检索结果-内蒙古大学图书馆

Sea ice type identification method based on MEMS sensor network combined with PCA-BPMIV-GRU

IEEE Transactions on Instrumentation and Measurement 2025年

作者： Yang, Le Quan, Xiyu Zhang, Jiankui Liu, Yunjing Zhao, Shiqi Fu, Changzeng Zhan, Zhikun Li, Lianliang Lv, Xiaoyong Zhao, Yuliang Northeastern University at Qinhuangdao Hebei Key Laboratory of MicroNano Precision Optical Sensing and Measurement Technology The School of Control Engineering Qinhuangdao066004 China Northeastern University at Qinhuangdao College of Control Science and Engineering Qinhuangdao066099 China Northeastern University at Qinhuangdao College of Computer Science and Engineering Qinhuangdao066004 China

Sea ice poses a significant hazard to vessels navigating in high-latitude maritime regions. To effectively prevent the collision between ships and large sea ice (such as icebergs) and other similar accidents, it is crucial to identify sea ice and its types in a timely and accurate manner. However, traditional sea ice identification techniques, such as optical and radar remote sensing, are often limited by visibility conditions, suffering from poor accuracy, high measurement costs, and low identification efficiency. This paper proposes a sea ice identification method based on a vibration sensor network, combined with the PCA-BPMIV-GRU strategy, which achieves low cost, high efficiency, and high accuracy in sea ice type detection. Firstly, a cost-effective MEMS vibration sensor network is deployed to capture vibration information of sea ice. The data collected from six sensors at different locations at the same time are treated as independent samples to construct a dataset, which contains time-frequency domain characteristic data of three sea-ice types: broken ice, flat ice, and open water. Secondly, the dimension reduction and feature optimization of vibration data were carried out by combining Principal Component Analysis (PCA) and the improved Mean Influence Value Optimization algorithm (BPMIV). This integration of unsupervised and supervised algorithms effectively eliminated unnecessary feature information, significantly improving model identification efficiency. Finally, seven commonly used classification algorithms are compared for the identification of three types of sea ice, evaluating their identification accuracy and efficiency under different dimensionality reduction methods. The results confirm that the Gated Recurrent Unit (GRU) model achieves the best comprehensive performance. Experimental data shows that the proposed method reduces the number of features to 9, resulting in a 24.2 % decrease in parameters compared to the GRU model alone, while achieving

关键词： Frequency domain analysis

来源：评论

学校读者我要写书评

暂无评论

Replay Without Saving: Prototype Derivation and Distribution Rebalance for Class-Incremental Semantic Segmentation

引用

IEEE Transactions on Pattern Analysis and Machine Intelligence 2025年第6期47卷 4699-4716页

作者： Jinpeng Chen Runmin Cong Yuxuan Luo Horace Ho Shing Ip Sam Kwong Department of Computer Science City University of Hong Kong Kowloon Hong Kong School of Control Science and Engineering Shandong University Jinan China Key Laboratory of Machine Intelligence and System Control Ministry of Education Jinan China Department of Computer Science and Centre for Innovative Applications of Internet and Multimedia Technologies City University of Hong Kong Kowloon Hong Kong School of Data Science Lingnan University Tuen Mun Hong Kong

The research of class-incremental semantic segmentation (CISS) seeks to enhance semantic segmentation methods by enabling the progressive learning of new classes while preserving knowledge of previously learned ones. A significant yet often neglected challenge in this domain is class imbalance. In CISS, each task focuses on different foreground classes, with the training set for each task exclusively comprising images that contain these currently focused classes. This results in an overrepresentation of these classes within the single-task training set, leading to a classification bias towards them. To address this issue, we propose a novel CISS method named STAR, whose core principle is to reintegrate the missing proportions of previous classes into current single-task training samples by replaying their prototypes. Moreover, we develop a prototype deviation technique that enables the deduction of past-class prototypes, integrating the recognition patterns of the classifiers and the extraction patterns of the feature extractor. With this technique, replay can be accomplished without using any storage to save prototypes. Complementing our method, we devise two loss functions to enforce cross-task feature constraints: the Old-Class Features Maintaining (OCFM) loss and the Similarity-Aware Discriminative (SAD) loss. The OCFM loss is designed to stabilize the feature space of old classes, thus preserving previously acquired knowledge without compromising the ability to learn new classes. The SAD loss aims to enhance feature distinctions between similar old and new class pairs, minimizing potential confusion. Our experiments on two public datasets, Pascal VOC 2012 and ADE20 K, demonstrate that our STAR achieves state-of-the-art performance.

