检索结果-内蒙古大学图书馆

An improved approach for automatic spine canal segmentation using probabilistic boosting tree (PBT) with fuzzy support vector machine

引用

Journal of Ambient Intelligence and Humanized Computing 2020年第6期12卷 6527-6536页

作者： Viji, C. Rajkumar, N. Suganthi, S. T. Venkatachalam, K. kumar, T. Rajesh Pandiyan, Sanjeevi Department of CSE Akshaya College of Engineering and Technology Coimbatore India Department of Computer Engineering Lebanese French University Erbil Iraq School of CSE VIT University Bhopal Bhopal India Department of Information Technology Sri Krishna College of Technology Kovaipudur India Key Laboratory of Advanced Process Control for Light Industry Ministry of Education Jiangnan University Wuxi China

Spine canal segmentation is an emerging zone in research proposed to help interpretation and processing of advanced MRI and CT images. For instance, high resolution three-dimensional volumes can be divided to provide an estimation of spine canal atrophy. Spine canal segmentation is complex because of assortment of MRI contrasts and variation in human life structures. This investigation illustrates the details of spine canal segmentation techniques and gives a few measurements that can be utilized to contrast with other segmentation strategies. The details of background and foreground subtraction techniques, spine canal segmentation approach and optimization approach which are utilized in the different applications have been considered. In this paper, spine canal segmentation on probabilistic booting tree (PBT) with fuzzy support vector machine performance measures and metrics are analysed in state-of-the art technologies. Proposed approach is performed on the base of the automatic spine canal segmentation with the group of data MR. This proposed segmentation continue with fuzzy support vector machine (FSVM) technique to make fully automatic stream pipeline. The declaration in an automatic segmentation of stream pipeline was implemented with flexible voxel wise classification accompanying dimensions analogous with 3D Haar and labelled machine learning algorithms i.e. probabilistic boosting tree combined fuzzy support vector machine (PBT-FSVM). The novel segmentation technique correlated with MR data sets provides better accuracy than the exiting techniques and it is shown in experimental outcomes. To still improve performance of the results, online learning classification method can be in the proposed work.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Automatic Stent Detection for Intravascular Optical Coherence Tomographic

An Automatic Stent Detection for Intravascular Optical Coher...

引用

第三十九届中国控制会议

作者： Yifan Guo Shangjie Ren Haibo Jia Bo Yu Feng Dong Tianjin Key Laboratory of Process Measurement and Control School of Electrical and Information Engineering Tianjin University Department of Cardiology The 2nd Affiliated Hospital of Harbin Medical University The Key Laboratory of Myocardial Ischemia Chinese Ministry of Education

Intravascular Optical Coherence Tomography（IVOCT） is an important imaging technique for diagnose of atherosclerosis due to its advantages of high spatial and temporal resolutions. In this paper, an automatic detection method is proposed for the evaluation of the stent placement in Percutaneous Coronary Intervention（PCI）. The method mainly contains the flowing three steps. Firstly, the IVOCT images are de-noised by total variation model. Secondly, the ROI zone and the seed points of stents are detected. Finally, the region growing algorithm is used to segment the stents according to the selected seed points. More than one thousand clinical OCT images are collected from 10 post-PCI treatment patients for evaluating the performance of the proposed method. The results show that the proposed method could achieve 89.3% accuracy and 86.5%sensitivity.

关键词： IVOCT Stent detection K-means Region growing

来源：评论

学校读者我要写书评

暂无评论

Off-Policy Q-Learning for Anti-Interference control of Multi-Player Systems ⁎

引用

IFAC-PapersOnLine 2020年第2期53卷 9189-9194页

作者： Jinna Li Zhenfei Xiao Tianyou Chai Frank. L. Lewis Sarangapani Jagannathan School of Information and Control Engineering Liaoning Shihua University Fushun 113001 China State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang 110819 China UTA Research Institute the University of Texas at Arlington Arlington TX 76118 USA Department of Electrical and Computer Engineering Missouri University of Science and Technology Rolla MO 65409 USA

