检索结果-内蒙古大学图书馆

P2TC: A Lightweight Pyramid Pooling Transformer-CNN Network for Accurate 3D Whole Heart Segmentation

IEEE Journal of Biomedical and Health Informatics 2025年第6期29卷 4279-4289页

作者： Hengfei Cui Yifan Wang Fan Zheng Yan Li Yanning Zhang Yong Xia National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer Science Northwestern Polytechnical University Xi'an China Research and Development Institute of Northwestern Polytechnical University in Shenzhen Shenzhen China Chongqing Innovation Center Northwestern Polytechnical University Chongqing China

Cardiovascular disease is a leading global cause of death, requiring accurate heart segmentation for diagnosis and surgical planning. Deep learning methods have been demonstrated to achieve superior performances in cardiac structures segmentation. However, there are still limitations in 3D whole heart segmentation, such as inadequate spatial context modeling, difficulty in capturing long-distance dependencies, high computational complexity, and limited representation of local high-level semantic information. To tackle the above problems, we propose a lightweight Pyramid Pooling Transformer-CNN (P2TC) network for accurate 3D whole heart segmentation. The proposed architecture comprises a dual encoder-decoder structure with a 3D pyramid pooling Transformer for multi-scale information fusion and a lightweight large-kernel Convolutional Neural Network (CNN) for local feature extraction. The decoder has two branches for precise segmentation and contextual residual handling. The first branch is used to generate segmentation masks for pixel-level classification based on the features extracted by the encoder to achieve accurate segmentation of cardiac structures. The second branch highlights contextual residuals across slices, enabling the network to better handle variations and boundaries. Extensive experimental results on the Multi-Modality Whole Heart Segmentation (MM-WHS) 2017 challenge dataset demonstrate that P2TC outperforms the most advanced methods, achieving the Dice scores of 92.6% and 88.1% in Computed Tomography (CT) and Magnetic Resonance Imaging (MRI) modalities respectively, which surpasses the baseline model by 1.5% and 1.7%, and achieves state-of-the-art segmentation results.

关键词： Transformers Image segmentation Three-dimensional displays Heart Accuracy Feature extraction Convolutional neural networks Context modeling Computational modeling Solid modeling

来源：评论

学校读者我要写书评

暂无评论

Tensor Graph Convolutional Network for Dynamic Graph Representation Learning

arXiv

引用

arXiv 2024年

作者： Wang, Ling Yuan, Ye The School of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing400065 China The Chongqing Key Laboratory of Big Data and Intelligent Computing Chongqing Engineering Research Center of Big Data Application for Smart Cities Chongqing Institute of Green and Intelligent Technology Chinese Academy of Sciences Chongqing400714 China The College of Computer and Information Science Southwest University Chongqing400715 China

Dynamic graphs (DG) describe dynamic interactions between entities in many practical scenarios. Most existing DG representation learning models combine graph convolutional network and sequence neural network, which model spatial-temporal dependencies through two different types of neural networks. However, this hybrid design cannot well capture the spatial-temporal continuity of a DG. In this paper, we propose a tensor graph convolutional network to learn DG representations in one convolution framework based on the tensor product with the following two-fold ideas: a) representing the information of DG by tensor form;b) adopting tensor product to design a tensor graph convolutional network modeling spatial-temporal feature simultaneously. Experiments on real-world DG datasets demonstrate that our model obtains state-of-the-art performance. Copyright © 2024, The Authors. All rights reserved.

关键词： Tensors

来源：评论

学校读者我要写书评

暂无评论

An Optimizing E-govenment Model for data Sharing via Distributed Ledgers

An Optimizing E-govenment Model for Data Sharing via Distrib...

