检索结果-内蒙古大学图书馆

34th IEEE International Conference on Visual Communications and Image processing, VCIP 2019

作者： Zheng, Chaoda Xu, Yong Xu, Ruotao Chi, Hongyu Quan, Yuhui South China University of Technology School of Computer Science and Engineering Guangzhou China Peng Cheng Laboratory Shenzhen China Communication and Computer Network Laboratory of Guangdong China Guangdong Provincial Key Laboratory of Computational Intelligence and Cyberspace Information China

ISBN: (纸本)9781728137230

3D shape recognition via deep learning is drawing more and more attention due to huge industry interests. As 3D deep learning methods emerged, the view-based approaches have gained considerable success in object classification. Most of these methods focus on designing a pooling scheme to aggregate CNN features of multi-view images into a single compact one. However, these view-wise pooling techniques suffer from loss of visual information. To deal with this issue, an adaptive rank pooling layer is introduced in this paper. Unlike max-pooling which only considers the maximum or mean-pooling that treats each element indiscriminately, the proposed pooling layer takes all the elements into account and dynamically adjusts their importances during the training. Experiments conducted on ModelNet40 and ModelNet10 shows both efficiency and accuracy gain when inserting such a layer into a baseline CNN architecture. © 2019 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Patch-wise label propagation for MR brain segmentation based on multi-atlas images

Patch-wise label propagation for MR brain segmentation based...

引用

作者： Wang, Yan Zu, Chen Ma, Zongqing Luo, Yong He, Kun Wu, Xi Zhou, Jiliu College of Computer Science Sichuan University Chengdu China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou350121 China College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing China Department of Head and Neck and Mammary Oncology West China Hospital Sichuan University Chengdu China College of Computer Science Chengdu University of Information Technology Chengdu China

In many neuroscience and clinical studies, accurate and automatic segmentation of subcortical structures is an important and difficult task. Multi-atlas-based segmentation method has been focus of considerable research due to its promising performance. In general, this technique first employs deformable image registration to construct the correspondences between pre-labeled atlas images and the target image. Then, using the acquired deformation field, labels in the atlas are propagated to the target image space. Obviously, anatomical differences between the target image and atlas images possibly affect the image registration accuracy, thus influencing the final segmentation performance. Another limitation is that the label propagation in most conventional multi-atlas based methods is implemented under a voxel-wise strategy, which cannot adequately utilize the local label information to determine the final label of the target sample. In this paper, we propose a patch-wise label propagation method based on multiple atlases for MR brain segmentation. First, each image patch is characterized by patch intensities and abundant texture features, to increase the accuracy of the patch-based similarity measurement. To determine the weights of the training patches for representing the test sample, a patch-based sparse coding procedure is employed. In the label propagation stage, to alleviate possible misalignment from the registration stage, we perform a patch-wise label propagation strategy in a nonlocal manner to predict the final label for each target sample. To evaluate the proposed segmentation method, we comprehensively implement our proposed method by conducting hippocampus segmentation on the ADNI data set. Experimental results demonstrate the effectiveness of the proposed method and show that the proposed method outperforms two conventional multi-atlas-based methods. © 2017, Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Image registration

来源：评论

学校读者我要写书评

暂无评论

An Effective Retinal Blood Vessel Segmentation by Using Automatic Random Walks Based on Centerline Extraction

引用

BioMed Research International 2020年第1期2020卷 7352129页

作者： Gao, Jianqing Chen, Guannan Lin, Wenru Smart Home Information Collection and Processing on Internet of Things Laboratory of Digital Fujian Fujian Jiangxia University Fuzhou 350108 China School of Electronic Information Science Fujian Jiangxia University Fuzhou 350108 China Key Laboratory of OptoElectronic Science and Technology for Medicine of Ministry of Education Fujian Provincial Key Laboratory for Photonics Technology Fujian Normal University Fuzhou 350007 China Fujian Provincial Engineering Technology Research Center of Photoelectric Sensing Application Fujian Normal University Fuzhou 350117 China College of Computer and Control Engineering Minjiang University Fuzhou 350121 China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou 350121 China

