检索结果-内蒙古大学图书馆

第三十八届中国控制会议

作者： Jianglong Yu Xiwang Dong Qingdong Li Zhang Ren Ming Ma School of Automation Science and Electrical Engineering Science and Technology on Aircraft Control Laboratory Beihang University Shananxi Key Laboratory of Integrated and Intelligent Navigation Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Xi'an Research Institute of Navigation Technology

Practical adaptive time-varying output formation tracking problems for high-order nonlinear strict-feedback multiagent systems are investigated in this paper. The time-varying output formation tracking requires the followers' output vectors to track the output vector of the leader while achieving a time-varying formation. The dynamics of the leader and the followers can have uncertain mismatched nonlinearities while the leader's control input is also unknown. To deal with the mismatched nonlinearities, the backstepping techniques are utilized to construct the protocols. Firstly, visual controllers are designed to overcome the effects of the uncertainties while guaranteeing the stability of each layer. The complicated visual controllers are estimated by the neural networks. A full adaptive protocol is constructed with adaptive gains to avoid using the global information of the interaction topology. Then, an algorithm is presented to design the protocol, whose parameters are much less. Besides, the stability of the algorithm is proved by Lyapunov theories. Finally, simulation results are presented to prove the effectiveness.

关键词： Practical time-varying formation tracking Adaptive control High-order nonlinear dynamics Multi-agent systems Neural networks

来源：评论

学校读者我要写书评

暂无评论

A hybrid NSGA-II for matching biomedical ontology 14th

A hybrid NSGA-II for matching biomedical ontology

引用

14th International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIH-MSP 2018

作者： Xue, Xingsi Chen, Jie Chen, Junfeng Chen, Dongxu College of Information Science and Engineering Fujian University of Technology FuzhouFujian350118 China Intelligent Information Processing Research Center Fujian University of Technology FuzhouFujian350118 China Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology FuzhouFujian350118 China Fujian Key Lab for Automotive Electronics and Electric Drive Fujian University of Technology FuzhouFujian350118 China College of IOT Engineering Hohai University ChangzhouJiangsu China Fujian Medical University Union Hospital FuzhouFujian350001 China

ISBN: (纸本)9783030037444

Over the recent years, ontologies are widely used in the biomedical domains. However, biomedical ontology heterogeneity problem hamper the cooperation between intelligent applications based on biomedical ontologies. It is crucial to establish correspondences between the heterogeneous biomedical concepts in different ontologies, which is so-called biomedical ontology matching. Approaches based on Multi-Objective Evolutionary Algorithm (MOEA), such as NSGA-II, are emerging as a new methodology to solve the ontology matching problem. In this paper, to further improve the quality of biomedical ontology alignments, a hybrid NSGA-II is proposed, which modifies the knee solutions in the Pareto front by using a local search method. Experiment utilizes two biomedical ontology matching tracks provided by Ontology Alignment Evaluation Initiative (OAEI 2017). The experimental results show that our approach outperforms the participants of OAEI 2017 and NSGA-II based ontology matching technique. © Springer Nature Switzerland AG 2019.

关键词： Ontology

来源：评论

学校读者我要写书评

暂无评论

Correction: Identification of a novel bile marker clusterin and a public online prediction platform based on deep learning for cholangiocarcinoma

引用

BMC medicine 2024年第1期22卷 179页

作者： Long Gao Yanyan Lin Ping Yue Shuyan Li Yong Zhang Ningning Mi Mingzhen Bai Wenkang Fu Zhili Xia Ningzu Jiang Jie Cao Man Yang Yanni Ma Fanxiang Zhang Chao Zhang Joseph W Leung Shun He Jinqiu Yuan Wenbo Meng Xun Li The First School of Clinical Medicine Lanzhou University Lanzhou 730030 Gansu China. Department of General Surgery The First Hospital of Lanzhou University Lanzhou 730030 Gansu China. Gansu Province Key Laboratory of Biological Therapy and Regenerative Medicine Transformation Lanzhou 730030 Gansu China. School of Medical Information and Engineering Xuzhou Medical University Xuzhou 221004 Jiangsu China. Clinical Research Center Big Data Center The Seventh Affiliated Hospital Sun Yat-Sen University Shenzhen 518107 Guangdong China. Division of Gastroenterology UC Davis Medical Center and Sacramento VA Medical Center Sacramento CA 95817 USA. Department of Endoscopy National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital Chinese Academy of Medical Sciences and Peking Union Medical College Beijing China. heshuns@***. Clinical Research Center Big Data Center The Seventh Affiliated Hospital Sun Yat-Sen University Shenzhen 518107 Guangdong China. yuanjq5@***. The First School of Clinical Medicine Lanzhou University Lanzhou 730030 Gansu China. mengwb@***. Department of General Surgery The First Hospital of Lanzhou University Lanzhou 730030 Gansu China. mengwb@***. Gansu Province Key Laboratory of Biological Therapy and Regenerative Medicine Transformation Lanzhou 730030 Gansu China. mengwb@***.

