检索结果-内蒙古大学图书馆

10th IEEE Smart World Congress, SWC 2024

作者： Wu, Ling Gao, Pingping Guo, Kun Fujian Key Laboratory of Network Computing and Intelligent Information Processing China

ISBN: (纸本)9798331520861

With deep learning's advancement in recent years, heterogeneous graph neural networks (HGNNs) have drawn a lot of interest. They are a group of deep learning models specifically designed for handling heterogeneous graph data, in which nodes and edges are of various types and all nodes are assumed to have either direct or indirect associations. A metaschema, which serves as a thorough and unified blueprint for the heterogeneous graph, elegantly connects varied node types to other heterogeneous nodes via multiple heterogeneous edges with rich sematincs. However, many existing methods that utilize meta-schema to mine heterogeneous information often focus on the different meta-relationships inside the schema, limiting the meta-schema to describing only the local relational semantics. To better utilize meta-schema for efficiently integrating different heterogeneous information, we organize them into a hierarchical structure(i.e., hierarchical meta-schema), with all types of nodes distributed across different layers. The layers are interconnected through heterogeneous relationships. The target type is placed at the final layer and others are arranged hierarchically in the front according to the heterogeneous relationships defined in the meta-schema. During information aggregation, according to the hierarchical meta-schema, the information of each layer is gradually aggregated to the target type on the final layer from far to near via the attention mechanism. Moreover, metapaths regularly begin and end with the same type and help to define complex structures and semantic. Therefore, we also consider the semantic information of neighbors based on metapaths within the proposed hierarchical meta-schema to enhance the complex semantics among nodes of the same-type that may be lacking in the meta-schema. Finally, we proposed a meta-path and meta-schema hierarchical aggregation for heterogeneous graph neural network model, named HGNN-MMHA. And we may allow the meta-schema to not

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Multimodal Cross-Attention Mechanism-Based Algorithm for Elderly Behavior Monitoring and Recognition

引用

Chinese Journal of Electronics 2025年第1期34卷 309-321页

作者： Hao Liu Zhiquan Feng Qingbei Guo School of Information Science and Engineering Unicersity of Jinan Shandong Provincial Key Laboratory of Network Based Intelligent Computing Unicersity of Jinan

In contrast to the general population, behavior recognition among the elderly poses increased specificity and difficulty, rendering the reliability and usability aspects of safety monitoring systems for the elderly more challenging. Hence, this study proposes a multi-modal perception-based solution for an elderly safety monitoring recognition system. The proposed approach introduces a recognition algorithm based on multi-modal cross-attention mechanism, innovatively incorporating complex information such as scene context and voice to achieve more accurate behavior recognition. By fusing four modalities, namely image, skeleton, sensor data, and audio, we further enhance the accuracy of recognition. Additionally, we introduce a novel human-robot interaction mode, where the system associates directly recognized intentions with robotic actions without explicit commands, delivering a more natural and efficient elderly assistance paradigm. This mode not only elevates the level of safety monitoring for the elderly but also facilitates a more natural and efficient caregiving approach. Experimental results demonstrate significant improvement in recognition accuracy for 11 typical elderly behaviors compared to existing methods.

关键词： Privacy Accuracy Image recognition Speech recognition Robot sensing systems Skeleton Safety Reliability Older adults Monitoring

来源：评论

学校读者我要写书评

暂无评论

JDC-GCN: joint diversity and consistency graph convolutional network

引用

Neural computing and Applications 2025年第16期37卷 10407-10423页

作者： Lin, Renjie Yao, Jie 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

In real-world scenarios, multi-view data comprises heterogeneous features, with each feature corresponding to a specific view. The objective of multi-view semi-supervised classification is to enhance classification performance by leveraging the inherent complementary and consistent information present within diverse views. Nevertheless, many existing frameworks primarily focus on assigning suitable weights to different views while neglecting the importance of consistent information. In this paper, a multi-view semi-supervised classification framework called joint diversity and consistency graph convolutional network (JDC-GCN) is proposed. Firstly, the structure of graph convolutional network is introduced to the multi-view semi-supervised classification, capable of propagating the label information over the topological structure of multi-view data. Secondly, the proposed JDC-GCN captures the complementary and consistent information from multiple views through two indispensable sub-modules, Diversity-GCN and Consistency-GCN, respectively. Finally, the attention mechanism is leveraged to dynamically adjust the weights of various views, allowing us to measure the significance of heterogeneous features and the consistent graph without introducing additional parameters. Comprehensive experiments on eight multi-view datasets are conducted to validate the effectiveness of the JDC-GCN algorithm. The results show that the proposed method exhibits superior classification performance compared to other state-of-the-art methods. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Degradation-Trend-Aware Deep Neural network with Attention Mechanism for Bearing Remaining Useful Life Prediction

