检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Shou, Yuntao Liu, Huan Cao, Xiangyong Meng, Deyu Dong, Bo School of Computer Science and Technology The Ministry of Education Key Laboratory for Intelligent Networks and Network Security The Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi’an Jiaotong Shaanxi Xi’an710049 China School of Computer Science and Technology Xi’an Jiaotong Shaanxi Xi’an710049 China The BigKE Joint Innovation Center SHMEEA Shanghai China School of Mathematics and Statistics Xi’an Jiaotong University Xi’an China

Conversational emotion recognition (CER) is an important research topic in human-computer interactions. Although recent advancements in transformer-based cross-modal fusion methods have shown promise in CER tasks, they tend to overlook the crucial intra-modal and inter-modal emotional interaction or suffer from high computational complexity. To address this, we introduce a novel and lightweight cross-modal feature fusion method called Low-Rank Matching Attention Method (LMAM). LMAM effectively captures contextual emotional semantic information in conversations while mitigating the quadratic complexity issue caused by the self-attention mechanism. Specifically, by setting a matching weight and calculating inter-modal features attention scores row by row, LMAM requires only one-third of the parameters of self-attention methods. We also employ the low-rank decomposition method on the weights to further reduce the number of parameters in LMAM. As a result, LMAM offers a lightweight model while avoiding overfitting problems caused by a large number of parameters. Moreover, LMAM is able to fully exploit the intra-modal emotional contextual information within each modality and integrates complementary emotional semantic information across modalities by computing and fusing similarities of intra-modal and inter-modal features simultaneously. Experimental results verify the superiority of LMAM compared with other popular cross-modal fusion methods on the premise of being more lightweight. Also, LMAM can be embedded into any existing state-of-the-art CER methods in a plug-and-play manner, and can be applied to other multi-modal recognition tasks, e.g., session recommendation and humour detection, demonstrating its remarkable generalization ability. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

A novel method for ECG signal classification via one-dimensional convolutional neural network

A novel method for ECG signal classification via one-dimensi...

引用

作者： Hua, Xuan Han, Jungang Zhao, Chen Tang, Haipeng He, Zhuo Chen, Qinghui Tang, Shaojie Tang, Jinshan Zhou, Weihua College of Electronic Engineering Xi’an University of Posts and Telecommunications Xi’an710121 China Key Laboratory of Network Data Analysis and Intelligent Processing in Shaanxi Xi’an710121 China College of Computer Science and Technology Xi’an University of Posts and Telecommunications Xi’an710121 China College of Computing Michigan Technological University HoughtonMI49931 United States School of Computing University of Southern Mississippi Long Beach39560 United States Department of Kinesiology and Integrative Physiology Michigan Technological University HoughtonMI49931 United States School of Automation Xi’an University of Posts and Telecommunications Xi’an710121 China

This paper develops an end-to-end ECG signal classification algorithm based on a novel segmentation strategy and 1D Convolutional Neural networks (CNN) to aid the classification of ECG signals and alleviate the workload of physicians. The ECG segmentation strategy named R-R-R strategy (i.e., retaining ECG data between the R peaks just before and after the current R peak) is used for segmenting the original ECG data into segments to train and test the 1D CNN models. The novel strategy mimics physicians in scanning ECG to a greater extent, and maximizes the inherent information of ECG segments for diagnosis. The performance of the proposed end to end ECG signal classification algorithm was verified with the ECG signals from 48 records in the MIT-BIH arrhythmia database. When the heartbeat types were divided into the five classes recommended by clinicians, i.e., normal beat, left bundle branch block beat, right bundle branch block beat, premature ventricular contraction, and paced beat, the classification accuracy, the area under the curve (AUC), the sensitivity, and the F1-score achieved by the proposed model were 0.9924, 0.9994, 0.99 and 0.99, respectively. When the heartbeat types were divided into six classes recommended by clinicians, i.e., normal beat, left bundle branch block beat, right bundle branch block beat, premature ventricular contraction, paced beat and other beats, the beat classification accuracy, the AUC, the sensitivity, and the F1-score achieved by the model reached 0.9702, 0.9966, 0.97, and 0.97, respectively. When the heartbeat types were divided into five classes recommended by the Association for Advancement of Medical Instrumentation (AAMI), i.e., normal beat, supraventricular ectopic beat, ventricular ectopic beat, fusion beat, and unknown beat, the beat classification accuracy, the sensitivity, and the F1-score were 0.9745, 0.97, and 0.97, respectively. Experimental results show that the proposed method achieves better performance than the s