来源：评论

学校读者我要写书评

暂无评论

Adaptive multi-graph hashing for scalable multimedia retrieval

引用

Pattern Recognition Letters 2019年

作者： Xiang, Lingyun Zhao, Guohan Shen, Xiaobo Li, Feng Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation Changsha University of Science and Technology Changsha410114 China School of Computer and Communication Engineering Changsha University of Science and Technology Changsha410114 China Hunan Provincial Key Laboratory of Smart Roadway and Cooperative Vehicle-Infrastructure Systems Changsha410114 China School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China

Hashing has become a promising technique to be applied to the large-scale visual retrieval tasks. Multi-view data has multiple views, providing more comprehensive information. Existing hashing methods measure the similarity among the data points by the pre-defined graph Laplacian in each view separately, and thus ignore the underlying common structures across different views. In this paper, we propose a novel hashing method, called adaptive multi-graph hashing (AMGH) to address the above issue. AMGH uses the adaptive weights among the data points, and the weights of each view to characterize the common structure of multi-view data. In addition, AMGH further minimizes the quantization errors. We develop an efficient alternating algorithm to solve the formulated optimization problem. The experiments on three large-scale datasets demonstrate the superiority of the proposed method over the existing multi-view hashing methods. © 2019

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

Mapping Heavy Metals in Cultivated Soils Based on Land Use Types and Cokriging 5th

Mapping Heavy Metals in Cultivated Soils Based on Land Use T...

引用

5th International Conference on Geo-Spatial knowledge and Intelligence, GSKI 2017

作者： Zhao, Jinling Liu, Chuang Song, Qixiang Jiang, Yan Hong, Qi Huang, Linsheng Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University Hefei230039 China Anhui Engineering Laboratory of Agro-Ecological Big Data Anhui University Hefei230601 China Information Engineering Institute Suzhou University Suzhou234000 China

ISBN: (纸本)9789811308925

It is extremely important to explore the heavy metal content and spatial distribution in different cultivated soils. In our study, cokriging (COK) method was used to investigate the relationship between heavy metals and land use types. A total of six heavy metals including Zn, Fe, Cu, Mn, B, S were selected to forecast the heavy metals in cultivated soils. Five types of cultivated land were considered in the study area, including vegetable land, irrigated land, irrigated paddy field, dry land, orchard. Test of normality was firstly carried out to assure that higher prediction accuracy can be obtained, and then correlation analysis and analysis of variance (ANOVA) were performed to find out the most sensitive heavy metals for spatial interpolation. The analysis results showed that Zn, Cu and Fe were the primary heavy metals in soil of the study area. It was obvious that the effect of Mn and Fe were much greater caused by land use types, while they were smaller for B and S. Three errors of mean standard (MS), root mean square error (RMSE), and root mean square standardized error (RMSSE) were derived to assess the prediction accuracy. In comparison with ordinary kriging (OK), the MS of COK approached to 1, the RMSE was much smaller and the RMSSE also approached to 1, which showed that COK can make better predictions than OK. © 2018, Springer Nature Singapore Pte Ltd.

关键词： Heavy metals

来源：评论

学校读者我要写书评

暂无评论

Stacked Cross Refinement Network for Edge-Aware Salient Object Detection

Stacked Cross Refinement Network for Edge-Aware Salient Obje...

