检索结果-内蒙古大学图书馆

Design, Automation and Test in Europe Conference and Exhibition

作者： Zhouquan Liu Libo Huang Ling Yang Gang Chen Wei Liu Mingche Lai Yongwen Wang College of Computer Science and Technology National University of Defense Technology Changsha China Key Laboratory of Advanced Microprocessor Chips and Systems Changsha China School of Computer Science and Engineering Sun Yat-Sen University Guangzhou China

ISBN: (数字)9783982674100

ISBN: (纸本)9798331534646

Mamba overcomes the quadratic complexity problem inherent in Transformer models while maintaining comparable contextual modeling capabilities. However, Mamba-based foundation models encounter challenges in achieving efficient inference on resource-constrained devices, primarily due to their considerable size. Model compression techniques, such as linear quantization, offer a viable solution to this problem. Nevertheless, the introduction of significant outliers during Mamba's past-state forgetting process can lead to a notable decrease in accuracy when employing linear quantization. To overcome these challenges, this paper introduces the Aggressive Forgetting Strategy (AFS), an innovative and efficient algorithm designed to mitigate the quantization issues caused by outliers in the state forgetting mechanism. AFS incorporates a computation-free approach for handling outliers, facilitating both efficient and accurate linear quantization for Mamba, which is essential for applications in resource-constrained scenarios. By leveraging the AFS strategy, Mamba can perform more efficient inference, while significantly improving the accuracy by up to 21.5× compared to conventional methods.

关键词： Performance evaluation Quantization (signal) Accuracy Foundation models Logic gates Transformers Inference algorithms Complexity theory Standards Context modeling

来源：评论

学校读者我要写书评

暂无评论

Equilibrium-Independent Control of Continuous-Time Nonlinear systems Via the LPV Framework

引用

IEEE Transactions on Automatic Control 2025年

作者： Koelewijn, Patrick J. W. Weiland, Siep Toth, Roland Eindhoven University of Technology Control Systems Group Department of Electrical Engineering Eindhoven Netherlands Institute for Computer Science and Control Systems and Control Laboratory Budapest Hungary

In this paper, we consider the analysis and control of continuous-time nonlinear systems to ensure universal shifted stability and performance, i.e., stability and performance w.r.t. each forced equilibrium point of the system. This "equilibrium-free"concept is especially beneficial for control problems that require the tracking of setpoints and rejection of persistent disturbances, such as input loads. In this paper, we show how the velocity form, i.e., the time-differentiated dynamics of the system, plays a crucial role in characterizing these properties and how the analysis of it can be solved by the application of Linear Parameter-Varying (LPV) methods in a computationally efficient manner. Furthermore, by leveraging the properties of the velocity form and the LPV framework, a novel controller synthesis method is presented which ensures closed-loop universal shifted stability and performance. The proposed controller design is verified experimentally on a real system. Additionally, we compare the proposed method to a standard LPV control design, demonstrating the improved stability and performance guarantees of the new approach. © 1963-2012 IEEE.

关键词： Equilibrium independent dissipativity linear parameter-varying systems output feedback stability of nonlinear systems

来源：评论

学校读者我要写书评

暂无评论

A Recurrent Neural Network Based Bicriteria Repetitive Motion Collision Avoidance Scheme for Motion Planning of Dual Redundant Manipulators 13

A Recurrent Neural Network Based Bicriteria Repetitive Motio...

引用

13th International Conference on Intelligent Control and Information Processing, ICICIP 2025

作者： Chen, Shirui Gao, Huanli Hu, Shaolin Zhang, Zhijun The School of Automation Science and Engineering South China University of Technology Guangzhou510640 China The School of Automation Guangdong University of Petrochemical Technology Maoming Guangzhou525000 China The Guangzhou Key Laboratory of Brain-Computer Interaction and Applications Guangzhou China The Key Library of Autonomous Systems and Network Control Ministry of Education The School of Automation Science and Engineering South China University of Technology Guangzhou510640 China Guangzhou510555 China The Jiangxi Thousand Talents Plan Nanchang University Nanchang330031 China The College of Computer Science and Engineering Jishou University Jishou416000 China Guangzhou510335 China The Shaanxi Provincial Key Laboratory of Industrial Automation School of Mechanical Engineering Shaanxi University of Technology Hanzhong723001 China The School of Information Science and Engineering Changsha Normal University Changsha410100 China The School of Automation Science and Engineering Maoming525000 China The Institute of Artificial Intelligence and Automation Guangdong University of Petrochemical Technology Maoming525000 China