关键词： Electrocardiograms

来源：评论

学校读者我要写书评

暂无评论

Multi-Scale Structure-Guided Graph Generation for Multi-View Semi-Supervised Classification

SSRN

引用

SSRN 2024年

作者： Wu, Yilin Chen, Zhaoliang Zou, Ying Wang, Shiping Guo, Wenzhong College of Computer and Data Science Fuzhou University Fuzhou350108 China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou350108 China Department of Computer Science Hong Kong Baptist University Hong Kong

Graph convolutional network has emerged as a focal point in machine learning because of its robust graph processing capability. Most existing graph convolutional network-based approaches are designed for single-view data, yet in many practical scenarios, data is represented through multiple views. Although the ability of graph convolutional network is undeniable, the quality of graph directly affects its performance. Moreover, the process of graph generation with traditional nearest neighbor in traditional multi-view learning actually amplifies the influence of different information on performance across these views. To tackle the aforementioned challenges, this paper proposes a multi-scale graph generation deep learning framework, called multi-scale semi-supervised graph generation based multi-view classification, consisting of two modules: edge sampling and path sampling. The former aims to generate an adjacency graph by selecting edges based on the maximum likelihood among graphs from different views. Meanwhile, the latter seeks to construct adjacency graphs according to the characteristics of paths within the graphs. Extensive experimental results robustly demonstrate the superior performance of our proposed framework, compared to other state-of-the-art multi-view semi-supervised approaches. © 2024, The Authors. All rights reserved.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Adaptive Multi-Channel Contrastive Graph Convolutional network with Graph and Feature Fusion

SSRN

引用

SSRN 2023年

作者： Zhong, Luying Lu, Jielong Chen, Zhaoliang Song, Na Wang, Shiping College of Computer and Data Science Fuzhou University Fuzhou350108 China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou350116 China School of Mechanical Electrical and Information Engineering Putian University Putian351100 China

Multi-view semi-supervised classification is an attractive topic in real-world applications. Due to the powerful capability of gathering information from neighbors, Graph Convolutional network (GCN) has become a hotspot in the classification task. However, most multi-view classification works based on GCN only assign weights for feature fusion, and directly consider the weighted sum of the adjacency matrices, ignoring the interaction and correlation among features. These may be problematic because aggregating the matrices from less relevant views may destroy the original topology space, leading to undesired performance. To address these issues, this paper proposes an Adaptive Multi-Channel Graph Convolutional network (AMC-GCN). To extract the interactive information, AMC-GCN designs a deep interactive feature integration network to incorporate consensus and complementary information. To fuse the graph structures, AMC-GCN exploits the relevance between views and imposes an adjacency matrix fusion network to construct multiple GCN channels, thereby delivering valuable information from relevant graphs. To enhance the homogeneity of the framework, AMC-GCN applies a contrastive loss to joint learning during the optimization for classification. With these techniques, AMC-GCN exploits relevant and interactive information between views to promote graph and feature fusion. Extensive experimental results on real-world datasets demonstrate the superiority of the proposed algorithm. © 2023, The Authors. All rights reserved.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Disentangled Noisy Correspondence Learning

arXiv

引用

arXiv 2024年

作者： Dang, Zhuohang Luo, Minnan Wang, Jihong Jia, Chengyou Han, Haochen Wan, Herun Dai, Guang Chang, Xiaojun Wang, Jingdong The School of Computer Science and Technology The Ministry of Education Key Laboratory of Intelligent Networks and Network Security The Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi'an Jiaotong University Shaanxi Xi'An710049 China SGIT AI Lab State Grid Shaanxi Electric Power Company Limited State Grid Corporation of China Shaanxi China The School of Information Science and Technology University of Science and Technology China United Arab Emirates The Baidu Inc China

