检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Yang, Zhiyong Xu, Qianqian Bao, Shilong Cao, Xiaochun Huang, Qingming The School of Computer Science and Technology University of Chinese Academy of Sciences Beijing101408 China The Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China The State Key Laboratory of Information Security Institute of Information Engineering Chinese Academy of Sciences Beijing100093 China The School of Cyber Security University of Chinese Academy of Sciences Beijing100049 China School of Cyber Science and Technology Sun Yat-sen University Shenzhen518100 China University of Chinese Academy of Sciences Beijing101408 China Peng Cheng Laboratory Shenzhen518055 China

The Area under the ROC curve (AUC) is a well-known ranking metric for problems such as imbalanced learning and recommender systems. The vast majority of existing AUC-optimization-based machine learning methods only focus on binary-class cases, while leaving the multiclass cases unconsidered. In this paper, we start an early trial to consider the problem of learning multiclass scoring functions via optimizing multiclass AUC metrics. Our foundation is based on the M metric, which is a well-known multiclass extension of AUC. We first pay a revisit to this metric, showing that it could eliminate the imbalance issue from the minority class pairs. Motivated by this, we propose an empirical surrogate risk minimization framework to approximately optimize the M metric. Theoretically, we show that: (i) optimizing most of the popular differentiable surrogate losses suffices to reach the Bayes optimal scoring function asymptotically;(ii) the training framework enjoys an imbalance-aware generalization error bound, which pays more attention to the bottleneck samples of minority classes compared with the traditional O(p1/N) result. Practically, to deal with the low scalability of the computational operations, we propose acceleration methods for three popular surrogate loss functions, including the exponential loss, squared loss, and hinge loss, to speed up loss and gradient evaluations. Finally, experimental results on 11 real-world datasets demonstrate the effectiveness of our proposed framework.. © 2021, CC BY.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Tracking control with event-triggered strategy for multi-agent systems with noises

Tracking control with event-triggered strategy for multi-age...

引用

作者： Tang, Zhaojun Li, Chuandong Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing Department of Electronics and Information Engineering Southwest University Chongqing400715 China School of Science Chongqing University of Technology Chongqing400054 China

This paper is concerned with a tracking control problem of multi-agent systems with noises. It is assumed that each agent in the network updates its state only at some discrete time instants, which determined by the event-triggered condition, and the agents are affected by noises. In order to attenuate the effect of noises, consensus-gain function is introduced in the control protocol. Centralized and decentralized event-triggered protocols are proposed to ensure that the followers track the considered leader. With the help of matrix theory and Lyapunov method, sufficient conditions are derived to solve the mean square tracking control. Simulation results are provided to illustrate the theoretical results. © 2018 John Wiley & Sons, Ltd.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Anomalydae: Dual Autoencoder for Anomaly Detection on Attributed Networks

Anomalydae: Dual Autoencoder for Anomaly Detection on Attrib...

引用

IEEE International Conference on Acoustics, Speech and Signal processing

作者： Haoyi Fan Fengbin Zhang Zuoyong Li School of Computer Science and Technology Harbin University of Science and Technology Harbin China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou China

ISBN: (数字)9781509066315

ISBN: (纸本)9781509066322

Anomaly detection on attributed networks aims at finding nodes whose patterns deviate significantly from the majority of reference nodes, which is pervasive in many applications such as network intrusion detection and social spammer detection. However, most existing methods neglect the complex cross-modality interactions between network structure and node attribute. In this paper, we propose a deep joint representation learning framework for anomaly detection through a dual autoencoder (AnomalyDAE), which captures the complex interactions between network structure and node attribute for high-quality embeddings. Specifically, Anoma-lyDAE consists of a structure autoencoder and an attribute autoencoder to learn both node embedding and attribute embedding jointly in latent space. Moreover, attention mechanism is employed in structure encoder to learn the importance between a node and its neighbors for an effective capturing of structure pattern, which is important to anomaly detection. Besides, by taking both the node embedding and attribute embedding as inputs of attribute decoder, the cross-modality interactions between network structure and node attribute are learned during the reconstruction of node attribute. Finally, anomalies can be detected by measuring the reconstruction errors of nodes from both the structure and attribute perspectives. Extensive experiments on real-world datasets demonstrate the effectiveness of the proposed method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Model-data co-driven U-net segmentation network for multimodal lung tumor images

引用

Applied Soft Computing 2025年 180卷

作者： Tao Zhou Pei Dang Yunfeng Pan Caiyue Peng Qitao Liu Huiling Lu Fuyuan Hu School of Computer Science and Engineering North Minzu University Yinchuan 750021 China Key Laboratory of Image and Graphics Intelligent Processing of State Ethnic Affairs Commission North Minzu University Yinchuan 750021 China School of Medical information and Engineering Ningxia Medical University Yinchuan 750004 China School of Electronic& Information Engineering Suzhou University of Science and Technology Suzhou 215009 China