IEEE Transactions on Artificial Intelligence

引用

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

High-precision end-to-end adaptive optics aided orbital angular momentum wireless communication with XFTC-Net

引用

Optics Letters 2025年第10期50卷 3265-3268页

作者： Xu, Panpan Chang, Huan Wang, Fei Gao, Ran Guo, Dong Zhu, Lei Li, Zhipei Zhou, Sitong Xu, Qi Chen, Jing Xin, Xiangjun Beijing100081 China National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing Beijing China Beijing100876 China Key Laboratory of Computing Power Network and Information Security Ministry of Education Qilu University of Technology 250353 China

In this Letter, we demonstrate high-precision end-to-end adaptive optics (AO) technique based on the X-Shape Fusion Transformer-convolutional neural network (XFTC-Net) without an additional probe path to compensate for distortions caused by atmospheric turbulence (AT) in orbital angular momentum (OAM) optical wireless communication links. The experimental results show that the XFTC-Net effectively extracts the intensity distribution features of distorted OAM beams, predicting AT phase screens and identifying OAM modes. After XFTC-Net-aided AO compensation, the bit error rate of the OAM optical communication system remains below 3.8 × 10−3, staying within Cn2 = 1 × 10−15–1 × 10−13 m−2/3. Moreover, the optical power with l= 3 increases from 5.08 dBm to 8.23 dBm at a transmission distance of 800 m. These experimental results indicate that the proposed XFTC-Net AO technique effectively compensates for OAM beam distortion in both single- and multiplexed-channel OAM links, which effectively balances the system complexity and transmission performance of OAM-based free space optical (FSO) communication systems, opening up new avenues for enhancing the performances of high-capacity optical communication. © 2025 Optica Publishing Group. All rights, including for text and data mining (TDM), Artificial Intelligence (AI) training, and similar technologies, are reserved.

关键词： Fiber to the x

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

A knowledge-enhanced interest segment division attention network for click-through rate prediction

引用

Neural computing and Applications 2024年第34期36卷 21817-21837页

作者： Liu, Zhanghui Chen, Shijie Chen, Yuzhong Su, Jieyang Zhong, Jiayuan Dong, Chen College of Computer and Data Science Fuzhou University Fujian Province Fuzhou350108 China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fujian Province Fuzhou350108 China

Click-through rate (CTR) prediction aims to estimate the probability of a user clicking on a particular item, making it one of the core tasks in various recommendation platforms. In such systems, user behavior data are crucial for capturing user interests, which has garnered significant attention from both academia and industry, leading to the development of various user behavior modeling methods. However, existing models still face unresolved issues, as they fail to capture the complex diversity of user interests at the semantic level, refine user interests effectively, and uncover users’ potential interests. To address these challenges, we propose a novel model called knowledge-enhanced Interest segment division attention network (KISDAN), which can effectively and comprehensively model user interests. Specifically, to leverage the semantic information within user behavior sequences, we employ the structure of a knowledge graph to divide user behavior sequence into multiple interest segments. To provide a comprehensive representation of user interests, we further categorize user interests into strong and weak interests. By leveraging both the knowledge graph and the item co-occurrence graph, we explore users’ potential interests from two perspectives. This methodology allows KISDAN to better understand the diversity of user interests. Finally, we extensively evaluate KISDAN on three benchmark datasets, and the experimental results consistently demonstrate that the KISDAN model outperforms state-of-the-art models across various evaluation metrics, which validates the effectiveness and superiority of KISDAN. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Security-Reliability Analysis and Optimization for Cognitive Two-Way Relay network with Energy Harvesting

引用

China Communications 2024年第11期21卷 163-179页

作者： Luo Yi Zhou Lihua Dong Jian Sun Yang Xu Jiahui Xi Kaixin Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Hunan Normal UniversityChangsha 410081China School of Electronic Information Central South UniversityChangsha 410075China

