检索结果-内蒙古大学图书馆

2024 IEEE International Conference on Robotics and Biomimetics, ROBIO 2024

作者： Tai, Beijia Wei, Yangjie Zhang, Guangyu He, Yuqing Cui, Siyao Ministry of Education College of Computer Science and Engineering Northeastern University Key Laboratory of Intelligent Computing in Medical Image Wenhua Street 3 Shenyang110819 China Shenyang Institute of Automation Chinese Academy of Science Shenyang China

ISBN: (纸本)9781665481090

Accurate tracking of unmanned devices is essen-tial for higher-level decision-making in collaborative confrontation scenarios. However, the robustness of current positioning methods based on Ultra-Wideband (UWB) is limit, and the positioning error is unstable. This paper presents a collabo-rative localization algorithm specifically designed for indoor unmanned systems, which leverages UWB technology combined with Least Squares (LS) and Extended Kalman Filter (EKF) models to achieve anchor calibration, as well as precise and stable positioning of unmanned devices. First, the positions of anchors is estimated using fixed-point ranging information;Second, the positions of anchors are simultaneously corrected while locating the tags on unmanned devices. The experimental results show that our algorithm achieves positioning accuracy within 10 cm in the three-dimensional space, even with a ranging error of 5 cm. © 2024 IEEE.

关键词： Ultra-wideband (UWB)

来源：评论

学校读者我要写书评

暂无评论

A novel approach for web data extraction based on XML encoding

A novel approach for web data extraction based on XML encodi...

引用

2010 7th International Conference on Fuzzy Systems and Knowledge Discovery, FSKD 2010

作者： Nie, Tiezheng Shen, Derong Yu, Ge Shi, Zhong Key Laboratory of Medical Image Computing Northeastern University Ministry of Education Shenyang China College of Information Science and Engineering Northeastern University Shenyang China

ISBN: (纸本)9781424459346

The problem of extracting data from a Web page has been studied by many works. In this paper, we present a novel approach that extracts data records from Web pages based on techniques of XML encoding. Firstly, our approach formats a given Web data page into an XML document. Then instead of using DOM-based approaches, we make use of XML encoding model to transform the XML document into a linear sequence. Our algorithm identifies the data records of a Web page from the sequence, which avoids the complex matching between sub trees in DOM model. Moreover, we address the problem of repetitive subparts in records and propose an algorithm for data alignment. Experimental results show that our approach can extract data records accurately from web pages. ©2010 IEEE.

关键词： XML

来源：评论

学校读者我要写书评

暂无评论

Competition on robust deep learning

引用

National Science Review 2023年第6期10卷 13-15页

作者： Yinpeng Dong Chang Liu Wenzhao Xiang Hang Su Jun Zhu Department of Computer Science and Technology Institute for AI Tsinghua-Bosch Joint ML Center THBI Lab BNRist Center Tsinghua University Institute of Image Communication and Networks Engineering in the Department of Electronic Engineering (EE) Shanghai Jiao Tong University Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Peng Cheng Laboratory Pazhou Laboratory (Huangpu)

PROBLEM In recent years,the rapid development of artificial intelligence (AI) technology,especially machine learning and deep learning, is profoundly changing human production and *** various fields,such as robotics,face recognition,autonomous driving and healthcare,AI is playing an important ***,although AI is promoting the technological revolution and industrial progress,its security risks are often *** studies have found that the wellperforming deep learning models are extremely vulnerable to adversarial examples [1-3].The adversarial examples are crafted by applying small,humanimperceptible perturbations to natural examples,but can mislead deep learning models to make wrong *** vulnerability of deep learning models to adversarial examples can raise security and safety threats to various realworld applications.

关键词： robustness adversarial example adversarial training deep learning

来源：评论

学校读者我要写书评

暂无评论

Pseudo Multi-Source Domain Extension and Selective Pseudo-Labeling for Unsupervised Domain Adaptive medical image Segmentation 48

Pseudo Multi-Source Domain Extension and Selective Pseudo-La...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Liu, Xiaokang Wang, Zhiqiang Hu, Kai Gao, Xieping Xiangtan University Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education Xiangtan411105 China Xiangnan University College of Medical Imaging Laboratory and Rehabilitation Chenzhou423000 China Hunan Normal University Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Changsha410081 China

