检索结果-内蒙古大学图书馆

Self-Supervised Learning for Activity Recognition Based on datasets With Imbalanced Classes

ieee TRANSACTIONS ON EMERGING TOPICS IN computational intelligence 2025年

作者： Hamad, Rebeen Ali Woo, Wai Lok Wei, Bo Yang, Longzhi Newcastle Univ Sch Comp Newcastle Upon Tyne NE4 5TG England Univ Northumbria Dept Comp & Informat Sci Newcastle Upon Tyne NE1 8ST England

Deep learning models have demonstrated significant efficacy across various domains, including healthcare, security, ubiquitous computing, and pervasive intelligence. Long short-term memory and convolutional neural networks, in particular, have revolutionized human activity recognition systems by effectively extracting semantic information directly from raw sensor data. However, the acquisition of large, well-annotated human activity datasets remains a considerable challenge due to privacy concerns, as well as the time and cost associated with labeling. To address this, unsupervised semantic representation learning, which bypasses the need for manual annotations, is crucial for utilizing the vast pool of unlabeled sensor data. In this study, we present a novel self-supervised learning network that extracts meaningful representations from sensor data without relying on predefined semantic labels. To address class imbalances, we enhance the synthetic minority oversampling technique, introducing an improved version called iSMOTE, which accurately labels synthetic samples. Additionally, we propose a random masking technique that removes identity mapping from input data, enabling the construction of generic semantic representations for downstream tasks. By utilizing balanced unlabeled data, our network significantly improves human activity recognition while reducing reliance on annotated data. We conducted extensive evaluations and comparisons of our proposed network against various supervised and self-supervised models using datasets from smart environments and wearable sensors. Remarkably, our network outperforms several existing methods across 12 public datasets. For instance, with just 25% of labeled data, our self-supervised network achieved an accuracy of 93.87% on the Ordonez Home A dataset, surpassing the performance of fully supervised methods such as DeepConvLSTM + Attention (84.97%), HAR + Attention (88.55%), and DCC + MSA (90.78%).

关键词： Human activity recognition Self-supervised learning data models Representation learning Monitoring data mining Noise computational modeling Unsupervised learning Supervised learning imbalanced learning reducing annotated data self-supervised representation learning sensor data

来源：评论

学校读者我要写书评

暂无评论

A Novel Method for Vessel Trajectory Clustering Based on Three-Dimensional Triangulation Division Algorithm

引用

ieee ACCESS 2025年 13卷 51388-51405页

作者： Xu, Kai Wang, Rui Gao, Qikai Tan, Jingjing Shanghai Maritime Univ Shanghai Int Shipping Inst Shanghai 200082 Peoples R China Shanghai Maritime Univ Sch Sci Shanghai 201306 Peoples R China Daiyue Dist Transportat Bur Tai An 271000 Shandong Peoples R China Shanghai Jizhi Shipping Dev Co Ltd Shanghai 200082 Peoples R China

Automatic identification system (AIS) performs vital functions in vessel collision avoidance and maritime security. The large-scale vessel trajectory data recorded by AIS has been facilitating vessel trajectory pattern mining, of which vessel trajectory clustering is a fundamental and indispensable approach. The precise and efficient measurement of trajectory similarity serves as the cornerstone of large-scale trajectory clustering. Most ship trajectory similarity measurement algorithms have issues of high time complexity, poor robustness and inability to distinguish the trajectories in opposite directions. This paper presents an improved measurement named three-dimensional Triangulation Division (3TD), which is based on area division in three-dimensional space with time axis incorporated, to ameliorate those deficiencies. In addition, a novel vessel trajectory clustering method is proposed by combining the 3TD algorithm with DBSCAN algorithm. AIS trajectory data in Yangshan Port area has been used to make experimental dataset. Experimental results indicate that the improved method in this paper has superior performance compared with some other existing methods in terms of clustering accuracy, robustness and computational efficiencies.

