检索结果-内蒙古大学图书馆

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

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 1-17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

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

Online Streaming Feature Selection Using Bidirectional Complementarity Based on Fuzzy Gini Entropy

引用

IEEE Transactions on Fuzzy Systems 2025年第5期33卷 1592-1604页

作者： Zhang, Chucai Lu, Zhengxiang Zhang, Yongkang Dai, Jianhua Hunan Normal University Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing College of Information Science and Engineering Changsha410081 China School of Mathematics and Statistics Changsha410081 China

Online streaming feature selection has garnered widespread attention due to its efficiency and adaptability in dynamic data environments. However, existing methods primarily focus on the correlation and redundancy among features, often overlooking the complementarity between candidate and selected features. In this article, we address this gap by introducing three key innovations. First, we construct a novel metric, fuzzy Gini entropy (FGE), to measure feature uncertainty within datasets. Unlike traditional information entropy, fuzzy Gini entropy inherits the advantages of the Gini index, effectively measuring the impurity of datasets, while also being capable of handling common fuzzy environments. Accordingly, related metrics such as fuzzy joint Gini entropy, fuzzy conditional Gini entropy, and fuzzy mutual Gini information are developed. Second, we innovatively propose the concept of the bidirectional complementarity ratio, which captures the relationship between candidate features and previously selected features in online streaming feature selection. This mitigates the unfairness associated with the late arrival of features, ensuring that candidate features with a bidirectional complementary effect that outweighs their redundancy effect with the selected features are chosen. Third, we design an online streaming feature selection method named FGE-OSFS. The method evaluates streaming features through three steps: Online relevance analysis, online bidirectional complementarity analysis, and online redundancy analysis. Finally, we compare the proposed method with five state-of-the-art online streaming feature selection methods, demonstrating the effectiveness of our new approach. © 1993-2012 IEEE.

关键词： Redundancy

来源：评论

学校读者我要写书评

暂无评论

PRPFD: Polynomial Resampling Particle Filter Based Deconvolution Approach for Resting-State BOLD-fMRI Data Analysis 24

PRPFD: Polynomial Resampling Particle Filter Based Deconvolu...

引用

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

作者： Luo, Yunying Zeng, Weiming Key Laboratory for Digital Imaging Processing and Intelligent Computing School of Information Engineering Shanghai Maritime University Shanghai China

ISBN: (纸本)9798400717826

Functional Magnetic Resonance Imaging (fMRI) stands out in brain science research due to its non-invasive, non-intrusive, radiation-free, high spatial resolution, and precise localization advantages. However, the BOLD-fMRI signals it generates exhibit a several-second delay compared to neural activity, making it unable to reflect brain neural activity directly. This discrepancy may lead to differences from the actual situation. Therefore, this study aims to enhance the deconvolution of fMRI by refining existing methods to reconstruct the brain’s neural signals more faithfully. Building upon the foundation of particle filtering deconvolution, this paper introduced a novel approach to deconvolving resting-state fMRI data: the polynomial resampling particle filtering deconvolution (PRPFD). They adapted the particle distribution better to match the actual state through weight computation and resampling. We performed a simulation-based experiment to validate the feasibility of our approach. Besides, we validated the performance of our method using group data, focusing on both effective connectivity and functional connectivity, providing strong evidence for the usability and stability of our approach, and compared our method with other deconvolution techniques, demonstrating improvements in accuracy and computational efficiency. © 2024 Copyright held by the owner/author(s).

关键词： Polynomials

来源：评论

学校读者我要写书评

暂无评论

An Improved Compressive Sensing-Based Model for Efficient Analysis of Monostatic Electromagnetic Scattering Problems

引用

IEEE Microwave and Wireless Technology Letters 2025年第4期35卷 388-391页

作者： Qi, Qi Fan, Yunuo Cao, Xinyuan Liu, Yi Kong, Meng Huang, Zhixiang Wu, Xianliang Hefei Normal University Anhui Province Key Laboratory of Simulation Calculation and Design for Electronic Information System Hefei230601 China Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Hefei230601 China

To further accelerate the analysis of monostatic electromagnetic (EM) scattering problems of objects, an improved compressive sensing (CS)-based model is proposed. First, an orthogonal subspace spanned by the wide-angle induced currents is identified by means of the wide-angle incident sources. Then, the sparse transform of the induced currents is replaced by the subspace projection. In addition, an optimal number of measurements is determined, only slightly larger than the dimension of the subspace. Finally, the recovery algorithm is simplified to the least-squares method to solve the resulting overdetermined system. Compared with the traditional CS-based model, the proposed model significantly improves the efficiency of the recovery step and optimizes both the requirement for and the way of determining the number of measurements. © 2023 IEEE.

