检索结果-内蒙古大学图书馆

Dynamic graph transformer network via dual-view connectivity for autism spectrum disorder identification

computers in Biology and Medicine 2024年 174卷 108415-108415页

作者： Guan, Zihao Yu, Jiaming Shi, Zhenshan Liu, Xiumei Yu, Renping Lai, Taotao Yang, Changcai Dong, Heng Chen, Riqing Wei, Lifang College of Computer and Information Science Fujian Agriculture and Forestry University Fuzhou350002 China Digital Fujian Research Institute of Big Data for Agriculture and Forestry Fujian Agriculture and Forestry University Fuzhou350002 China Department of Radiology The First Affiliated Hospital of Fujian Medical University Fuzhou350002 China Developmental and Behavior Pediatrics Department Fujian Children's Hospital - Fujian Branch of Shanghai Children's Medical Center Fuzhou350002 China College of Clinical Medicine for Obstetrics Gynecology and Pediatrics Fujian Medical University Fuzhou350012 China School of Electrical and Information Engineering Zhengzhou University Zhengzhou450001 China College of Computer and Control Engineering Minjiang University Fuzhou350108 China

Autism Spectrum Disorder (ASD) is a neurodevelopmental disorder that requires objective and accurate identification methods for effective early intervention. Previous population-based methods via functional connectivity (FC) analysis ignore the differences between positive and negative FCs, which provide the potential information complementarity. And they also require additional information to construct a pre-defined graph. Meanwhile, two challenging demand attentions are the imbalance of performance caused by the class distribution and the inherent heterogeneity of multi-site data. In this paper, we propose a novel dynamic graph Transformer network based on dual-view connectivity for ASD Identification. It is based on the Autoencoders, which regard the input feature as individual feature and without any inductive bias. First, a dual-view feature extractor is designed to extract individual and complementary information from positive and negative connectivity. Then Graph Transformer network is innovated with a hot plugging K-Nearest Neighbor (KNN) algorithm module which constructs a dynamic population graph without any additional information. Additionally, we introduce the PolyLoss function and the Vrex method to address the class imbalance and improve the model's generalizability. The evaluation experiment on 1102 subjects from the ABIDE I dataset demonstrates our method can achieve superior performance over several state-of-the-art methods and satisfying generalizability for ASD identification. © 2024 Elsevier Ltd

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Parallel Planning:A New Motion Planning Framework for Autonomous Driving

引用

IEEE/CAA Journal of Automatica Sinica 2019年第1期6卷 236-246页

作者： Long Chen Xuemin Hu Wei Tian Hong Wang Dongpu Cao Fei-Yue Wang IEEE School of Data and Computer Science Sun Yat-sen University the School of Computer Science and Information Engineering Hubei University Institute of Measurement and Control Systems Karlsruhe Institute of Technology Department of Mechanical and Mechatronics Engineering University of Waterloo the State Key Laboratory of Management and Control for Complex Systems.Institute of Automation Chinese Academy of Sciences the Research Center for Military Computational Experiments and Parallel Systems Technology National University of Defense Technology

Motion planning is one of the most significant technologies for autonomous driving. To make motion planning models able to learn from the environment and to deal with emergency situations, a new motion planning framework called as"parallel planning" is proposed in this paper. In order to generate sufficient and various training samples, artificial traffic scenes are firstly constructed based on the knowledge from the reality.A deep planning model which combines a convolutional neural network(CNN) with the Long Short-Term Memory module(LSTM) is developed to make planning decisions in an end-toend mode. This model can learn from both real and artificial traffic scenes and imitate the driving style of human ***, a parallel deep reinforcement learning approach is also presented to improve the robustness of planning model and reduce the error rate. To handle emergency situations, a hybrid generative model including a variational auto-encoder(VAE) and a generative adversarial network(GAN) is utilized to learn from virtual emergencies generated in artificial traffic scenes. While an autonomous vehicle is moving, the hybrid generative model generates multiple video clips in parallel, which correspond to different potential emergency scenarios. Simultaneously, the deep planning model makes planning decisions for both virtual and current real scenes. The final planning decision is determined by analysis of real observations. Leveraging the parallel planning approach, the planner is able to make rational decisions without heavy calculation burden when an emergency occurs.