This paper develops a novel off-policy game Q-learning algorithm to solve the anti-interference control problem for discrete-time linear multi-player systems using only data without requiring system matrices to be known. The primary contribution of this paper lies in that the Q-learning strategy employed in the proposed algorithm is implemented in an off-policy policy iteration approach other than on-policy learning due to the well-known advantages of off-policy Q-learning over on-policy Q-learning. All of the players work hard together for the goal of minimizing their common performance index meanwhile defeating the disturbance that tries to maximize the specific performance index, and finally they reach the Nash equilibrium of the game resulting in satisfying disturbance attenuation condition. In order to find the solution to the Nash equilibrium, the anti-interference control problem is first transformed into an optimal control problem. Then an off-policy Q-learning algorithm is proposed in the framework of typical adaptive dynamic programming (ADP) and game architecture, such that control policies of all players can be learned using only measured data. Comparative simulation results are provided to verify the effectiveness of the proposed method.

关键词： H ∞ control off-policy Q-learning game theory Nash equilibrium

来源：评论

学校读者我要写书评

暂无评论

Retraction Note to: An improved approach for automatic spine canal segmentation using probabilistic boosting tree (PBT) with fuzzy support vector machine

引用

Journal of Ambient Intelligence and Humanized Computing 2022年第1期14卷 303-303页

作者： Viji, C. Rajkumar, N. Suganthi, S. T. Venkatachalam, K. Rajesh kumar, T. Pandiyan, Sanjeevi Department of CSE Akshaya College of Engineering and Technology Coimbatore India Department of Computer Engineering Lebanese French University Erbil Iraq School of CSE VIT University Bhopal Bhopal India Department of Information Technology Sri Krishna College of Technology Kovaipudur India Key Laboratory of Advanced Process Control for Light Industry Ministry of Education Jiangnan University Wuxi China

来源：评论

学校读者我要写书评

暂无评论

Joint graphical consistency learning for simultaneous lumen and neovascularization segmentation and analyzation in intravascular optical coherence tomography

引用

Biomedical Signal processing and control 2025年 110卷

作者： Lin Ding Chen Zhao Haibo Jia Bo Yu Jingjiang Xu Shiyong Zhao Feng Dong Shangjie Ren Tianjin Key Laboratory of Process Measurement and Control School of Electrical and Information Engineering Tianjin University Tianjin 300072 China State Key Laboratory of Frigid Zone Cardiovascular Diseases (SKLFZCD) Key Laboratory of Myocardial Ischemia Chinese Ministry of Education Department of Cardiology of the Second Affiliated Hospital Harbin Medical University 246 Xuefu Road Nangang District Harbin 150086 Heilongjiang China School of Physics and Optoelectronic Engineering Foshan University Foshan 528000 China Tianjin Horimed Technology Co. Ltd. Tianjin 300072 China

Accurate segmentation of the lumen and neovascularization (NV) in intravascular optical coherence tomography (IVOCT) images is critical for the precise diagnosis and treatment of coronary artery disease (CAD). However, the complex vascular geometry and the small, irregular morphology of NV pose significant challenges to traditional segmentation methods based on handcrafted features or single deep learning models. To address these limitations, this study proposes the Joint Graphical Consistency Learning Network (JGCLNet), which integrates convolutional neural networks and graph neural networks to enhance structural representation learning. The network employs a dual-branch architecture, allowing dedicated processing of lumen and NV segmentation tasks, and incorporates a graph convolutional module to extract vascular topological information, improving boundary delineation. Additionally, a joint consistency learning module is introduced to facilitate cross-task information sharing and interaction. To mitigate the severe class imbalance between NV and lumen, a weighted joint loss function is designed. Experimental validation on a dataset of 11,027 IVOCT images demonstrates that JGCLNet achieves Dice coefficients of 74.25% for NV and 99.11% for the lumen, significantly outperforming state-of-the-art methods while reducing false positive rates. Clinically, JGCLNet enables fully automated quantitative NV assessment, including NV area, density, count, and 3D visualization, providing robust support for early CAD diagnosis, lesion stability evaluation, and interventional planning. The high accuracy and automation capabilities of JGCLNet make it a promising tool for IVOCT-based CAD imaging analysis.

