检索结果-内蒙古大学图书馆

Safety Control of Switched Systems via Multiple Barrier Functions

IEEE Transactions on Automatic Control 2025年

作者： Long, Lijun Huang, Chunxiao Sun, Zhendong Northeastern University College of Information Science and Engineering Shenyang110819 China Northeastern University State Key Laboratory of Synthetical Automation for Process Industries Shenyang110819 China Ministry of Education Key Laboratory of Data Analytics and Optimization for Smart Industry Northeastern University China

This paper is concerned with the problem of safety control for switched systems, where different safe sets are allowed for different subsystems and safety is not necessarily possessed for subsystems. A necessary and sufficient condition is presented for safety of switched systems by exploiting a multiple barrier functions (MBFs) method. To reveal the relationship about safety between subsystems and switched systems, an extended Nagumo's Theorem in the switched systems framework is derived. Also, several switched control design conditions are respectively provided to ensure safety of switched systems. Based on the union of MBFs and multiple Lyapunov functions (MLFs), a novel safety-critical control framework is established to simultaneously ensure safety and stability of switched systems. Also, an auxiliary cost function is introduced to transform the safety-critical optimal control (SCOC) problem of switched systems into the one of non-switched systems. Finally, three examples are illustrated to demonstrate the effectiveness of the proposed methods. © 1963-2012 IEEE.

关键词： Lyapunov functions

来源：评论

学校读者我要写书评

暂无评论

DeepSeek: Paradigm Shifts and Technical Evolution in Large AI Models

引用

IEEE/CAA Journal of Automatica Sinica 2025年第5期12卷 841-858页

作者： Luolin Xiong Haofen Wang Xi Chen Lu Sheng Yun Xiong Jingping Liu Yanghua Xiao Huajun Chen Qing-Long Han Yang Tang Key Laboratory of Smart Manufacturing in Energy Chemical Process Ministry of Education and the Engineering Research Center of Process System Engineering Ministry of Education East China University of Science and Technology Shanghai China College of Design and Innovation Tongji University Shanghai China Shanghai Key Laboratory of Data Science School of Computer Science Fudan University Shanghai China School of Software Beihang University Beijing China School of Information Science and Engineering East China University of Science and Technology Shanghai China AZFT Joint Laboratory for Knowledge Engine Hangzhou Innovation Center College of Computer Science and Technology Zhejiang University Hangzhou China School of Science Computing and Engineering Technologies Swinburne University of Technology Melbourne VIC Australia

DeepSeek, a Chinese artificial intelligence (AI) startup, has released their V3 and R1 series models, which attracted global attention due to their low cost, high performance, and open-source advantages. This paper begins by reviewing the evolution of large AI models focusing on paradigm shifts, the mainstream large language model (LLM) paradigm, and the DeepSeek paradigm. Subsequently, the paper highlights novel algorithms introduced by DeepSeek, including multi-head latent attention (MLA), mixture-of-experts (MoE), multi-token prediction (MTP), and group relative policy optimization (GRPO). The paper then explores DeepSeek's engineering breakthroughs in LLM scaling, training, inference, and system-level optimization architecture. Moreover, the impact of DeepSeek models on the competitive AI landscape is analyzed, comparing them to mainstream LLMs across various fields. Finally, the paper reflects on the insights gained from DeepSeek's innovations and discusses future trends in the technical and engineering development of large AI models, particularly in data, training, and reasoning.

关键词： Training Technological innovation Foundation models Large language models Reinforcement learning Prediction algorithms Market research Cognition Inference algorithms Optimization

来源：评论

学校读者我要写书评

暂无评论

A two-way dynamic adaptive pricing resource allocation model based on combinatorial double auctions in computational network

引用

Computer Communications 2025年 238卷

作者： Xu, Yanjun Tian, Chunqi Wang, Wei Bai, Lizhi Xia, Xuhui School of Computer Science and Technology Tongji University Shanghai China School of Data Science and Engineering East China Normal University Shanghai China Embedded System and Service Computing Key Laboratory of Ministry of Education China

