检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2024年第6期5卷 2997-3011页

作者： Liu, Yongkang Pan, Donghui Zhang, Haifeng Zhong, Kai Anhui University Key Laboratory of Intelligent Computing and Signal Processing of the Ministry of Education School of Mathematical Sciences Hefei230601 China Anhui University Key Laboratory of Intelligent Computing and Signal Processing of the Ministry of Education Institutes of Physical Science and Information Technology Hefei230601 China

Remaining useful life (RUL) prediction of bearings has extraordinary significance for prognostics and health management (PHM) of rotating machinery. RUL prediction approaches based on deep learning have been dedicated to finding a nonlinear mapping relationship between nonstationary monitoring data and RUL. However, most existing approaches pay little attention to the degradation trend of diverse health stages of bearing and lack the discriminative power of crucial degradation features, resulting in the loss of some important information associated with RUL. To address this challenge, this article proposes a novel RUL prediction framework based on degradation-trend-aware deep neural network with attention mechanism (DTADAN). First the multidirection features with evident degradation trend are extracted via the analysis of bearing vibration signal from both time-domain and time-frequency domain. Next, the deep neural network architecture with attention mechanism is utilized to adaptively learn the critical degradation features beneficial for RUL prediction. Distinct from the existing approaches, the proposed framework is able to dynamically extract key degradation features of the bearing including degradation trend information and effectively fuse multidirection information to improve RUL prediction accuracy. The performance of the proposed approach is evaluated via case studies on XJTU-SY bearing dataset and PRONOSTIA bearing dataset. Compared with other state-of-the-art approaches, the proposed framework has better predictive accuracy and robustness. Additionally, interpretable analysis is provided to reveal the process of model learning and data characteristics, and the analysis results are helpful in guiding model learning. © 2020 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

A Modified BGM-PHD Filter with Unknown Detection Probability 6

A Modified BGM-PHD Filter with Unknown Detection Probability

引用

6th International Conference on Information Communication and signal processing, ICICSP 2023

作者： Wei, Jingxin Luo, Feng Qi, Jiawei Ruan, Luyao Xidian University National Key Laboratory of Radar Signal Processing Xi'an China Hangzhou Institute of Technology Xidian University National Key Laboratory of Radar Signal Processing Xi'an China Hangzhou Institute of Technology Xidian University Hangzhou China

ISBN: (纸本)9798350339994

The standard Probability Hypothesis Density (PHD) filter requires manually presetting the detection probability before tracking. In addition, incorrect settings would lead to deterioration in filter performance. Beta GM-PHD filter introduces the unknown detection probability modeled by Beta distribution into the Bayes recursion to enhance the robustness under the lack of detection model parameters. However, the limitation that biases the target number and detection probability estimations significantly affects the application of the Beta GM-PHD filter. In this paper, the mechanism of the estimation biases is analyzed and a simple but effective modification is presented. Simulation results demonstrate that the modified filter provides more accurate detection probability and target state estimates in unknown and space-varying detection probability scenarios. © 2023 IEEE.

关键词： multi-target tracking parameter estimation PHD filter unknown detection probability

来源：评论

学校读者我要写书评

暂无评论

Three-Dimensional Cooperative Localization Based on Active radar/Infrared at Different Sites 2

Three-Dimensional Cooperative Localization Based on Active R...

引用

2nd IEEE International Conference on signal, Information and Data processing, ICSIDP 2024

作者： Qian, Jialun Wang, Linhai Zhou, Shenghua Gong, Min Zhao, Pengfei Yang, Jian Sui, Xin Xidian University National Key Laboratory of Radar Signal Processing Xi'an China China Academy of Launch Vehicle Technology Beijing China

ISBN: (纸本)9798331515669

Multi-source perception fusion positioning technology based on heterogeneous sensors is a key research area in the field of target positioning. The heterogeneous sensor positioning system composed of radar and infrared has a wide range of applications. However, existing works mostly use radar measurement to expand the dimension of infrared data to locate target, which will introduce the large angle measurement error of radar into infrared. In this paper, we propose a radar/infrared linear weighted least-squares (WLS) localization algorithm based on target motion model. First, we build linear equations of target position relative to radar and infrared based on the space relationship, respectively. In this manner, the position of target can be solved through a linear optimization problem. Two kinds of equations are combined by deformation and solved by WLS algorithm to achieve the target localization. Simulation results show that the proposed method has better target localization performance than that of single radar, and with the improvement of the measurement accuracy of radar/infrared sensors, the localization effect is better. © 2024 IEEE.