关键词： Optical coherence tomography

来源：评论

学校读者我要写书评

暂无评论

The determination of deforestation rate in eastern Slovakia in the years 1998-2018 based on multispectral satellite images from missions Landsat 5 and 7 11

The determination of deforestation rate in eastern Slovakia ...

引用

11th International Scientific and Technical Conference on Geodesy, Cartography and Geoinformatics, GCG 2019

作者： Pukanská, Katarína Bartoš, Karol Gašinec, Juraj Kseňak, Ľubomír Frąckiewicz, Pawel Bieda, Agnieszka Institute of Geodesy Cartography and Geographical Information Systems Faculty of Mining Ecology Process Control and Geotechnologies Technical University of Košice Košice Slovakia Faculty of Environmental Geomatic and Energy Engineering Kielce University of Technology Kielce Poland Department of Geomatics Faculty of Mining Surveying and Environmental Engineering AGH University of Science and Technology Kraków Poland

ISBN: (纸本)9780367346515

By using the instruments and methods of remote sensing, it is possible to detect forest damage caused by pests or calamities, while reducing time demands and achieving nationwide assessment of the area. This paper deals with the determination of the extent of deforestation in the Rožňava district (Slovakia) on the principle of calculating the normalized difference vegetation index NDVI from multispectral images of Landsat 5 and Landsat 7 satellites. The data sets were prepared in 5-year epochs using the JavaScript programming language and satellite bands B3, B4, B5, and B7 so that the cloudiness is eliminated from images while displaying the forest cover during the vegetation period. The NDVI calculation was performed in the ESA SNAP software. The resulting data classification was subsequently realized by calculating the percentage decrease in QGIS 2.18 software. © 2020 Taylor & Francis Group, London.

关键词： Deforestation

来源：评论

学校读者我要写书评

暂无评论

Integration of multispectral and radar satellite images for flood range determination of historical flood in Slovakia 2010 11

Integration of multispectral and radar satellite images for ...

引用

11th International Scientific and Technical Conference on Geodesy, Cartography and Geoinformatics, GCG 2019

作者： Pukanská, Katarína Bartoš, Karol Hurčíková, Viera Kseňak, Ľubomír Gil, Marcin Bieda, Agnieszka Institute of Geodesy Cartography and Geographical Information Systems Faculty of Mining Ecology Process Control and Geotechnologies Technical University of Košice Košice Slovakia Faculty of Environmental Geomatic and Energy Engineering Kielce University of Technology Kielce Poland Department of Geomatics Faculty of Mining Surveying and Environmental Engineering AGH University of Science and Technology Kraków Poland

ISBN: (纸本)9780367346515

The objective of this work is to evaluate the extent of historic floods on rivers within Košice region in June 2010. Nowadays, massive floods are an annual reality, as the increasing number of natural disasters is a consequence of global climate changes. Their increasing frequency and severity cause immense damage to property, but also loss of human lives. For the purpose of mapping these floods, historical multispectral satellite images from Landsat 5 were used as the input data, together with radar image from Envisat, from the time of floods in 2010. The results of the floods were compared with the corresponding satellite data from the data with a normal situation. All used image and radar data are freely available to download and process. Given data sets were opened and processed in open-source software ESA-SNAP. The result of the study is the determination of the extent and quantification of historical floods in Eastern Slovakia in 2010. © 2020 Taylor & Francis Group, London.

