检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Qi, Binhang Sun, Hailong Gao, Xiang Zhang, Hongyu SKLSDE Lab Beihang University China The University of Newcastle Australia Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100191 China

Despite great success in many applications, deep neural networks are not always robust in practice. For instance, a convolutional neuron network (CNN) model for classification tasks often performs unsatisfactorily in classifying some particular classes of objects. In this work, we are concerned with patching the weak part of a CNN model instead of improving it through the costly retraining of the entire model. Inspired by the fundamental concepts of modularization and composition in software engineering, we propose a compressed modularization approach, CNNSplitter, which decomposes a strong CNN model for N-class classification into N smaller CNN modules. Each module is a sub-model containing a part of the convolution kernels of the strong model. To patch a weak CNN model that performs unsatisfactorily on a target class (TC), we compose the weak CNN model with the corresponding module obtained from a strong CNN model. The ability of the weak CNN model to recognize the TC can thus be improved through patching. Moreover, the ability to recognize non-TCs is also improved, as the samples misclassified as TC could be classified as non-TCs correctly. Experimental results with two representative CNNs on three widely-used datasets show that the averaged improvement on the TC in terms of precision and recall are 12.54% and 2.14%, respectively. Moreover, patching improves the accuracy of non-TCs by 1.18%. The results demonstrate that CNNSplitter can patch a weak CNN model through modularization and composition, thus providing a new solution for developing robust CNN models. Copyright © 2022, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

A Channel-Augmented Multi-Domain Graph Convolutional Network for Fatigue Driving Detection

A Channel-Augmented Multi-Domain Graph Convolutional Network...

引用

Industrial Automation, Robotics and Control Engineering (IARCE), International Conference on

作者： Mingyi Sun Weigang Cui Yang Li Department of Automation Science and Electrical Engineering Beihang University Beijing China School of Engineering Medicine Beihang University Beijing China Department of Automation Science and Electrical Engineering State Key Laboratory of Virtual Reality Technology and Systems The Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing China

ISBN: (数字)9798350380323

ISBN: (纸本)9798350380330

Electroencephalography (EEG) has emerged as a crucial cornerstone within the realm of brain-computer interface (BCI) applications, with its significance notably pronounced in the field of fatigue detection. However, the inherent limitations of EEG acquisition equipment during real driving scenarios have contributed to the constrained robustness of existing models. Moreover, most of recent methods failed to extract robust multi-domain features, leading to a suboptimal performance. To address these challenges, we propose a novel channel-augmented multi-domain graph convolutional network (CA-MDGCNet). Specifically, the initial EEG signals are enriched by incorporating supplementary virtual EEG channels, distinguished as learnable parameters within the network architecture. Then, differential entropy features are extracted from the augmented EEG signals. Following this, a multi-domain graph convolutional network is designed to encode high-level EEG features by means of convolutions in diverse paths, which is beneficial to integrating the characteristics extracted from multiple domains. Finally, the classification block derives the detection outcome from the refined feature maps. To substantiate the potency of the proposed method, the validation was conducted on the publicly accessible SEED-VIG. The proposed CA-MDGCNet not only demonstrates more promising performance compared to state-of-the-art approaches but also underscores the potential viability of our method for the realm of fatigue driving detection.

关键词： Graph convolutional networks Convolution Service robots Neural activity Feature extraction Fatigue brain modeling Electroencephalography Entropy Robustness

来源：评论

学校读者我要写书评

暂无评论

A Multi-DOF Robot System Based on LightGBM-Driven EEG Decoding Model for BCI Human-Machine Interaction

A Multi-DOF Robot System Based on LightGBM-Driven EEG Decodi...