关键词： Autonomous driving artificial traffic scene deep learning emergencies motion planning parallel planning

来源：评论

学校读者我要写书评

暂无评论

Investigation of Conditions for Non-degeneracy and Normality in control Problems with Equality and Inequality State Constraints

引用

IFAC-PapersOnLine 2020年第2期53卷 6869-6874页

作者： Aram Arutyunov Dmitry Karamzin Fernando L. Pereira Institute of Control Sciences of the Russian Academy of Science Moscow Russia Federal Research Center “Computer Science and Control” of the Russian Academy of Science Moscow Russia Research Center for Systems and Technologies (SYSTEC) Electrical and Computer Engineering Department Faculty of Engineering University of Porto 4200-465 Portugal

This work aims to investigate conditions for normality and non-degeneracy of the maximum principle for general state-constrained optimal control problems in which the state constraints are given by equalities and inequalities. Non-degeneracy is proved under a regularity condition formulated in terms of the limiting normal cone to the feasible control set. The same regularity condition implies normality of the maximum principle if one of the end-points is free.

关键词： Optimal control maximum principle state constraints

来源：评论

学校读者我要写书评

暂无评论

SSD-KD: A Self-supervised Diverse Knowledge Distillation Method for Lightweight Skin Lesion Classification Using Dermoscopic Images

arXiv

引用

arXiv 2022年

作者： Wang, Yongwei Wang, Yuheng Lee, Tim K. Miao, Chunyan Wang, Z. Jane Joint NTU-WeBank Research Center on Fintech Nanyang Technological University Singapore Singapore Department of Electrical and Computer Engineering University of British Columbia VancouverBC Canada School of Biomedical Engineering University of British Columbia VancouverBC Canada Department of Dermatology and Skin Science University of British Columbia VancouverBC Canada Photomedicine Institute Vancouver Coast Health Research Institute VancouverBC Canada Cancer Control Research Program Bc Cancer VancouverBC Canada School of Computer Science and Engineering Nanyang Technological University Singapore Singapore

Skin cancer is one of the most common types of malignancy, affecting a large population and causing a heavy economic burdenworldwide. Over the last fewyears, computer-aided diagnosis has been rapidly developed and make great progress in healthcare and medical practices due to the advances in artificial intelligence, particularly with the adoption of convolutional neural networks. However, most studies in skin cancer detection keep pursuing high prediction accuracies without considering the limitation of computing resources on portable devices. In this case, the knowledge distillation (KD) method has been proven as an efficient tool to help improve the adaptability of lightweight models under limited resources, meanwhile keeping a high-level representation capability. To bridge the gap, this study specifically proposes a novel method, termed SSD-KD, that unifies diverse knowledge into a generic KD framework for skin diseases classification. Our method models an intra-instance relational feature representation and integrates it with existing KD research. A dual relational knowledge distillation architecture is self-supervisedly trained while the weighted softened outputs are also exploited to enable the student model to capture richer knowledge from the teacher model. To demonstrate the effectiveness of our method, we conduct experiments on ISIC 2019, a large-scale open-accessed benchmark of skin diseases dermoscopic images. Experiments show that our distilled lightweight model can achieve an accuracy as high as 85% for the classification tasks of 8 different skin diseases with minimal parameters and computing requirements. Ablation studies confirm the effectiveness of our intra- and inter-instance relational knowledge integration strategy. Compared with state-of-the-art knowledge distillation techniques, the proposed method demonstrates improved performances. To the best of our knowledge, this is the first deep knowledge distillation application for multi-diseases cl

