysis methods, traditional machine learning methods and deep learning methods. According to different characteristic angles, the existing stock price prediction methods can be divided into those based on numerical data and those based on text mixed with numerical data. Finally, we summarize the research challenges faced by stock price prediction and provide future research directions. © 2023

关键词： Investments

来源：评论

学校读者我要写书评

暂无评论

Improvement in oxidation resistance of Cantor alloy through microstructure tailoring

引用

China Foundry 2022年第6期19卷 503-510页

作者： Bao-lin Pang Man Wang Yue-gang Shen Xiao-li Xi Zuo-ren Nie Collaborative Innovation Center of Capital Resource-Recycling Material Technology Faculty of Materials and ManufacturingBeijing University of TechnologyBeijing 100124China Key Laboratory of Advanced Functional Materials Ministry of EducationBeijing University of TechnologyBeijing 100124China National Engineering Laboratory for Industrial Big-data Application Technology Beijing University of TechnologyBeijing 100124China

A method of improving the oxidation resistance of Cantor alloy through microstructure tailoring was *** with distinctive microstructures were achieved by different annealing treatments on the cold-rolled Cantor *** test was then carried out on the various annealed samples at 800°C for 24 h in *** oxidation behavior was evaluated in terms of oxidation rate,surface and cross-section microstructure *** stratified oxide layers including outer Mn_(2)O_(3) and inner Cr_(2)O_(3) were observed in all the annealed samples,the thickness of Mn_(2)O_(3) and Cr_(2)O_(3) layers was ***,the samples exhibited different oxidation *** results indicate that the oxidation resistance of various annealed samples is closely related with grain size as well as twin density.

关键词： Cantor alloy annealing temperature grain size twins oxidation behavior

来源：评论

学校读者我要写书评

暂无评论

Adaptive Movement Sampling Physics-Informed Residual Network (AM-PIRN) for Solving Nonlinear Option Pricing models

arXiv

引用

arXiv 2025年

作者： Gao, Qinjiao Wang, Zuowei Zhang, Ran Wang, Dongjiang School of Statistics and Mathematics Zhejiang Gongshang University Hangzhou China Collaborative Innovation Center of Statistical Data Engineering Technology & Application Zhejiang Gongshang University Hangzhou China School of Mathematics Shanghai University of Finance and Economics Shanghai China

In this paper, we propose the Adaptive Movement Sampling Physics-Informed Residual Network (AM-PIRN) to address challenges in solving nonlinear option pricing PDE models, where solutions often exhibit significant curvature or shock waves over time. The AM-PIRN architecture is designed to concurrently minimize PDE residuals and achieve high-fidelity option price approximations by dynamically redistributing training points based on evolving PDE residuals, while maintaining a fixed total number of points. To enhance stability and training efficiency, we integrate a ResNet backbone, replacing conventional fully connected neural networks used in Physics-Informed Neural Networks (PINNs). Numerical experiments across nonlinear option pricing models demonstrate that AM-PIRN outperforms PINN, RAM-PINN, and WAM-PINN in both resolving PDE constraints and accurately estimating option prices. The method’s advantages are particularly pronounced in complex or multi-dimensional models, where its adaptive sampling and robust architecture effectively mitigate challenges posed by sharp gradients and high nonlinearity. Copyright © 2025, The Authors. All rights reserved.

关键词： Convergence of numerical methods

来源：评论

学校读者我要写书评

暂无评论

Does Urbanization Promote the Urban–Rural Equalization of Basic Public Services? Evidence from Prefectural Cities in China

SSRN

引用

SSRN 2022年

作者： Cheng, Kaiming Liu, Shucheng Hangzhou310018 China Collaborative Innovation Center of Statistical Data Engineering Technology & Application Zhejiang Gongshang University Hangzhou310018 China

The question of how urbanization affects the urban–rural equalization of basic public services (BPS) remains unexplored, although BPS equalization is an important means of achieving common prosperity. Based on the BPS supply and demand perspective, we examine the path mechanisms through which urbanization affects urban–rural BPS equalization. Based on panel data from Chinese prefectural cities from 2003 to 2020, a Technique for Order of Preference by Similarity to Ideal Solution model, combined CRITIC-entropy weights and an information entropy function, are used to measure the level of urban–rural BPS equalization. The study found that, overall, the direct and indirect effects of urbanization on urban–rural BPS equalization are significantly positive, and urbanization is conducive to urban–rural BPS equalization improvement in cities and surrounding areas. The effect of urbanization on urban–rural BPS equalization significantly varies between different regions. The study concludes that the process of people-centered urbanization should be accelerated to optimize the spatial layout of BPS, promote high-quality economic development and achieve common prosperity. © 2022, The Authors. All rights reserved.