关键词： Prototypes Training Feature extraction Semantic segmentation Continuing education Stars Semantics Vectors Transformers Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Semantic-aware dynamic scene tracking and reconstruction for mobile robots leveraging visual SLAM

引用

The Journal of Supercomputing 2025年第7期81卷 1-39页

作者： Liu, Tianwei Luo, Jingwen School of Information Science and Technology Yunnan Normal University Kunming China Engineering Research Center of Computer Vision and Intelligent Control Technology Department of Education of Yunnan Province Kunming China

Mobile robots operating in dynamic environments often encounter challenges due to interference from moving objects, compromising the performance of their SLAM systems. To address this issue, we propose a depth camera based semantic-aware visual SLAM approach for mobile robots, aimed at dynamic scene tracking and reconstruction. By leveraging a lightweight Yolact++ network, we segment and detect objects in the scene, eliminate dynamic features through prior knowledge and epipolar constraints, and utilize high-confidence static features for robot’s pose estimation. Subsequently, the overall similarity between images is evaluated based on the similarity of the matched semantic object regions between images to select high-quality candidate keyframes, effectively enhancing the precision of loop closure detection. Furthermore, we employ Delta Generalized Labeled Multi-Bernoulli (Delta-GLMB) filtering to track the masks of prior dynamic objects provided by Yolact++. A global semantic octree map is then constructed, integrating both the semantic knowledge of the static scene and the tracking information of dynamic targets, which in turn realizes the tracking & reconstruction of the dynamic scene. This allows mobile robots to mimic human behavior and cognitive abilities, not merely to construct a map of unknown environments more efficiently, but also to track the state of moving targets in the field-of-view(FoV) in real-time, enabling self-localization and navigation functions. Experimental results demonstrate the effectiveness of our approach in improving the robustness, accuracy, and adaptability of mobile robots in dynamic environments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-Source Data with Laplacian Eigenmaps and Denoising Autoencoder for Predicting Microbe-Disease Associations via Convolutional Neural Network

引用

Journal of computer science and Technology 2025年第2期40卷 588-604页

作者： Lei, Xiu-Juan Chen, Ya-Li Pan, Yi School of Computer Science Shaanxi Normal University Xi’an China Faculty of Computer Science and Control Engineering Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China Shenzhen Key Laboratory of Intelligent Bioinformatics Shenzhen Institute of Advanced Technology Chinese Academy of Science Shenzhen China

Identifying microbes associated with diseases is important for understanding the pathogenesis of diseases as well as for the diagnosis and treatment of diseases. In this article, we propose a method based on a multi-source association network to predict microbe-disease associations, named MMHN-MDA. First, a heterogeneous network of multi-molecule associations is constructed based on associations between microbes, diseases, drugs, and metabolites. Second, the graph embedding algorithm Laplacian eigenmaps is applied to the association network to learn the behavior features of microbe nodes and disease nodes. At the same time, the denoising autoencoder (DAE) is used to learn the attribute features of microbe nodes and disease nodes. Finally, attribute features and behavior features are combined to get the final embedding features of microbes and diseases, which are fed into the convolutional neural network (CNN) to predict the microbe-disease associations. Experimental results show that the proposed method is more effective than existing methods. In addition, case studies on bipolar disorder and schizophrenia demonstrate good predictive performance of the MMHN-MDA model, and further, the results suggest that gut microbes may influence host gene expression or compounds in the nervous system, such as neurotransmitters, or metabolites that alter the blood-brain barrier.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cluster-Refined Optimal Transport for Unsupervised Action Segmentation

Cluster-Refined Optimal Transport for Unsupervised Action Se...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Wang, Shijie Zhang, Jinrong Liu, Yule Li, Shiyao Feng, Lin School of Computer Science and Technology Dalian University of Technology Dalian China School of Control Science and Engineering Dalian University of Technology Dalian China School of Innovation and Entrepreneurship Dalian University of Technology Dalian China

ISBN: (纸本)9798350368741

Action segmentation in untrimmed videos is essential for comprehensive video understanding. Despite significant progress in unsupervised methods, capturing both long-range dependencies and short-duration actions simultaneously remains a challenging task. To address this challenge, this paper introduces the Cluster-Refined Optimal Transport (CROT) method, combining hierarchical clustering and optimal transport for unsupervised action segmentation. We first hierarchically cluster video frame representations to capture long-range dependencies and generate pseudo-boundaries. Initial pseudo-labels are then obtained via optimal transport, ensuring short-duration actions are recognized. Finally, these pseudo-labels are refined using the pseudo-boundaries, resulting in the final segmentation output. Extensive experiments on three public datasets, i.e., YouTube Instructions, Breakfast, and 50Salads, demonstrate that our method performs on par with or better than previous approaches. © 2025 IEEE.