The retinal blood vessel analysis has been widely used in the diagnoses of diseases by ophthalmologists. According to the complex morphological characteristics of the blood vessels in normal and abnormal images, an automatic method by using the random walk algorithms based on the centerlines is proposed to segment retinal blood vessels. Hessian-based multiscale vascular enhancement filtering is used to display the vessel structures in maximum intensity projection. Random walk algorithm provides a unique and quality solution, which is robust to weak object boundaries. Seed groups in the random walk segmentation are labeled according to the centerlines, which are extracted by using the divergence of the normalized gradient vector field and the morphological method. Experiments of the proposed method are implemented on the publicly available STARE (the Structured Analysis of the Retina) database. The results are compared to other existing retinal blood vessel segmentation methods with respect to the accuracy, sensitivity, and specificity, and the proposed method is proved to be more sensitive in detecting the retinal blood vessels in both normal and pathological areas. © 2020 Jianqing Gao et al.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An approach to the applicability evaluation of moving target tracking algorithm 1

引用

2nd Chinese Conference on Pattern Recognition and computer Vision, PRCV 2019

作者： Xi, Runping Xue, Shaohui Han, Qianqian Chen, Jiaxin School of Computer Science Northwestern Polytechnical University Xi’an710129 China National Engineering Laboratory of Integrated Aero-Space-Ground-Ocean Big Data Application Technology Xi’an710129 China Shaanxi Provincial Key Laboratory of Speech and Image Information Processing Xi’an710129 China

ISBN: (数字)9783030317263

ISBN: (纸本)9783030317256

Objective and effective algorithm performance evaluation results are an important basis for the selection of tracking algorithms. Problems in the existing performance evaluation of moving target tracking algorithms include an enlarge number of trials, and in particular, failure to consider the influence of algorithm performance on the multifactor combination scenario. This study proposes a method based on the orthogonal test to evaluate algorithms. First, the factors and levels of the tracking algorithm are analyzed, and an orthogonal test dataset is constructed by using an orthogonal table. Second, the experiments of the performance evaluation are arranged with the dataset and the results are analyzed via range analysis. Finally, evaluation results show that the strong– weak sequence of factors affect the performance of the algorithm and the combination of levels form the factors that can achieve enhanced algorithm performance. Experimental results show that the proposed method can evaluate algorithms comprehensively, objectively, and effectively with decreased test and data volume. © Springer Nature Switzerland AG 2019.

关键词： Clutter (information theory)

来源：评论

学校读者我要写书评

暂无评论

A minimum spanning tree algorithm based on fuzzy weighted distance 5th

A minimum spanning tree algorithm based on fuzzy weighted di...

引用

5th Euro-China Conference on Intelligent Data Analysis and Applications, ECC 2018

作者： Sun, Lu Liang, Yong-quan Fan, Jian-cong Princeton University PrincetonNJ08544 United States College of Computer Science and Engineering Shandong University of Science and Technology Qingdao China Provincial Key Laboratory for Information Technology of Wisdom Mining of Shandong Province Shandong University of Science and Technology Qingdao China Provincial Experimental Teaching Demonstration Center of Computer Shandong University of Science and Technology Qingdao China

ISBN: (纸本)9783030037659

The traditional minimum spanning tree clustering algorithm uses a simple Euclidean distance metric method to calculate the distance between two entities. For the processing of noise data, the similarity can’t be well described. In this regard, first of all, we integrate fuzzy set theory to improve, and propose a method with indeterminacy fuzzy distance measurement. In the distance metric method, fuzzy set theory is introduced to measure the differences between two entities. Moreover, the attributes are fuzzy weighted on this basis, which overcomes the shortcomings of the simple Euclidean distance measurement method. So, it not only has a good tolerance for data noise to solve the misclassification of noise information in the actual data, but also takes into account the difference of distinguishability contribution degree of attributes in classification. Thus, the accuracy of clustering is improved, and it also has significance in practical project application. Then, the proposed distance metric is applied into the traditional MST clustering algorithm. Compared with the traditional MST clustering algorithm and other classical clustering algorithms, the results show that the MST algorithm based on the new distance metric is more effective. © Springer Nature Switzerland AG 2019.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Harmonized-Multinational qEEG norms (HarMNqEEG)

