Query:
学者姓名:胡永利
Refining:
Year
Type
Indexed by
Source
Complex
Co-Author
Language
Clean All
Abstract :
Traffic prediction is an important part of intelligent transportation system. Recently, graph convolution network (GCN) is introduced for traffic flow forecasting and achieves good performance due to its superiority of representing the graph traffic road structure network. Moreover, the dynamic GCN is put forward to model the temporal property of the traffic flow. Although great progress has been made, most GCN based traffic flow forecasting methods utilize a single graph for convolution, which is considered not enough to reveal the inherent property of traffic graph as it is influenced by many factors, for example weather, season and traffic accidents etc. In this paper, an exotic graph transformer based dynamic multiple graph convolution networks (GTDMGCN) is conceived for traffic flow forecasting. Instead of the single graph, multiple graphs are constructed to modulate the complex traffic network by the proposed graph transformer network. Additionally, a temporal gate convolution is proposed to get the temporal property of traffic flow. The proposed GTDMGCN model is evaluated on four real traffic datasets of PEMS03, PEMS04, PEMS07, PEMS08, and there are average increments of 9.78%, 7.80%, 5.96% under MAE, RMSE, and MAPE metrics compared with the current results.
Keyword :
intelligent transportation systems intelligent transportation systems traffic information systems traffic information systems
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | Hu, Yongli , Peng, Ting , Guo, Kan et al. Graph transformer based dynamic multiple graph convolution networks for traffic flow forecasting [J]. | IET INTELLIGENT TRANSPORT SYSTEMS , 2023 , 17 (9) : 1835-1845 . |
MLA | Hu, Yongli et al. "Graph transformer based dynamic multiple graph convolution networks for traffic flow forecasting" . | IET INTELLIGENT TRANSPORT SYSTEMS 17 . 9 (2023) : 1835-1845 . |
APA | Hu, Yongli , Peng, Ting , Guo, Kan , Sun, Yanfeng , Gao, Junbin , Yin, Baocai . Graph transformer based dynamic multiple graph convolution networks for traffic flow forecasting . | IET INTELLIGENT TRANSPORT SYSTEMS , 2023 , 17 (9) , 1835-1845 . |
Export to | NoteExpress RIS BibTex |
Abstract :
Our paper proposes a new feature extraction method, named as robust discriminant analysis (RDA), for data classification tasks. Based on linear discriminant analysis (LDA), RDA integrates the feature selection and feature extraction into a unified framework. The transformation matrix with l2,1-norm constraint is introduced to map original data feature into a discriminative low-dimensional subspace, in which the l2,1 sparsity regularizer can endow the feature selection with better interpretability. And, we use two different matrices (i.e., transformation matrix P and reconstruction matrix Q) for better data reconstruction, which can provide more freedom to ensure that the learned data representation holds the main variance and hence improve robustness to noises. To ensure that the learned features are optimal for classification, the structurally incoherent learning is introduced to add additional discriminant ability by minimizing the correlation of different classes. In other hand, the between-classes structural incoherence term is also equivalent to cosine distance metric, which is robust to noises and outliers. An efficient optimization algorithm is designed to solve the proposed optimization model. Extensive experiments conducted on all kinds of benchmark databases confirm the superiority of the proposed method.(c) 2022 Elsevier Inc. All rights reserved.