ISBN: (纸本)9798331516147

To achieve low joint-angle drift and avoid mutual collision between dual redundant manipulators (DRMs) when they are doing collaboration works, a recurrent neural network based bicriteria repetitive motion collision avoidance (BRMCA) scheme is proposed for motion planning of DRMs. By designing a combined optimization objective encompassing both repetitive motion criterion and collision avoidance criterion, the BRMCA scheme has larger feasible region and less constraint contradiction issues compared with traditional inequality constraints based method. Furthermore, by incorporating velocity-level kinematic model and physical limits of DRMs into the scheme, a time varying quadratic programming (TVQP) problem is formulated. The linear variational inequality-based primal–dual neural network (LVI-PDNN) is used to solve the proposed scheme due to the high accuracy and low computation complexity. Finally, through comparison simulations of tracking Circle-shape and C-shape trajectories between BRMCA scheme and minimum velocity norm (MVN) scheme, it exhibits that the proposed BRMCA scheme can achieve low joint-angle drift, collision avoidance and high tracking accuracy when DRMs are doing cooperative tasks. © 2025 IEEE.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

A Lightweight Encoder-Decoder Framework for Carpooling Route Planning

引用

IEEE Transactions on Mobile Computing 2025年

作者： Gao, Yucen Ma, Li Yu, Zhemeng Zhang, Songjian Gao, Hui Fang, Jun Gao, Xiaofeng Shanghai Jiao Tong University Shanghai Key Laboratory of Scalable Computing and Systems College of Computer Science and Engineering Shanghai200240 China Didi Global Inc. Beijing100190 China

Carpooling Route Planning (CRP) has become an important issue with the growth of low-carbon traffic systems. We investigate a novel, meaningful and challenging scenario for CRP in industry, called Multi-Candidate Carpooling Route Planning (MCRP) problem, where each passenger may have several potential positions to get on and off the car. We surprisingly notice that this problem can be easily generalized for similar services such as express, takeout, or crowdsensing services, which means MCRP is a new fundamental combinatorial optimization problem. Traditional graph search algorithms or indexing methods are usually time and space consuming or perform poorly, which are not suitable for solving the problem. In this paper, we propose an end-to-end encoder-decoder model to plan a route for each many-to-one carpooling order with various data-driven mechanisms such as graph partitioning and feature crossover. The encoder is a filter-integrated Graph Convolution Network with external information fusion combining a supervised pre-training classification task, while the latter mimics a pointer network with a rule-based mask mechanism and a domain feature crossover module. We validate the effectiveness and efficiency of our model based on both synthetic and real-world datasets. Our code is available at https://***/GaoYucen/Lite-GD © 2002-2012 IEEE.

关键词： Network coding

来源：评论

学校读者我要写书评

暂无评论

On Space-Filling Input Design for Nonlinear Dynamic Model Learning: A Gaussian Process Approach

arXiv

引用

arXiv 2025年

作者： Liu, Yuhan Kiss, Máté Tóth, Roland Schoukens, Maarten Control Systems Group Department of Electrical Engineering Eindhoven University of Technology Eindhoven5600 MB Netherlands Systems and Control Laboratory HUN-REN Institute for Computer Science and Control Budapest1111 Hungary

While optimal input design for linear systems has been well-established, no systematic approach exists for nonlinear systems, where robustness to extrapolation/interpolation errors is prioritized over minimizing estimated parameter variance. To address this issue, we develop a novel identification-oriented space-filling input design strategy for efficient covering of a well-defined region of interest. By placing a Gaussian Process (GP) prior on the joint input-state space, the proposed strategy leverages the GP posterior variance to construct a space-filling promoting input design cost function from the Bayesian point of view. This accordingly enables maximization of the coverage in the region of interest, thereby facilitating the generation of informative datasets. Furthermore, we theoretically prove that minimization of the cost function indicates the space-filling behavior. The effectiveness of the proposed strategy is demonstrated on both an academic example and a mass-spring-damper system, highlighting its potential practical impact on efficient exploration in identification scenarios for nonlinear dynamical systems. © 2025, CC BY-NC-SA.