引用

NEUROIMAGE 2022年 256卷 119190-119190页

作者： Li, Min Wang, Ying Lopez-Naranjo, Carlos Hu, Shiang Reyes, Ronaldo Cesar Garcia Paz-Linares, Deirel Areces-Gonzalez, Ariosky Hamid, Aini Ismafairus Abd Evans, Alan C. Savostyanov, Alexander N. Calzada-Reyes, Ana Villringer, Arno Tobon-Quintero, Carlos A. Garcia-Agustin, Daysi Yao, Dezhong Dong, Li Aubert-Vazquez, Eduardo Reza, Faruque Razzaq, Fuleah Abdul Omar, Hazim Abdullah, Jafri Malin Galler, Janina R. Ochoa-Gomez, John F. Prichep, Leslie S. Galan-Garcia, Lidice Morales-Chacon, Lilia Valdes-Sosa, Mitchell J. Trondle, Marius Zulkifly, Mohd Faizal Mohd Rahman, Muhammad Riddha Bin Abdul Milakhina, Natalya S. Langer, Nicolas Rudych, Pavel Koenig, Thomas Virues-Alba, Trinidad A. Lei, Xu Bringas-Vega, Maria L. Bosch-Bayard, Jorge F. Valdes-Sosa, Pedro Antonio [a]The Clinical Hospital of Chengdu Brain Science Institute MOE Key Lab for Neuroinformation School of Life Science and Technology University of Electronic Science and Technology of China Chengdu China [b]Cuban Center for Neurocience La Habana Cuba [c]McGill Centre for Integrative Neuroscience Ludmer Centre for Neuroinformatics and Mental Health Montreal Neurological Institute Canada [d]Department of Neurosciences School of Medical Sciences Universiti Sains Malaysia Universiti Sains Malaysia Health Campus Kota Bharu Kelantan 16150 Malaysia [e]Brain and Behaviour Cluster School of Medical Sciences Universiti Sains Malaysia Health Campus Kota Bharu Kelantan 16150 Malaysia [f]Hospital Universiti Sains Malaysia Universiti Sains Malaysia Health Campus Kota Bharu Kelantan 16150 Malaysia [g]Humanitarian Institute Novosibirsk State University Novosibirsk 630090 Russia [h]Laboratory of Psychophysiology of Individual Differences Federal State Budgetary Scientific Institution Scientific Research Institute of Neurosciences and Medicine Novosibirsk 630117 Russia [i]Laboratory of Psychological Genetics at the Institute of Cytology and Genetics Siberian Branch of the Russian Academy of Sciences Novosibirsk 630090 Russia [j]University of Pinar del Río “Hermanos Saiz Montes de Oca” Pinar del Río Cuba [k]Department of Neurology Max Planck Institute for Human Cognitive and Brain Sciences Leipzig Germany [l]Department of Cognitive Neurology University Hospital Leipzig Leipzig Germany [m]Center for Stroke Research Charité-Universitätsmedizin Berlin Berlin Germany [n]Grupo Neuropsicología y Conducta - GRUNECO Faculty of Medicine Universidad de Antioquia Colombia [o]Research Department Institución Prestadora de Servicios de Salud IPS Universitaria Colombia [p]The Cuban center aging longevity and health Havana Cuba [q]Research Unit of NeuroInformation Chinese Academy of Medical Sciences Chengdu 2019RU035 China [r]School of Electrical Engineering Zhengzhou University Zhengzhou 4500