There are some challenges in multimodal medical image segmentation. Based on this, the Model-Data Co-driven U-Net Segmentation Network for Multimodal Lung Tumor Images is proposed. About “How to extract edge features in CT image?”, Edge-Driven U-Net is designed, which includes CT Data Stream Edge-Driven Module. The model ability to perceive lesion edge features is improved. About “How to extract position features in PET image?”, Position-Driven U-Net is designed, which includes PET Data Stream Position-Driven Module. The model ability to perceive lesion position features is improved. About “How to extract content features in PET/CT image?”, Content-Driven U-Net is designed, which includes PET/CT Data Stream Content-Driven Module. Under the guidance of semantic information in deep features, the model ability to perceive lesion content features is improved. About “How to fuse image features of PET/CT, PET and CT images?”, Model-Data Co-driven Module is designed. The main work of this model are as following: Firstly, the Shallow Model-Data Co-driven Module is designed, which realizes the interactive learning of different model data streams. Secondly, the Deep Model-Data Co-driven Module is designed, which realizes the interactive guide to learn position, edge and content features. The effectiveness of Model-Data Co-driven U-Net Segmentation Network for Multimodal Lung Tumor Images is validated on a clinical multimodal lung medical image dataset. The results for Miou, Dice, Voe, Rvd, Acc, and Recall are 91.60 %，95.94 %，95.92 %，95.73 %，97.92 and 95.28 % in lung lesion segmentation. The method proposed in this paper has positive significance for computer-aided diagnosis.

关键词：

来源：评论

学校读者我要写书评

暂无评论

On the transferability of adversarial attacks against neural text classifier

arXiv

引用

arXiv 2020年

作者： Yuan, Liping Zheng, Xiaoqing Zhou, Yi Hsieh, Cho-Jui Chang, Kai-Wei School of Computer Science Fudan University Shanghai China Shanghai Key Laboratory of Intelligent Information Processing Department of Computer Science University of California Los Angeles United States

Deep neural networks are vulnerable to adversarial attacks, where a small perturbation to an input alters the model prediction. In many cases, malicious inputs intentionally crafted for one model can fool another model. In this paper, we present the first study to systematically investigate the transferability of adversarial examples for text classification models and explore how various factors, including network architecture, tokenization scheme, word embedding, and model capacity, affect the transferability of adversarial examples. Based on these studies, we propose a genetic algorithm to find an ensemble of models that can be used to induce adversarial examples to fool almost all existing models. Such adversarial examples reflect the defects of the learning process and the data bias in the training set. Finally, we derive word replacement rules that can be used for model diagnostics from these adversarial examples. © 2020, CC BY.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

Learning data-adaptive non-parametric kernels

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2020年第1期21卷 8590-8628页

作者： Fanghui Liu Xiaolin Huang Chen Gong Jie Yang Li Li Department of Electrical Engineering ESAT-STADIUS KU Leuven Belgium Institute of Image Processing and Pattern Recognition Institute of Medical Robotics Shanghai Jiao Tong University Shanghai China PCA Lab Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology China and Department of Computing Hong Kong Polytechnic University Hong Kong SAR China Department of Automation BNRist Tsinghua University China

In this paper, we propose a data-adaptive non-parametric kernel learning framework in margin based kernel methods. In model formulation, given an initial kernel matrix, a data-adaptive matrix with two constraints is imposed in an entry-wise scheme. Learning this data-adaptive matrix in a formulation-free strategy enlarges the margin between classes and thus improves the model flexibility. The introduced two constraints are imposed either exactly (on small data sets) or approximately (on large data sets) in our model, which provides a controllable trade-off between model flexibility and complexity with theoretical demonstration. In algorithm optimization, the objective function of our learning framework is proven to be gradient-Lipschitz continuous. Thereby, kernel and classifier/regressor learning can be efficiently optimized in a unified framework via Nesterov's acceleration. For the scalability issue, we study a decomposition-based approach to our model in the large sample case. The effectiveness of this approximation is illustrated by both empirical studies and theoretical guarantees. Experimental results on various classification and regression benchmark data sets demonstrate that our non-parametric kernel learning framework achieves good performance when compared with other representative kernel learning based algorithms.

关键词： support vector machines non-parametric kernel learning gradient-Lipschitz continuous

来源：评论

学校读者我要写书评

暂无评论

Global stability of the periodic solution of the three level food chain model with extinction of top predator

arXiv

引用

arXiv 2021年

作者： Cheng, Kaijen You, Hongming Yang, Ting-Hui School of Mathematics and Statistics Zhaoqing University Guangdong Zhaoqing526061 China College of Mathematics and Computer Science Quanzhou Normal University Quanzhou362000 China Department of Mathematics Tamkang University No. 151 Yingzhuan Road Tamsui Dist. New Taipei City25137 Taiwan Fujian Provincial Key Laboratory of Data-Intensive Computing Key Laboratory of Intelligent Computing and Information Processing School of Mathematics and Computer Science Quanzhou Normal University Quanzhou China

In this work, we revisit the classical Holling type II three species food chain model from a different viewpoint. Two critical parameters λ1 and λ2 dependent on all parameters are defined. The existence and local stabilities of all equilibria can be reformulated by λ1 and λ2, and the complete classifications of parameters and its corresponding dynamics are given. Moreover, with the extinction of top-predator, there is an invariant two dimensional subsystem containing the prey and the intermediate predator. We prove the global stability of the boundary equilibrium in 3+ by differential inequality as well as Butler-McGehee lemma if it is stable. Alternatively, there is a unique limit cycle when the boundary equilibrium lost its stability, and we also show the global stability of the limit cycle in 3+ by differential inequality and computing the Floquet Multipliers. Finally, some interesting numerical simulations, the chaotic and the bi-stability phenomena, are presented numerically. A brief discussion and biological implications are also *** Codes 92D25 Copyright © 2021, The Authors. All rights reserved.