Efficient resource allocation in computing networks is essential for managing fluctuating demands and optimizing system performance. Traditional auction and pricing models often fail to adapt to diverse demands and supply–demand fluctuations, resulting in inefficiencies. This paper proposes a bidirectional price-adaptive bundled resource auction model that considers not only the autonomous adjustment of sellers’ quotations in response to supply–demand fluctuations but also the impact of these fluctuations on buyers’ willingness to pay and bidding behavior. The model integrates Combinatorial Double Auction (CDA) mechanism and Genetic Algorithm (GA), constructing a bundled resource auction mechanism that accommodates diverse resource demands and an adaptive pricing strategy that dynamically responds to real-time supply–demand variations. This approach enhances resource allocation accuracy in dynamic and competitive computing network environments. Furthermore, a reserve price mechanism and a delay compensation strategy are introduced to ensure that the proposed mechanism satisfies individual rationality, budget balance, and incentive compatibility while maintaining computational efficiency. Simulation results demonstrate that, compared to traditional methods, the proposed model not only improves allocation efficiency and enhances resource utilization but also helps reduce operational costs. Specifically, resource allocation dispersion decreases by 4.26%, while service providers’ revenue increases by 7.47%. This study provides a scalable and adaptive solution for dynamic resource allocation in cloud and edge computing platforms. It contributes significantly to the development of resource management and flexible pricing strategies in markets characterized by diverse demands and fluctuating conditions. © 2025

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

Building Extraction From Multi-View RGB-H Images With General Instance Segmentation Networks and a Grouping Optimization Algorithm

引用

IEEE Geoscience and Remote Sensing Letters 2025年 22卷

作者： Yu, Dawen Cheng, Hao Fuzhou University Key Laboratory of Spatial Data Mining and Information Sharing of Ministry of Education The Academy of Digital China Fuzhou350108 China Wuhan University School of Remote Sensing and Information Engineering Wuhan430079 China

Bird’s-eye-view (BEV) building mapping from remote sensing images is a studying hotspot with broad applications. In recent years, deep learning (DL) has significantly advanced the development of automatic building extraction methods. However, most existing research focuses on segmenting buildings from a single perspective, such as orthophotos, overlooking the rich information of multi-view images. In surveying and mapping, individual building instances need to be separated even when they are adjacent or touching. Since orthophotos cannot capture building walls due to self-occlusion, distinguishing between closely connected buildings in densely built areas becomes challenging. To tackle this issue, we propose a multi-view collaborative pipeline for instance-level building segmentation. This pipeline utilizes a grouping optimization algorithm to merge segmentation results from multiple views, which are predicted by general instance segmentation networks and projected onto the BEV, to produce the final building instance polygons. Both qualitative and quantitative results show that the proposed multi-view collaborative pipeline significantly outperforms the popular orthophoto-based pipeline on the InstanceBuilding dataset. © 2004-2012 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

DFF: Decision-Focused Fine-tuning for Smarter Predict-then-Optimize with Limited data

arXiv

引用

arXiv 2025年

作者： Yang, Jiaqi Liang, Enming Su, Zicheng Zou, Zhichao Zhen, Peng Guo, Jiecheng Ma, Wanjing An, Kun The Key Laboratory of Road and Traffic Engineering of the Ministry of Education Tongji University China Department of Data Science City University of Hong Kong Hong Kong Didi Chuxing Beijing China

Decision-focused learning (DFL) offers an end-to-end approach to the predict-then-optimize (PO) framework by training predictive models directly on decision loss (DL), enhancing decision-making performance within PO contexts. However, the implementation of DFL poses distinct challenges. Primarily, DL can result in deviation from the physical significance of the predictions under limited data. Additionally, some predictive models are non-differentiable or black-box, which cannot be adjusted using gradient-based methods. To tackle the above challenges, we propose a novel framework, Decision-Focused Fine-tuning (DFF), which embeds the DFL module into the PO pipeline via a novel bias correction module. DFF is formulated as a constrained optimization problem that maintains the proximity of the DL-enhanced model to the original predictive model within a defined trust region. We theoretically prove that DFF strictly confines prediction bias within a predetermined upper bound, even with limited datasets, thereby substantially reducing prediction shifts caused by DL under limited data. Furthermore, the bias correction module can be integrated into diverse predictive models, enhancing adaptability to a broad range of PO tasks. Extensive evaluations on synthetic and real-world datasets, including network flow, portfolio optimization, and resource allocation problems with different predictive models, demonstrate that DFF not only improves decision performance but also adheres to fine-tuning constraints, showcasing robust adaptability across various scenarios. Copyright © 2025, The Authors. All rights reserved.