关键词： Least squares approximations

来源：评论

学校读者我要写书评

暂无评论

A numerical magnitude aware multi-channel hierarchical encoding network for math word problem solving

引用

Neural computing and Applications 2025年第3期37卷 1651-1672页

作者： Xu, Junjie Chen, Yuzhong Xiao, Lingsheng Liao, Hongmiao Zhong, Jiayuan Dong, Chen College of Computer and Data Science Fuzhou University Fujian Province Fuzhou350108 China Engineering Research Center of Big Data Intelligence Ministry of Education Fuzhou China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fujian Province Fuzhou350108 China

Math word problem (MWP) represents a critical research area within reading comprehension, where accurate comprehension of math problem text is crucial for generating math expressions. However, current approaches still grapple with unresolved challenges in grasping the sensitivity of math problem text and delineating distinct roles across various clause types, and enhancing numerical representation. To address these challenges, this paper proposes a Numerical Magnitude Aware Multi-Channel Hierarchical Encoding network (NMA-MHEA) for math expression generation. Firstly, NMA-MHEA implements a multi-channel hierarchical context encoding module to learn context representations at three different channels: intra-clause channel, inter-clause channel, and context-question interaction channel. NMA-MHEA constructs hierarchical constituent-dependency graphs for different levels of sentences and employs a Hierarchical Graph Attention Neural network (HGAT) to learn syntactic and semantic information within these graphs at the intra-clause and inter-clause channels. NMA-MHEA then refines context clauses using question information at the context-question interaction channel. Secondly, NMA-MHEA designs a number encoding module to enhance the relative magnitude information among numerical values and type information of numerical values. Experimental results on two public benchmark datasets demonstrate that NMA-MHEA outperforms other state-of-the-art models. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Domain Transfer for Object Classification in 3D Point Clouds via Hierarchical Prompt Learning

引用

IEEE Signal processing Letters 2025年 32卷 1750-1754页

作者： Luo, Huan Fu, Kaiwei Fang, Lina Fuzhou University College of Computer and Data Science China Fuzhou University Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing China Ministry of Education Key Laboratory of Spatial Data Mining & Information Sharing Fuzhou350003 China Chinese Academy of Sciences Quanzhou Institute of Equipment Manufacturing Haixi Institute Fujian Quanzhou362216 China

Traditional object classification in 3D point cloud scenes relies heavily on large-scale labeled training data, which is both time-consuming and labor-intensive to obtain. Unsupervised Domain Transfer (UDT) mitigates this challenge by transferring knowledge from a labeled source domain to an unlabeled target domain. However, existing UDT-based methods often require complex neural architectures and substantial computational resources. This letter proposes a novel UDT framework that integrates hierarchical prompt learning with a 3D foundational model. The proposed method consists of a modality alignment stage and an unsupervised transfer stage. In the modality alignment stage, cross-modal hierarchical prompts are employed to align the Visual-Language (V-L) modality in the 3D foundational model through a V-L coupling module. In the unsupervised transfer stage, cross-domain hierarchical prompts and a Target-Source (T-S) coupling module facilitate the alignment of multi-scale contextual information across domains, ensuring efficient and accurate knowledge transfer. Extensive experiments conducted on multiple datasets collected from various laser scanners demonstrate the effectiveness of our proposed approach. © 1994-2012 IEEE.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Glare-SNet: Unsupervised Glare Suppression Balance network 27th

Glare-SNet: Unsupervised Glare Suppression Balance Network

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Li, Pei Zuo, Chengyu Wei, Wangjuan Pan, Xiaoying Wang, Zhanhao School of Computer Science and Technology Xi’an University of Posts and Telecommunications Xi’an710121 China Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi’an China Shaanxi Key Laboratory of Intelligent Media Computing and interaction Xi’an China Xi’an Key Laboratory of Big Data and Intelligent Computing Xi’an China

ISBN: (纸本)9783031781681

In light of the problems associated with glare and halo effects in low-light images, as well as the inadequacy of existing processing algorithms in handling details, a glare suppression balance network based on unsupervised learning has been designed and implemented in this study. A network that perceives brightness through light decomposition has been proposed, and an illumination learning network has been designed. The idea of integration has been employed to form an unsupervised glare suppression balance network, aiming to tackle the issues of glare and the accompanying halo effects. Through objective and subjective evaluations of real images, it has been proven that the method introduced in this paper surpasses other methods in suppressing glare and enhancing the overall quality of low-light images. Furthermore, it has been shown to exhibit good performance and effectiveness in target detection. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Image enhancement

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：