引用

2022 International Conference on Artificial Intelligence, Information Processing and Cloud Computing, AIIPCC 2022

作者： Peng, Sheng Zhu, Linkai Lu, Jiadong Tian, Renhui Song, Shiyang Wang, Wennan Academy of Management Guangdong University of Science and Technology Zhuhai Yingying Technology Co. Ltd. Dongguan China Information Technology School Hebei University of Economics and Business Shijiazhuang050061 China Alibaba Cloud Big Data Application College Zhuhai College of Science and Technology Zhuhai China Institute of Data Science City University of Macau China Academy of Management Guangdong University of Science and Technology Dongguan China

ISBN: (纸本)9781665462877

With the development of terminal technology and the expansion of application areas, the value of e-government applications and service requirements continue to increase. To develop and apply e-government, data sharing efficiency is essential. Using the e-government data sharing as a research object, a blockchain-based method is developed for optimizing data transfer. Blockchain technology is used for storing and delivering distributed data. Rather than distributing data nodes randomly, our network scenario model employs a matrix lattice model based on a complete undirected graph. Dual optimization is then applied to solve the problem. In order to find the optimal solution, a mathematical model and an artificial neural network are developed. To verify the performance and packet loss rate of the government data transmission method, a case study is conducted. data Sharing is optimized to increase the lifetime of static aggregation nodes by at least 30% and lifetime of static aggregation nodes by at least 20%. The network lifetime can be extended by optimizing static aggregation nodes. Furthermore,it effectively improves the robustness. © 2022 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

An ADRC-Incorporated Stochastic Gradient Descent Algorithm for Latent Factor Analysis

arXiv

引用

arXiv 2024年

作者： Li, Jinli Yuan, Ye The School of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing400065 China The Chongqing Key Laboratory of Big Data and Intelligent Computing Chongqing Engineering Research Center of Big Data Application for Smart Cities Chongqing Institute of Green and Intelligent Technology Chinese Academy of Sciences Chongqing400714 China The College of Computer and Information Science Southwest University Chongqing400715 China

High-dimensional and incomplete (HDI) matrix contains many complex interactions between numerous nodes. A stochastic gradient descent (SGD)-based latent factor analysis (LFA) model is remarkably effective in extracting valuable information from an HDI matrix. However, such a model commonly encounters the problem of slow convergence because a standard SGD algorithm only considers the current learning error to compute the stochastic gradient without considering the historical and future state of the learning error. To address this critical issue, this paper innovatively proposes an ADRC-incorporated SGD (ADS) algorithm by refining the instance learning error by considering the historical and future state by following the principle of an ADRC controller. With it, an ADS-based LFA model is further achieved for fast and accurate latent factor analysis on an HDI matrix. Empirical studies on two HDI datasets demonstrate that the proposed model outperforms the state-of-the-art LFA models in terms of computational efficiency and accuracy for predicting the missing data of an HDI matrix. Copyright © 2024, The Authors. All rights reserved.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

引用

Frontiers of Computer Science 2020年第3期14卷 113-128页

作者： Yun PENG Yitong XU Huawei ZHAO Zhizheng ZHOU Huimin HAN Research Center of Big Data Application Qilu University of TechnologyJinan 250353China Data Science Institute Columbia UniversityNew York 10027USA College of Mechanics and Materials Hohai UniversityNanjing 210098China

This paper studies the most similar maximal clique query(MSMCQ).Given a graph G and a set of nodes Q,MSMCQ is to find the maximal clique of G having the largest similarity with *** has many real applications including advertising industry,public security,task crowdsourcing and social network,*** can be studied as a special case of the general set similarity query(SSQ).However,the MCs of G has several specialties from the general *** on the specialties of MCs,we propose a novel index,namely *** outperforms the state-of-the-art SSQ method significantly in terms of the number of candidates and the query ***,we first construct an inverted indexⅠfor all the MCs of *** the MCs in a posting list often have a lot of overlaps,MCIndex selects some pivots to cluster the MCs with a small *** a query Q,we compute the distance from the pivots to *** clusters of the pivots assured not answer can be pruned by our distance based pruning *** it is NP-hard to construct a minimum MCIndex,we propose to construct a minimal MCIndex onⅠ(v)with an approximation ratio 1+ln|Ⅰ(v)|.Since the MCs have properties that are inherent of graph structure,we further propose a S Index within each cluster of a MCIndex and a structure based pruning rule.S Index can significantly reduce the number of *** the sizes of intersections between Q and many MCs need to be computed during the query evaluation,we also propose a binary representation of MCs to improve the efficiency of the intersection size *** extensive experiments confirm the effectiveness and efficiency of our proposed techniques on several real-world datasets.