关键词： Floods

来源：评论

学校读者我要写书评

暂无评论

Coding Graphic Groups for Network Security 4

Coding Graphic Groups for Network Security

引用

4th IEEE Advanced information Technology, Electronic and Automation control Conference, IAEAC 2019

作者： Zhao, Meimei Yao, Ming Zhang, Xiaohui Sun, Yirong Yao, Bing Gansu Agricultural University College of Science Lanzhou730070 China Lanzhou PetrochemicalCollege of Vocational Technology Department of Information Process and Control Engineering Lanzhou730060 China Jishou University College of Mathematics and Statistics Jishou416000 China Northwest Normal University College of Mathematics and Statistics Lanzhou730070 China

ISBN: (纸本)9781728119076

The overall security is a new topic on network security in Today's digital business. As known, graphical passwords (GPWs) are applied in the world. Topological graphic passwords (Topsnut-gpws) differ from the existing GPWs, since they can be expressed by popular matrices and can produce graphic groups for encrypting networks. New coding techniques are introduced and new coding graphic groups and matrix groups are constructed in this article. Some new problems are given for investigating deeply graphic groups and matrix groups. © 2019 IEEE.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

Dexterous Manipulation through Imitation Learning: A Survey

arXiv

引用

arXiv 2025年

作者： An, Shan Meng, Ziyu Tang, Chao Zhou, Yuning Liu, Tengyu Ding, Fangqiang Zhang, Shufang Mu, Yao Song, Ran Zhang, Wei Hou, Zeng-Guang Zhang, Hong School of Electrical and Information Engineering Tianjin University Tianjin300072 China School of Control Science and Engineering Shandong University Jinan250061 China State Key Laboratory of General Artificial Intelligence Beijing100086 China Department of Mechanical and Process Engineering ETH Zurich Zurich8092 Switzerland Department of Electronic and Electrical Engineering Southern University of Science and Technology Shenzhen518055 China School of Informatics University of Edinburgh EH8 9AB United Kingdom Department of Computer Science University of Hong Kong 999077 Hong Kong State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China CASIA-MUST Joint Laboratory of Intelligence Science and Technology Institute of Systems Engineering Macau University of Science and Technology 999078 China

Dexterous manipulation, which refers to the ability of a robotic hand or multi-fingered end-effector to skillfully control, reorient, and manipulate objects through precise, coordinated finger movements and adaptive force modulation, enables complex interactions similar to human hand dexterity. With recent advances in robotics and machine learning, there is a growing demand for these systems to operate in complex and unstructured environments. Traditional model-based approaches struggle to generalize across tasks and object variations due to the high-dimensionality and complex contact dynamics of dexterous manipulation. Although model-free methods such as reinforcement learning (RL) show promise, they require extensive training, large-scale interaction data, and carefully designed rewards for stability and effectiveness. Imitation learning (IL) offers an alternative by allowing robots to acquire dexterous manipulation skills directly from expert demonstrations, capturing fine-grained coordination and contact dynamics while bypassing the need for explicit modeling and large-scale trial-and-error. This survey provides an overview of dexterous manipulation methods based on imitation learning (IL), details recent advances, and addresses key challenges in the field. Additionally, it explores potential research directions to enhance IL-driven dexterous manipulation. Our goal is to offer researchers and practitioners a comprehensive introduction to this rapidly evolving domain. Copyright © 2025, The Authors. All rights reserved.

关键词： Grippers

来源：评论

学校读者我要写书评

暂无评论

Delays in Model Reduction of Chemical Reaction Networks

引用

IFAC-PapersOnLine 2018年第14期51卷 100-105页

作者： Lipták, György Hangos, Katalin M. Process Control Research Group Systems and Control Laboratory Computer and Automation Research Institute Hungarian Academy of Sciences P.O. Box 63 BudapestH-1518 Hungary Department of Electrical Engineering and Information Systems University of Pannonia Veszprém Hungary

A novel engineering model reduction method is proposed in this paper that can be applied to a chemical reaction network (CRN) with chains of linear reactions. The reduced model is a delayed CRN with possibly different delays but with less state variables than the original model. As the first step of the model reduction, a decomposition method is also developed to transform chains with joint reactions into independent chains of linear reactions. The well known example of McKeithan's network is used as a case study to illustrate the basic concepts and the design method. © 2018

关键词： Reduction

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：