关键词： Trajectory Clustering algorithms Marine vehicles Clustering methods Time measurement Time complexity Noise Artificial intelligence Heuristic algorithms computational efficiency AIS area division DBSCAN trajectory similarity vessel trajectory clustering vessel trajectory pattern mining

来源：评论

学校读者我要写书评

暂无评论

Exploring the Potential of Fuzzy Sets in Cyborg Enhancement: A Comprehensive Review

引用

ieee TRANSACTIONS ON FUZZY SYSTEMS 2025年第3期33卷 810-827页

作者： Su, Hang Ovur, Salih Ertug Xu, Zhaoyang Alfayad, Samer Univ Evry Val Essonne Univ Paris Saclay IBISC Lab F-91000 Evry France Imperial Coll London Dept Elect & Elect Engn London SW7 2AZ England Univ Cambridge Dept Paedatr Cambridge CB2 1TN England

In an era marked by the rapid advancement of information technology, individuals now have the ability to enhance their organic bodies with mechanical and computational devices, revolutionizing their capabilities in everyday activities. However, the seamless integration of biosignals with mechanical counterparts continues to pose significant challenges. To address this, fuzzy logic (FL) emerges as a potential key to these challenges, offering a promising solution for handling the uncertainties and ambiguity inherent in biosignals. It thereby facilitates improved cyborg intelligence in an array of applications, including but not limited to wireless body area networks, brain-computer interfaces, prosthetics, and exoskeletons. Although previous works have highlighted the enhancement of cyborg intelligence using fuzzy sets, all of them only dived single aspects of the cyborg intelligence enhancement applications, leading to a lack of comprehensive understanding. Therefore, we provide a holistic overview of the state-of-the-art applications of FL in cyborg enhancement technology, encompassing its benefits, challenges, and potential directions for future research.

关键词： Human-machine systems Fuzzy logic Fuzzy sets Fuzzy systems data mining Wireless communication Body area networks Uncertainty Reviews Prosthetics Assistive technologies biomedical computing cyborg enhancement fuzzy logic

来源：评论

学校读者我要写书评

暂无评论

Scalable Min-Max Multi-View Spectral Clustering

引用

ieee TRANSACTIONS ON KNOWLEDGE AND data ENGINEERING 2025年第5期37卷 2918-2931页

作者： Yang, Ben Zhang, Xuetao Wu, Jinghan Nie, Feiping Wang, Fei Chen, Badong Xi An Jiao Tong Univ Inst Artificial Intelligence & Robot Natl Engn Res Ctr Visual Informat & Applicat Natl Key Lab Human Machine Hybrid Augmented Intell Xian 710049 Peoples R China Northwestern Polytech Univ Sch Comp Sci Xian 710072 Peoples R China Northwestern Polytech Univ Sch Artificial Intelligence Opt & Elect IOPEN Xian 710072 Peoples R China

Multi-view spectral clustering has attracted considerable attention since it can explore common geometric structures from diverse views. Nevertheless, existing min-min framework-based models adopt internal minimization to find the view combination with the minimized within-cluster variance, which will lead to effectiveness loss since the real clusters often exhibit high within-cluster variance. To address this issue, we provide a novel scalable min-max multi-view spectral clustering (SMMSC) model to improve clustering performance. Besides, anchor graphs, rather than full sample graphs, are utilized to reduce the computational complexity of graph construction and singular value decomposition, thereby enhancing the applicability of SMMSC to large-scale applications. Then, we rewrite the min-max model as a minimized optimal value function, demonstrate its differentiability, and develop an efficient gradient descent-based algorithm to optimize it with linear computational complexity. Moreover, we demonstrate that the resultant solution of the proposed algorithm is the global optimum. Numerous experiments on different real-world datasets, including some large-scale datasets, demonstrate that SMMSC outperforms existing state-of-the-art multi-view clustering methods regarding clustering performance.