关键词： action segmentation hierarchical clustering optimal transport unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Dual defense:Combining preemptive exclusion of members and knowledge distillation to mitigate membership inference attacks

引用

Journal of Information and Intelligence 2025年第1期3卷 68-90页

作者： Jun Niu Peng Liu Chunhui Huang Yangming Zhang Moxuan Zeng Kuo Shen Yangzhong Wang Suyu An Yulong Shen Xiaohong Jiang Jianfeng Ma He Wang Gaofei Wu Anmin Fu Chunjie Cao Xiaoyan Zhu Yuqing Zhang School of Computer Science and Technology Xidian UniversityXi'an 710071China Information Sciences and Technology Pennsylvania State UniversityPA 16802USA School of Cyberspace Security Hainan UniversityHaikou 570228China School of Hangzhou Institute of Technology Xidian UniversityHangzhou 311231China School of Systems Information Science Future University of HakodateHakodate 041-8655Japan School of Cyber Engineering Xidian UniversityXi'an 710071China School of Computer Science and Engineering Nanjing University of Science and TechnologyNanjing 210094China School of Telecommunications Engineering Xidian UniversityXi'an 710071China School of Computer&Control Engineering University of Chinese Academy of SciencesBeijing 101408China

Membership inference(MI)attacks threaten user privacy through determining if a given data example has been used to train a target *** MI defenses protect the membership privacy through preemptive exclusion of members techniques and knowledge ***,using either of these two defenses alone,the defense effect can still offers an unsatisfactory trade-off between membership privacy and *** that the defense method that directly combines these two defenses is still very limited(e.g.,the test accuracy of the target model is decreased by about 40%(in our experiments)),in this work,we propose a dual defense(DD)method that includes the preemptive exclusion of high-risk member samples module and the knowledge distillation module,which thwarts the access of the resulting models to the private training data twice to mitigate MI *** defense method can be divided into two steps:the preemptive exclusion of high-risk member samples(Step 1)and the knowledge distillation to obtain the protected student model(Step 2).We propose three types of exclusions:existing MI attacks-based exclusions,sample distances of members and nonmembers-based exclusions,and mutual information value-based exclusions,to preemptively exclude the high-risk member *** the knowledge distillation phase,we add ground-truth labeled data to the reference dataset to decrease the protected student model's dependency on soft labels,aiming to maintain or improve its test *** evaluation shows that DD significantly outperforms state-of-the-art defenses and offers a better privacy-utility *** example,DD achieves∼100%test accuracy improvement over the distillation for membership privacy(DMP)defense for ResNet50 trained on *** simultaneously achieves the reductions in the attack effectiveness(e.g.,the TPR@0.01%FPR of enhanced MI attacks decreased by 2.10%on the ImageNet dataset,the membership advantage(MA)of risk score-based attacks d

关键词： Machine learning Membership inference defenses Preemptive exclusion Knowledge distillation

来源：评论

学校读者我要写书评

暂无评论

Cluster-Refined Optimal Transport for Unsupervised Action Segmentation

Cluster-Refined Optimal Transport for Unsupervised Action Se...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Shijie Wang Jinrong Zhang Yule Liu Shiyao Li Lin Feng School of Computer Science and Technology Dalian University of Technology Dalian China School of Control Science and Engineering Dalian University of Technology Dalian China School of Innovation and Entrepreneurship Dalian University of Technology Dalian China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

关键词： Video on demand Signal processing Acoustics Web sites Speech processing Videos

来源：评论

学校读者我要写书评

暂无评论

Image Inversion: A Survey from GANs to Diffusion and Beyond

arXiv

引用

arXiv 2025年

作者： Chen, Yinan Zhang, Jiangning Bi, Yali Hu, Xiaobin Hu, Teng Xue, Zhucun Yi, Ran Liu, Yong Tai, Ying College of Control Science and Engineering Zhejiang University China YouTu Lab Tencent China College of Computer and Information Science Southwest University China Department of Computer Science & Engineering Shanghai Jiao Tong University China School of Intelligence Science and Technology Nanjing University China

