检索结果-内蒙古大学图书馆

ResDO-UNet: A deep residual network for accurate retinal vessel segmentation from fundus images

BIOMEDICAL SIGNAL PROCESSING AND control 2023年第Part1期79卷 000-000页

作者： Liu, Yanhong Shen, Ji Yang, Lei Bian, Guibin Yu, Hongnian Zhengzhou Univ Sch Elect & Informat Engn Zhengzhou 450001 Henan Peoples R China Robot Percept & Control Engn Lab Henan Prov Zhengzhou 450001 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Edinburgh Napier Univ Built Environm Edinburgh EH10 5DT Scotland

For the clinical diagnosis, it is essential to obtain accurate morphology data of retinal blood vessels from patients, and the morphology of retinal blood vessels can well help doctors to judge the patient's condition and give targeted therapeutic measures. Conventional manual retinal blood vessel segmentation by the doctors from the fundus images is time-consuming and laborious, while it also requires the rich doctor's expertise. With the strong context feature expression ability of deep convolutional neural networks (DCNN), it has shown a promising performance on retinal blood vessel segmentation, specially U-shape network (U-Net) and its variant. However, due to the information loss issue caused by multiple pooling operations and insufficient process issue of local context features by skip connections, most of segmentation methods still exist a certain shortcoming on accurate fine vessel detection. To address this issue, based on the encoder-decoder framework, a novel retinal vessel segmentation network, called ResDO-UNet, is proposed to provide an automatic and end-to-end detection scheme from fundus images. To enhance feature extraction capabilities, combined with depth-wise over-parameterized convolutional layer (DO-conv), a residual DO-conv (ResDO-conv) network is proposed to act as the backbone network to acquire strong context features. In addition, to reduce the effect of information loss caused by multiple pooling operations, taking advantages of max pooling and average pooling layers, a pooling fusion block (PFB) is proposed to realize nonlinear fusion pooling. Meanwhile, faced with insufficient process of local context features by skip connections, an attention fusion block (AFB) is proposed to realize effective multi-scale feature expression. Combined with the three public available data sets on retinal vessel segmentation, including DRIVE, STARE and CHASE_DB1, the proposed segmentation network could reach a state-of-the-art detection performance compa

关键词： Retinal vessels segmentation Deep learning U-Net network Residual DO-conv network

来源：评论

学校读者我要写书评

暂无评论

China's 12-Year Quest of Autonomous Vehicular Intelligence: The Intelligent Vehicles Future Challenge Program

引用

IEEE INTELLIGENT TRANSPORTATION systems MAGAZINE 2021年第2期13卷 6-19页

作者： Wang, Fei-Yue Zheng, Nan-Ning Li, Li Xin, Jingmin Wang, Xiao Xu, Linhai Tian, Bin Wu, Guozheng Zhang, Zhaotian Wang, Chenghong Chen, Long Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Xi An Jiao Tong Univ Inst Artificial Intelligence & Robot Xian 710049 Shaanxi Peoples R China Tsinghua Univ BNRist Dept Automat Beijing 100084 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Qingdao Acad Intelligent Ind Beijing 100190 Peoples R China Natl Nat Sci Fdn China Dept Informat Sci Beijing 100085 Peoples R China Chinese Assoc Automat Beijing 100190 Peoples R China Sun Yat Sen Univ Sch Comp Sci & Engn Guangzhou 510006 Guangdong Peoples R China

In this article, we introduce the Intelligent Vehicles Future Challenge of China (IVFC), which has lasted 12 years. Some key features of the tests and a few interesting findings of IVFC are selected and presented. Through the IVFCs held between 2009 and 2020, we gradually established a set of theories, methods, and tools to collect tests' data and efficiently evaluate the performance of autonomous vehicles so that we could learn how to improve both the autonomous vehicles and the testing system itself.