关键词： most similar maximal clique similarity query graph data

来源：评论

学校读者我要写书评

暂无评论

Synergistic Effects of Er and Sc on the Aging Behavior and Θ' Precipitation Stability of Al-Cu Alloys

SSRN

引用

SSRN 2023年

作者： Hou, Xingkai Wen, Shengping Qi, Peng Wei, Wu Wu, Xiaolan Huang, Hui Gao, Kunyuan Xiong, Xiangyuan Nie, Zuoren Faculty of Materials and Manufacturing National Engineering Laboratory for Industrial Big-data Application Technology Beijing University of Technology Beijing100124 China Chinalco Science and Technology Institute Co. LTD. Beijing102209 China

The synergistic effects of Er and Sc on the aging behavior and θ' precipitation stability of Al-Cu alloys were systematically investigated. The combination of Er and Sc plays an important role in promoting the formation of θ' precipitates and enhancing the stability of θ' precipitates. To this end, the effects of synergistic addition of Er and Sc on the aging and interfacial segregation behavior of the alloy were studied in detail by transmission electron microscopy (TEM) and high angle annular dark field (HAADF). The TEM results showed that the Al3(Sc, Zr) dispersoids with core-shell structure can act as the nucleation particles of θ' and promote the uniform and fine precipitation of θ' plate. The STEM results showed that Er solute atoms were preferentially enriched inside the θ' precipitate during thermal exposure at 225°C for 150 h, which inhibited the serious coarsening of the θ' precipitate. After thermal exposure at 300°C, Sc and Mn with slow diffusion rate segregated at the interface of the θ' precipitate. Due to the early enrichment of Er in the θ' precipitate, the slowly diffused Sc and Mn can be segregated to the interface of the θ' precipitate before the severe coarsening of the θ' precipitate, thus further stabilizing the θ' precipitate at a higher temperature. © 2023, The Authors. All rights reserved.

关键词： Stability

来源：评论

学校读者我要写书评

暂无评论

Inverse Markov Process Based Constrained Dynamic Graph Layout

引用

Journal of Computer Science & technology 2021年第3期36卷 707-718页

作者： Shi-Ying Sheng Sheng-Tao Chen Xiao-Ju Dong Chun-Yuan Wu Xiao-Ru Yuan ParisTech Elite Institute of Technology Shanghai Jiao Tong UniversityShanghai 200240China Department of Computer Science and Engineering Shanghai Jiao Tong UniversityShanghai 200240China Key Laboratory of Machine Perception(Ministry of Education) National Engineering Laboratory for Big Data Analysis and ApplicationPeking UniversityBeijing 100080China

In online dynamic graph drawing,constraints over nodes and node pairs help preserve a coherent mental map in a sequence of *** the constraints is challenging due to the requirements of both preserving mental map and satisfying the visual aesthetics of a graph *** existing algorithms basically depend on local changes but fail to do proper evaluations on the global propagation when setting *** solve this problem,we introduce a heuristic model derived from PageRank which simulates the node movement as an inverse Markov process hence to give a global analysis of the layout's change,according to which different constraints can be *** constraints,along with stress function,generate layouts maintaining spatial positions and shapes of relatively stable substructures between adjacent *** demonstrate that our method preserves both structure and position similarity to help users track graph changes visually.

关键词： graph drawing data stream dynamic graph layout

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Residual Airspace Resources Based on Civil Aviation Operation big data 3

Evaluation of Residual Airspace Resources Based on Civil Avi...