引用

International Conference on Computer Vision (ICCV)

作者： Zhe Wu Li Su Qingming Huang School of Computer Science and Technology University of Chinese Academy of Sciences (UCAS) Beijing China Key Lab of Big Data Mining and Knowledge Management UCAS Beijing China Key Lab of Intell. Info. Process. Inst. of Comput. Tech. CAS Beijing China Peng Cheng Laboratory ShenZhen China

ISBN: (数字)9781728148038

ISBN: (纸本)9781728148045

Salient object detection is a fundamental computer vision task. The majority of existing algorithms focus on aggregating multi-level features of pre-trained convolutional neural networks. Moreover, some researchers attempt to utilize edge information for auxiliary training. However, existing edge-aware models design unidirectional frameworks which only use edge features to improve the segmentation features. Motivated by the logical interrelations between binary segmentation and edge maps, we propose a novel Stacked Cross Refinement Network (SCRN) for salient object detection in this paper. Our framework aims to simultaneously refine multi-level features of salient object detection and edge detection by stacking Cross Refinement Unit (CRU). According to the logical interrelations, the CRU designs two direction-specific integration operations, and bidirectionally passes messages between the two tasks. Incorporating the refined edge-preserving features with the typical U-Net, our model detects salient objects accurately. Extensive experiments conducted on six benchmark datasets demonstrate that our method outperforms existing state-of-the-art algorithms in both accuracy and efficiency. Besides, the attribute-based performance on the SOC dataset show that the proposed model ranks first in the majority of challenging scenes. Code can be found at https://***/wuzhe71/SCAN.

关键词： Image edge detection Task analysis Feature extraction Object detection Image segmentation Silicon Computational modeling

来源：评论

学校读者我要写书评

暂无评论

A novel hyperspectral index for quantifying chlorophyll-a concentration in productive waters

引用

Remote Sensing of Environment 2025年 328卷

作者： Huaxin Yao Junsheng Li Yaming Zhou Yao Liu Dalin Jiang Shoujing Yin Xuezhu Jiang Fangfang Zhang Shenglei Wang Bing Zhang Key Laboratory of Digital Earth Science Aerospace Information Research Institute Chinese Academy of Sciences Beijing 100094 China College of Resources and Environment University of Chinese Academy of Sciences Beijing 100049 China International Research Center of Big Data for Sustainable Development Goals Beijing 100094 China School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing 100049 China Satellite Application Center for Ecology and Environment Ministry of Ecology and Environment of the People's Republic of China Beijing 100094 China Land Satellite Remote Sensing Application Center Ministry of Natural Resources of China Beijing 100048 China Department of Biological and Environmental Studies University of Stirling Stirling United Kingdom

Hyperspectral remote sensing has great potential for monitoring chlorophyll-a concentration (Chla) in optically complex waters. However, various hyperspectral indices currently used for retrieving Chla in productive waters exhibit drawbacks due to interference from other water parameters, imperfect atmospheric correction, and the constraints imposed by discrete spectral bands. To address these issues, we proposed a novel spectral index called the Red-Edge reflectance Peak Width Index (REPWI) for productive waters, which is defined as the horizontal wavelength distance from the fixed wavelength of red reflectance valley (678 nm) to the intersection of the right side of the red-edge reflectance peak curve. Firstly, the bio-optical model was used to clarify the theoretical basis and relationship between REPWI and Chla. Then, in situ remote sensing reflectance and Chla data from 57 water bodies worldwide were used to calibrate and validate the REPWI-based Chla retrieval model. The REPWI-based model achieved high accuracy (coefficient of determination (R 2 ) of 0.92, mean relative error of 26.5 %, and root mean square error of 13.7 mg/m 3 ), significantly outperforming other spectral indices. Furthermore, REPWI maintained a strong correlation with Chla (R 2 = 0.87–0.90) when applied to major on-orbit hyperspectral satellites equivalent spectra. Finally, the REPWI-based Chla retrieval model was applied to ZY1-02D hyperspectral imagery, which obtained high accuracy and demonstrated resistance to imperfect atmospheric correction. In summary, this novel hyperspectral index, REPWI, has demonstrated a solid theoretical foundation and significant advantages in monitoring Chla in productive waters.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Nearest Neighbor Search Techniques Applied in the Nearest Feature Line Classifier 4th

Nearest Neighbor Search Techniques Applied in the Nearest Fe...