关键词： computational modeling Optimization Laplace equations Convergence Vectors data mining computational complexity Clustering algorithms Training Sparse matrices Multi-view clustering min-max framework anchor graph gradient descent method

来源：评论

学校读者我要写书评

暂无评论

Adaptive Center-Focused Hybrid Attention Network for Change Detection in Hyperspectral Images

引用

ieee TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2025年 63卷

作者： Jiang, Fenlong Zhang, Shining Zhang, Mingyang Gong, Maoguo Zhou, Yu Zhao, Wei Guan, Ziyu Xidian Univ Sch Comp Sci & Technol Key Lab Collaborat Intelligence Syst Minist Educ Xian 710071 Peoples R China Xidian Univ Sch Elect Engn Key Lab Collaborat Intelligence Syst Minist Educ Xian 710071 Peoples R China Inner Mongolia Normal Univ Acad Artificial Intelligence Coll Math Sci Hohhot 010011 Peoples R China

Hyperspectral images (HSIs) capture extensive spatial and spectral information, facilitating detailed change detection (CD) of complex land covers. However, the high correlation among spectral data can lead to information redundancy, increasing processing dimensions and introducing irrelevant or detrimental data to CD. To address these challenges, we propose an adaptive center-focused hybrid attention network (ACFHAN) for CD in HSIs. This network adaptively emphasizes the spatial regions and spectral channels most pertinent to CD while suppressing irrelevant information. The architecture establishes an end-to-end mapping from the two HSIs to the change results, featuring multiple center-focused hybrid attention blocks (CFHABs). Each CFHAB integrates two different attention modules, including an adaptive spatial-spectral hybrid self-attention (S2HSA) module that dynamically adjusts spatial-spectral feature weights and a center-focused attention (CFA) module that enhances the area most relevant to the center pixel to be classified. Additionally, to tackle the challenges of expensive labeling, we further designed a multiscale superpixel-based data augmentation method which combines traditional unsupervised and supervised methods to provide sufficient low-cost but high-confidence labeled data for CD. Experimental results across various HSI CD datasets validate the effectiveness of our proposed method.

关键词： Feature extraction Accuracy Costs Vectors Redundancy Labeling Correlation Hyperspectral imaging data mining computational modeling Center-focused self-attention change detection (CD) hyperspectral images (HSIs) superpixel segmentation

来源：评论

学校读者我要写书评

暂无评论

SNN-SC: A Spiking Semantic Communication Framework for Collaborative intelligence

引用

ieee TRANSACTIONS ON VEHICULAR TECHNOLOGY 2025年第4期74卷 5883-5896页

作者： Wang, Mengyang Li, Jiahui Ma, Mengyao Fan, Xiaopeng Harbin Inst Technol Sch Comp Sci Harbin 150001 Peoples R China Peng Cheng Lab Shenzhen 519055 Peoples R China Huawei Wireless Technol Lab Shenzhen 518129 Peoples R China

Collaborative intelligence (CI) has emerged as a promising framework for deploying Artificial intelligence (AI) models on resource-constrained edge devices. In CI, the AI model is partitioned between the edge device and the cloud, with intermediate features transmitted from the edge sub-model to the cloud sub-model to complete the inference task. However, reducing feature transmission overhead while maintaining task performance remains a challenge, particularly in the case of noisy wireless channels. In this paper, we propose a Spiking Neural Network (SNN)-based Semantic Communication (SC) model, SNN-SC, which extracts compact semantic information from features and transmits it through digital binary channels. Compared to the Deep Neural Network (DNN)-based SC model, whose output is floating-point, the binary output of SNN makes SNN-SC directly applicable to digital binary channels without the need for extra quantization. Moreover, we introduce a novel spiking neuron called IHF to enhance the reconstruction capability of the SNN-SC decoder. Finally, we enhance the performance of SNN-SC by maximizing the entropy of semantic information. SNN-SC achieves a higher compression ratio and overcomes the 'cliff effect' compared to the traditional separate source and channel coding method. In addition, SNN-SC has lower computational complexity than the DNN-based SC model and maintains higher task performance under poor channel conditions.