This paper investigates the security and reliability of information transmission within an underlay wiretap energy harvesting cognitive two-way relay *** the network,energy-constrained secondary network(SN)nodes harvest energy from radio frequency signals of a multi-antenna power *** SN sources exchange their messages via a SN decode-and-forward relay in the presence of a multiantenna eavesdropper by using a four-phase time division broadcast protocol,and the hardware impairments of SN nodes and eavesdropper are *** alleviate eavesdropping attacks,the artificial noise is applied by SN *** physical layer security performance of SN is analyzed and evaluated by the exact closed-form expressions of outage probability(OP),intercept probability(IP),and OP+IP over quasistatic Rayleigh fading ***,due to the complexity of OP+IP expression,a self-adaptive chaotic quantum particle swarm optimization-based resource allocation algorithm is proposed to jointly optimize energy harvesting ratio and power allocation factor,which can achieve security-reliability tradeoff for *** simulations demonstrate the correctness of theoretical analysis and the effectiveness of the proposed optimization algorithm.

关键词： artificial noise energy harvesting cognitive two-way relay network hardware impairments physical layer security security-reliability tradeoff self-adaptive quantum particle swarm optimization

来源：评论

学校读者我要写书评

暂无评论

RECONSTRUCTION-BASED A POSTERIORI ERROR ESTIMATES FOR THE L1 METHOD FOR TIME FRACTIONAL PARABOLIC PROBLEMS

引用

Journal of Computational Mathematics 2025年第2期43卷 345-368页

作者： Jiliang Cao Aiguo Xiao Wansheng Wang Department of Mathematics Shanghai Normal UniversityShanghai 200234China Hunan Key Laboratory for Computation and Simulation in Science and Engineering&Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education Xiangtan UniversityXiangtan 411105China

In this paper,we study a posteriori error estimates of the L1 scheme for time discretizations of time fractional parabolic differential equations,whose solutions have generally the initial *** derive optimal order a posteriori error estimates,the quadratic reconstruction for the L1 method and the necessary fractional integral reconstruction for the first-step integration are *** using these continuous,piecewise time reconstructions,the upper and lower error bounds depending only on the discretization parameters and the data of the problems are *** numerical experiments for the one-dimensional linear fractional parabolic equations with smooth or nonsmooth exact solution are used to verify and complement our theoretical results,with the convergence ofαorder for the nonsmooth case on a uniform *** recover the optimal convergence order 2-αon a nonuniform mesh,we further develop a time adaptive algorithm by means of barrier function recently *** numerical implementations are performed on nonsmooth case again and verify that the true error and a posteriori error can achieve the optimal convergence order in adaptive mesh.

关键词： Time fractional parabolic differential equations A posteriori error estimates Ll method Fractional integral reconstruction Quadratic reconstruction

来源：评论

学校读者我要写书评

暂无评论

Underwater target recognition based on adaptive multi-feature fusion network

引用

Multimedia Tools and Applications 2025年第10期84卷 7297-7317页

作者： Pan, Xiaoying Sun, Jia Feng, TianHao Lei, MingZhu Wang, Hao Zhang, WuXia Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi’an710121 China Xi’an Key Laboratory of Big Data and Intelligent Computing Xi’an710121 China School of Computer Science and Technology Xi’an University of Post & Telecommunications Xi’an710121 China

Due to the complexity of the underwater environment, underwater acoustic target recognition is more challenging than ordinary target recognition, and has become a hot topic in the field of underwater acoustics research. In recent years, deep learning has been widely used in underwater recognition due to its powerful feature learning capabilities. However, most deep learning-based underwater target recognition methods use only the time-frequency domain features of signals, ignoring the frequency domain image features of signals. Additionally, they only use simple summation or splicing strategies to fuse and discriminate the extracted features, which leads to limited improvement in the accuracy of underwater target recognition. To address these issues, this paper proposes an underwater target recognition method based on an adaptive multi-feature fusion network. The method consists of a data pre-processing module, a multi-dimensional feature extraction module, and an adaptive multi-feature fusion module. In the multi-dimensional feature extraction module, the long short time memory network (LSTM) and the one-dimensional convolutional neural network (1DCNN) are used to extract the time-frequency features of the underwater signal. Furthermore, the two-dimensional convolutional neural network (2DCNN) is used to extract the image features in the frequency domain. The adaptive multi-feature fusion module uses an attention mechanism for adaptive weighted fusion to make full use of the learned features. The effectiveness of the proposed method is validated on the ShipEar dataset, and the recognition accuracy reaches 94.92%, which is higher than other existing methods. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Feature extraction

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

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

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：