Keyword :
Robust data reconstruction Robust data reconstruction Feature selection Feature selection Feature extraction Feature extraction Structural incoherence Structural incoherence Linear discriminant analysis Linear discriminant analysis
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | Guo, Jipeng , Sun, Yanfeng , Gao, Junbin et al. Robust discriminant analysis with feature selective projection and between-classes structural incoherence [J]. | DIGITAL SIGNAL PROCESSING , 2023 , 134 . |
MLA | Guo, Jipeng et al. "Robust discriminant analysis with feature selective projection and between-classes structural incoherence" . | DIGITAL SIGNAL PROCESSING 134 (2023) . |
APA | Guo, Jipeng , Sun, Yanfeng , Gao, Junbin , Hu, Yongli , Yin, Baocai . Robust discriminant analysis with feature selective projection and between-classes structural incoherence . | DIGITAL SIGNAL PROCESSING , 2023 , 134 . |
Export to | NoteExpress RIS BibTex |
Abstract :
In industrial manufacturing, how to accurately classify defective products and locate the location of defects has always been a concern. Previous studies mainly measured similarity based on extracting single-scale features of samples. However, only using the features of a single scale is hard to represent different sizes and types of anomalies. Therefore, the authors propose a set of memory banks of multi-scale features (MBMF) to enrich feature representation and detect and locate various anomalies. To extract features of different scales, different aggregation functions are designed to produce the feature maps at different granularity. Based on the multi-scale features of normal samples, the MBMF are constructed. Meanwhile, to better adapt to the feature distribution of the training samples, the authors proposed a new iterative updating method for the memory banks. Testing on the widely used and challenging dataset of MVTec AD, the proposed MBMF achieves competitive image-level anomaly detection performance (Image-level Area Under the Receiver Operator Curve (AUROC)) and pixel-level anomaly segmentation performance (Pixel-level AUROC). To further evaluate the generalisation of the proposed method, we also implement anomaly detection on the BeanTech AD dataset, a commonly used dataset in the field of anomaly detection, and the Fashion-MNIST dataset, a widely used dataset in the field of image classification. The experimental results also verify the effectiveness of the proposed method. The authors propose a novel approach for accurate classification and localisation of defects in industrial manufacturing. The method, called Memory Banks of Multi-Scale Features (MBMF), enriches feature representation by utilising multi-scale features extracted through different aggregation functions. The authors demonstrate the effectiveness of MBMF through competitive performance in image-level anomaly detection and pixel-level anomaly segmentation on the challenging MVTec AD dataset.image
Keyword :
feature extraction feature extraction unsupervised learning unsupervised learning computer vision computer vision convolutional neural nets convolutional neural nets Gaussian distribution Gaussian distribution
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | Sun, Yanfeng , Wang, Haitao , Hu, Yongli et al. MBMF: Constructing memory banks of multi-scale features for anomaly detection [J]. | IET COMPUTER VISION , 2023 , 18 (3) : 355-369 . |
MLA | Sun, Yanfeng et al. "MBMF: Constructing memory banks of multi-scale features for anomaly detection" . | IET COMPUTER VISION 18 . 3 (2023) : 355-369 . |
APA | Sun, Yanfeng , Wang, Haitao , Hu, Yongli , Jiang, Huajie , Yin, Baocai . MBMF: Constructing memory banks of multi-scale features for anomaly detection . | IET COMPUTER VISION , 2023 , 18 (3) , 355-369 . |
Export to | NoteExpress RIS BibTex |
Abstract :
本发明涉及一种基于对偶动态时空图卷积的交通预测方法,用于解决当前基于图网络的交通预测方法中存在缺少对边建模以及动态建模导致的预测精度不高的问题。首先输入历史交通数据,送到输入层进行处理,然后将输入层的输出送入动态时空层,经过动态时空层中多个堆叠的对偶动态时空块进行时空相关性特征抽取,再将这些特征输入到输出层,最后输出的即是最终的预测结果。其中,最核心和关键的对偶动态时空块包括动态图卷积模块、动态超图卷积模块,以及两个之间的动态交互模块。本发明能很好的挖掘交通数据中复杂的时空相关性,从而揭示动态交通系统潜在的时空关联,进而更加准确的对城市交通数据进行预测。
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | 孙艳丰 , 江相衡 , 胡永利 et al. 一种基于对偶动态时空图卷积的交通预测方法 : CN202210096933.X[P]. | 2022-01-26 . |
MLA | 孙艳丰 et al. "一种基于对偶动态时空图卷积的交通预测方法" : CN202210096933.X. | 2022-01-26 . |
APA | 孙艳丰 , 江相衡 , 胡永利 , 郭侃 , 尹宝才 . 一种基于对偶动态时空图卷积的交通预测方法 : CN202210096933.X. | 2022-01-26 . |
Export to | NoteExpress RIS BibTex |
Abstract :