Cross-modal retrieval is crucial in understanding latent correspondences across modalities. However, existing methods implicitly assume well-matched training data, which is impractical as real-world data inevitably involves imperfect alignments, i.e., noisy correspondences. Although some works explore similarity-based strategies to address such noise, they suffer from sub-optimal similarity predictions influenced by modality-exclusive information (MEI), e.g., background noise in images and abstract definitions in texts. This issue arises as MEI is not shared across modalities, thus aligning it in training can markedly mislead similarity predictions. Moreover, although intuitive, directly applying previous cross-modal disentanglement methods suffers from limited noise tolerance and disentanglement efficacy. Inspired by the robustness of information bottlenecks against noise, we introduce DisNCL, a novel information-theoretic framework for feature Disentanglement in Noisy Correspondence Learning, to adaptively balance the extraction of MII and MEI with certifiable optimal cross-modal disentanglement efficacy. DisNCL then enhances similarity predictions in modality-invariant subspace, thereby greatly boosting similarity-based alleviation strategy for noisy correspondences. Furthermore, DisNCL introduces soft matching targets to model noisy many-to-many relationships inherent in multi-modal input for noise-robust and accurate cross-modal alignment. Extensive experiments confirm DisNCL's efficacy by 2% average recall improvement. Mutual information estimation and visualization results show that DisNCL learns meaningful MII/MEI subspaces, validating our theoretical analyses. Copyright © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Adaptive-Propagating Heterophilous Graph Convolutional network

SSRN

引用

SSRN 2024年

作者： Huang, Yang Pi, Yueyang Shi, Yiqing Wang, Shiping Guo, Wenzhong College of Computer and Data Science Fuzhou University Fuzhou350116 China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou350116 China College of Photonic and Electronic Engineering Fujian Normal University Fuzhou350007 China

Graph convolutional network have significant advantages in tasks dealing with graph-structured data, but most existing approaches based on graph convolutional network usually potentially assume that nodes belonging to the same class in a graph tend to form edges, yet inter-class edges exist in many real graph-structured data. Due to the propagation mechanism of graph convolutional network, it is usually difficult to avoid the aggregation of interference information of nodes from different classes, leading to the inclusion of noise and irrelevant information in the results, thus affecting the performance of the model. We propose a new framework to address this issue, which can extend graph convolutional network to heterophilous graph-structured data. The proposed method has two main parts: Firstly, from the perspective of feature space, the heterophily of the graph-structured data is modeled so that the model can adaptively change the information propagation process according to the homophily of the edges, and mitigate the influence of inter-class information on the model. Secondly, the implicit node interaction information is captured through the feature space, which is then fused with the original interaction information to aggregate sufficient intra-class information. Extensive experiments on real-world datasets demonstrate the competitiveness of our approach among current state-of-the-art methods. © 2024, The Authors. All rights reserved.

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

Video Smoke Detection Based on Motion Analysis and Fused Temporal-Spatial Model

SSRN

引用

SSRN 2022年

作者： Jia, Yang Mao, Zixu Zhang, Xinmeng Chen, Weiguang Wang, Ben Wang, Gang Zhang, Qixing School of Computer Science Xi'an University of Posts and Telecommunications Xi'An710121 China Shaanxi Key Laboratory of Network Data Intelligent Processing Xi'an University of Posts and Telecommunications Xi'An710121 China XNIC262 Xi'An710121 China School of Information Science and Technology University of Science and Technology of China Hefei230026 China State Key Laboratory of Fire Science University of Science and Technology of China Hefei230026 China

Researchers have proposed various video smoke detection methods based on deep learning. However, most methods are based on two-dimensional image analysis, which hasn't effectively used the motion information of smoke. Therefore, an improved two-stream CNN based smoke detection method is proposed. Firstly, we use sparse sampling to extract sampled frames and capture the suspected area of the sampled frame with background modeling. Then we extract the dense optical flow of consecutive frames of the sampled frames and merge them into a stacked optical flow sequence. A sampled frame and a stacked optical flow sequence are fed into the Two-Stream CNN to obtain video-level recognition results. The performance of 97.32% accuracy, and 4.07% false alarm rate can be achieved, and the effectiveness of the method has been proved through comparative experiments. Combined with the explicitly expressed motion information, we can get a better detection performance. © 2022, The Authors. All rights reserved.

关键词： Motion analysis

来源：评论

学校读者我要写书评

暂无评论

Bilinear Semi-Tensor Product Attention (BSTPA) model for visual question answering

Bilinear Semi-Tensor Product Attention (BSTPA) model for vis...

