检索结果-内蒙古大学图书馆

2011 IEEE International conference on intelligent Computation and Bio-Medical Instrumentation, ICBMI 2011

作者： Jin, Jiaoying Ding, Mingyue Yang, Xin Image Processing and Intelligence Control Key Laboratory of Education Ministry of China Life School of Science and Technology Huazhong University of Science and Technology Wuhan China State Key Laboratory for Multi-spectral Information Processing Technologies Life School of Science and Technology Huazhong University of Science and Technology Wuhan China

ISBN: (纸本)9780769546230

The analysis of the carotid artery wall is of paramount importance in clinical practice. Especially, the intima-media thickness is a risk index for some of the most severe acute cerebrovascular pathologies, hence, an accurate segmentation of the different layers of the carotid artery is needed. IMT is usually manually measured on longitudinal B-mode ultrasound images. In the past ten years, many computer-based techniques for intima-media thickness measurement have been proposed to overcome the limits of manual segmentation, but almost all of them require a certain degree of user interaction. In this paper we proposed a novel approach for the completely user-independent segmentation of the common carotid artery wall. Our algorithm is designed for the extraction of the intima and media layers of the distal carotid wall in ultrasound images. It is based on integrated approach consisting of common carotid artery region identification, contour initialization with threshold segmentation, intima-lumen segmentation with Snake, and media-adventitia segmentation with GVF-Snake that enables the automated tracing of the carotid walls. The acoustic impedance's difference is employed to locate common carotid artery region. Finally, the characterization of the algorithm in terms of segmentation error was evaluated with a set of 40 common carotid artery ultrasound images and compared to the segmentation traced by a trained operator. Experiments showed that a mean error lower than 1.3 pixel both on the intima and media layers was obtained, which is comparable to that obtained by means of operator dependent techniques. © 2011 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Estimation of local and global superpixel covariance for salient object detection in low contrast images 2017

Estimation of local and global superpixel covariance for sal...

引用

9th International Conference on Machine Learning and Computing, ICMLC 2017

作者： Mu, Nan Xu, Xin Zhang, Xiaolong School of Computer Science and Technology Wuhan University of Science and Technology Wuhan Hubei430065 China Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial Systems Wuhan University of Science and Technology Wuhan Hubei430065 China

ISBN: (纸本)9781450348171

Salient object detection has become a hot topic in computer vision as it can substantially facilitate a wide range of applications. Conventional salient object detection models primarily rely on low-level image features, which may face great difficulties in low lighting scenarios. This paper proposes to estimate the saliency of low contrast images via covariance features. The input image is firstly decomposed into superpixel regions to estimate their covariances. Then, the local and global image saliency can be calculated using the covariance features respectively. Finally, a graph-based diffusion process is performed to refine the saliency maps. Extensive experiments have been conducted to evaluate the performance of the proposed model against eleven state-of-the-art models on five benchmark datasets and a nighttime image dataset. © 2017 ACM.

关键词： Superpixels

来源：评论

学校读者我要写书评

暂无评论

Affine-Projection Maximum Asymmetric Correntropy Criterion Algorithm Under System Identifications 11

Affine-Projection Maximum Asymmetric Correntropy Criterion A...

引用

11th IEEE International Conference on Computer Science and Network technology, ICCSNT 2023

作者： Peng, Yan Huang, Xinqi Yu, Canping Mao, Qi Li, Yingsong College of Information and Communication Engineering Harbin Engineering University Harbin150001 China Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education China

ISBN: (纸本)9798350311594

The Affine-Projection Maximum Asymmetric Correntropy Criterion (APMACC) is constructed, drawing upon the fundamental principles of the maximum asymmetric correntropy criterion and an affine-projection scheme. The APMACC algorithm incorporates the asymmetric Gaussian model as a kernel function within the Affine-Projection (AP) algorithm framework, thereby endowing it with robustness against asymmetrically distributed noise. Furthermore, the bound for step-size is established in the literature. Simulation results demonstrate that the APMACC has fast convergence and low steady-state. © 2023 IEEE.

关键词： Adaptive filtering

来源：评论

学校读者我要写书评

暂无评论

A comprehensive assessment method of asset importance for key asset protection 9

A comprehensive assessment method of asset importance for ke...