关键词： computational modeling Neurons Membrane potentials Artificial intelligence Feature extraction Performance evaluation Quantization (signal) Image coding Decoding data mining Collaborative intelligence edge AI semantic communication spiking neural network

来源：评论

学校读者我要写书评

暂无评论

A Semi-Supervised Active Learning Neural Network for data Streams With Concept Drift

引用

ieee computational intelligence MAGAZINE 2025年第1期20卷 18-33页

作者： Jiao, Botao Gomes, Heitor Murilo Xue, Bing Guo, Yinan Zhang, Mengjie China Univ Petr East China Qingdao 266580 Peoples R China Victoria Univ Wellington Wellington 6140 New Zealand China Univ Min & Technol Beijing Beijing Peoples R China

Learning from data streams originating from non-stationary environments is vital for many real-world applications. A notable challenge in this task is concept drift. Most existing methods rely on a large number of labeled instances to detect and tackle concept drift in data streams. However, obtaining labeled data is not easy due to high costs, especially in potentially infinite data streams. To address this issue, a semi-supervised active learning neural network for data streams with concept drift is proposed to build an accurate classification model from incompletely labeled data. First, a semi-supervised regularization based on smoothness assumption is proposed to adjust the network weights and utilize unlabeled data. Second, a smoothness loss-based query strategy is designed to select instances that effectively improve model performance in line with the semi-supervised regularization objective. Notably, the query strategy and semi-supervised regularization form a closed learning loop that realizes the mutual enhancement of semi-supervised learning and active learning. Furthermore, an adaptive node adjustment method is proposed, which adjusts only a few neurons to adapt to local changes. Experiments on 17 synthetic and real-world datasets show that the proposed approach outperforms other state-of-the-art methods under various labeling budgets.

关键词： Adaptation models Accuracy Smoothing methods Concept drift Active learning Supervised learning Semisupervised learning data models Streams Biological neural networks

来源：评论

学校读者我要写书评

暂无评论

Robust SCN for data-Driven Modeling Based on Heavy-Tailed Noise Distribution

引用

ieee TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2025年 74卷

作者： Liu, Xin Liu, Xiaoqing Dai, Wei China Univ Min & Technol Artificial Intelligence Res Inst Xuzhou 221116 Peoples R China

This article focuses on discussing the extensive application of data-driven models in industry and the challenges it faces, particularly in dealing with interference and outliers in process data. To this end, the basic stochastic configuration network (SCN) is expanded with the heavy-tailed Laplace distribution in order to effectively address the outliers in industrial data, and a novel robust data-driven modeling method (renamed as Lap-RSC) is proposed. First, the prototype of the SCN learner model is constructed with the stochastic configuration algorithm, which means the hidden nodes number, the input weights, and biases of the SCN learner model are all determined in this step. Second, as the output data are contaminated with the outliers, the expectation-maximization (EM) algorithm is combined with the Laplace distribution to estimate the output weights of the SCN learner model robustly. Furthermore, the mathematical decomposition of the Laplace distribution is introduced in this work, which brings three major advantages: 1) it largely improves the computational efficiency of the Lap-RSC;2) it allows a more clearly and evident explanation of the robustness of the Lap-RSC;and 3) it facilitates the mathematical proof of the convergence property of the Lap-RSC. Finally, the verification results demonstrate the effectiveness of the proposed Lap-RSC.

