检索结果-内蒙古大学图书馆

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

Multi-Modal Transformer for Accelerated MR Imaging

arXiv

引用

arXiv 2021年

作者： Feng, Chun-Mei Yan, Yunlu Chen, Geng Xu, Yong Hu, Ying Shao, Ling Fu, Huazhu Shenzhen Key Laboratory of Visual Object Detection and Recognition Harbin Institute of Technology Shenzhen518055 China National Engineering Laboratory for Integrated AeroSpace-Ground-Ocean Big Data Application Technology School of Computer Science and Engineering Northwestern Polytechnical University Xi’an710072 China Terminus Group China Institute of High Performance Computing A*STAR Singapore138632 Singapore

Accelerated multi-modal magnetic resonance (MR) imaging is a new and effective solution for fast MR imaging, providing superior performance in restoring the target modality from its undersampled counterpart with guidance from an auxiliary modality. However, existing works simply combine the auxiliary modality as prior information, lacking in-depth investigations on the potential mechanisms for fusing different modalities. Further, they usually rely on the convolutional neural networks (CNNs), which is limited by the intrinsic locality in capturing the long-distance dependency. To this end, we propose a multi-modal transformer (MTrans), which is capable of transferring multi-scale features from the target modality to the auxiliary modality, for accelerated MR imaging. To capture deep multi-modal information, our MTrans utilizes an improved multi-head attention mechanism, named cross attention module, which absorbs features from the auxiliary modality that contribute to the target modality. Our framework provides three appealing benefits: (i) Our MTrans use an improved transformers for multi-modal MR imaging, affording more global information compared with existing CNN-based methods. (ii) A new cross attention module is proposed to exploit the useful information in each modality at different scales. The small patch in the target modality aims to keep more fine details, the large patch in the auxiliary modality aims to obtain high-level context features from the larger region and supplement the target modality effectively. (iii) We evaluate MTrans with various accelerated multi-modal MR imaging tasks, e.g., MR image reconstruction and super-resolution, where MTrans outperforms state-of-the-art methods on fastMRI and real-world clinical datasets. © 2021, CC BY.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Managing Evacuation of Mixed Traffic Flow: Fleet Configuration, Lane Allocation, Lane Reversal, and Cross Elimination

SSRN

引用

SSRN 2022年

作者： Liu, Jialin Jiang, Rui Jia, Bin Liu, Yang Li, Xingang Wang, Ting Key Laboratory of Transport Industry of Big Data Application Technologies for Comprehensive Transport Beijing Jiaotong University Beijing100044 China Department of Industrial Systems Engineering and Management National University of Singapore Singapore117516 Singapore School of Automotive and Transportation Engineering Hefei University of Technology Hefei230009 China

Mixed traffic dynamic evacuation is a challenging task considering heterogeneous populations and traffic congestion. Based on a novel objective function of minimum evacuation network clearance time (ENCT), this paper proposes a mixed traffic dynamic evacuation planning (MTDEP) model, which determines both fleet demand and road supply management strategies, including mixed fleet configuration, lane allocation, lane reversal, and cross-elimination intersections. In this model, a road network is discretized into a multi-size cell network to load mixed traffic, and the holding-back problem of the relaxed CTM is eliminated by adding the penalty term. Then, the proposed model is linearized as a mixed-integer linear program, and a Kriging surrogate-based optimization (KSBO) algorithm is developed. Numerical experiments are conducted on a six-link network and the Sioux-Falls network to validate the effectiveness of our proposed model and solution method. The results show that: (a) the evacuation efficiency of using a mixed fleet is better than that of using a homogeneous fleet in a certain evacuation demand range;(b) while the collaborative management strategies could improve evacuation efficiency, they also take into account the evacuation fairness of the mixed fleet;and (c) the holding-back problem does not affect ENCT but increases the total travel time of all evacuees (ETTT), which should be completely eliminated. © 2022, The Authors. All rights reserved.

关键词： Kriging

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

Service Decomposition method for multimodal data exchange sc...