引用

9th International Conference on Communication and Network Security, ICCNS 2019

作者： Gao, Xiaoling Liu, Yanhua Qiu, Yanbin Liu, Huajun College of Mathematics and Computer Science Fuzhou University Fuzhou Fujian China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou Fujian China

ISBN: (纸本)9781450376624

In a given system network, an important prerequisite for security risk control is how to accurately calculate the impact of different host assets in the topology on the spread of attack risk. In this regard, we propose a comprehensive asset importance assessment model for critical asset protection. First, the importance of local static assets in the topology was evaluated using three methods: degree centrality, mediation centrality, and closeness centrality. At the same time, PageRank was used to assess the importance of local dynamic assets for asset level changes. By combining the above two methods, and using K-CORE to evaluate the core position of the host in the network topology as the global weight indicator of the importance of assets. The comprehensive evaluation results of the importance of topology-oriented assets was finally obtained, and the validity of the model was verified through the experiment of the simulation ER random network. © 2019 Association for Computing Machinery.

关键词： Network topology

来源：评论

学校读者我要写书评

暂无评论

Minimum norm estimates based dipole source estimation 2

Minimum norm estimates based dipole source estimation

引用

2nd International Conference on Biological information and Biomedical Engineering, BIBE 2018

作者： Li, Ming-Ai Wang, Yi-Fan Sun, Yan-Jun Faculty of Information Technology Beijing University of Technology Beijing100124 China Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing China

ISBN: (纸本)9783800747276

Motor Imagery EEG (MI-EEG) conceals a large amount of biological information in the sensorimotor cortex. Although sensor recognition mode benefits from the high time-frequency resolution of EEG, the decoding accuracy of complex MI-tasks is limited resulting from the finite scalp electrodes which contain partial available information of motor cortex in sensor domain. With the development of biomedical engineering, a spatial analysis technique of EEG Source Imaging (ESI) has generated to transform the EEG signals of low dimension into brain source space of high dimension. However, for the general inverse transformation of MI-EEG, the raw signals are previously decomposed to independent components, and the most relevant component to MI-tasks is selected to reconstruct the brain sources of active area. The dipole esti-mates generated through this process may not reflect all effective information of active motor cortex. Therefore we propose a novel Minimum Norm Estimates (MNE) based Dipole Source Estimation (DSE) integrated with overlapping averaging in the temporal domain in this paper. Based on a public dataset, abundant experiment results show that DSE can make full use of MI-EEG from entire time series and present more complete information of brain source with higher spatial resolution, which will contribute to the source recognition mode. © VDE VERLAG GMBH - Berlin - Offenbach.

关键词： Biomedical engineering

来源：评论

学校读者我要写书评

暂无评论

BigVid at MediaEval 2016: Predicting interestingness in images and videos

BigVid at MediaEval 2016: Predicting interestingness in imag...

引用

2016 Multimedia Benchmark Workshop, MediaEval 2016

作者： Xu, Baohan Fu, Yanwei Jiang, Yu-Gang School of Computer Science Fudan University China School of Data Science Fudan University China Shanghai Key Laboratory of Intelligent Information Processing Fudan University China

Despite growing research interest, the tasks of predicting the interestingness of images and videos remain as an open challenge. The main obstacles come from both the diversity and complexity of video content and highly subjective and varying judgements of interestingness of different persons. In the MediaEval 2016 Predicting Media Interestingness Task, our team of BigVid@Fudan had submitted five runs exploring various methods of extraction, and modeling the low-level features (from visual and audio modalities) and hundreds of high-level semantic attributes;and fusing these features for classification. We not only investigated the use of the SVM (Support Vector Machine) model;but the recent deep learning methods were explored as well. We had submitted 5 runs using SVM/Ranking-SVM (Run1, Run3 and Run4) and Deep Neural Networks (Run2 and Run5) respectively. We achieved a mean average precision of 0.23 for the image subtask and 0.15 for the video subtask. Furthermore, our experiments revealed some insights of this task which are interesting and potential useful. For example, our results show that the visual features and high-level attributes are complementary to each other.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Performance analysis of UAV-based mixed underwater PLC-RF systems

引用

Digital Communications and Networks 2024年第5期10卷 1332-1340页

作者： Shenghai Chen Liang Yang Xianfu Lei College of Computer Science and Electronic Engineering Hunan UniversityChangsha410082China Key Laboratory of Intelligent Control Technology for Wuling-Mountain Ecological Agriculture in Hunan Province Huaihua UniversityHuaihua418000China School of Information Science and Technology Southwest Jiaotong UniversityChengdu610031China

In this study,we analyzed the performance of an Unmanned Aerial Vehicle(UAV)-based mixed Underwater Power Line Communication-Radio Frequency(UPLC-RF)*** this network,a buoy located at the sea is used as a relay to transmit signals from the underwater signal source to the UAV through the PLC *** assume that the UPLC channel obeys a log-normal distribution and that the RF link follows the Rician *** this model,we obtained the closed-form expressions for the Outage Probability(OP),Average Bit-error-rate(ABER),and Average Channel Capacity(ACC).In addition,the asymptotic analysis of the OP and ABER was performed,and an upper bound for the average capacity was ***,the analytical results were verified by Monte Carlo simulation thereby demonstrating the effect of impulse noise and the altitude of the UAV on network performance.