引用

Chinese Control Conference (CCC)

作者： Weidong Yan Zhaoliang Xu Yang Li The Department of Automation Science and Electrical Engineering Beihang University Beijing China The Beijing Advanced Innovation Center for Big Data and Brain Computing Beijing China State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China Advanced Institute of Information Technology Peking University Hangzhou China

In this study, a multi-degree-of-freedom (Multi-DOF) robot (MDR) system based on a LightGBM-driven electroencephalogram (EEG) decoding model is designed and developed to assist subjects with hand motor dysfunction in their daily activities and neurorehabilitation. The system mainly consists of a motor imagery electroencephalogram (MI-EEG) evoking layer, an intention decoding layer, and an interaction executive layer. The MI-EEG evoking layer initially displays a virtual reality (VR) motion imagination scenario, instructing the subjects to imagine a real hand gripping movement, simultaneously collecting the electrical EEG signals and preprocessing the EEG signals. Secondly, in the intention decoding layer, a network combining temporal-spectral feature fusion and LightGBM (TSFF-LightGBM) for MI-BCI classification is used to more effectively boost brain decoding accuracy and decrease decoding time. Finally, in the interaction executive layer, the Multi-DOF wearable robot is developed to offer hand grasp motion kinesthetic feedback and visual feedback synced with MI. The following are the key benefits of the proposed MDR system: (1) We propose a new lightweight network structure more suitable for brain computer interface (BCI) interaction systems, achieving more accurate decoding and shorter identification time in different data sets, which helps to improve the practicability of the system and promote the practical clinical application of BCI rehabilitation technology. (2) We integrate BCI, VR, a wearable Multi-DOF robot, motion kinesthetic feedback, and visual feedback to improve human-machine interaction. Compared to the most recent investigations, the average accuracy of the MDR system on the publicly accessible datasets BCI IV 2a and HGD reached 75.89% and 93.53%, respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Multi-Head Convolution Network with Attention Consistency for Facial Expression Recognition

A Multi-Head Convolution Network with Attention Consistency ...

引用

Chinese Control Conference (CCC)

作者： Wenkang Liu Mingyi Sun Yang Li the Department of Automation Science and Electrical Engineering Beihang University Beijing China the Beijing Advanced Innovation Center for Big Data and Brain Computing Beijing China State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China Advanced Institute of Information Technology Peking University Hangzhou China

In recent years, the demand for facial expression recognition applications has increased rapidly, and its research has received extensive attention from researchers. However, the current recognition methods based on deep learning ignore the idea of multiple head attention and semantic consistency, resulting in the model only paying attention to the local area of the feature map. In addition, the model's inconsistent attention to the images before and after the flip, resulting the poor robustness, poor interpretation, and other shortcomings in the model. To address the above problems, we propose an Affinity Separation Loss (ASLoss), which improves the separability of samples through clustering. Moreover, a Separate Multi-head Attention block (SMA), and a Zonal Loss (ZLoss) are also designed to decentralize the model's attention. Experimental results demonstrate that our proposed MACNet method achieves competitive recognition performance on two public datasets RAF-DB and FERPlus.

关键词：

来源：评论

学校读者我要写书评

暂无评论

HiGIL: Hierarchical Graph Inference Learning for Fact Checking

HiGIL: Hierarchical Graph Inference Learning for Fact Checki...

引用

IEEE International Conference on data Mining (ICDM)

作者： Qianren Mao Yiming Wang Chenghong Yang Linfeng Du Hao Peng Jia Wu Jianxin Li Zheng Wang Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing China Zhongguancun Laboratory Beijing China Department of Computing Macquarie University Sydney Australia The School of Computing University of Leeds Leeds U.K.

Fact-checking is vital for countering fake news. This process requires verifying the truthfulness of a claim by reasoning about multiple pieces of evidence. The current dominant approach depends upon capturing the claim-evidence relations from a claim-evidence interaction graph. Existing solutions utilize phrase-level semantics on a single-granularity but ignore other hierarchical features, such as fact- and sentence-level textual semantics and their logical topology. Since the hierarchical features often provide hints to infer collaborative high-order clues that can be essential for fact-checking, they should not be overlooked. This paper proposes a better method to model the claim-evidence graph in a multi-granularity manner. Doing so allows one to exploit more textual semantics and logical topology between a claim and its evidence. To achieve the target, we first employ a graph inference learning framework to infer graph nodes on different granular semantic units within their hierarchical topology. Then, an inference learning procedure is designed to optimize the global textual similarity and local topological reachability from the claim-evidence graph. We evaluate our approach by applying it to fact-checking on an open dataset, and experimental results show that our technique outperforms existing graph-based techniques by a large margin.