引用

Computer Science and Management technology (ICCSMT), International Conference on

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

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.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Multi-Source Information Fusion Model for Outlier Detection

SSRN

引用

SSRN 2022年

作者： Zhang, Pengfei Li, Tianrui Wang, Guoqiang Wang, Dexian Lai, Pei Zhang, Fan School of Computing and Artificial Intelligence Southwest Jiaotong University Chengdu611756 China Institute of Artificial Intelligence Southwest Jiaotong University Chengdu611756 China National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University Chengdu611756 China

Multi-source information fusion (MSIF) is a useful strategy for combining complimentary data from numerous information sources to produce an overall precise description, which can help with effective decision-making, prediction, and categorization, etc. In order to find the objects that are different from the expected ones after fusion, i.e., anomalies, or outliers, an MSIF model is put forward for outlier detection. First, the concept of information set (ISet) is developed, which is a collection of the sum of the products of information source values (ISVs) and the corresponding information gains (Gaussian membership degrees). Moreover, it is possible to capture the uncertainty in the information gains itself, besides that in the ISVs. Then, on the basis of the ISet, Shannon source transform and Shannon inverse source transform of ISVs are presented, and their sum is taken as the total uncertainty measure (TUM) of ISVs. Using TUM-based minimal measure fusion strategy, a multi-source information system can be fused into a single-source information system. Further, in the framework of a single-source information system, the Gaussian kernel function is utilized to map the newly fused data to a fuzzy approximation space, and a novel fuzzy knowledge measure (FKM) is proposed. Several metrics are derived on the basis of FKM to describe the outlier degree of objects after fusion. Finally, the FKM-based outlier factor is integrated to implement outlier detection, and the relevant FKMbased outlier detection algorithm (FKMOD) is designed. The experimental results help quantify the performance of the FKMOD. © 2022, The Authors. All rights reserved.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Modality Decoupling is All You Need: A Simple Solution for Unsupervised Hyperspectral Image Fusion

arXiv

引用

arXiv 2024年

作者： Du, Songcheng Zou, Yang Wang, Zixu Li, Xingyuan Li, Ying Shen, Qiang School of Computer Science Northwestern Polytechnical University China School of Software Technology Dalian University of Technology China Institute of Mathematics Physics and Computer Science Aberystwyth University United Kingdom The National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Northwestern Polytechnical University China

Hyperspectral Image Fusion (HIF) aims to fuse low-resolution hyperspectral images (LR-HSIs) and high-resolution multispectral images (HR-MSIs) to reconstruct high spatial and high spectral resolution images. Current methods typically apply direct fusion from the two modalities without valid supervision, failing to fully perceive the deep modality-complementary information and hence, resulting in a superficial understanding of inter-modality connections. To bridge this gap, we propose a simple and effective solution for unsupervised HIF with an assumption that modality decoupling is essential for HIF. We introduce the modality clustering loss that ensures clear guidance of the modality, decoupling towards modality-shared features while steering clear of modality-complementary ones. Also, we propose an end-to-end Modality-Decoupled Spatial-Spectral Fusion (MossFuse) framework that decouples shared and complementary information across modalities and aggregates a concise representation of the LR-HSI and HR-MSI to reduce the modality redundancy. Systematic experiments over multiple datasets demonstrate that our simple and effective approach consistently outperforms the existing HIF methods while requiring considerably fewer parameters with reduced inference time. Copyright © 2024, The Authors. All rights reserved.

关键词： Spectral resolution

来源：评论

学校读者我要写书评

暂无评论

A Survey of Stochastic Computing in Energy-Efficient DNNs On-Edge

A Survey of Stochastic Computing in Energy-Efficient DNNs On...

引用

IEEE International Conference on big data and Cloud Computing (BdCloud)

作者： Danghui Wang Zhaoqing Wang Linfan Yu Ying Wu Jiaqi Yang Kuizhi Mei Jihe Wang Northwestern Polytechnical University National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Xi'an China Northwestern Polytechnical University Engineering Research Center of Embedded System Integration Ministry of Education Xi'an China Faculty of Electronic and Information Engineering Xi'an Jiaotong University Xi'an China

In recent years, "edge intelligent computing power deployment" has become a key and difficult problem in key areas such as system structure and artificial intelligence. Some independent decision-making scenario requires the edge devices to have the ability to handle high energy efficient and high throughput tasks. However, restricted by the traditional accurate computing mode and memory-computation separation structure, the edge devices often fail to provide the computing power guarantee of high throughput and high energy efficiency, which seriously hinders the edge intelligent deployment. This paper summarizes the new computing model integrating memory and computation of deploying stochastic circuits around memory, and constructs an edge intelligent system taking stochastic computing as a core from three levels of microstructure of circuit, architecture of near-memory stochastic computing and system-level software/hardware cooptimization. It strives to break through the power consumption and performant bottleneck of traditional computing model, and greatly improves the deploying ability of complex intelligent computing on edge equipment.