关键词： Task analysis Autonomous vehicles Testing Roads Sensors Automation control systems

来源：评论

学校读者我要写书评

暂无评论

Near-infrared fluorescence imaging-guided lymphatic mapping in thoracic esophageal cancer surgery

引用

SURGICAL ENDOSCOPY AND OTHER INTERVENTIONAL TECHNIQUES 2022年第6期36卷 3994-4003页

作者： Wang, Xiaojin Hu, Yi Wu, Xiangwen Liang, Mingzhu Hu, Zhenhua Gan, Xiangfeng Li, Dan Cao, Qingdong Shan, Hong Sun Yat Sen Univ Dept Thorac Surg Affiliated Hosp 8 Zhuhai Peoples R China Sun Yat Sen Univ Affiliated Hosp 8 Res Ctr Mol Imaging Guangdong Prov Key Lab Biomed Imaging & Guangdong 52 Meihua E Rd Zhuhai 519000 Peoples R China Sun Yat Sen Univ Dept Thorac Surg Ctr Canc Guangzhou Peoples R China Sun Yat Sen Univ Ctr Canc State Key Lab Oncol South China Collaborat Innovat Ctr Canc Med Guangzhou Peoples R China Guangdong Esophageal Canc Inst GECI Guangzhou Peoples R China Chinese Acad Sci CAS Key Lab Mol Imaging State Key Lab Management & Control Complex Syst Beijing Key Lab Mol ImagingInst Automat Beijing Peoples R China Sun Yat Sen Univ Fifth Affiliated Hosp Ctr Intervent Med Zhuhai Peoples R China

Purpose Identifying the lymphatic drainage pathway is important for accurate lymph node (LN) dissection in esophageal cancer (EC). This study aimed to assess lymphatic drainage mapping in thoracic EC using near-infrared fluorescent (NIRF) imaging with indocyanine green (ICG) and identify its feasibility for intraoperative LN drainage visualization and dissection. Methods From November 2019 to August 2020, esophagectomy was performed using intraoperative NIRF navigation with ICG injected into the esophageal submucosa by endoscopy. All LNs were divided into four groups according to the NIRF status and presence of metastasis: -NIRF+LN+, -NIRF+LN-, -NIRF-LN+, and -NIRF-LN-. Results Regional LNs were detected in all 84 enrolled patients with thoracic EC. A total of 2164 LNs were removed, and the mean number of dissected LNs was 25.68 +/- 12.00. -NIRF+ LNs were observed in all patients and distributed at 19 LN stations, which formed lymphatic drainage maps. The top five LN stations of -NIRF+ probability in upper thoracic EC were No. 7, 106ecR, 107, 1, and 106recL;in middle thoracic EC, they were No. 107, 7, 110, 1, and 105;and in lower thoracic EC, they were No. 107, 7, 110, 106recR, and 1. There were no cases of ICG-related adverse events or chylothorax. The 30-day mortality rate was 0%. Major complications included anastomotic fistula (7.14%), pneumonia (4.76%), pleural effusion (13.10%), atelectasis (3.75%), hoarseness (8.33%), and arrhythmia (4.76%). Conclusion Regional LN mapping of thoracic EC was performed using ICG/NIRF imaging, which showed different preferred LN drainage stations in various anatomical locations of the thoracic esophagus. ICG/NIRF imaging is feasible for intraoperative LN drainage visualization and dissection.

关键词： Esophageal cancer Intraoperative navigation Indocyanine green Near-infrared fluorescence imaging Lymphatic mapping

来源：评论

学校读者我要写书评

暂无评论

A Unified Weight Initialization Paradigm for Tensorial Convolutional Neural Networks 39

A Unified Weight Initialization Paradigm for Tensorial Convo...

引用

39th International Conference on Machine Learning (ICML)

作者： Pan, Yu Su, Zeyong Liu, Ao Wang, Jingquan Li, Nannan Xu, Zenglin Harbin Inst Technol Shenzhen Shenzhen Peoples R China Univ Elect Sci & Technol China Chengdu Peoples R China Tokyo Inst Technol Tokyo Japan Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing Peoples R China Pengcheng Lab Shenzhen Peoples R China