引用

4th Euro-China Conference on Intelligent data Analysis and Applications, ECC 2017

作者： Guo, Fang Pan, Jeng-Shyang Department of Information Science and Engineering Fujian University of Technology FuzhouFujian350118 China Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology FuzhouFujian350118 China

ISBN: (纸本)9783319685267

Pointing to the computational complexity to find the minimum distance in the nearest feature line (NFL) classification algorithm, the nearest neighbor search methods with Full Search (FS), Partial Distortion Search (PDS), Absolute Error Inequality (AEI) and Equal-average Nearest Neighbor Search (ENNS) is used to evaluate the calculated performance on NFL. The experimental results demonstrate that the computational complexity on NFL using these search techniques is different and some of the nearest neighbor search methods could improve the calculated performance on finding out the minimum distance applied in the NFL classification. © 2018, Springer International Publishing AG.

关键词： Nearest neighbor search

来源：评论

学校读者我要写书评

暂无评论

Learning Structured Twin-Incoherent Twin-Projective Latent Dictionary Pairs for Classification

Learning Structured Twin-Incoherent Twin-Projective Latent D...

引用

IEEE International Conference on data Mining (ICDM)

作者： Zhao Zhang Yulin Sun Zheng Zhang Yang Wang Guangcan Liu Meng Wang School of Computer Science and Technology Soochow University Suzhou China Key Laboratory of Knowledge Engineering with Big Data (Ministry of Education) Hefei University of Technology School of Computer Science and Information Engineering Hefei University of Technology Hefei China Bio-Computing Research Center Harbin Institute of Technology (Shenzhen) Shenzhen China School of Information and Control Nanjing University of Information Science and Technology Nanjing China

In this paper, we extend the popular dictionary pair learning (DPL) into the scenario of twin-projective latent flexible DPL under a structured twin-incoherence. Technically, a novel framework called Twin-Projective Latent Flexible DPL (TP-DPL) is proposed, which minimizes the twin-incoherence constrained flexibly-relaxed reconstruction error to avoid the possible over-fitting issue and produce accurate reconstruction. In this setting, TP-DPL integrates the twin-incoherence based latent flexible DPL and the joint embedding of codes as well as salient features by twin-projection into a unified model in an adaptive neighborhood-preserving manner. Therefore, TP-DPL can unify the procedures of salient feature representation and classification. The twin-incoherence constraint on coefficients and features can explicitly ensure high intra-class compactness and inter-class separation over them. TP-DPL also integrates the adaptive weighting to preserve local neighborhood of both coefficients and salient features within each class explicitly. For efficiency, TP-DPL selects the Frobenius-norm and abandons the costly l0/l1-norm for group sparse representation. Another byproduct is that TP-DPL can directly apply the class-specific twin-projective reconstruction residual to compute the label of data. Extensive results on public databases show that TP-DPL can deliver the state-of-the-art performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Rapid and accurate classification of retinal OCT diseases using reparameterized one-dimensional convolutional networks

引用

Biomedical Signal Processing and Control 2025年 110卷

作者： Dexun Zhang Mengjiao Zhang Youming Sun Wenjing Meng Zhenzhen Li Changmiao Wang Huoling Luo Zhengwei Zhang Tianqiao Zhang School of Life and Environmental Sciences Guilin University of Electronic Technology Guilin 541004 China Guangxi Key Laboratory of Wireless Wideband Communication and Signal Processing Guilin University of Electronic Technology Guilin 541004 China Guilin University of Electronic Technology Guilin 541004 China School of Information Engineering Nanchang Institute of Technology Nanchang 330099 China Shenzhen Research Institute of Big Data Shenzhen 518172 China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen 518055 China Department of Ophthalmology Jiangnan University Medical Center Wuxi 214002 China Department of Ophthalmology Wuxi No. 2 People’s Hospital Affiliated Wuxi Clinical College of Nantong University Wuxi 214002 China

Efficient and precise classification of retinal optical coherence tomography (OCT) images is crucial for accurate diagnosis of eye diseases. However, existing classification networks often struggle with balancing inference speed and accuracy. To address this, we propose a novel retinal disease classification network that leverages prior knowledge of OCT images. By employing structural reparameterization and transforming the convolutional kernel shape to 1D, our network enhances its ability to focus on the inherent layering information of OCT images. Experimental results demonstrate that our approach significantly improves inference speed while maintaining high classification accuracy, compared to conventional and state-of-the-art networks. This advancement addresses real-time diagnostic needs in clinical settings. Our source code is available at: https://***/xunlizhinian1124/1D-OCT-Classification .

关键词：

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：