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

Self-Supervised Reflective Learning Through Self-Distillation and Online Clustering for Speaker Representation Learning

引用

IEEE Transactions on Audio, Speech and Language Processing 2025年 33卷 1535-1550页

作者： Danwei Cai Zexin Cai Ze Li Ming Li Department of Electrical and Computer Engineering Duke University Durham NC USA Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems Digital Innovation Research Center Duke Kunshan University Kunshan China School of Computer Science Wuhan University Wuhan China

Speaker representation learning is crucial for voice recognition systems, with recent advances in self-supervised approaches reducing dependency on labeled data. Current two-stage iterative frameworks, while effective, suffer from significant computational overhead due to repeated rounds of clustering and training. They also struggle with noisy pseudo labels that can impair model learning. This paper introduces self-supervised reflective learning (SSRL), an improved framework that addresses these limitations by enabling continuous refinement of pseudo labels during training. Through a teacher-student architecture and online clustering mechanism, SSRL eliminates the need for iterative training rounds. To handle label noise, we incorporate noisy label modeling and pseudo label queues that maintain temporal consistency. Experiments on VoxCeleb show SSRL's superiority over current two-stage iterative approaches, surpassing the performance of a 5-round method in just a single training round. Ablation studies validate the contributions of key components like noisy label modeling and pseudo label queues. Moreover, consistent improvements in pseudo labeling and the convergence of cluster counts demonstrate SSRL's effectiveness in deciphering unlabeled data. This work marks an important advancement in efficient and accurate self-supervised speaker representation learning through the novel reflective learning paradigm.

关键词： Training Representation learning Iterative methods Noise Adaptation models Noise measurement Predictive models Speech processing Robustness Convergence

来源：评论

学校读者我要写书评

暂无评论

Design of Distributed Nonlinear Observers Without Using Global Inputs

引用

IEEE Transactions on Automatic Control 2025年

作者： Cao, Ganghui Wang, Jinzhi Polycarpou, Marios M. Peking University State Key Laboratory for Turbulence and Complex Systems Department of Mechanics and Engineering Science College of Engineering Beijing100871 China University of Cyprus KIOS Research and Innovation Center of Excellence and the Department of Electrical and Computer Engineering Nicosia1678 Cyprus

This paper investigates the design of distributed observers for a class of nonlinear systems. The designed distributed observers reside in a network of sensor nodes. The communication links in the network enable each sensor node to estimate all states of the nonlinear system, even though each one can only collect a small portion of the system's outputs. However, all inputs of the system are still needed at each node to carry out a correct state estimation. For this problem, the paper further proposes a distributed nonlinear observer without using global inputs, in which each sensor node only needs partial input information of the nonlinear system. © 1963-2012 IEEE.

关键词： Nonlinear simulations

来源：评论

学校读者我要写书评

暂无评论

Worst-Case Integrity Attacks and Resilient State Estimation With Partially Secured Measurements

引用

IEEE Transactions on Control of Network systems 2025年

作者： Zhou, Jing Shang, Jun Chen, Tongwen University of Alberta Department of Electrical and Computer Engineering EdmontonABT6G 1H9 Canada Tongji University Department of Control Science and Engineering Shanghai Institute of Intelligent Science and Technology National Key Laboratory of Autonomous Intelligent Unmanned Systems Frontiers Science Center for Intelligent Autonomous Systems Shanghai200092 China

This paper examines the problem of optimal deception attacks against state estimation with partially secured measurements, where smart sensors transmit innovation sequences to the remote end for information fusion. Due to resource limitations or defensive countermeasures, the adversary can only modify data packets transmitted through unreliable channels. Meanwhile, the attack should be synthesized with sophistication to deceive an anomaly detector. To investigate the vulnerabilities of such estimation systems without feedback links and enhance security performance, the optimal attack policy is derived by formulating and explicitly solving a convex optimization problem, with the goal of maximizing the sum of estimation errors. Subsequently, a novel attack detection and resilient state estimation algorithm is proposed to ensure an acceptable level of estimation accuracy. The theoretical performance metrics, including false alarm rates for the proposed detector, are provided. Finally, the effectiveness of the results is confirmed through numerical examples. © 2014 IEEE.