Tensorial Convolutional Neural Networks (TCNNs) have attracted much research attention for their power in reducing model parameters or enhancing the generalization ability. However, exploration of TCNNs is hindered even from weight initialization methods. To be specific, general initialization methods, such as Xavier or Kaiming initialization, usually fail to generate appropriate weights for TCNNs. Meanwhile, although there are ad-hoc approaches for specific architectures (e.g., Tensor Ring Nets), they are not applicable to TCNNs with other tensor decomposition methods (e.g., CP or Tucker decomposition). To address this problem, we propose a universal weight initialization paradigm, which generalizes Xavier and Kaiming methods and can be widely applicable to arbitrary TCNNs. Specifically, we first present the Reproducing Transformation to convert the backward process in TCNNs to an equivalent convolution process. Then, based on the convolution operators in the forward and backward processes, we build a unified paradigm to control the variance of features and gradients in TCNNs. Thus, we can derive fan-in and fan-out initialization for various TCNNs. We demonstrate that our paradigm can stabilize the training of TCNNs, leading to faster convergence and better results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fusion of heterogeneous attention mechanisms in multi-view convolutional neural network for text classification

引用

INFORMATION SCIENCES 2021年 548卷 295-312页

作者： Liang, Yunji Li, Huihui Guo, Bin Yu, Zhiwen Zheng, Xiaolong Samtani, Sagar Zeng, Daniel D. Northwestern Polytech Univ Sch Comp Sci Xian Shaanxi Peoples R China Chinese Acad Sci State Key Lab Management & Control Complex Syst Inst Automat Beijing Peoples R China Indiana Univ Kelley Sch Business Operat & Decis Technol Dept Bloomington IN 47405 USA Univ Chinese Acad Sci Beijing Peoples R China

The rapid proliferation of user generated content has given rise to large volumes of text corpora. Increasingly, scholars, researchers, and organizations employ text classification to mine novel insights for high-impact applications. Despite their prevalence, conventional text classification methods rely on labor-intensive feature engineering efforts that are task specific, omit long-term relationships, and are not suitable for the rapidly evolving domains. While an increasing body of deep learning and attention mechanism literature aim to address these issues, extant methods often represent text as a single view and omit multiple sets of features at varying levels of granularity. Recognizing that these issues often result in performance degradations, we propose a novel Spatial View Attention Convolutional Neural Network (SVA-CNN). SVA-CNN leverages an innovative and carefully designed set of multi-view representation learning, a combination of heterogeneous attention mechanisms and CNN-based operations to automatically extract and weight multiple granularities and fine-grained representations. Rigorously evaluating SVA-CNN against prevailing text classification methods on five large-scale benchmark datasets indicates its ability to outperform extant deep learning based classification methods in both performance and training time for document classification, sentiment analysis, and thematic identification applications. To facilitate model reproducibility and extensions, SVA-CNN's source code is also available via GitHub. (c) 2020 Elsevier Inc. All rights reserved.

关键词： View attention Spatial attention Multi-view representation Series and parallel connection Conventional neural network Text classification

来源：评论

学校读者我要写书评

暂无评论

Parallel Surfaces: Service-Oriented V2X Communications for Autonomous Vehicles

IEEE TRANSACTIONS ON INTELLIGENT VEHICLES

引用

IEEE TRANSACTIONS ON INTELLIGENT VEHICLES 2023年第11期8卷 4536-4545页

作者： Han, Shuangshuang Wang, Fei-Yue Luo, Guiyang Li, Lefei Qu, Fengzhong Univ Sci & Technol Beijing Sch Comp & Commun Engn Beijing 100083 Peoples R China Beijing Huairou Acad Parallel Sensing Beijing 101400 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Beijing Univ Posts & Telecommun Comp Sci Dept Beijing 100876 Peoples R China Tsinghua Univ Dept Ind Engn Beijing 100084 Peoples R China Key Lab Ocean Observat Imaging Testbed Zhejiang P Zhoushan 316000 Peoples R China Zhejiang Univ Engn Res Ctr Ocean Sensing Technol & Equipment Minist Educ Zhoushan 316000 Peoples R China Zhejiang Univ Hainan Inst Sanya 572000 Peoples R China Zhejiang Univ Ocean Coll Zhoushan 316000 Peoples R China