关键词： Training Stochastic processes Robustness Mathematical models Heavily-tailed distribution Predictive models data-driven modeling Probability density function Gaussian distribution data mining expectation-maximization (EM) algorithm Laplace distribution robust parameter estimation stochastic configuration networks (SCNs)

来源：评论

学校读者我要写书评

暂无评论

Angular Reconstructive Discrete Embedding With Fusion Similarity for Multi-View Clustering

引用

ieee TRANSACTIONS ON KNOWLEDGE AND data ENGINEERING 2025年第1期37卷 45-59页

作者： Bian, Jintang Xie, Xiaohua Wang, Chang-Dong Yang, Lingxiao Lai, Jian-Huang Nie, Feiping Sun Yat Sen Univ Sch Comp Sci & Engn Guangzhou 510006 Peoples R China Guang Dong Prov Key Lab Informat Secur Technol Guangzhou 510006 Peoples R China Northwestern Polytech Univ Sch Comp Sci Sch Artificial Intelligence Opt & Elect iOPEN Xian 710072 Peoples R China Northwestern Polytech Univ Key Lab Intelligent Interact & Applicat Minist Ind & Informat Technol Xian 710072 Peoples R China

Effectively and efficiently mining valuable clustering patterns is a challenging problem when handling large-scale data from diverse sources. Existing approaches adopt anchor graph learning or binary representation embedding to reduce computational complexity. Normally, anchor graph learning can not directly obtain the clustering assignment except adopt the post-processing stage, such as graph cut or k-means clustering. The binary representation embedding neglects the structure information in Hamming space. In order to overcome these limitations, this paper proposes a novel, effective, and efficient angular reconstructive discrete embedding method with fusion similarity for a multi-view clustering (AFMC) that can jointly learn the global and local structure preserving binary representation and clustering assignment. Specifically, we propose to use angular reconstructive error minimization to maintain the global similarity correlation of binary representations of heterogeneous features in a common Hamming space. Moreover, we design a multi-view discrete ridge regression with fusion similarity term to handle the out-of-sample problem and preserve the local manifold structure. In addition, we propose an efficient optimization algorithm with linear computational complexity to solve the non-convex and non-smooth objective function. The experimental results demonstrate that AFMC outperforms several state-of-the-art large-scale multi-view clustering methods.

关键词： Clustering methods Vectors Correlation Manifolds Hypercubes Optimization Costs computational complexity Linear programming Eigenvalues and eigenfunctions Angular reconstructive embedding binary representation learning large-scale clustering multi-view learning

来源：评论

学校读者我要写书评

暂无评论

VIPeR: Visual Incremental Place Recognition With Adaptive mining and Continual Learning

引用

ieee ROBOTICS AND AUTOMATION LETTERS 2025年第3期10卷 3038-3045页

作者： Ming, Yuhang Xu, Minyang Yang, Xingrui Ye, Weicai Wang, Weihan Peng, Yong Dai, Weichen Kong, Wanzeng Hangzhou Dianzi Univ Sch Comp Sci Key Lab Brain Machine Collaborat Intelligence Zhej Hangzhou 310018 Peoples R China CARDC High Speed Aerodynam Inst Mianyang 621000 Peoples R China Zhejiang Univ State Key Lab CAD & CG Hangzhou 310058 Peoples R China Stevens Inst Technol Hoboken NJ 07030 USA

Visual place recognition (VPR) is essential to many autonomous systems. Existing VPR methods demonstrate attractive performance at the cost of limited generalizability. When deployed in unseen environments, these methods exhibit significant performance drops. Targeting this issue, we present VIPeR, a novel approach for visual incremental place recognition with the ability to adapt to new environments while retaining the performance of previous ones. We first introduce an adaptive mining strategy that balances the performance within a single environment and the generalizability across multiple environments. Then, to prevent catastrophic forgetting in continual learning, we design a novel multi-stage memory bank for explicit rehearsal. Additionally, we propose a probabilistic knowledge distillation to explicitly safeguard the previously learned knowledge. We evaluate our proposed VIPeR on three large-scale datasets-Oxford Robotcar, Nordland, and TartanAir. For comparison, we first set a baseline performance with naive finetuning. Then, several more recent continual learning methods are compared. Our VIPeR achieves better performance in almost all aspects with the biggest improvement of 13.85% in average performance.

关键词： Continuing education Visualization Training Measurement Atmospheric modeling Adaptation models computational modeling data mining Probabilistic logic Image recognition Localization recognition continual learning

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：