Self-expressiveness based subspace clustering methods have received wide attention for unsupervised learning tasks. However, most existing subspace clustering methods consider data features as a whole and then focus only on one single self-representation. These approaches ignore the intrinsic multi-attribute information embedded in the original data feature and result in one-attribute self-representation. This paper proposes a novel multi-attribute subspace clustering (MASC) model that understands data from multiple attributes. MASC simultaneously learns multiple subspace representations corresponding to each specific attribute by exploiting the intrinsic multi-attribute features drawn from original data. In order to better capture the high-order correlation among multi-attribute representations, we represent them as a tensor in low-rank structure and propose the auto-weighted tensor nuclear norm (AWTNN) as a superior low-rank tensor approximation. Especially, the non-convex AWTNN fully considers the difference between singular values through the implicit and adaptive weights splitting during the AWTNN optimization procedure. We further develop an efficient algorithm to optimize the non-convex and multi-block MASC model and establish the convergence guarantees. A more comprehensive subspace representation can be obtained via aggregating these multi-attribute representations, which can be used to construct a clustering-friendly affinity matrix. Extensive experiments on eight real-world databases reveal that the proposed MASC exhibits superior performance over other subspace clustering methods.
Keyword :
Subspace clustering Subspace clustering multi-attribute representation learning multi-attribute representation learning auto-weighted tensor nuclear norm auto-weighted tensor nuclear norm non-convex low-rank tensor approximation non-convex low-rank tensor approximation
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | Guo, Jipeng , Sun, Yanfeng , Gao, Junbin et al. Multi-Attribute Subspace Clustering via Auto-Weighted Tensor Nuclear Norm Minimization [J]. | IEEE TRANSACTIONS ON IMAGE PROCESSING , 2022 , 31 : 7191-7205 . |
MLA | Guo, Jipeng et al. "Multi-Attribute Subspace Clustering via Auto-Weighted Tensor Nuclear Norm Minimization" . | IEEE TRANSACTIONS ON IMAGE PROCESSING 31 (2022) : 7191-7205 . |
APA | Guo, Jipeng , Sun, Yanfeng , Gao, Junbin , Hu, Yongli , Yin, Baocai . Multi-Attribute Subspace Clustering via Auto-Weighted Tensor Nuclear Norm Minimization . | IEEE TRANSACTIONS ON IMAGE PROCESSING , 2022 , 31 , 7191-7205 . |
Export to | NoteExpress RIS BibTex |
Abstract :
Long document classification has aroused tremendous attention in the field of Nature Language Processing, due to the exponential increasing of publications. Although the common text classification methods can be extended for long document classification, they are confined to the length of text and do not have enough expressiveness to model the structure of the long document. To solve these problems, we proposed a hierarchical multiple granularity attention network for long document classification, in which the word and section level features are extracted and fused to represent the complex structure of the long document. Furthermore, a feature-based section pooling module is adopted to eliminate redundant text information and accelerate the computing. A series of experiments are conducted to evaluate the proposed method. The experimental results verify that our method is effective, efficient and competitive compared with the related state-of-the-art methods.
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | Hu, Yongli , Ding, Wen , Liu, Tengfei et al. Hierarchical Multiple Granularity Attention Network for Long Document Classification [J]. | 2022 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN) , 2022 . |
MLA | Hu, Yongli et al. "Hierarchical Multiple Granularity Attention Network for Long Document Classification" . | 2022 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN) (2022) . |
APA | Hu, Yongli , Ding, Wen , Liu, Tengfei , Gao, Junbin , Sun, Yanfeng , Yin, Baocai . Hierarchical Multiple Granularity Attention Network for Long Document Classification . | 2022 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN) , 2022 . |
Export to | NoteExpress RIS BibTex |
Abstract :
Domain adaptation in the Euclidean space is a challenging task on which researchers recently have made great progress. However, in practice, there are rich data representations that are not Euclidean. For example, many high-dimensional data in computer vision are in general modeled by a low-dimensional manifold. This prompts the demand of exploring domain adaptation between non-Euclidean manifold spaces. This article is concerned with domain adaption over the classic Grassmann manifolds. An optimal transport-based domain adaptation model on Grassmann manifolds has been proposed. The model implements the adaption between datasets by minimizing the Wasserstein distances between the projected source data and the target data on Grassmann manifolds. Four regularization terms are introduced to keep task-related consistency in the adaptation process. Furthermore, to reduce the computational cost, a simplified model preserving the necessary adaption property and its efficient algorithm is proposed and tested. The experiments on several publicly available datasets prove the proposed model outperforms several relevant baseline domain adaptation methods.