关键词： Dermatology

来源：评论

学校读者我要写书评

暂无评论

Insights into Polycrystalline Microstructure of Blood Films with 3D Mueller Matrix Imaging Approach

arXiv

引用

arXiv 2024年

作者： Ushenko, Volodimyr A. Dubolazov, Alexander V. Ushenko, Yuriy A. Soltys, Irina V. Gorsky, Mykhailo P. Gantyuk, Vyacheslav K. Sdobnov, Anton Bykov, Alexander Trifonyuk, Liliya Doronin, Alexander Ushenko, Alexander G. Yan, Wenjun Meglinski, Igor Optics and Publishing Department Chernivtsi National University 2 Kotsiubynskyi Str. Chernivtsi58012 Ukraine Optoelectronics and Measurement Techniques University of Oulu P.O. Box 4500 OuluFI-90014 Finland Rivne State Medical Center 78 Kyivska Str. Rivne33007 Ukraine School of Engineering and Computer Science Victoria University ofWellington Wellington6140 New Zealand College of Electrical Engineering Taizhou Research Institute Zhejiang University Hangzhou310027 China College of Engineering and Physical Sciences Aston University BirminghamB4 7ET United Kingdom

We introduce a 3D Mueller Matrix (MM) image reconstruction technique using digital holographic approach for the layer-by-layer profiling thin films with polycrystalline structures, like dehydrated blood smears. The proposed method effectively extracts optical anisotropy parameters for a detailed quantitative analysis. The investigation revealed the method’s sensitivity to subtle changes in optical anisotropy properties resulting from alterations in the quaternary and tertiary structures of blood proteins, leading to disturbances in crystallization structures at the macro level at the very early stage of a disease. Spatial distributions of linear and circular birefringence and dichroism are analyzed in partially depolarizing polycrystalline blood films obtained from healthy tissues and cancerous prostate tissues at various stages of adenocarcinoma. Changes in the values of the 1st to 4th order statistical moments, characterizing the distributions of optical anisotropy in different "phase" sections of the smear volumes, are observed and quantified. Comparative analysis of optical anisotropy distributions from healthy patients highlighted the 3rd and 4th order statistical moments for linear and circular birefringence and dichroism as the most promising for diagnostic purposes. We achieved an excellent accuracy (> 90%) for early cancer diagnosis and differentiation of its stages, demonstrating the technique’s significant potential for rapid and accurate definitive cancer diagnosis compared to existing screening approaches. © 2024, CC BY.

关键词： Histology

来源：评论

学校读者我要写书评

暂无评论

Efficient Pyramid Channel Attention Network for Pathological Myopia Recognition

arXiv

引用

arXiv 2023年

作者： Zhang, Xiaoqing Zhao, Jilu Li, Yan Wu, Hao Zhou, Xiangtian Liu, Jiang Research Institute of Trustworthy Autonomous Systems Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China Center for High Performance Computing Shenzhen Key Laboratory of Intelligent Bioinformatics Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China National Clinical Research Center for Ocular Diseases Eye Hospital Wenzhou Medical University Wenzhou325027 China State Key Laboratory of Ophthalmology Optometry and Visual Science Eye Hospital Wenzhou Medical University Wenzhou325027 China Research Unit of Myopia Basic Research and Clinical Prevention and Control Chinese Academy of Medical Sciences Wenzhou325027 China Singapore Eye Research Institute 169856 Singapore

Pathological myopia (PM) is the leading ocular disease for impaired vision worldwide. Clinically, the characteristic of pathology distribution in PM is global-local on the fundus image, which plays a significant role in assisting clinicians in diagnosing PM. However, most existing deep neural networks focused on designing complex architectures but rarely explored the pathology distribution prior of PM. To tackle this issue, we propose an efficient pyramid channel attention (EPCA) module, which fully leverages the potential of the clinical pathology prior of PM with pyramid pooling and multi-scale context fusion. Then, we construct EPCA-Net for automatic PM recognition based on fundus images by stacking a sequence of EPCA modules. Moreover, motivated by the recent pretraining-and-finetuning paradigm, we attempt to adapt pre-trained natural image models for PM recognition by freezing them and treating the EPCA and other attention modules as adapters. In addition, we construct a PM recognition benchmark termed PM-fundus by collecting fundus images of PM from publicly available datasets. The comprehensive experiments demonstrate the superiority of EPCA-Net over state-of-the-art methods in the PM recognition task. For example, EPCA-Net achieves 97.56% accuracy and outperforms ViT by 2.85% accuracy on the PM-fundus dataset. The results also show that our method based on the pretraining-and-finetuning paradigm achieves competitive performance through comparisons to part of previous methods based on traditional fine-tuning paradigm with fewer tunable parameters, which has the potential to leverage more natural image foundation models to address the PM recognition task in limited medical data regime. Copyright © 2023, The Authors. All rights reserved.

