检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Zhang, Dengke Tang, Quan Liu, Fagui Mei, Haiqing Chen, C.L. Philip The School of Computer Science and Engineering South China University of Technology Guangzhou510006 China The Department of New Network Pengcheng Laboratory Shenzhen518000 China The China Tobacco Guangdong Industrial Corporation Guangzhou510385 China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100080 China

Semi-supervised semantic segmentation has witnessed remarkable advancements in recent years. However, existing algorithms are based on convolutional neural networks and directly applying them to Vision Transformers poses certain limitations due to conceptual disparities. To this end, we propose TokenMix, a data augmentation technique specifically designed for semi-supervised semantic segmentation with Vision Transformers. TokenMix aligns well with the global attention mechanism by mixing images at the token level, enhancing learning capability for contextual information among image patches. We further incorporate image augmentation and feature augmentation to promote the diversity of augmentation. Moreover, to enhance consistency regularization, we propose a dual-branch framework where each branch applies image and feature augmentation to the input image. We conduct extensive experiments across multiple benchmark datasets, including Pascal VOC 2012, Cityscapes, and COCO. Results suggest that the proposed method outperforms state-of-the-art algorithms with notably observed accuracy improvement, especially under limited fine annotations. Copyright © 2025, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Feature Selection and Feature Learning for High-dimensional Batch Reinforcement Learning: A Survey

引用

International Journal of Automation and computing 2015年第3期12卷 229-242页

作者： De-Rong Liu Hong-Liang Li Ding Wang State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences

Tremendous amount of data are being generated and saved in many complex engineering and social systems every *** is significant and feasible to utilize the big data to make better decisions by machine learning techniques. In this paper, we focus on batch reinforcement learning(RL) algorithms for discounted Markov decision processes(MDPs) with large discrete or continuous state spaces, aiming to learn the best possible policy given a fixed amount of training data. The batch RL algorithms with handcrafted feature representations work well for low-dimensional MDPs. However, for many real-world RL tasks which often involve high-dimensional state spaces, it is difficult and even infeasible to use feature engineering methods to design features for value function approximation. To cope with high-dimensional RL problems, the desire to obtain data-driven features has led to a lot of works in incorporating feature selection and feature learning into traditional batch RL algorithms. In this paper, we provide a comprehensive survey on automatic feature selection and unsupervised feature learning for high-dimensional batch RL. Moreover, we present recent theoretical developments on applying statistical learning to establish finite-sample error bounds for batch RL algorithms based on weighted Lpnorms. Finally, we derive some future directions in the research of RL algorithms, theories and applications.

关键词： Intelligent control reinforcement learning adaptive dynamic programming feature selection feature learning big data.

来源：评论

学校读者我要写书评

暂无评论

Sliding Mode control for Flexible-link Manipulators Based on Adaptive Neural Networks

引用

International Journal of Automation and computing 2018年第2期15卷 239-248页

作者： Hong-Jun Yang Min Tan State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of Sciences

This paper mainly focuses on designing a sliding mode boundary controller for a single flexible-link manipulator based on adaptive radial basis function （RBF） neural network. The flexible manipulator in this paper is considered to be an Euler-Bernoulli beam. We first obtain a partial differential equation （PDE） model of single-link flexible manipulator by using Hamiltons approach. To improve the control robustness, the system uncertainties including modeling uncertainties and external disturbances are compensated by an adaptive neural approximator. Then, a sliding mode control method is designed to drive the joint to a desired position and rapidly suppress vibration on the beam. The stability of the closed-loop system is validated by using Lyapunov＇s method based on infinite dimensional model, avoiding problems such as control spillovers caused by traditional finite dimensional truncated models. This novel controller only requires measuring the boundary information, which facilitates implementation in engineering practice. Favorable performance of the closed-loop system is demonstrated by numerical simulations.

关键词： Sliding mode control adaptive control neural network flexible manipulator partial differential equation （PDE）.

来源：评论

学校读者我要写书评

暂无评论

Remembering Dave Waltz (1943-2012) IN MEMORIAM

引用

IEEE INTELLIGENT systems 2012年第4期27卷 86-88页

作者： Wang, Fei-Yue State Key Laboratory of Management and Control for Complex Systems

IEEE Intelligent systems remembers Dave Walz, a longtime member of its advisory board and a great friend.