关键词： Semantics Collaboration Information retrieval Cognition Topology data mining Usability

来源：评论

学校读者我要写书评

暂无评论

Hyperbolic Geometric Latent Diffusion Model for Graph Generation

arXiv

引用

arXiv 2024年

作者： Fu, Xingcheng Gao, Yisen Wei, Yuecen Sun, Qingyun Peng, Hao Li, Jianxin Li, Xianxian Key Lab of Education Blockchain and Intelligent Technology Ministry of Education Guangxi Normal University Guilin China Institute of Artificial Intelligence Beihang University Beijing China School of Software Beihang University Beijing China Beijing Advanced Innovation Center for Big Data and Brain Computing School of Computer Science and Engineering Beihang University Beijing China

Diffusion models have made significant contributions to computer vision, sparking a growing interest in the community recently regarding the application of them to graph generation. Existing discrete graph diffusion models exhibit heightened computational complexity and diminished training efficiency. A preferable and natural way is to directly diffuse the graph within the latent space. However, due to the non-Euclidean structure of graphs is not isotropic in the latent space, the existing latent diffusion models effectively make it difficult to capture and preserve the topological information of graphs. To address the above challenges, we propose a novel geometrically latent diffusion framework HypDiff. Specifically, we first establish a geometrically latent space with interpretability measures based on hyperbolic geometry, to define anisotropic latent diffusion processes for graphs. Then, we propose a geometrically latent diffusion process that is constrained by both radial and angular geometric properties, thereby ensuring the preservation of the original topological properties in the generative graphs. Extensive experimental results demonstrate the superior effectiveness of HypDiff for graph generation with various topologies. Copyright © 2024, The Authors. All rights reserved.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

Curvature Graph Generative Adversarial Networks

arXiv

引用

arXiv 2022年

作者： Li, Jianxin Fu, Xingcheng Sun, Qingyun Ji, Cheng Tan, Jiajun Wu, Jia Peng, Hao Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100191 China School of Computer Science and Engineering Beihang University Beijing100191 China School of Computing Macquarie University Sydney Australia

Generative adversarial network (GAN) is widely used for generalized and robust learning on graph data. However, for non-Euclidean graph data, the existing GAN-based graph representation methods generate negative samples by random walk or traverse in discrete space, leading to the information loss of topological properties (e.g. hierarchy and circularity). Moreover, due to the topological heterogeneity (i.e., different densities across the graph structure) of graph data, they suffer from serious topological distortion problems. In this paper, we proposed a novel Curvature Graph Generative Adversarial Networks method, named CurvGAN, which is the first GAN-based graph representation method in the Riemannian geometric manifold. To better preserve the topological properties, we approximate the discrete structure as a continuous Riemannian geometric manifold and generate negative samples efficiently from the wrapped normal distribution. To deal with the topological heterogeneity, we leverage the Ricci curvature for local structures with different topological properties, obtaining to low-distortion representations. Extensive experiments show that CurvGAN consistently and significantly outperforms the state-of-the-art methods across multiple tasks and shows superior robustness and generalization. Copyright © 2022, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Universality of explosive percolation under product and sum rule

引用

Physical Review E 2023年第3期108卷 034108-034108页

作者： Ziting Luo Wei Chen Jan Nagler LMIB and School of Mathematical Sciences Beihang University Beijing 100191 China Institute of Artificial Intelligence Beihang University Beijing 100191 China Zhongguancun Laboratory Beijing 100094 People's Republic of China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing 100191 China Deep Dynamics Centre for Human and Machine Intelligence Frankfurt School of Finance and Management Frankfurt am Main 60322 Germany