关键词： Power demand Computational modeling Architecture Stochastic processes Computer architecture Throughput Energy efficiency

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

The Incoming Influenza Season—China,the United Kingdom,and the United States,2021–2022

引用

China CDC weekly 2021年第49期3卷 1039-1045页

作者： Shasha Han Ting Zhang Yan Lyu Shengjie Lai Peixi Dai Jiandong Zheng Weizhong Yang Xiaohua Zhou Luzhao Feng Beijing International Center for Mathematical Research Peking UniversityBeijingChina Harvard Medical School Harvard UniversityBostonMAUSA School of Population Medicine and Public Health Chinese Academy of Medical Sciences&Peking Union Medical CollegeBeijingChina Academy for Advanced Interdisciplinary Studies Peking UniversityBeijingChina WorldPop School of Geography and Environmental ScienceUniversity of SouthamptonSouthamptonUK Division for Infectious Diseases Chinese Center for Disease Control and PreventionBeijingChina Department of Biostatistics School of Public HealthPeking UniversityBeijingChina National Engineering Laboratory of Big Data Analysis and Applied Technology Peking UniversityBeijingChina.

Introduction:Seasonal influenza activity has declined globally since the widespread of severe acute respiratory syndrome coronavirus 2(SARS-CoV-2)*** has been scarce information to understand the future dynamics of influenza—and under different hypothesis on relaxation of nonpharmaceutical interventions(NPIs)in particular—after the disruptions to seasonal ***:We collected data from public sources in China,the United Kingdom,and the United States,and forecasted the influenza dynamics in the incoming 2021–2022 season under different *** considered Northern China and Southern China separately,due to the sharp difference in the patterns of seasonal *** the United Kingdom,data were collected for England ***:Compared to the epidemics in 2017–2019,longer and blunter influenza outbreaks could occur should NPIs be fully lifted,with percent positivity varying from 10.5 to 18.6 in the studying *** rebounds would be smaller if the maskwearing intervention continued or the international mobility stayed low,but sharper if the mask-wearing intervention was lifted in the middle of influenza ***,influenza activity could stay low under a much less stringent mask-wearing intervention coordinated with influenza ***:The results added to our understandings of future influenza dynamics after the global decline during the coronavirus disease 2019(COVID-19)*** light of the uncertainty on the incoming circulation strains and the relatively low negative impacts of mask wearing on society,our findings suggested that wearing mask could be considered as an accompanying mitigation measure in influenza prevention and control,especially for seasons after long periods of low-exposure to influenza *** influenza activity declines globally during the coronavirus disease 2019(COVID-19)pandemic(1–4).For instance,in China,influenza activity,as measured by percentage of submitted specimens testing

关键词： prevention globally continued

来源：评论

学校读者我要写书评

暂无评论

A Planning Model for Flexibility Retrofitting of Coal-Fired Power Plants

A Planning Model for Flexibility Retrofitting of Coal-Fired ...

引用

Power Systems and Electrical technology (PSET), IEEE International Conference on

作者： Xinjiang Chen Jianxiao Wang Zongxian Wang Michael R. Davidson Ruaridh MacDonald Jie Song Guannan He College of Engineering Peking University Beijing China National Engineering Laboratory for Big Data Analysis and Applications Peking University Beijing China Department of Mechanical and Aerospace Engineering University of California San Diego San Diego CA USA MIT Energy Initiative Massachusetts Institute of Technology Cambridge MA USA

ISBN: (数字)9798350353204

ISBN: (纸本)9798350353211

China’s distinctive resource endowment, characterized by abundant coal, limited oil, and scarce gas, shapes the long-term development focus on coal power. However, the requirement for stable combustion imposes limitations on the deep peak-shaving flexibility of coal power. While previous studies have explored the technical feasibility of deep peak shaving for coal power, there is a scarcity of research addressing the delicate balance between the costs of flexibility retrofitting and the benefits of promoting renewable energy integration in power system. To this end, in this paper, we develop an optimal planning technology for the flexibility retrofitting of coal plants. The proposed technology employs a capacity expansion and dispatch model which formulate a flexibility retrofitting plan for coal-fired power plants and a configuration scheme for battery energy storage. Incorporating the proposed model and real-world data from power grid in Yunnan, China, we assess the decarbonization potential of coal fleet flexibility. The experimental results demonstrate that coal fleet flexibility effectively reduces renewable energy curtailment by 3.0% and decreases carbon emissions by more than 6 megatons compared to the coal fleet without retrofitting. Furthermore, the flexibility retrofitting of coal-fired power plants is projected to yield a 12.5% total cost reduction and a 11.1% decrease in coal power generation.

关键词： Renewable energy sources Costs Coal Carbon dioxide Low carbon economy Planning Batteries Spatiotemporal phenomena Power generation Capacity planning

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：