ISBN: (纸本)9781728163277

Unsupervised domain adaptation (UDA) attracts extra attention in medical image processing because no additional labels are required when adapting to different distributions. In this work, we propose a novel unsupervised domain adaptation framework named as Domain Expansion and PseudoLabeling (DEPL). We extend the domain of a labeled source domain data to four different distributed domains and use adversarial learning to align the image appearance level and feature level from the four different domains to the unlabeled target domain. In addition, we propose a selective pseudolabeling mechanism, namely using strong confidence pseudolabeling to boost model performance. We evaluate our model for the MR to CT adaptation segmentation task on the public dataset MMWHS. Compared to seven other state-of-the-art segmentation methods, our DEPL achieves the best Dice similarity coefficient by 82.4%, which is at least 3.9% higher than the other UDA segmentation methods. © 2023 IEEE.

关键词： Adversarial learning domain extension image segmentation Selective pseudo-labeling Unsupervised domain adaptive

来源：评论

学校读者我要写书评

暂无评论

iHDFS: A distributed file system supporting incremental computing

iHDFS: A distributed file system supporting incremental comp...

引用

International Conference of Young Computer Scientists, Engineers and Educators, ICYCSEE 2015

作者： Wang, Zhenhua Ding, Qingsong Gao, Fuxiang Shen, Derong Yu, Ge College of Information Science and Engineering Northeastern University Shenyang China Key Laboratory of Medical Image Computing Northeastern University Ministry ofEducation Shenyang China

ISBN: (纸本)9783662462478

Big data are always processed repeatedly with small changes, which is a major form of big data processing. The feature of incremental change of big data shows that incremental computing mode can improve the performance greatly. HDFS is a distributed file system on Hadoop which is the most popular platform for big data analytics. And HDFS adopts fixed-size chunking policy, which is inefficient facing incremental computing. Therefore, in this paper, we proposed iHDFS (incremental HDFS), a distributed file system, which can provide basic guarantee for big data parallel processing. The iHDFS is implemented as an extension to HDFS. In iHDFS, Rabin fingerprint algorithm is applied to achieve content defined chunking. This policy make data chunking has much higher stability, and the intermediate processing results can be reused efficiently, so the performance of incremental data processing can be improved significantly. The effectiveness and efficiency of iHDFS have been demonstrated by the experimental results. © Springer-Verlag Berlin Heidelberg 2015.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

A novel lung nodules detection scheme based on vessel segmentation on CT images

A novel lung nodules detection scheme based on vessel segmen...

引用

作者： Jia, Tong Zhang, Hao Meng, Haixiu College of Information Science and Engineering Northeastern University Shenyang110819 China Key Laboratory of Medical Image Computing Ministry of Education Shenyang110819 China

Lung vessels often interfere with the detection of lung nodules. In this paper, a novel computer-Aided lung nodule detection scheme on vessel segmentation is proposed. This paper describes an active contour model which can combine image region mean gray value and image edge energy. It is used to segment and remove lung vessels. A selective shape filter based on Hessian Matrix is used to detect suspicious nodules and remove omitted lung vessels. This paper extracts density, shape and position features of suspicious nodules, and uses a Rule-Based Classification (RBC) method to identify true positive nodules. In the experiment results, the detection sensitivity is about 90% and FP is 1/scan. © 2014 - IOS Press and the authors.

关键词： Computerized tomography

来源：评论

学校读者我要写书评

暂无评论

4D real-time cardiac MDCT image volume rendering method research based on GPU texture mapping

4D real-time cardiac MDCT image volume rendering method rese...

引用

4th International Conference on Bioinformatics and Biomedical Engineering, iCBBE 2010

作者： Feng, Chaolu Yang, Jinzhu Zhao, Dazhe Chaolu, Feng Liu, J. Key Laboratory of Medical Image Computing Ministry of Education Northeast University Shenyang China School of Information Science and Engineering Northeast University Shenyang China