关键词： ABER Average bit-error-rate ACC Average channel capacity OP Outage probability UAV Unmanned aerial vehicle UPLC Underwater power line communication

来源：评论

学校读者我要写书评

暂无评论

Small targets recognition in SAR ship image based on improved SSD

Small targets recognition in SAR ship image based on improve...

引用

2019 IEEE International Conference on Signal, information and Data processing, ICSIDP 2019

作者： Li, Yong Chen, Jing Ke, Meng Li, Linghao DIng, Zegang Wang, Yan Radar Research Lab School of Information and Electronics Beijing Institute of Technology Beijing China Beijing Key Laboratory of Embedded Real-time Information Processing Technology Beijing Institute of Technology Beijing China

ISBN: (纸本)9781728123455

Synthetic Aperture Radar(SAR) ship recognition is significant in marine applications and plays an important role in maritime traffic management, fisheries management, and maritime rescue, etc. A major difficulty in SAR ship recognition is that the SAR ships have a small size in images, which results in low recognition accuracy of the SSD. This paper first analyzes the reasons for the low recognition accuracy for small targets in SSD. First, the poor matching of the default boxes leads to a small number of positive samples. Second, the representation ability of low-level feature map for recognizing small targets is weak. Then two strategies are proposed to improve the SSD. Firstly, a default box optimization design method based on Kmeans clustering is proposed, which improves the matching performance of the default boxes. Secondly, a feature fusion method based on deconvolution is proposed, which effectively improves the representation ability of low-level feature maps. The experimental results show that the proposed method can greatly improve the recognition accuracy of SSD for small targets in SAR ship images. © 2019 IEEE.

关键词： Synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

Adaptive Step-Size Sparse Millimeter Wave Imaging Algorithm Based on Approximate Observations 11

Adaptive Step-Size Sparse Millimeter Wave Imaging Algorithm ...

引用

11th IEEE International Conference on Computer Science and Network technology, ICCSNT 2023

作者： Wang, Dianhao Huang, Xinqi Yu, Canping Mao, Qi Li, Yingsong College of Information and Communication Engineering Harbin Engineering University Harbin150001 China Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education China

ISBN: (纸本)9798350311594

The currently constructed millimeter wave imaging system has the problems of long sampling time and more sampling points of antenna units, and the use of compressed perception algorithm can improve the imaging quality when the number of sampling points are much smaller than the Nyquist distance sampling. The traditional compressed perception algorithm can achieve better sparse recovery than the matched filter imaging algorithm, but there is a large dimension of the measurement matrix and high computational complexity. For the problems of difficult data processing and large dimensions of measurement matrix, a sparse imaging regularization model is constructed based on approximate observation, and an improved soft threshold iterative algorithm is used with adaptive step size, which improves the convergence performance, reduces the computational complexity of the sparse recovery dramatically and achieves a better quality of sparse imaging than the traditional compressed perception algorithm. © 2023 IEEE.

关键词： Computational complexity

来源：评论

学校读者我要写书评

暂无评论

Active learning for Chinese word sense disambiguation

Active learning for Chinese word sense disambiguation

引用

2009 4th International Conference on Innovative Computing, information and Control, ICICIC 2009

作者： Jin, Peng Wu, Yunfang Dai, Zuxu Liu, Yi Laboratory of Intelligent Information Processing and Application Leshan Normal University Leshan China Ministry of Education China College of Science Wuhan Institute of Technology Wuhan China

ISBN: (纸本)9780769538730

Word sense disambiguation (WSD) suffers from the lack of large scale corpus which annotated with word senses. The reason is that creating this corpus with human annotation is time-consuming and expensive. Active learning could save the human effort to obtain the same quality corpus. We investigate eight Chinese polysemous words and show the effectiveness of active learning for Chinese WSD. © 2009 IEEE.

关键词： Natural language processing systems

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：