Keyword :
domain adaptation domain adaptation Classification Classification Costs Costs Manifolds Manifolds Data models Data models Adaptation models Adaptation models Computational modeling Computational modeling Task analysis Task analysis Transportation Transportation optimal transport optimal transport Grassmann manifolds Grassmann manifolds
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | Long, Tianhang , Sun, Yanfeng , Gao, Junbin et al. Domain Adaptation as Optimal Transport on Grassmann Manifolds [J]. | IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS , 2022 , 34 (10) : 7196-7209 . |
MLA | Long, Tianhang et al. "Domain Adaptation as Optimal Transport on Grassmann Manifolds" . | IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 34 . 10 (2022) : 7196-7209 . |
APA | Long, Tianhang , Sun, Yanfeng , Gao, Junbin , Hu, Yongli , Yin, Baocai . Domain Adaptation as Optimal Transport on Grassmann Manifolds . | IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS , 2022 , 34 (10) , 7196-7209 . |
Export to | NoteExpress RIS BibTex |
Abstract :
Compared with natural images, underwater images are usually degraded with blur, scale variation, colour shift and texture distortion, which bring much challenge for computer vision tasks like object detection. In this case, generic object detection methods usually fail to achieve satisfactory performance. The main reason is considered that the current methods lack sufficient discriminativeness of feature representation for the degraded underwater images. A a novel multi-scale feature representation and interaction network for underwater object detection is proposed, in which two core modules are elaborately designed to enhance the discriminativeness of feature representation for underwater images. The first is the Context Integration Module, which extracts rich context information from high-level features and is integrated with the feature pyramid network to enhance the feature representation in a multi-scale way. The second is the Dual-refined Attention Interaction Module, which further enhances the feature representation by sufficient interactions between different levels of features both in channel and spatial domains based on attention mechanism. The proposed model is evaluated on four public underwater datasets. The experimental results compared with state-of-the-art object detection methods show that the proposed model has leading performance, which verifies that it is effective for underwater object detection. In addition, object detection experiments on a foggy dataset of Real-world Task-driven Testing Set (RTTS) and the natural image dataset of pattern analysis statistical modelling and computational learning, visual object classes (PASCAL VOC) are conducted. The results show that the proposed model can be applied on the degraded dataset of RTTS but fails on PASCAL VOC.
Keyword :
convolutional neural nets convolutional neural nets object detection object detection computer vision computer vision
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | Yuan, Jiaojiao , Hu, Yongli , Sun, Yanfeng et al. A multi-scale feature representation and interaction network for underwater object detection [J]. | IET COMPUTER VISION , 2022 , 17 (3) : 265-281 . |
MLA | Yuan, Jiaojiao et al. "A multi-scale feature representation and interaction network for underwater object detection" . | IET COMPUTER VISION 17 . 3 (2022) : 265-281 . |
APA | Yuan, Jiaojiao , Hu, Yongli , Sun, Yanfeng , Yin, Baocai . A multi-scale feature representation and interaction network for underwater object detection . | IET COMPUTER VISION , 2022 , 17 (3) , 265-281 . |
Export to | NoteExpress RIS BibTex |
Abstract :
Probabilistic linear discriminant analysis (PLDA) is a very effective feature extraction approach and has obtained extensive and successful applications in supervised learning tasks. It employs the squared L-2-norm to measure the model errors, which assumes a Gaussian noise distribution implicitly. However, the noise in real-life applications may not follow a Gaussian distribution. Particularly, the squared L-2-norm could extremely exaggerate data outliers. To address this issue, this article proposes a robust PLDA model under the assumption of a Laplacian noise distribution, called L1-PLDA. The learning process employs the approach by expressing the Laplacian density function as a superposition of an infinite number of Gaussian distributions via introducing a new latent variable and then adopts the variational expectation-maximization (EM) algorithm to learn parameters. The most significant advantage of the new model is that the introduced latent variable can be used to detect data outliers. The experiments on several public databases show the superiority of the proposed L1-PLDA model in terms of classification and outlier detection.