We study explosive percolation processes on random graphs for the so-called product rule (PR) and sum rule (SR), in which M candidate edges are randomly selected from all possible ones at each time step, and the edge with the smallest product or sum of the sizes of the two components that would be joined by the edge is added to the graph, while all other M−1 candidate edges are being discarded. These two rules are prototypical “explosive” percolation rules, which exhibit an extremely abrupt yet continuous phase transition in the thermodynamic limit. Recently, it has been demonstrated that PR and SR belong to the same universality class for two competing edges, i.e., M=2. Here we investigate whether the claimed PR-SR universality is valid for higher-order models with M larger than 2. Based on traditional finite-size scaling theory and largest-gap scaling, we obtain the percolation threshold and the critical exponents of the order parameter, susceptibility, and the derivative of entropy for PR and SR for M from 2 to 9. Our results strongly suggest PR-SR universality, for any fixed M.

关键词： Percolation phase transition

来源：评论

学校读者我要写书评

暂无评论

Self-training through Classifier Disagreement for Cross-Domain Opinion Target Extraction

arXiv

引用

arXiv 2023年

作者： Sun, Kai Zhang, Richong Mensah, Samuel Aletras, Nikolaos Mao, Yongyi Liu, Xudong Beijing Advanced Innovation Center for Big Data and Brain Computing School of Computer Science and Engineering Beihang University Beijing China Department of Computer Science University of Sheffield Sheffield United Kingdom School of Electrical Engineering and Computer Science University of Ottawa Ottawa Canada

Opinion target extraction (OTE) or aspect extraction (AE) is a fundamental task in opinion mining that aims to extract the targets (or aspects) on which opinions have been expressed. Recent work focus on cross-domain OTE, which is typically encountered in real-world scenarios, where the testing and training distributions differ. Most methods use domain adversarial neural networks that aim to reduce the domain gap between the labelled source and unlabelled target domains to improve target domain performance. However, this approach only aligns feature distributions and does not account for class-wise feature alignment, leading to suboptimal results. Semi-supervised learning (SSL) has been explored as a solution, but is limited by the quality of pseudo-labels generated by the model. Inspired by the theoretical foundations in domain adaptation [2], we propose a new SSL approach that opts for selecting target samples whose model output from a domain-specific teacher and student network disagree on the unlabelled target data, in an effort to boost the target domain performance. Extensive experiments on benchmark cross-domain OTE datasets show that this approach is effective and performs consistently well in settings with large domain shifts. © 2023, CC BY.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Research on Hardware-in-the-Loop Test System for the Main Control Unit of Unmanned Vehicles

Research on Hardware-in-the-Loop Test System for the Main Co...

引用

Chinese Intelligent Systems Conference, CISC 2020

作者： Ni, Haoyuan Yu, Guizhen Zhou, Bin Liu, Guoqiang School of Transportation Science and Engineering Beijing Advanced Innovation Center for Big Data and Brain Computing Beijing Key Laboratory for Cooperative Vehicle Infrastructure Systems and Safety Control Beihang University Beijing100191 China School of Electronic Information Engineering Beihang University Beijing100191 China

ISBN: (纸本)9789811584572

At present, there are more researches on the automatic driving technology of unmanned vehicles. It needs a main control unit, which enables the vehicle to automatically drive. The main control unit supports the access of various sensors and controllers. It can process data of each device and control the movement state of vehicles. Therefore, the main control unit needs to be tested repeatedly to ensure its functionality and stability. Based on Prescan simulation software and Matlab/Simulink software, this paper studies a hardware-in-the-loop (HIL) test system for testing the main control unit of unmanned vehicles according to the communication protocol and communication method of the real sensor and controller hardware devices. At the same time, this paper studies a simulation method of the main control unit, which can effectively verify the function of the test system and conduct the feasibility test of the communication protocol and communication method used. © 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Simulink

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：