关键词： Equalizers

来源：评论

学校读者我要写书评

暂无评论

Time–frequency co-movement and risk connectedness among cryptocurrencies:new evidence from the higher-order moments before and during the COVID-19 pandemic

引用

Financial innovation 2022年第1期8卷 2411-2466页

作者： Jinxin Cui Aktham Maghyereh Collaborative Innovation Center of Statistical Data Engineering Technology and Application Zhejiang Gongshang UniversityHangzhou 310018People’s Republic of China International Business School Zhejiang Gongshang UniversityHangzhou 310018People’s Republic of China Department of Accounting and Finance United Arab Emirates UniversityAbu DhabiUnited Arab Emirates

Analyzing comovements and connectedness is critical for providing significant implications for crypto-portfolio risk ***,most existing research focuses on the lower-order moment nexus(*** return and volatility interactions).For the first time,this study investigates the higher-order moment comovements and risk connectedness among cryptocurrencies before and during the COVID-19 pandemic in both the time and frequency *** combine the realized moment measures and wavelet coherence,and the newly proposed time-varying parameter vector autoregression-based frequency connectedness approach(Chatziantoniou et *** Integration and risk transmission in the market for crude oil a time-varying parameter frequency connectedness *** report,University of Pretoria,Department of Economics,2021)using intraday high-frequency *** empirical results demonstrate that the comovement of realized volatility between BTC and other cryp-tocurrencies is stronger than that of the realized skewness,realized kurtosis,and signed jump *** comovements among cryptocurrencies are both time-dependent and *** the volatility spillovers,the risk spillovers of high-order moments and jumps are also significant,although their magnitudes vary with moments,making them moment-dependent as well and are lower than volatility *** connectedness demonstrates that the risk connectedness is mainly transmitted in the short term(1–7 days).Furthermore,the total dynamic connectedness of all realized moments is time-varying and has been significantly affected by the outbreak of the COVID-19 *** practical implications are drawn for crypto investors,portfolio managers,regulators,and policymakers in optimizing their investment and risk management tactics.

关键词： Cryptocurrencies Higher-order realized moments and jumps Time-frequency comovements and connectedness High-frequency data COVID-19 pandemic

来源：评论

学校读者我要写书评

暂无评论

MP-DPCC: A Motion Proxy-Based Dynamic Point Cloud Compression Framework

MP-DPCC: A Motion Proxy-Based Dynamic Point Cloud Compressio...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： ZhaoYi Jiang Dong Han Cao Song FangZhe Nan Bailin Yang School of Computer Science and Technolgy Zhejiang Gongshang University School of Statistics and Mathematics Zhejiang Gongshang University Economic Forecasting and Policy Simulation Laboratory Zhejiang Gongshang University Collaborative Innovation Center of Statistical Data Engineering Technology & Application Zhejiang Gongshang University

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

The increasing data volume and the demand for real-time transmission highlight the necessity for efficient compression of dynamic point cloud data. Existing methods primarily focus on reducing inter-frame redundancy by calculating per-point motion information, overlooking the computational and storage costs involved. In this paper, we propose a novel motion proxy-based dynamic point cloud compression framework to enhance the efficiency and accuracy of motion information utilization. Specifically, we introduce a feature proxy module to adaptively locate proxy points, which represent the overall motion through the motion of proxy points. Additionally, a motion enhancement module is employed to refine motion details and prevent local information loss caused by dense motion trajectories. Extensive experiments demonstrate the superiority of our approach. Compared with baseline methods, it achieves an average BD-rate improvement of 12.07% (D1) and 11.90% (D2).

关键词： Point cloud compression Costs Accuracy Dynamics Termination of employment Signal processing Real-time systems Acoustics Trajectory Speech processing

来源：评论

学校读者我要写书评

暂无评论

A grain loss prediction method based on integration of multiple classification models

A grain loss prediction method based on integration of multi...

引用

作者： Li, Bingchan Mao, Bo College of Marine Engineering Electrization and Intelligence Jiangsu Maritime Institute Nanjing211170 China National Center for Grain Big Data Collection and Application Technology Innovation Collaborative Innovation Center for Modern Grain Circulation and Safety College of Information Engineering Nanjing University of Finance and Economics Nanjing China

Grain production is an essential part of the Chinese economic system. It not only related to the survival and health of each people but also plays a critical role in social stability. However, more and more foods are wasted in different stages such as harvest, production, storage, and consumption. Therefore, it is essential to accurately evaluate the loss rate of grain during different stages and deal with it accordingly. With the advantages of the information technologies, a large volume of data has been collected in the different stages of grain production, such as harvest, processing, transportation, and consumption. In this paper, we propose an integrated structure to combine multiple clustering models to analyze the grain loss rate in different stages. kNN, softmax regression, decision tree, and XGBoost algorithms are studied and integrated with the proposed combined framework. The experimental results on the survey dataset suggested that the relevant algorithms of machine learning can be combined to improve the prediction accuracy of the grain loss rates. The evaluation results indicate that the proposed method can improve the accuracy to 94% in the test dataset which is higher than any other compared methods. © 2020 John Wiley & Sons, Ltd.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Online Bayesian prediction of remaining useful life for gamma degradation process under conjugate priors

arXiv

引用

arXiv 2022年

作者： Xu, Ancha Department of Statistics Zhejiang Gongshang University Zhejiang China Collaborative Innovation Center of Statistical Data Engineering Technology & Application Zhejiang Gongshang University Zhejiang China

Gamma process has been extensively used to model monotone degradation data. statistical inference for the gamma process is difficult due to the complex parameter structure involved in the likelihood function. In this paper, we derive a conjugate prior for the homogeneous gamma process, and some properties of the prior distribution are explored. Three algorithms (Gibbs sampling, discrete grid sampling, and sampling importance resampling) are well designed to generate posterior samples of the model parameters, which can greatly lessen the challenge of posterior inference. Simulation studies show that the proposed algorithms have high computational efficiency and estimation precision. The conjugate prior is then extended to the case of the gamma process with heterogeneous effects. With this conjugate structure, the posterior distribution of the parameters can be updated recursively, and an efficient online algorithm is developed to predict remaining useful life of multiple systems. The effectiveness of the proposed online algorithm is illustrated by two real cases. Copyright © 2022, The Authors. All rights reserved.

关键词： Computational efficiency

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：