关键词： Stability

来源：评论

学校读者我要写书评

暂无评论

Research on Accurate Model of Lithium Battery

Research on Accurate Model of Lithium Battery

引用

第32届中国控制与决策会议

作者： Yongxue Ye Hongyan Ma Jingjian Yang Beijing University of Civil Engineering and Architecture Beijing Key Laboratory of Intelligent Processing for Building Big Data College of Electrical and Information EngineeringBeijing University of Civil Engineering and Architecture

In order to build accurately the external characteristic curve of lithium-ion batteries,this paper improve existing lithium-ion battery models,and verify the improved lithium-ion battery model in *** this paper,for reflecting the accuracy of the improved external characteristics of the lithium-ion battery model,the external characteristic curves of lithium-ion battery model simulation before and after improvement are compared under different temperature and discharge current *** comparison results show that under different operating conditions,the improved model can more accurately reflect the experimental conditions of lithium battery discharge in the concave function discharge area than before the improvement.

关键词： lithium battery mathematical model research Simulink modeling data comparison

来源：评论

学校读者我要写书评

暂无评论

Joint Coronary Centerline Extraction And Lumen Segmentation From Ccta Using Cnntracker And Vascular Graph Convolutional Network

Joint Coronary Centerline Extraction And Lumen Segmentation ...

引用

IEEE International Symposium on Biomedical Imaging

作者： Ruochen Gao Zhihui Hou Jun Li Hu Han Bin Lu S. Kevin Zhou Medical Imaging Robotics Analytic Computing Laboratory/Engineering (MIRACLE) Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Beijing China University of Chinese Academy of Sciences Beijing China Fuwai Hospital Chinese Academy of Medical Sciences and Peking Union Medical College Peng Cheng Laboratory Shenzhen China

Automatic analysis of coronary artery in coronary computed tomography angiography (CCTA) is important for clinicians to diagnose and evaluate coronary artery disease (CAD). Often there are two analysis tasks involved: centerline extraction and lumen segmentation, which are related yet often treated separately in the literature. In this work, we leverage their mutual relationship and propose an automatic approach for joint centerline extraction and lumen segmentation from CCTA using a hybrid of deep learning models. Our approach features the following designs, including: (i) the use of CNNTracker that traces out the centerline from seeds to detected ostia or the end of vessels, which fixes the breakage issue commonly found in previous pixel-based segmentation methods; (ii) a vascular Graph Convolutional Network (GCN) that leverages the geometric shape prior for accurate mesh-based lumen segmentation; (iii) the alternation between CNNTracker and GCN that refines the centerline and reduces the drift in tracking. We experiment the proposed method on CCTA data from 101 patients and achieve state-of-the-art performance in both centerline extraction and lumen segmentation of the right coronary artery (RCA), left anterior descending (LAD), and left circumflex (LCX).

关键词： Deep learning Solid modeling Image segmentation Shape Predictive models Feature extraction Data mining

来源：评论

学校读者我要写书评

暂无评论

Multi-scale convolutional neural network for road extraction in remote sensing imagery 2nd

Multi-scale convolutional neural network for road extraction...

引用

2nd CCF International Conference on Artificial Intelligence, CCF-ICAI 2019

作者： Li, Jun Gong, Xue Zhang, Yiming Key Laboratory of Intelligent Computing and Information Processing Ministry of Education Xiangtan University Xiangtan411105 China College of Civil Engineering and Mechanics Xiangtan University Xiangtan411105 China

ISBN: (纸本)9789813292970

Road is an important semantic region in remote sensing imagery and plays an important role in many applications. Deep learning has obtained a great success in image classification, since it can directly learn from labeled training samples and extract different level image features to encode the input image. In this paper, we propose a multi-scale convolutional neural network (MSCNN) for extracting road from high-resolution remote sensing image, in which road detection can be seen as a regional classification. This core trainable detection engine consists of an encoder-decoder network and a fusion model. Firstly, image was encoded as a feature representation with several stacked convolutional layers. And then guided by the different scale road training data, the pre-trained decoder networks output a series of classification maps. Finally, we investigate the fusion model utilizing different scale classification maps and obtain a final road decision map. To validate the performance of the proposed method, we test our MSCNN based method and other state-of-the-art approaches on two challenging datasets of high-resolution images. Experiments show our method gets the best results both in quantitative and qualitative evaluation. © 2019, Springer Nature Singapore Pte Ltd.

关键词： Semantics

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：