The application of reconfigurable intelligent surfacess (RIS) in the Internet of Vehicles (IoV) is rapidly progressing, with a focus on intelligent signal manipulation, adaptive channel estimation, and real-time reconfiguration to optimize communication performance. While RIS technology holds significant potential for improving connectivity in IoV and vehicle settings, its fixed configuration falls short in meeting the dynamic demands in IoV. To address the diverse requirements of IoV services, including stringent safety norms, societal acceptance, and cost efficiency, this article proposes a parallel surfaces system to facilitate service-oriented V2X communications for autonomous vehicles. By harnessing artificial models of the physical RIS-assisted IoV system, conducting extensive computational experiments, and parallel execution, the proposed system enables real-time monitoring, predictive analysis, and optimization. Parallel intelligence empowers efficient and adaptable channel estimation, configuration, and energy management, thereby establishing a more intelligent and secure RIS-assisted IoV infrastructure. In addition, the parallel surfaces system encompasses descriptive, predictive, and prescriptive intelligence in IoV for addressing coverage gaps, enabling hotspot offloading, facilitating multiple antenna signal transmission, and enhancing high-precision positioning.

关键词： Parallel intelligence reconfigurable intelligent surfaces V2X autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Online Semisupervised Active Classification for Multiview PolSAR Data

引用

IEEE TRANSACTIONS ON CYBERNETICS 2022年第6期52卷 4415-4429页

作者： Nie, Xiangli Fan, Mingyu Huang, Xiayuan Yang, Wenjing Zhang, Bo Ma, Xiaoshuang Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Chinese Acad Sci Beijing Key Lab Res & Applicat Robot Intelligence Beijing 100190 Peoples R China Wenzhou Univ Coll Comp Sci & Artificial Intelligence Wenzhou 325035 Peoples R China Natl Univ Def Technol State Key Lab High Performance Comp Changsha 410073 Peoples R China Chinese Acad Sci LSEC AMSS Beijing 100190 Peoples R China Chinese Acad Sci AMSS Inst Appl Math Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Math Sci Beijing 100049 Peoples R China Anhui Univ Informat Mat & Intelligent Sensing Lab Anhui Prov Hefei 230000 Peoples R China Anhui Univ Dept Resources & Environm Engn Hefei 230000 Peoples R China

Polarimetric synthetic aperture radar (PolSAR) data are sequentially acquired and have multiple views obtained from different feature extractors or multiple frequency bands. The fast and accurate classification of PolSAR data in dynamically changing environments is a critical and challenging task. Online learning can handle this task by learning a classifier incrementally from a stream of samples. In this article, we propose an online semisupervised active learning framework for multiview PolSAR data classification, called OSAM. First, a novel online active learning strategy is designed based on the relationships among multiple views and a randomized rule, which allows to only query the labels of some informative incoming samples. Then, in order to utilize both the incoming labeled and unlabeled samples to update the classifiers, a novel online semisupervised learning model is proposed based on co-regularized multiview learning and graph regularization. In addition, the proposed method can deal with the dynamic large-scale multifeature or multifrequency PolSAR data where not only the amount of data but also the number of classes gradually increases in the learning process. Moreover, the mistake bound of the proposed method is derived rigorously. Extensive experiments are conducted on real PolSAR data to evaluate the performance of our algorithm, and the results demonstrate the effectiveness of the proposed method.

关键词： Task analysis Feature extraction Heuristic algorithms Data models Manifolds Semisupervised learning Training Online active learning online multiview learning online semisupervised learning (SSL) polarimetric synthetic aperture radar (PolSAR) data classification

来源：评论

学校读者我要写书评

暂无评论

Building Intelligence Identification System via Large Language Model Watermarking: A Survey and Beyond

arXiv

引用

arXiv 2024年

作者： Wang, Xuhong Jiang, Haoyu Yu, Yi Yu, Jingru Lin, Yilun Yi, Ping Wang, Yingchun Yu, Qiao Li, Li Wang, Fei-Yue Shanghai Artificial Intelligence Laboratory Shanghai200433 China School of Cyber Science and Engineering Shanghai Jiao Tong University Shanghai200240 China Department of Automation BNRist Tsinghua University Beijing100084 China The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China