Image inversion is a fundamental task in generative models, aiming to map images back to their latent representations to enable downstream applications such as editing, restoration, and style transfer. This paper provides a comprehensive review of the latest advancements in image inversion techniques, focusing on two main paradigms: Generative Adversarial Network (GAN) inversion and diffusion model inversion. We categorize these techniques based on their optimization methods. For GAN inversion, we systematically classify existing methods into encoder-based approaches, latent optimization approaches, and hybrid approaches, analyzing their theoretical foundations, technical innovations, and practical trade-offs. For diffusion model inversion, we explore training-free strategies, fine-tuning methods, and the design of additional trainable modules, highlighting their unique advantages and limitations. Additionally, we discuss several popular downstream applications and emerging applications beyond image tasks, identifying current challenges and future research directions. By synthesizing the latest developments, this paper aims to provide researchers and practitioners with a valuable reference resource, promoting further advancements in the field of image inversion. We keep track of the latest works at https://***/RyanChenYN/ImageInversion. Copyright © 2025, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Multiagent Confrontation Method Based on Three-Party Dynamic Multistrategy Evolutionary Game

引用

IEEE Transactions on Computational Social Systems 2025年

作者： Jin, Shilong Wang, Yingjie Duan, Peiyong Zhang, Haijing Li, Gang Cai, Zhipeng Yantai University School of Computer and Control Engineering Yantai264005 China Qilu University of Technology Shandong Academy of Sciences Faculty of Electronics Electrical and Control Jinan250353 China Georgia State University Department of Computer Science AtlantaGA30303 United States

Unmanned agents represent a significant advancement in unmanned control and constitute an important element in the future agent warfare. Their autonomous decision-making capabilities are integral to accomplishing tasks independently. To address challenges inherent in multiparty game scenarios that traditional method struggle with and enhance the applicability and accuracy of game decision-making, this article proposes a novel multiagent confrontation method for unmanned vessels, tailored to a three-party dynamic multistrategy evolutionary game in incomplete information scenarios. The approach introduces a new incentive mechanism designed to enhance both individual and collective profits of agents. Using evolutionary game theory, a three-party model is developed, incorporating interactions among player, enemy, and neutral agents. The model tracks the evolution of strategies to identify stable equilibria across various perceptual conditions. Simulations validate the effectiveness of the proposed method in selecting optimal strategies for unmanned vessels in complex battlefield scenarios, demonstrating its potential for improving autonomous decision-making in multiparty confrontations. © 2014 IEEE.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

HaloFL: Efficient Heterogeneity-Aware Federated Learning Through Optimal Submodel Extraction and Dynamic Sparse Adjustment

引用

IEEE Transactions on computer-Aided Design of Integrated Circuits and Systems 2025年

作者： Lian, Zirui Cao, Qianyue Liang, Chao Cao, Jing Zhu, Zongwei Yang, Zhi Ji, Cheng Li, Changlong Zhou, Xuehai School of Computer Science and Technology University of Science and Technology of China Hefei230026 China Suzhou Institute for Advanced Research University of Science and Technology of China Suzhou215123 China School of Software Engineering University of Science and Technology of China Hefei230026 China Xi'an Modern Control Technology Research Institute China Dfh satellite co. Ltd Cast China School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China School of Computer Science and Technology East China Normal University Shanghai200063 China

Federated Learning (FL) is an advanced framework that enables collaborative training of machine learning models across edge devices. An effective strategy to enhance training efficiency is to allocate the optimal submodel based on each device's resource capabilities. However, system heterogeneity significantly increases the difficulty of allocating submodel parameter budgets appropriately for each device, leading to the straggler problem. Meanwhile, data heterogeneity complicates the selection of the optimal submodel structure for specific devices, thereby impacting training performance. Furthermore, the dynamic nature of edge environments, such as fluctuations in network communication and computational resources, exacerbates these challenges, making it even more difficult to precisely extract appropriately sized and structured submodels from the global model. To address the challenges in heterogeneous training environments, we propose an efficient FL framework, namely HaloFL. The framework dynamically adjusts the structure and parameter budget of submodels during training by evaluating three dimensions: model-wise performance, layer-wise performance, and unit-wise performance. First, we design a data-aware model unit importance evaluation method to determine the optimal submodel structure for different data distributions. Next, using this evaluation method, we analyze the importance of model layers and reallocate parameters from non-critical layers to critical layers within a fixed parameter budget, further optimizing the submodel structure. Finally, we introduce a resource-aware dual-UCB multi-armed bandit agent, which dynamically adjusts the total parameter budget of submodels according to changes in the training environment, allowing the framework to better adapt to the performance differences of heterogeneous devices. Experimental results demonstrate that HaloFL exhibits outstanding efficiency in various dynamic and heterogeneous scenarios, achieving up to a 14

关键词： Federated 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：