This paper extends frequency domain quantitative electroencephalography (qEEG) methods pursuing higher sensitivity to detect Brain Developmental Disorders. Prior qEEG work lacked integration of cross-spectral information omitting important functional connectivity descriptors. Lack of geographical diversity precluded accounting for site-specific variance, increasing qEEG nuisance variance. We ameliorate these weaknesses. (i) Create lifespan Riemannian multinational qEEG norms for cross-spectral tensors. These norms result from the HarMNqEEG project fostered by the Global Brain Consortium. We calculate the norms with data from 9 countries, 12 devices, and 14 studies, including 1564 subjects. Instead of raw data, only anonymized metadata and EEG cross spectral tensors were shared. After visual and automatic quality control, developmental equations for the mean and standard deviation of qEEG traditional and Riemannian DPs were calculated using additive mixed-effects models. We demonstrate qEEG "batch effects " and provide methods to calculate harmonized z-scores. (ii) We also show that harmonized Riemannian norms produce z-scores with increased diagnostic accuracy predicting brain dysfunction produced by malnutrition in the first year of life and detecting COVID induced brain dysfunction. (iii) We offer open code and data to calculate different individual z-scores from the HarMNqEEG dataset. These results contribute to developing bias-free, low-cost neuroimaging technologies applicable in various health settings.

关键词： Quantitative EEG EEG cross-spectrum Riemannian geometry Batch effects Z-score Harmonization Malnutrition Covid induced brain dysfunction Developmental Brain Chart

来源：评论

学校读者我要写书评

暂无评论

Matching Biomedical Ontologies with Long Short-Term Memory Networks

Matching Biomedical Ontologies with Long Short-Term Memory N...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Chao Jiang Xingsi Xue Intelligent Information Processing Research Center Fujian University of Technology Fuzhou Fujian China School of Computer Science and Mathematics Fujian University of Technology Fuzhou Fujian China Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology Fuzhou Fujian China Guangxi Key Laboratory of Automatic Detecting Technology and Instruments Guilin University of Electronic Technology Guilin Guangxi China Fujian Key Lab for Automotive Electronics and Electric Drive Fujian University of Technology Fuzhou Fujian China

ISBN: (数字)9781728162157

ISBN: (纸本)9781728162164

Semantic Web (SW) has attracted the increasing attention of researchers, which facilitates people to link and handle various data. Ontology is the kernel technique of SW, and biomedical ontology is a state-of-art biomedical knowledge modeling technique, which formally defines the biomedical concepts and their relationships. However, the same biomedical concepts in different biomedical ontologies could be defined in various contexts or with different terms, which yields the biomedical ontology heterogeneity problem. It is crucial to find mapping among heterogeneity concepts of different biomedical ontologies for bridging the semantic gaps, which is the so-called biomedical ontology matching. Biomedical ontology matching problem is an open challenge due to the rich semantic meaning and the flexible representation on a biomedical concept. To address this challenging problem, in this work, it is regarded as a binary classification problem, and a Long Short-Term Memory Networks (LSTM)-based ontology matching technique is proposed to solve it. Our proposal improves the quality of the alignment by introducing the char-embedding technique, which takes into account the semantic and context information of concepts. The comparing results with OAEI's participants show the effectiveness of our proposal.

关键词： Ontologies Semantics Logic gates Training Human anatomy Proposals Biomedical measurement

来源：评论

学校读者我要写书评

暂无评论

Unsupervised ensemble learning based on graph embedding for image clustering 25th

Unsupervised ensemble learning based on graph embedding for ...