Keyword :
outliers outliers variational expectation-maximization (EM) variational expectation-maximization (EM) probabilistic linear discriminant analysis (PLDA) probabilistic linear discriminant analysis (PLDA) Laplacian distribution Laplacian distribution
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | Hu, Xiangjie , Sun, Yanfeng , Gao, Junbin et al. Probabilistic Linear Discriminant Analysis Based on L-1-Norm and Its Bayesian Variational Inference [J]. | IEEE TRANSACTIONS ON CYBERNETICS , 2022 , 52 (3) : 1616-1627 . |
MLA | Hu, Xiangjie et al. "Probabilistic Linear Discriminant Analysis Based on L-1-Norm and Its Bayesian Variational Inference" . | IEEE TRANSACTIONS ON CYBERNETICS 52 . 3 (2022) : 1616-1627 . |
APA | Hu, Xiangjie , Sun, Yanfeng , Gao, Junbin , Hu, Yongli , Ju, Fujiao , Yin, Baocai . Probabilistic Linear Discriminant Analysis Based on L-1-Norm and Its Bayesian Variational Inference . | IEEE TRANSACTIONS ON CYBERNETICS , 2022 , 52 (3) , 1616-1627 . |
Export to | NoteExpress RIS BibTex |
Abstract :
Benefiting from exploiting the data topological structure, graph convolutional network (GCN) has made considerable improvements in processing clustering tasks. The performance of GCN significantly relies on the quality of the pretrained graph, while the graph structures are often corrupted by noise or outliers. To overcome this problem, we replace the pre-trained and fixed graph in GCN by the adaptive graph learned from the data. In this article, we propose a novel end-to-end parallelly adaptive graph convolutional clustering (AGCC) model with two pathway networks. In the first pathway, an adaptive graph convolutional (AGC) module alternatively updates the graph structure and the data representation layer by layer. The updated graph can better reflect the data relationship than the fixed graph. In the second pathway, the auto-encoder (AE) module aims to extract the latent data features. To effectively connect the AGC and AE modules, we creatively propose an attention-mechanism-based fusion (AMF) module to weight and fuse the data representations of the two modules, and transfer them to the AGC module. This simultaneously avoids the over-smoothing problem of GCN. Experimental results on six public datasets show that the effectiveness of the proposed AGCC compared with multiple state-of-the-art deep clustering methods. The code is available at https://github.com/HeXiax/AGCC.
Keyword :
Convolutional codes Convolutional codes graph mining graph mining Automatic generation control Automatic generation control clustering clustering Data models Data models Deep learning Deep learning Representation learning Representation learning Clustering methods Clustering methods Adaptive graph convolution Adaptive graph convolution Task analysis Task analysis graph convolutional network (GCN) graph convolutional network (GCN)
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | He, Xiaxia , Wang, Boyue , Hu, Yongli et al. Parallelly Adaptive Graph Convolutional Clustering Model [J]. | IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS , 2022 . |
MLA | He, Xiaxia et al. "Parallelly Adaptive Graph Convolutional Clustering Model" . | IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2022) . |
APA | He, Xiaxia , Wang, Boyue , Hu, Yongli , Gao, Junbin , Sun, Yanfeng , Yin, Baocai . Parallelly Adaptive Graph Convolutional Clustering Model . | IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS , 2022 . |
Export to | NoteExpress RIS BibTex |
Export
Results: |
Selected to |
Format: |