关键词： Pathology

来源：评论

学校读者我要写书评

暂无评论

Review of Approaches to the Use of UAVs, Remote Sensing and GIS in Humanitarian Demining: Ukrainian Case

SSRN

引用

SSRN 2024年

作者： Hutsul, Taras Khobzei, Mykola Tkach, Vladyslav Krulikovskyi, Oleh Moisiuk, Oleksandr Ivashko, Victor Samila, Andrii Department of Geomatics Land and Agromanagement Yuriy Fedkovych Chernivtsi National University Kotsyubynsky 2 Chernivtsi58002 Ukraine Department of Radio Engineering and Information Security Yuriy Fedkovych Chernivtsi National University Kotsyubynsky 2 Chernivtsi58002 Ukraine Department of Computer Sciences Yuriy Fedkovych Chernivtsi National University Kotsyubynsky 2 Chernivtsi58002 Ukraine Integrated Center for Research Development and Innovation in Advanced Materials Nanotechnologies and Distributed Systems for Fabrication and Control Stefan cel Mare University of Suceava Street University 13 Suceava720229 Romania Faculty of Electrical Engineering and Computer Science Stefan cel Mare University of Suceava Street University 13 Suceava720229 Romania

The history of the use of mines dates back almost two centuries. The geography of their use and the associated social harm have made them, without exaggeration, a global problem. At the same time, searches were underway for safe methods of their neutralization using various technical means. In so doing, until now, none of the existing methods provides a 100% guarantee of cleaning the territory, which determines the purpose of finding innovative methods and the possibility of combining them with existing ones. Unmanned aerial vehicles (UAVs) are becoming a real modern breakthrough in the field of intellectual achievements. Obtaining optimal results when solving a wide range of different problems, together with the development of composite materials, software, and the latest navigation equipment, make the tasks assigned to them and the expected results more and more difficult. UAVs allow people not to be in life-threatening conditions, to conduct activities beyond their physiological and psychophysiological abilities. The combination of the ability to collect spatial data during flight in various ranges of remote sensing with the possibility of carrying variants of useful equipment opens up prospects for their use in the field of demining territories. Supplementing UAV technologies with modern information systems for processing and analysis of information (expert systems, machine learning, computational intelligence, distributed artificial intelligence, neural networks, etc.), including spatial (GIS), opens up great prospects in the field of humanitarian demining of territories. © 2024, The Authors. All rights reserved.

关键词： Geographic information systems

来源：评论

学校读者我要写书评

暂无评论

Extended Horizon Predictive control for Software Defined Networked Microgrids

SSRN

引用

SSRN 2024年

作者： Guzmán, Ricardo Pérez Rivera, Marco Araya, Baldomero Gómez, Juan S. Salgueiro, Yamisleydi Restrepo, Carlos Wheeler, Patrick You, Minglei Sumner, Mark Department of Computer Science Faculty of Engineering Universidad de Talca Curicó Maule 3341717 Chile Power Electronics Machines and Control Research Group Faculty of Engineering University of Nottingham NottinghamNG7 2GT United Kingdom Laboratorio de Conversión de Energías y Electrónica de Potencia LCEEP Dirección de Investigación Universidad de Talca Curicó Maule 3341717 Chile Department of Electrical Engineering Faculty of Engineering Universidad de Talca Curicó Maule 3341717 Chile Department of Engineering Sciences The Energy Transformation Center Universidad Andrés Bello Santiago-Chile Santiago de Chile8370035 Chile Department of Industrial Engineering Faculty of Engineering Universidad de Talca Curicó Maule 3341717 Chile