引用

3rd IEEE International Conference on Civil Aviation Safety and Information technology, ICCASIT 2021

作者： Shi, Hongfang Zheng, Yinger Zhang, Xiaoyue Sun, Huabo Big Data Analysis and Application Center China Academy of Civil Aviation Science and Technology Beijing China Institute of Aviation Safety China Academy of Civil Aviation Science and Technology Beijing China

ISBN: (纸本)9781665425186

The problem of efficient utilization and capacity improvement of airspace resources has become increasingly prominent as the demand for civil aviation transportation increases. A reasonable evaluation of residual airspace resources can provide support for airport capacity assessment, layout planning, air route optimization, flight schedule adjustment, etc., particularly under the existing service and support capabilities. Based on the quick access recorder (QAR) data of civil aviation operations, this paper constructs an evaluation method of residual civil aviation airspace resources. The entrance and exit of the terminal area and key waypoints are used as key elements of the evaluation, and residual airspace resources are then calculated with the airport as the core. Finally, taking an airport in the Yangtze River Delta as an example, the characteristics of the surrounding airspace resources are analyzed under the influence of the national civil aviation transportation system. The residual airspace resources are determined as 62 sorties/hour and 1302 sorties/day. © 2021 IEEE

关键词： big data

来源：评论

学校读者我要写书评

暂无评论

Service Decomposition method for multimodal data exchange scenarios 3

Service Decomposition method for multimodal data exchange sc...

引用

3rd International Conference on Computer Science and Management technology, ICCSMT 2022

作者： Jiang, Deyou Huang, Lei Tian, Hanyu Xie, Yujie Li, Xiaoming Beijing Jiaotong University School of Economics and Management Beijing China Beijing Jingwei Information Technologies Limited Company National Engineering Laboratory of Comprehensive Transportation Big Data Application Technology Beijing China Institute of Computing Technologies China Academy of Railway Sciences Beijing China

ISBN: (纸本)9798350320404

Influenced by the complexity of multimodal data exchange scenarios and their differences in data flow graph construction, the objective basis of existing service decomposition methods is not sufficient, and the granularity of the results is too large and difficult to be decomposed. To address this problem, this paper presents a service decomposition method for multimodal data exchange scenarios. This method reconstructs the differentially constructed data flow diagram by unified rules at the stage of requirement analysis and design, and then completes the fine-grained division of microservices around documents based on service-decomposed rules. The case study shows that the method is more effective than the existing method in the multimodal data exchange scenario. © 2022 IEEE.

关键词： Electronic data interchange

来源：评论

学校读者我要写书评

暂无评论

A Revised Model for Sea-Surface Wind Inversion data with Joint Interpolation Optimization and Residual Network

A Revised Model for Sea-Surface Wind Inversion Data with Joi...

引用

International Conference on Intelligent System and Knowledge Engineering, ISKE

作者： Weihong Lin Lijun You Tianqiang Huang Liqing Huang Haifeng Luo Chao Xu College of Computer and Cyber Security Fujian Normal University Fujian Provincal Engineering Research Center of Big Data Analysis and Application Digital Fujian Institute of Big Data Security Technology Fuzhou China Fujian Meteorological Information Center Fujian Key Laboratory of Severe Weather Fuzhou China

The sea-surface wind fields are pivotal for studies in both oceanography and meteorology. However, the acquisition of ocean wind data is often challenged by practical constraints, especially near coasts, leading to significant data gaps. This paper introduces a two-stage approach that combines interpolation optimization with a residual network to improve satellite-derived sea-surface wind fields data. Initially, the Kriging interpolation method is employed to fill missing regions. Subsequently, a network structure similar to ResNet-18 is tailored to revise the interpolated data using buoy anemometer observations. By establishing a correlation model between the interpolated results and ground truth through supervised training, the approach ensures the interpolated results gravitate towards the actual measurements. The efficacy of the proposed model is corroborated through experimental visual analysis and error cure assessments.

关键词：

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：