引用

International Joint Conference on Neural networks (IJCNN)

作者： Zongwen Bai Ying Li Meili Zhou Di Li Dong Wang Dawid Połap Marcin Woźniak School of Computer Science Northwestern Polytechnical University Xi’an CHINA Shaanxi Key Laboratory of Intelligent Processing for Big Energy Data Yan’an CHINA School of Physics and Electronic Information Yan’an University Yan’an CHINA Faculty of Applied Mathematics Silesian University of Technology Gliwice POLAND

ISBN: (数字)9781728169262

ISBN: (纸本)9781728169279

We propose a semi-tensor product attention network model as a visual question answering tool for complex interaction over image features. Proposed model performs matrix multiplication of two arbitrary dimensions, which is used to overcome possible dimensional limitations and improve recognition flexibility. In used block-wise operation we preserve spatial and temporal information but reduce the number of parameters by using low-rank pooling scheme. Applied BERT pre-train model is tuned to recognize question features. The proposed model is evaluated on the VQA2.0 dataset. Research results show that our model has good accuracy and easy reconfiguration for future research.

关键词： Feature extraction Visualization Knowledge discovery Cognition Task analysis Computational modeling Bit error rate

来源：评论

学校读者我要写书评

暂无评论

ADEdgeDrop: Adversarial Edge Dropping for Robust Graph Neural networks

arXiv

引用

arXiv 2024年

作者： Chen, Zhaoliang Wu, Zhihao Sadikaj, Ylli Plant, Claudia Dai, Hong-Ning Wang, Shiping Cheung, Yiu-Ming Guo, Wenzhong College of Computer and Data Science Fuzhou University Fuzhou350116 China Department of Computer Science Hong Kong Baptist University Hong Kong Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou350116 China Faculty of Computer Science and with the research network Data Science @ Uni Vienna University of Vienna Vienna1090 Austria

Although Graph Neural networks (GNNs) have exhibited the powerful ability to gather graph-structured information from neighborhood nodes via various message-passing mechanisms, the performance of GNNs is limited by poor generalization and fragile robustness caused by noisy and redundant graph data. As a prominent solution, Graph Augmentation Learning (GAL) has recently received increasing attention in the literature. Among the existing GAL approaches, edge-dropping methods that randomly remove edges from a graph during training are effective techniques to improve the robustness of GNNs. However, randomly dropping edges often results in bypassing critical edges. Consequently, the effectiveness of message passing is weakened. In this paper, we propose a novel adversarial edgedropping method (ADEdgeDrop) that leverages an adversarial edge predictor guiding the removal of edges, which can be flexibly incorporated into diverse GNN backbones. Employing an adversarial training framework, the edge predictor utilizes the line graph transformed from the original graph to estimate the edges to be dropped, which improves the interpretability of the edge-dropping method. The proposed ADEdgeDrop is optimized alternately by stochastic gradient descent and projected gradient descent. Comprehensive experiments on eight graph benchmark datasets demonstrate that the proposed ADEdgeDrop outperforms state-of-the-art baselines across various GNN backbones, demonstrating improved generalization and robustness. Copyright © 2024, The Authors. All rights reserved.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Multi-Strategy Bus Deviation-Driven Layer Assignment Algorithm

Multi-Strategy Bus Deviation-Driven Layer Assignment Algorit...

引用

Electronics Design Automation (ISEDA), International Symposium of

作者： Yantao Yu Zepeng Li Jiarui Chen Xing Huang Genggeng Liu Ning Xu College of Computer and Data Science Fuzhou University Fuzhou China Fujian Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou China School of Computer Science Northwestern Polytechnical University Xian China School of Information Engineering Wuhan University of Technology Wuhan China

ISBN: (数字)9798350352030

ISBN: (纸本)9798350352047

In modern very large-scale integration (VLSI) design, the solution quality of the bus routing is a crucial factor that determines the timing and power of circuit, and finally affects the performance and yield of chips. Taking bus deviation as the main optimization objective, an effective multi-strategy bus deviation-driven layer assignment algorithm is proposed to solve the timing-matching problem of bus routing. First, a net priority determination method that integrates multiple features is presented to determine the layer assignment order, thus obtaining a routing sequence which can weigh the wirelength and bus deviation well. Second, an effective single net layer assignment algorithm is proposed to assign each net based on dynamic programming, thus reducing the number of vias. Third, a layer shifting strategy based on the bus lookup table is designed to effectively balance total wirelength and bus deviation by sacrificing a certain number of vias. Experimental results, compared to existing work, show that the proposed algorithm can achieve significant optimization on the bus deviation and total wirelength, and finally obtain the best results in terms of the bus deviation, which is the most important optimization objective for bus routing.

关键词： Design automation Heuristic algorithms Very large scale integration Routing Timing Pins Dynamic programming

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：