关键词： radar measurement

来源：评论

学校读者我要写书评

暂无评论

TBIA-DBNet: A Two-Branch Image-Adaptive DBNet for Scene Text Detection in Real-World Foggy Scenes 27th

TBIA-DBNet: A Two-Branch Image-Adaptive DBNet for Scene Tex...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Liu, Zhaoxi Zhou, Gang He, Runlin Zhang, Mengnan Jia, Zhenhong Ma, Jing Key Laboratory of Signal Detection and Processing Department of Computer Science and Technology Xinjiang University Urumqi China

ISBN: (纸本)9783031781186

Though deep learning-based scene text detection methods have achieved promising results on conventional datasets, these methods are unable to maintain optimal performance in adverse weather conditions, such as foggy weather. To alleviate this problem, we propose a Two-Branch Image-Adaptive DBNet (TBIA-DBNet) framework. Specifically, to avoid missing discriminable features from the original image in one branch, we design an Image Enhancement Network (IENet) in another branch. Additionally, we design a Fusion Module based on Coordinate Attention (FMCA) to fully integrate original and enhanced features. Experimental results demonstrate that TBIA-DBNet significantly enhances scene text detection performance in foggy weather. Notably, it improves detection accuracy by nearly 10% in real-world foggy weather conditions compared to existing methods. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

E-RNS: Enhancing Negative Sample Quality from Gradient Perspective for Graph Recommendation

E-RNS: Enhancing Negative Sample Quality from Gradient Persp...

引用

2025 IEEE International Conference on Acoustics, Speech, and signal processing, ICASSP 2025

作者： Feng, Qiangsheng Qin, Jiwei Ma, Jie School of Computer Science and Technology Xinjiang University China Key Laboratory of Signal Detection and Processing China

ISBN: (纸本)9798350368741

Bayesian Personalized Ranking (BPR) is a widely used optimization function in GNN-based recommender systems, and negative samples are usually obtained through the Random Negative Sampling (RNS) method during BPR training. However, from the gradient perspective, RNS tends to select low-quality samples with minimal information, resulting in small gradients. These small gradients contribute little to BPR optimization, limiting the model's ability to effectively distinguish between positive and negative samples. To alleviate this issue, we propose a general negative sample information enhancement method: Enhancing Random Negative Sampling (E-RNS), which constructs hard negative samples by enhancing the information in randomly selected negative samples. Specifically, in the Noise Injection step, it generates initial noise and injects a certain amount of noise in the same direction into the vector dimensions of positive samples to create enriched information. Then, in the Information Fusion step, this enriched information is mixed with the negative samples to synthesize new hard negative samples. Extensive experiments demonstrate that applying E-RNS to GNN-based recommender models significantly improves performance. © 2025 IEEE.

关键词： Collaborative Filtering Graph Neural Networks Negative Sampling Recommender Systems

来源：评论

学校读者我要写书评

暂无评论

Hyperparameter free sparse estimation for MIMO radar direction finding in the presence of unknown gain-phase errors 16

Hyperparameter free sparse estimation for MIMO radar directi...

引用

16th International Conference on signal processing Systems, ICSPS 2024

作者： Xiao, Jiong Huang, Ping Tang, Bo Zuo, Lei College of Electronic Engineering National University of Defense Technology Hefei China National Key Laboratory of Radar Signal Processing Xidian University Xi’an China

ISBN: (纸本)9781510689251

To improve the accuracy of direction of arrival (DOA) estimation in multiple-input-multiple-output (MIMO) radar systems under unknown gain-phase errors, we propose a gain-phase error calibration and DOA estimation algorithm based on sparse learning via iterative minimization (SLIM). The proposed algorithm harnesses the spatial sparsity of the target signals, and estimates the spatial spectrum and gain-phase error matrices of MIMO arrays through a cyclic optimization procedure. Numerical results show that even in the presence of unknown gain-phase uncertainties, the proposed algorithm can accurately estimate the target DOA using a limited number of samples. © 2025 SPIE.

关键词： Direction of arrival

来源：评论

学校读者我要写书评

暂无评论

Deformable Multi-Scale Network for Snow Removal in Video 27th

Deformable Multi-Scale Network for Snow Removal in Video

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： He, Runlin Zhou, Gang Xue, Tianhao Liu, Zhaoxi Jia, Zhenhong Key Laboratory of Signal Detection and Processing Department of Computer Science and Technology Xinjiang University Urumqi China

ISBN: (纸本)9783031781247

Snowfall severely degrades outdoor video visibility while reducing the performance of subsequent vision tasks. Although video recovery methods based on deep learning have achieved amazing accomplishments, video snow removal still faces problems such as varying scales and intricate trajectories of snowflakes, which makes it difficult to remove snowflakes and easy to create artifacts on moving objects. To address these issues, we propose a deformable multi-scale video desnowing network. Specifically, we design a multi-scale pseudo-3D residual block(MSRB-P3D) that can effectively remove snowflakes of different scales. Furthermore, a deformable large kernel attention 3Dblock(D-LKA 3Dblock) is introduced to capture the inter-frame dynamic information and reduce the artifacts. Due to the scarcity of dataset, we proposed a new dataset named Synthetic and Real Snowy Video Dataset(SRSVD). Extensive experiments have proven that our proposed method not only outperforms other state-of-the-art methods on both synthetic and real snowy videos, but also effectively improves performance on subsequent vision task. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Snow

来源：评论

学校读者我要写书评

暂无评论

DMFVAE:miRNA-disease associations prediction based on deep matrix factorization method with variational autoencoder