关键词： Obituaries Waltz Dave IEEE Intelligent systems Dave Walz Advisory Board

来源：评论

学校读者我要写书评

暂无评论

Evaluation of indocyanine green inhalation to detect air leak sites during video-assisted thoracoscopic surgery: a prospective study

引用

BMC Surgery 2025年第1期25卷 1-9页

作者： Wang, Zhenfan Tian, Xue Wei, Zihan Xu, Hao He, Kunshan Chi, Chongwei Zhao, Songjing Jiang, Ruiheng Yang, Fan Li, Yun Zhou, Jian Department of Thoracic Surgery Peking University People’s Hospital Beijing 100044 China Department of Anaesthesia Peking University People’s Hospital Beijing China China-Japan Friendship Hospital Beijing China CAS Key Laboratory of Molecular Imaging Beijing Key Laboratory of Molecular Imaging The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Peking University Health Science Center Beijing China Department of Thoracic Surgery Beijing Aerospace General Hospital Beijing China

Background: This study aimed to investigate the feasibility and clinical benefits of indocyanine green (ICG) inhalation for detecting air leak sites during video-assisted thoracoscopic surgery (VATS). Methods: Between February 2023 and May 2023, a total of 288 patients underwent VATS were enrolled in this study. Among the population, 72 patients received ICG inhalation test following the traditional submersion sealing test. And 216 patients only underwent the submersion sealing test were matched using 1:3 propensity score matching analysis. The results of ICG inhalation test and the clinical outcomes were compared. Results: In the ICG group, 48 air leak sites were detected in 25 patients (25/72, 34.7%). The conventional submersion sealing test identified 30 air leak sites, while the ICG inhalation test detected 47 sites. Among these detected air leak sites, 34 sites were repaired by suturing or stapling. The postoperative air leak rate in the ICG group (20.8%) was significantly lower than the control group (37.0%, P = 0.011). ICG inhalation test was a favorable factor for reducing postoperative air leaks (OR: 0.40;95%CI: 0.20–0.78;P = 0.008). Conclusions: The ICG inhalation test facilitates the identification of air leak sites that may have been overlooked in the conventional submersion sealing test. This technique is useful to reduce postoperative air leaks for patients undergoing VATS. Trial registration : Chinese Clinical Trial Registry: ChiCTR2300067603 on January 13rd 2023. © The Author(s) 2025.

关键词： Air leaks Indocyanine green Inhalation Video-assisted thoracoscopic surgery

来源：评论

学校读者我要写书评

暂无评论

Forecasting complex group behavior via multiple plan recognition

引用

Frontiers of Computer Science 2012年第1期6卷 102-110页

作者： Xiaochen LI Wenji MAO Daniel ZENG State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China

Group behavior forecasting is an emergent re- search and application field in social computing. Most of the existing group behavior forecasting methods have heavily re- lied on structured data which is usually hard to obtain. To ease the heavy reliance on structured data, in this paper, we pro- pose a computational approach based on the recognition of multiple plans/intentions underlying group behavior. We fur- ther conduct human experiment to empirically evaluate the effectiveness of our proposed approach.

关键词： group behavior forecasting multiple planrecognition graph search

来源：评论

学校读者我要写书评

暂无评论

New control Paradigm for Industry 5.0:From Big Models to Foundation control and management

引用

IEEE/CAA Journal of Automatica Sinica 2023年第8期10卷 1643-1646页

作者： Fei-Yue Wang IEEE the State Key Laboratory for Management and Control of Complex Systems Chinese Academy of SciencesBeijing 100190China

DO we need a fundamental change in our professional culture and knowledge foundation for control and automation?If so,what are necessary and critical steps we must take to ensure such a change would take place effecti... 详细信息

关键词： smoothly steps culture

来源：评论

学校读者我要写书评

暂无评论

Near-infrared fluorescence imaging with an MET-targeting probe for biopsy site selection in patients with oral potentially malignant disorders

引用

CELL REPORTS MEDICINE 2025年第3期6卷 101978-101978页

作者： Wang, Jingbo Shen, Xuemin Ma, Qifan Yang, Lin Zhou, Xiaoyu Wang, Luting Cui, Junqi Zhang, Chunye Li, Guojun Gross, Neil Li, Siyi Huang, Ruimin Zhan, Changyou Cheng, Zhen Wang, Kun Tian, Jie Yuan, Ying Tao, Xiaofeng Shanghai Jiao Tong Univ Shanghai Peoples Hosp 9 Sch Med Dept Radiol Shanghai 200011 Peoples R China Shanghai Jiao Tong Univ Shanghai Peoples Hosp 9 Sch Med Dept Oral Mucosal DisColl Stomatol Shanghai Peoples R China Natl Clin Res Ctr Oral Dis Shanghai Key Lab Stomatol Shanghai 200011 Peoples R China Shanghai Res Inst Stomatol Shanghai 200011 Peoples R China Fujian Childrens Hosp Fujian Branch Shanghai Childrens Med Ctr Dept Radiol Fujian 350014 Peoples R China Chinese Acad Sci Shanghai Inst Mat Med Mol Imaging Ctr State Key Lab Drug Res Shanghai 201203 Peoples R China Shanghai Jiao Tong Univ Sch Med Shanghai Peoples Hosp 9 Dept Pathol Shanghai 200011 Peoples R China Univ Texas MD Anderson Canc Ctr Dept Head & Neck Surg Houston TX 77030 USA Shanghai Jiao Tong Univ Shanghai Peoples Hosp 9 Coll Stomatol Dept Oral & Maxillofacial Head & Neck OncolSch M Shanghai 200011 Peoples R China Chinese Acad Sci Ctr Drug Safety Evaluat & Res Shanghai Inst Mat Med Shanghai 201203 Peoples R China Fudan Univ Sch Basic Med Sci Dept Pharmacol Shanghai 200433 Peoples R China Fudan Univ Shanghai Pudong Hosp Ctr Med Res & Innovat Shanghai 200433 Peoples R China Fudan Univ State Key Lab Mol Engn Polymers Shanghai 200433 Peoples R China Chinese Acad Sci State Key Lab Management & Control Complex Syst CAS Key Lab Mol Imaging Beijing Key Lab Mol ImagingInst Automat Beijing 100190 Peoples R China