关键词： Constrained optimization

来源：评论

学校读者我要写书评

暂无评论

Information Entropy Invariance: Enhancing Length Extrapolation in Attention Mechanisms

arXiv

引用

arXiv 2025年

作者： Li, Kewei Kong, Yanwen Xu, Yiping Su, Jianlin Huang, Lan Zhang, Ruochi Zhou, Fengfeng College of Computer Science and Technology Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Jilin Changchun130012 China Moonshot AI Ltd. Beijing100086 China

Since the emergence of research on improving the length extrapolation capabilities of large models in 2021, some studies have made modifications to the scaling factor in the scaled dot-product attention mechanism as part of their proposed methods without rigorous theoretical justifications. To fill this gap, we propose two new scaled temperatures based on entropy invariance to enhance length extrapolation. First, a training-free method InfoScale is designed for dot-product attention, and preserves focus on original tokens during length extrapolation by ensuring consistent entropy. Second, we theoretically analyze the impact of scaling (CosScale) on cosine attention. Experimental data demonstrates that combining InfoScale and CosScale achieves state-of-the-art performance on the GAU-α model with a context window extended to 64 times the training length, and outperforms seven existing methods. Our analysis reveals that significantly increasing CosScale approximates the Windowed Attention, and highlights the significance of attention score dilution as a key challenge in long-range context handling. The code and data are available at https://***/HT-NEKO/InfoScale. © 2025, CC BY-NC-ND.

关键词： data handling

来源：评论

学校读者我要写书评

暂无评论

Regularized Total Least Squares Broad Learning System for Regression

引用

Journal of Computers (Taiwan) 2025年第1期36卷 89-112页

作者： Xiong, Ke-Jia Yang, Guan-Ci Zhou, Tao Xie, Zhen-Qiang State Key Laboratory of Public Big Data Guizhou University Guizhou Province Guiyang City550025 China Key Laboratory of Advanced Manufacturing Technology of the Ministry of Education Guizhou University Guizhou Province Guiyang City550025 China National Engineering Research Center of Big Data Application to The Improvement of Governance Capacity Guizhou Province Guiyang City550000 China

The Broad Learning System (BLS) has been extensively developed and applied across various fields due to its significant advantages, including high efficiency, strong generality, and scalability. However, in practical applications where both inputs and outputs are contaminated by noise, traditional BLS demonstrates suboptimal performance in handling sample data. This study introduces a novel regularized total least squares broad learning system (RTLS-BLS) designed to enhance the robustness of BLS when noisy values are present in both the input and the output of the training set. Initially, the k-support norm is integrated into the BLS-based autoencoder (BLS-AE), embedded within BLS, to extract robust features from the original input data. The BLS-AE equipped with the k-support norm effectively addresses or mitigates issues related to overly sparse (based on L1-norm) or overly dense (based on L2-norm) regularization of extracted features. Subsequently, regularized total least squares (RTLS) are employed to assess the output weights of BLS, further enhancing its robustness. Moreover, simultaneous perturbation measures for the coefficient matrix and the output are provided. Experimental results from two function approximation tasks, eight benchmark regression tasks, and two network interface flow datasets demonstrate that the proposed RTLS-BLS achieves significantly robust performance under noisy conditions compared to other methods. © 2025 Codon Publications. All rights reserved.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Multimodal Fusion for Android Malware Detection Based on Large Pre-trained Models

引用

IEEE Transactions on Software engineering 2025年第05期51卷 1569-1590页

作者： Li, Xun Liu, Lei Liu, Yuzhou Zhao, Yu Zhang, Peng Liu, Huaxiao Jilin University College of Computer Science and Technology Changchun130012 China Jilin University Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Changchun130012 China College of Computer Science University of Cincinnati OH United States

Malware detection is a critical issue in software engineering as it directly threatens user information security. Existing approaches often focus on individual modality (either source code or binary code) for the detection, but it ignores to effectively exploit the complementary information between them. This limits the detection performance, especially in complex and evasive malware scenarios. In this paper, we take Android applications written in Java as objects, and provide a novel fine-grained multimodal fusion method with large pre-trained models to combine the features from source and binary codes for the malware detection. For the source code modality, we employ the graphical user interface (GUI) as a framework to segment the source code into snippets, and use a pre-trained programming language model to extract feature representations. For the binary code modality, we convert binary code into grayscale images and fine-tune a pre-trained vision model to extract features indirectly. We then implement cross-modal attention and devise a contrastive loss to align features across modalities, supplementing this with supervised classification loss to refine the multimodal fusion process specifically for malware detection. Our experiments, conducted using the data-MD and data-MC benchmarks, demonstrate that our approach achieves a precision of 0.977 and a recall of 0.984 in detecting malware. This underscores the advantages of using large pre-trained models for feature representation and the fusion of information across different modalities for effective malware detection. © 1976-2012 IEEE.