关键词： Optimal detection

来源：评论

学校读者我要写书评

暂无评论

Gemini+: Enhancing Real-Time Video Analytics with Dual-Image FPGAs

引用

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

作者： Wu, Jingrou Hu, Chuang Zhang, Jin Wang, Dan Jiang, Jing University of Technology Sydney Australian Artificial Intelligence Institute SydneyNSW2007 Australia Southern University of Science and Technology Research Institute of Trustworthy Autonomous Systems The Department of Computer Science and Engineering Shenzhen518055 China Wuhan University School of Computer Science Wuhan430072 China Southern University of Science and Technology Department of Computer Science and Engineering The Research Institute of Trustworthy Autonomous Systems Shenzhen518055 China Peng Cheng Laboratory Shenzhen518055 China Hong Kong Polytechnic University Department of Computing Hong Kong Hong Kong

Real-time video analytics demand intensive computing resources, often exceeding device capabilities. Heterogeneous computing resources like CPU and GPU, usually work collaboratively to ensure real-time performance. GPU manage data-intensive computing, while CPU handle instruction-intensive tasks. However, analytics accuracy can degrade because of the imbalance between CPU-GPU workloads and resources, and static resources in most systems limit adaptability to dynamic workloads. In addition to CPU-GPU resource control, accuracy is highly dependent on video analytics configuration including resolution, frame rate, and model selection. In this paper, we propose Gemini+, a hardware-accelerated video analytics pipeline empowered by dual-image FPGAs. It enables flexible CPU-GPU resource adaptation by providing near-instantaneous switching between two pre-configured images. We investigate CPU-GPU resource control and video analytics configuration adaptation in a dual-image FPGA-based video analytics pipeline. We study and formulate two problems of practical importance, a single-camera and multi-camera dual computing resource control problem, i.e., SC-DCRC and MC-DCRC. We analyze the problem complexity and develop optimal and sub-optimal algorithms. We evaluate our algorithms through simulation and build a prototype for verification. The results show that Gemini+ can improve analytic accuracy by 25% compared to fixed CPU-GPU resource systems and 88% compared to GPU-dominant systems. © 2025 IEEE.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Systematic Bernoulli Generator Matrix Codes

arXiv

引用

arXiv 2025年

作者： Wang, Yixin Meng, Fanhui Ma, Xiao School of Systems Science and Engineering Sun Yat-sen University Guangzhou510006 China Guangdong Key Laboratory of Information Security Technology School of Computer Science and Engineering Sun Yat-sen University Guangzhou510006 China

This paper is concerned with the systematic Bernoulli generator matrix (BGM) codes, which have been proved to be capacity-achieving over binary-input output-symmetric (BIOS) channels in terms of bit-error rate (BER). We prove that the systematic BGM codes are also capacity-achieving over BIOS channels in terms of frame-error rate (FER). To this end, we present a new framework to prove the coding theorems for binary linear codes. Different from the widely-accepted approach via ensemble enlargement, the proof directly applies to the systematic binary linear codes. The new proof indicates that the pair-wise independence condition is not necessary for proving the binary linear code ensemble to achieve the capacity of the BIOS channel. The Bernoulli parity-check (BPC) codes, which fall within the framework of the systematic BGM codes with parity-check bits known at the decoder can also be proved to achieve the capacity. The presented framework also reveals a new mechanism pertained to the systematic linear codes that the systematic bits and the corresponding parity-check bits play different roles. Precisely, the noisy systematic bits are used to limit the list size of candidate codewords, while the noisy parity-check bits are used to select from the list the maximum likelihood codeword. For systematic BGM codes with finite length, we derive the lower bounds on the BER and FER, which can be used to predict the error floors. Numerical results show that the systematic BGM codes match well with the derived error floors. The performance in water-fall region can be improved with approaches in statistical physics and the error floors can be significantly improved by implementing the concatenated codes with the systematic BGM codes as the inner codes. © 2025, CC BY.

关键词： Decoding

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：