This paper presents a model-based predictive control implementation (FCS-MPC) with extended horizon prediction to address the resiliency problem and voltage/frequency deviations for hierarchical microgrids. The proposed framework integrates Software-Defined Networking (SDN) as a set of microservices, where prediction models enable effective coordination and enhance system reliability by including communication constraints. The control strategy considers the variability of communication latency and packet loss to adjust the shared references based on the secondary control’s spatial and temporal correlation. The system is subjected to four test case scenarios to analyze the impact of communications in distributed generation, plugand-play capabilities, and load fluctuations on the microgrid. The proposed SDN-based framework enables the resolution of slow dynamic responses to parameter variations, by exploiting the advantages of FCS-MPC. The prediction block in the proposed secondary control outperforms traditional communication methods in terms of latency, recovery time, and packet loss among distributed energy resources, improving hierarchical microgrid performance. © 2024, The Authors. All rights reserved.

关键词： Software defined networking

来源：评论

学校读者我要写书评

暂无评论

Towards non-uniform shadow removal using shadow adaptive normalization

引用

Digital Signal Processing 2025年 166卷

作者： Xinjie Li Yang Zhao Yuan Chen Dong Wang Li Cao Xiaoping Liu School of Computer Science and Information Engineering Hefei University of Technology Hefei Anhui 230009 China Engineering Research Center of Safety Critical Industrial Measurement and Control Technology Ministry of Education Hefei Anhui 230009 China School of Internet Anhui University Hefei Anhui 230039 China

Image shadow removal has received increasing attention in recent years. Existing deep learning-based shadow removal methods usually rely on the assumption of globally uniform illumination or employ simplified multiplicative illumination models to estimate parameters related to shadow-free image reconstruction. However, the shading process often contains non-uniform, diverse, and complex shadow patterns, substantially reducing the robustness of current shadow removal techniques and limiting their performance. To address this issue, this paper revisits the traditional shadow degradation model and introduces a pixel-wise adaptive non-uniform illumination model. Building upon this model, a shadow adaptive normalization (SAN) module is designed to estimate the parameter maps of the illumination model and rectify the shadow features within the latent space. The proposed SAN dynamically performs attentive normalization on shadow region features, which can align the statistical distributions of shadow and non-shadow regions. To enhance the efficiency of the SAN module, this paper introduces an intra-module complexity reduction strategy to reduce computational complexity while improving the stability of the training process. In addition, to mitigate the color deviation between paired training data, this paper introduces a Poisson-function-based loss to achieve color robustness. Extensive experiments on image shadow triplet dataset (ISTD), adjusted image shadow triplet dataset (ISTD+), and shadow removal dataset (SRD) validate the superiority of the proposed method over other state-of-the-art (SOTA) approaches.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Coverage Probability Analysis of RIS-Assisted High-Speed Train Communications

arXiv

引用

arXiv 2022年

作者： Liu, Changzhu He, Ruisi Niu, Yong Ai, Bo Han, Zhu Ma, Zhangfeng Gao, Meilin Zhong, Zhangdui Wang, Ning State Key Laboratory of Rail Traffic Control and Safety Beijing Jiaotong University Beijing China Research Center of Networks and Communications Peng Cheng Laboratory Shenzhen China Department of Electrical and Computer Engineering University of Houston HoustonTX77004 United States Beijing National Research Center for Information Science and Technology Tsinghua University China School of Information Engineering Zhengzhou University Zhengzhou450001 China

Reconfigurable intelligent surface (RIS) has received increasing attention due to its capability of extending cell coverage by reflecting signals toward receivers. This paper considers a RIS-assisted high-speed train (HST) communication system to improve the coverage probability. We derive the closed-form expression of coverage probability. Moreover, we analyze impacts of some key system parameters, including transmission power, signal-to-noise ratio threshold, and horizontal distance between base station and RIS. Simulation results verify the efficiency of RIS-assisted HST communications in terms of coverage probability. Copyright © 2022, The Authors. All rights reserved.

关键词： Railroads

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：