引用

Frontiers of Computer science 2024年第6期18卷 259-270页

作者： Pijing WEI Qianqian WANG Zhen GAO Ruifen CAO Chunhou ZHENG Information Materials and Intelligent Sensing Laboratory of Anhui Province Institutes of Physical Science and Information TechnologyAnhui UniversityHefei 230601China Key Lab of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and TechnologyAnhui UniversityHefei 230601China Key Lab of Intelligent Computing and Signal Processing of Ministry of Education School of Artificial IntelligenceAnhui UniversityHefei 230601China

MicroRNAs(miRNAs)are closely related to numerous complex human diseases,therefore,exploring miRNA-disease associations(MDAs)can help people gain a better understanding of complex disease *** increasing number of computational methods have been developed to predict ***,the sparsity of the MDAs may hinder the performance of many *** addition,many methods fail to capture the nonlinear relationships of miRNA-disease network and inadequately leverage the features of network and neighbor *** this study,we propose a deep matrix factorization model with variational autoencoder(DMFVAE)to predict potential *** first decomposes the original association matrix and the enhanced association matrix,in which the enhanced association matrix is enhanced by self-adjusting the nearest neighbor method,to obtain sparse vectors and dense vectors,***,the variational encoder is employed to obtain the nonlinear latent vectors of miRNA and disease for the sparse vectors,and meanwhile,node2vec is used to obtain the network structure embedding vectors of miRNA and disease for the dense ***,sample features are acquired by combining the latent vectors and network structure embedding vectors,and the final prediction is implemented by convolutional neural network with channel *** evaluate the performance of DMFVAE,we conduct five-fold cross validation on the HMDD v2.0 and HMDD v3.2 datasets and the results show that DMFVAE performs ***,case studies on lung neoplasms,colon neoplasms,and esophageal neoplasms confirm the ability of DMFVAE in identifying potential miRNAs for human diseases.

关键词： miRNA-disease association deep matrix factorization self-adjusted nearest neighbor variational encoder network structure

来源：评论

学校读者我要写书评

暂无评论

Residual Graph Convolution Collaborative Filtering with Asymmetric neighborhood aggregation

引用

Neural Computing and Applications 2024年第22期36卷 13989-14003页

作者： Wang, Tao Qin, Jiwei Ma, Chao School of Computer Science and Technology Xinjiang University Urumqi830046 China Xinjiang Key Laboratory of Signal Detection and Processing Xinjiang University Urumqi830046 China

Due to the superior performance of graph convolutional networks (GCNs) in feature extraction and representation, researchers have introduced GCNs to collaborative filtering (CF) to improve the accuracy of recommendations. However, existing GCN-based CF models still have three shortcomings: degrading the model performance due to symmetric normalization in neighborhood aggregation, underutilizing the node (user or item) representations at lower layers, and failing to alleviate the over-smoothing effect in graph convolution operations. We present a Residual Graph Convolution Collaborative Filtering model with Asymmetric neighborhood aggregation (ARGCCF) to tackle the above shortcomings. Firstly, ARGCCF utilizes asymmetric normalization in neighborhood aggregation, enabling better preservation of high-degree node information for more precisely learning node representations. Secondly, the propagation of ARGCCF embeddings proceeds in two steps. During the initial propagation, a residual connection is established between the node representation of the current layer and the previous layer to utilize the low-level layer’s node representation fully. The embeddings generated after the initial propagation are propagated again in the same graph convolutional layer, which obtains more refined embedding representations to alleviate the over-smoothing problem. Finally, experimentations on five truthful datasets exhibit that ARGCCF has better-improved performance over several mainstream methods. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

WDE-TransUNet: Brain Tumor Segmentation in MRI Images Utilizing Detail Enhancement and Transformers 24

WDE-TransUNet: Brain Tumor Segmentation in MRI Images Utiliz...

引用

5th International Symposium on Artificial Intelligence for Medicine science, ISAIMS 2024

作者： Ni, Xinhu Mo, Jiaqing Xinjiang Key Laboratory of Signal Detection and Processing School of Computer Science and Technology Xinjiang Urumqi China

ISBN: (纸本)9798400717826

WDE-TransUNet is a novel neural network architecture specifically designed for robust and precise semantic segmentation in medical imaging. This method addresses the challenges posed by inconsistent image quality, diverse pathologies, and anatomical variations due to different imaging techniques by integrating Transformer and convolutional neural network (CNN) modules within an encoder-decoder framework. It utilizes prior knowledge to assign weights at the input stage, optimizing feature utilization across modalities and mitigating the impact of irrelevant features. The encoder employs detail enhanced convolution (DEConv) and root mean square (RMS)Transformer modules to enhance local feature extraction, and then conveys these features to the decoder via skip connections, enriching both spatial and channel information. Evaluated on the Brain Tumor Segmentation Challenge (BraTS)2019, 2020, and 2021 datasets, this method achieved outstanding performance, with average Dice scores of 84.74%, 86.64%, and 90.66%, respectively. Our experimental results demonstrate that WDE-TransUNet, by integrating RSM Transformer with CNN in an encoder-decoder configuration, is superior to existing algorithms for brain tumor segmentation. © 2024 Copyright held by the owner/author(s).

关键词： Semantic Segmentation

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：