引用

25th International Conference on Neural information processing, ICONIP 2018

作者： Luo, Xiaohui Zhang, Li Li, Fanzhang Hu, Chengxiang School of Computer Science and Technology and Joint International Research Laboratory of Machine Learning and Neuromorphic Computing Provincial Key Laboratory for Computer Information Processing Technology Soochow University SuzhouJiangsu215006 China

ISBN: (纸本)9783030041816

Manifold learning has attracted more and more attention in machine learning for past decades. Unsupervised Large Graph Embedding (ULGE), which performs well on the large-scale data, has been proposed for manifold learning. To improve the clustering performance, a novel Unsupervised Ensemble Learning based on Graph Embedding (UEL-GE) is explored, which takes ULGE to get low-dimensional embeddings of the given data and uses the K-means method to obtain the clustering results. Furthermore, the multiple clusterings are corrected by using the bestMap method. Finally, the corrected clusterings are combined to generate the final clustering. Extensive experiments on several data sets are conducted to show the efficiency and effectiveness of the proposed ensemble learning method. © Springer Nature Switzerland AG 2018.

关键词： K-means clustering

来源：评论

学校读者我要写书评

暂无评论

A Machine Learning-Assisted Self-powered and Wearable Optical Sensor Glove for Gesture Recognition

引用

Journal of Lightwave technology 2025年

作者： Zou, Yang Lu, Chenxu Zhang, Chaomao Chen, Guozhen Kuang, Renfei Chen, Zhenshi Min, Rui Huang, Quandong Zhu, Shuyan Peng, Yungen Song, Jingcui Chen, Qingming Sun Yat-Sen University School of Microelectronics Science and Technology Guangdong Zhuhai519082 China Fujian Xiamen361005 China Guangdong 519000 China Sun Yat-Sen University School of Software Engineering Guangdong Zhuhai519082 China Huzhou College School of Electronic Information Zhejiang Huzhou313002 China Beijing Normal University Department of Psychology Faculty of Arts and Sciences Zhuhai519087 China Beijing Normal University Faculty of Psychology Beijing100875 China Sun Yat-sen University School of Electronics and Information Technology Guangdong Provincial Key Laboratory of Optoelectronic Information Processing Chips and Systems Guangzhou510006 China Guangdong University of Technology Institute of Advanced Photonics Technology School of Information Engineering Guangzhou China

Gesture recognition is a vital component of human-computer interaction (HCI), which plays a key role in artificial intelligent (AI) technology. Self-powered, portable and wearable sensors are highly desirable for HCI applications. Optical wearable sensors have gained widespread attention in gesture recognition due to their high sensitivity and great biocompatibility. This paper reports a novel mechanoluminescent (ML) polymer optical fiber-based glove designed for self-powered and portable gesture recognition. The elastic ML optical fiber directly converts finger movements into fluorescence for strain sensing. Combined with the supplementary alumina nanoparticles, the fluorescence intensity of ZnS: Cu ML phosphors has been enhanced by 7 times to achieve a high-performance strain sensor. By integrating five ML fibers into a flexible printed circuit (FPC) with a wireless communication unit, we developed a smart glove capable of gesture detection. With the assistance of machine-learning training, the proposed glove can accurately identify six hand gestures and five grasping actions with recognition accuracies of 100% and 90%, respectively. This portable intelligent glove operates without external light sources and electrical drivers, making it highly suitable for potential applications in HCI and AI fields. © 1983-2012 IEEE.

关键词： Fiber optic sensors

来源：评论

学校读者我要写书评

暂无评论

Fully distributed certificateless threshold signature without random oracles

引用

Science China(information Sciences) 2018年第9期61卷 259-269页

作者： Wenjie YANG Weiqi LUO Xizhao LUO Jian WENG Anjia YANG College of Cyber Security/College of Information Science and Technology Jinan University Guangdong Key Laboratory of Data Security and Privacy Preserving Guangzhou Key Laboratory of Data Security and Privacy Preserving School of Computer and Technology Soochow University

A certificateless(t,n)threshold signature(CLTS)scheme allows at least t members to cooperatively sign a message on behalf of an n-member group,which is a good way to share the responsibility and *** researchers have f... 详细信息

关键词： Fully distributed certificateless threshold signature without random oracles PKR Si DKG CLS

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：