关键词： Android malware

来源：评论

学校读者我要写书评

暂无评论

Causal-Inspired Multitask Learning for Video-Based Human Pose Estimation

arXiv

引用

arXiv 2025年

作者： Chen, Haipeng Wu, Sifan Wang, Zhigang Yin, Yifang Jiao, Yingying Lyu, Yingda Liu, Zhenguang College of Computer Science and Technology Jilin University China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University China College of Computer Science and Technology Zhejiang Gongshang University China A*STAR Singapore Public Computer Education and Research Center Jilin University China The State Key Laboratory of Blockchain and Data Security Zhejiang University China Institute of Blockchain and Data Security China

Video-based human pose estimation has long been a fundamental yet challenging problem in computer vision. Previous studies focus on spatio-temporal modeling through the enhancement of architecture design and optimization strategies. However, they overlook the causal relationships in the joints, leading to models that may be overly tailored and thus estimate poorly to challenging scenes. Therefore, adequate causal reasoning capability, coupled with good interpretability of model, are both indispensable and prerequisite for achieving reliable results. In this paper, we pioneer a causal perspective on pose estimation and introduce a causal-inspired multitask learning framework, consisting of two stages. In the first stage, we try to endow the model with causal spatio-temporal modeling ability by introducing two self-supervision auxiliary tasks. Specifically, these auxiliary tasks enable the network to infer challenging keypoints based on observed keypoint information, thereby imbuing causal reasoning capabilities into the model and making it robust to challenging scenes. In the second stage, we argue that not all feature tokens contribute equally to pose estimation. Prioritizing causal (keypoint-relevant) tokens is crucial to achieve reliable results, which could improve the interpretability of the model. To this end, we propose a Token Causal Importance Selection module to identify the causal tokens and non-causal tokens (e.g., background and objects). Additionally, non-causal tokens could provide potentially beneficial cues but may be redundant. We further introduce a non-causal tokens clustering module to merge the similar non-causal tokens. Extensive experiments show that our method outperforms state-of-the-art methods on three large-scale benchmark datasets. Copyright © 2025, The Authors. All rights reserved.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Explainable Application Intent for Zero-Touch Networking: An Incorporation of Hypergraph and Transformer

引用

IEEE Transactions on Communications 2025年

作者： Wu, Bing Zou, Sai Liwang, Minghui Ni, Wei Wang, Xianbin Guizhou University College of Big Data and Information Engineering China National Key Laboratory of Autonomous Intelligent Unmanned Systems Department of Control Science and Engineering China Tongji University Frontiers Science Center for Intelligent Autonomous Systems Ministry of Education Shanghai China Data61 CSIRO Australia Department of Electrical and Computer Engineering Western University Canada

The autonomous interpretation of application intent (APPI) represents the primary step towards achieving closed-loop autonomy in zero-touch networking (ZTN) and also a prerequisite for intent-based networking (IBN). However, understanding APPIs and invoking the corresponding network resources require network professionals with extensive technical expertise to customize network service requests (NSRs), which presents significant challenges for the large-scale deployment of ZTN. This paper investigates an interesting problem of autonomous interpretation of APPIs for ZTN, where a novel mechanism integrating hypergraph and transformer with completeness assurance (HyperTrans-CA) is proposed. In particular, we first involve the Bayesian theory to model APPIs interpretability as maximizing the correct transition probability, where hypergraph is used to describe the complex relationship between application characteristics (e.g., scenario function, and performance) and NSRs, including network devices, virtual network functions (VNFs), and resources. Then, the hypergraph is integrated into the encoder, decoder, and attention mechanisms of Transformer, and a completeness assurance mechanism is designed to improve the prediction accuracy. The convergence of HyperTrans-CA and the corresponding convergence speed of the hypergraph-boosted Transformer in the graph search process are also analyzed. Comprehensive simulations and empirical measurements regarding industrial internet demonstrate that HyperTrans-CA can effectively explain/understand APPIs. Compared to the state-of-the-art Transformer and ChatGPT3.5 models, HyperTrans-CA improves the prediction accuracy of APPIs mapped to VNFs by 23% and 46%, respectively, while raising the prediction accuracy of VNF locations by 8.6 and 17.3 times. © 2025 IEEE.

关键词： Bayesian networks

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：