Accurate detection of malignant transformation in oral potentially malignant disorders (OPMDs) is crucial for guiding effective treatment and improving patient management. This study evaluates the potential of MET- binding peptide-indocyanine green (cMBP-ICG), a mesenchymal-epithelial transition factor (MET)-targeted near-infrared fluorescence imaging (NIRFI) probe, for biopsy site selection in OPMDs. Preclinical results demonstrate the superior accuracy of NIRFI-assisted biopsy over conventional oral examination (COE)based biopsy in detecting high-grade dysplasia (HGD) or squamous cell carcinoma (SCC) and reducing missed detection rates. In a clinical trial with 50 patients, NIRFI-assisted biopsy achieves significantly higher diagnostic accuracy compared to COE-based biopsy (91% vs. 72%, p = 0.0005). These findings underscore the importance of NIRFI in enhancing diagnostic precision, supporting early detection and enabling timely and accurate treatment interventions for patients with OPMDs. The clinical trial is registered under the registration number ChiCTR2300074454.

关键词： oral squamous cell carcinoma oral potentially malignant disorders mesenchymal-epithelial transition factor near-infrared targeted fluorescent imaging topical application biopsy site selection fluorescence-guided biopsy 4-NQO-induced OSCC model molecular imaging

来源：评论

学校读者我要写书评

暂无评论

Cross-view face recognition via structured dictionary based domain shift

引用

IET COMPUTER VISION 2015年第4期9卷 531-540页

作者： Chen, Xue Wang, Chunheng Xiao, Baihua Cai, Xinyuan CASIA State Key Lab Management & Control Complex Syst Beijing Peoples R China

View variation is a major challenge in face recognition. In this study, the authors propose a novel cross-view face recognition method by seeking potential intermediate domains between the source and target views to model the connection of varying-views faces. Specifically, each intermediate domain is associated with a dictionary subspace. Learning proceeds in two phases. First, the authors discriminatively train a sub-dictionary for each subclass of data, which then compose a structured dictionary of powerful reconstructive and discriminative capability on the source data. Secondly, the authors gradually adapt the source domain dictionary to the target domain by incrementally reducing the reconstruction error on the target data, which forms a smooth transition path connecting the source and target domains. Instead of updating the structured dictionary integrally, the authors develop a refined sub-dictionary-based updating algorithm, which makes the intermediate dictionaries fit on the target data better and faster. Finally, the authors apply invariant sparse codes across the source, intermediate and target domains to render domain-shared representations, where the sample differences caused by view changes are reduced. Experiments on the CMU-PIE and Multi-PIE dataset demonstrate the effectiveness of the proposed method.

关键词： face recognition learning (artificial intelligence) image reconstruction CMU-PIE dataset multiPIE dataset domain-shared representations invariant sparse codes refined sub-dictionary based updating algorithm smooth transition path reconstruction error source domain dictionary source data dictionary subspace structured dictionary based domain shift cross-view face recognition method

来源：评论

学校读者我要写书评

暂无评论

Attribute Regularization Based Human Action Recognition

引用

IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY 2013年第10期8卷 1600-1609页

作者： Zhang, Zhong Wang, Chunheng Xiao, Baihua Zhou, Wen Liu, Shuang CASIA State Key Lab Management & Control Complex Syst Beijing Peoples R China

Recently, attributes have been introduced as a kind of high-level semantic information to help improve the classification accuracy. Multitask learning is an effective methodology to achieve this goal, which shares low-level features between attributes and actions. Yet such methods neglect the constraints that attributes impose on classes, which may fail to constrain the semantic relationship between the attributes and actions. In this paper, we explicitly consider such attribute-action relationship for human action recognition, and correspondingly, we modify the multitask learning model by adding attribute regularization. In this way, the learned model not only shares the low-level features, but also gets regularized according to the semantic constrains. In addition, since attribute and class label contain different amounts of semantic information, we separately treat attribute classifiers and action classifiers in the framework of multitask learning for further performance improvement. Our method is verified on three challenging datasets (KTH, UIUC, and Olympic Sports), and the experimental results demonstrate that our method achieves better results than that of previous methods on human action recognition.

关键词： Attribute regularization human action multitask learning

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：