ISBN: (纸本)9781424447138

A low-injury, high success rate, and no side effects treatment for curing heart physical defects is urgently needed in the medical field. Although with electrocardiographically (ECG) gated technology, the timeline information of heartbeat can be collected by Multi-detector Computed Tomography (MDCT), the traditional CPU-based volume rendering methods can not meet the dynamic cardiac real-time reconstruction. This paper presents a GPU texture mapping based dynamic cardiac 4D real time rendering method. It uses ECG-gated MDCT acquiring cardiac real-time volume data sets, each of which called one time-phased data and mapped to a GPU texture unit. The material and lighting properties, color and opacity data, computed by GPU, are also mapped to other two texture units. Then through the fragment programs, these textures are looked up, and the result pixel color is received. Volume textures switch are controlled by the time interval from ECG-gated 4D real-time cardiac data acquisition. Experimental results show that the method we presented can achieve a dynamic cardiac real-time rendering;quality is better, and speed faster enough to meet clinical needs. ©2010 IEEE.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

A study of pulmonary nodule detection in three-dimensional thoracic CT scans

A study of pulmonary nodule detection in three-dimensional t...

引用

2010 International Conference on Computer Modeling and Simulation, ICCMS 2010

作者： Liu, Yang Yang, Jinzhu Zhao, Dazhe Liu, Jiren Key Laboratory of Medical Image Computing Ministry of Education Northeastern University Shenyang China School of Information Science and Engineering Northeastern University Shenyang China

ISBN: (纸本)9780769539416

Early detection of pulmonary nodules on Multi-Slice Computed Tomography(MSCT) is an important clinical indication for early-stage lung cancer diagnosis. Currently, support vector machines (SVMs) have been widely used in pattern recognition. We are developing a nodule detection system by using the combination of SVMs. For training and testing the SVM classifier, a lung nodule simulation method in three-dimensional (3D) image space is developed to provide a better test environment. The detection method is multi-step, including 3D nodule simulation and insertion, lung fields segmentation, initial nodule candidates extraction, 3D geometry and intensity features calculation and false positives (FPs) reduction based on SVM. The proposed scheme is applied on three mixed chest MSCT datasets and evaluated using Receiver Operating Characteristic (ROC) curve analysis. The experimental results illustrate the efficiency of the proposed method and the sensitivity of SVM classifier is found to be 86%. © 2010 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Efficient link scheduling for TDMA based WMN using multi-objective genetic algorithm

Efficient link scheduling for TDMA based WMN using multi-obj...

引用

International Conference on Bio-Inspired computing: Theories and Applications, BICTA

作者： Chen, Jian Jia, Jie Wen, Ying-You Zhao, Da-Zhe Liu, Ji-Ren School of Information Science and Engineering Northeastern university Shenyang China Key Laboratory of Medical Image Computing Ministry of Education Northeastern University Shenyang China

ISBN: (纸本)9781424464388

Link Scheduling plays an important role for the performance of TDMA based wireless mesh networks. Traditional algorithms merely aim at maximizing the overall network throughput, which may introduce the scheduling delay. Theoretically the model of relationship between link scheduling with the network throughput and end to end scheduling delay is analyzed. Then, a heuristic algorithm to solve the near optimal scheduling period and scheduling delay for link list with fixed schedule order is proposed. Furthermore, as the performance is much more effected by the scheduling sequence, the link scheduling scheme to sort the overall network link list based on NSGA-II is proposed. By choosing the optimal scheduling sequence, the ratio of the slot spatial reuse is enhanced, thus to increase the network throughput with the overall network scheduling delay is minimized. Simulation results are presented to verify these approaches. © 2010 IEEE.

关键词： Scheduling

来源：评论

学校读者我要写书评

暂无评论

Modeling and stability analysis of the propagation of a worm

Modeling and stability analysis of the propagation of a worm

引用

2013 International Conference on Sport Science and Computer Science, CCCS 2013

作者： Yao, Yu Zhang, Zhao Li, Shuo Gao, Fuxiang Yu, Ge College of Information Science and Engineering Northeastern University Shenyang China Key Laboratory of Medical Image Computing Northeastern University Ministry of Education Shenyang China

ISBN: (纸本)9781845649166

Internet worm can spread not only via networks but also through external removable devices. In this paper, considering the influence of removable media, we construct two new worm propagation models. By analyzing the local asymptotic stability at infection-free equilibrium, a basic reproduction number is derived. System is locally stable at infection-free equilibrium if basic reproduction number is less than one;whereas system will lose its stability. Several numerical experiments are given to support the theoretical analysis. Finally, simulating the propagation behavior via simulation experiments, we further demonstrate the correctness of theoretical analysis. © 2014 WIT Press.

关键词： Asymptotic stability

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：