Large Language Models (LLMs) are increasingly integrated into diverse industries, posing substantial security risks due to unauthorized replication and misuse. To mitigate these concerns, robust identification mechanisms are widely acknowledged as an effective strategy. Identification systems for LLMs now rely heavily on watermarking technology to manage and protect intellectual property and ensure data security. However, previous studies have primarily concentrated on the basic principles of algorithms and lacked a comprehensive analysis of watermarking theory and practice from the perspective of intelligent identification. To bridge this gap, firstly, we explore how a robust identity recognition system can be effectively implemented and managed within LLMs by various participants using watermarking technology. Secondly, we propose a mathematical framework based on mutual information theory, which systematizes the identification process to achieve more precise and customized watermarking. Additionally, we present a comprehensive evaluation of performance metrics for LLM watermarking, reflecting participant preferences and advancing discussions on its identification applications. Lastly, we outline the existing challenges in current watermarking technologies and theoretical frameworks, and provide directional guidance to address these challenges. Our systematic classification and detailed exposition aim to enhance the comparison and evaluation of various methods, fostering further research and development toward a transparent, secure, and equitable LLM ecosystem. Copyright © 2024, The Authors. All rights reserved.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

An End-to-End Recommendation System for Urban Traffic controls and management Under a Parallel Learning Framework

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION systems 2021年第3期22卷 1616-1626页

作者： Jin, Junchen Guo, Haifeng Xu, Jia Wang, Xiao Wang, Fei-Yue Enjoyor Co Ltd Hangzhou 310030 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Zhejiang Univ Technol Coll Informat Engn Hangzhou 310013 Peoples R China Zhejiang Univ Coll Civil Engn & Architecture Hangzhou 310058 Peoples R China

A paradigm shift towards agile and adaptive traffic signal control empowered with the massive growth of Big Data and Internet of Things (IoT) technologies is emerging rapidly for Intelligent Transportation systems. Generally, an adaptive signal control system fine-tunes signal timing parameters based on pre-defined control hyperparameters using instantaneous traffic detection information. Once traffic pattern changes, those hyperparameters (e.g., maximum and minimum green times) need to be adjusted according to the evolution of traffic dynamics over a very short-term period. Such adjustment processes are usually conducted by professional and experienced traffic engineers. Here we present a human-in-the-loop parallel learning framework and its utilization in an end-to-end recommendation system that mimics and enhances professional signal control engineers' behaviors. The system has been deployed into a real-world application for an extended period in Hangzhou, China, where signal control hyperparameters are recommended based on large-scale multidimensional traffic datasets. Experimental evaluations demonstrate significant improvements in traffic efficiency through the use of our signal recommendation system.

关键词： control systems Urban areas Timing Adaptive systems Real-time systems Recurrent neural networks Process control Intelligent traffic control traffic signal control parallel learning recommendation systems deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Remote Operation with Haptic Force and Virtual Proxy for an Underwater Vehicle-Manipulator System 10

Remote Operation with Haptic Force and Virtual Proxy for an ...

引用

10th IEEE Data Driven control and Learning systems Conference, DDCLS 2021

作者： Ma, Jin Wang, Yu Wang, Rui Wang, Shuo University of Chinese Academy of Sciences Beijing100049 China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China Cas Center for Excellence in Brain Science and Intelligence Technology Shanghai200031 China

ISBN: (纸本)9781665424233

This paper aims to investigate a smooth teleoperation method for the underwater vehicle-manipulator system. First, a coordinated mapping control method for the vehicle is presented. The haptic force is considered to help assist the operation. Then, two mapping modes are used to teleoperate the manipulator: when the end-effector needs to move in a large area, two virtual points and a spring-damping system are implemented to filter the operator's hand jitter and limit the manipulator's speed;when the end-effector needs to move in a small area, a position increment control method with a small proportional coefficient is used to improve the precision. Finally, the simulation demonstrates the effectiveness of the proposed teleoperation method. © 2021 IEEE.

关键词： Manipulators

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：