检索结果-内蒙古大学图书馆

13th ieee data driven control and learning systems conference, DDCLS 2024

作者： Wang, Qianlong Wu, Peng Guo, Lili Chen, Ping Ling, Yu School of Economics and Management University of Chinese Academy of Sciences Beijing100190 China Technology and Engineering Center for Space Utilization Chinese Academy of Sciences Beijing100094 China Key Laboratory of Space Utilization Technology and Engineering Center for Space Utilization Chinese Academy of Sciences Beijing100094 China Business School Nankai University Tianjin300071 China School of Transportation and Logistics Engineering Wuhan University of Technology Wuhan430063 China

ISBN: (纸本)9798350361674

In response to practical challenges in food delivery logistics, we introduce a novel algorithm to address the Pickup and Delivery Problem with Time Windows (PDPTW). Our method employs a Double Deep Q-Network (DDQN)-based Large Neighborhood Search (LNS) strategy, which builds on the Adaptive Large Neighborhood Search (ALNS) framework, tailored specifically for the PDPTW. To mitigate the issues of slow convergence and instability observed in the ALNS algorithm, we have refined the state representation of the DDQN agent by integrating information on the current solution, historical data, and the time usage patterns of operators. We evaluated our algorithm using publicly available benchmark instances. The empirical results indicate that our approach not only surpasses the ALNS algorithm in terms of macro-level solution quality and stability but also demonstrates superior performance at the micro-level by achieving faster convergence and enhanced efficiency in operator usage strategy. © 2024 ieee.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Deep learning Framework for Low-Observable Distribution System State Estimation With Multitimescale Measurements

引用

ieee TRANSACTIONS ON INDUSTRIAL INFORMATICS 2024年第11期20卷 13273-13283页

作者： Zhang, Xihai Ge, Shaoyun Zhou, Yue Liu, Hong Tianjin Univ Sch Elect & Informat Engn Tianjin 300072 Peoples R China Cardiff Univ Sch Engn Dept Elect & Elect Engn Cardiff CF24 3AA Wales

The deployment of microphasor measurement units, supervisory control and data acquisition systems, and smart meters has revolutionized distribution systems, moving toward more intelligence and facilitating state estimation. However, the asynchronous nature and varying sample rates of the measurements raise a significant challenge to state estimation in low-observable distribution systems. This article proposes a novel data-driven framework for state estimation in low-observable distribution systems. The framework incorporates super-resolution imputation techniques that are capable of handling multitime scale measurements. Specifically, the proposed framework utilizes Wasserstein divergence conditional adversarial networks to implement multivariate super-resolution imputation. This involves employing a gated recurrent unit generator with additive attention to impute super-resolution measurements, as well as a discriminator with self-attention to approximate the Wasserstein divergence between the imputed values and the ground truth. Furthermore, a tailor-made physical-guided bilinear neural network is employed to estimate the operational state of low-observable distribution systems by leveraging matrix factorization techniques to capture the low-rank characteristics. Simulation results illustrate the superiority of the proposed approach from the standpoint of multitimescale measurements imputation and state estimation in low-observable distribution systems.

关键词： Imputation Superresolution State estimation Task analysis Generators Deep learning Additives Bilinear neural networks (BNNs) conditional adversarial networks (CANs) low-observable distribution system matrix factorization multitimescale measurements

来源：评论

学校读者我要写书评

暂无评论

data-driven Model Discrimination of Switched Nonlinear systems With Temporal Logic Inference

IEEE OPEN JOURNAL OF CONTROL SYSTEMS

引用

ieee OPEN JOURNAL OF control systems 2023年 2卷 410-424页

作者： Jin, Zeyuan Baharisangari, Nasim Xu, Zhe Yong, Sze Zheng Arizona State Univ Sch Engn Matter Transport & Energy Tempe AZ 85287 USA Northeastern Univ Dept Mech & Ind Engn Boston MA 02115 USA

This article addresses the problem of data-driven model discrimination for unknown switched systems with unknown linear temporal logic (LTL) specifications, representing tasks, that govern their mode sequences, where only sampled data of the unknown dynamics and tasks are available. To tackle this problem, we propose data-driven methods to over-approximate the unknown dynamics and to infer the unknown specifications such that both set-membership models of the unknown dynamics and LTL formulas are guaranteed to include the ground truth model and specification/task. Moreover, we present an optimization-based algorithm for analyzing the distinguishability of a set of learned/inferred model-task pairs as well as a model discrimination algorithm for ruling out model-task pairs from this set that are inconsistent with new observations at run time. Further, we present an approach for reducing the size of inferred specifications to increase the computational efficiency of the model discrimination algorithms.

关键词： Task analysis Syntactics Grammar System dynamics Symbols Switches Production Fault detection and isolation formal verification/synthesis learning for control model validation nonlinear systems identification

来源：评论

学校读者我要写书评

暂无评论

On-Chip Incremental learning based on Unsupervised STDP Implementation 6

On-Chip Incremental Learning based on Unsupervised STDP Impl...

引用

6th International conference on AI Circuits and systems (AICAS)

作者： Chen, Guang Cao, Jian Feng, Shuo Wang, Zilin Zhong, Yi Li, Qibin Zhao, Xiongbo Zhang, Xing Wang, Yuan Peking Univ Sch Software & Microelect Beijing Peoples R China Peking Univ MPW Ctr Key Lab Microelect Devices & Circuits MoE Beijing 100871 Peoples R China Peking Univ Sch Integrated Circuits Beijing 100871 Peoples R China Beijing Aerosp Automat Control Inst Beijing 100854 Peoples R China

ISBN: (纸本)9798350383638;9798350383645

Spiking neural network (SNN), a bio-inspired neuron network, utilizes a learning rule named spike-timing-dependent plasticity (STDP) to achieve high-performance unsupervised learning. However, it may suffer from catastrophic forgetting when the distribution of new data significantly differs from that of old data. To address this issue, an incremental learning implementation for ship classification is presented in this paper. We develop an incremental learning algorithm based on STDP and corresponding platform. A competitive SNN is built into our algorithm, and add-STDP is utilized to update the weights of network for efficient learning. To enhance learning performance, we incorporate weight decay. And to avoid catastrophic forgetting, we incorporate data replay. The corresponding learning platform consists of the FPGA Zynq 7100 and the STDP neuromorphic prototype chip, and our algorithm is executed on the chip. We evaluate the ship classification task on our platform, which demonstrates the superior potential of our on-chip implementation for incremental learning.

关键词： On-chip incremental learning spike-timing-dependent plasticity (STDP) competitive spike neural network (SNN) weight decay data replay

来源：评论

学校读者我要写书评

暂无评论

Observer-Based Fault Tolerant Formation control of Multi-Agent systems via Adaptive Dynamic Programming 13

Observer-Based Fault Tolerant Formation Control of Multi-Age...

引用

13th ieee data driven control and learning systems conference, DDCLS 2024

作者： Zhang, Yongwei Zhao, Bo Liu, Derong College of Mathematics and Informatics South China Agricultural University Guangzhou510642 China School of Systems Science Beijing Normal University Beijing100875 China School of System Design and Intelligent Manufacturing Southern University of Science and Technology Shenzhen518055 China

ISBN: (纸本)9798350361674

This paper develops a fault tolerant formation control scheme for multi-agent systems (MASs) by using adaptive dynamic programming. In MASs, there exist one leader and multiple followers, where the leader is a generated ideal trajectory and the followers catch up with the leader using appropriate designed control inputs based on their own and neighbors' information. To obtain accurate fault information, a fault observer is established for each follower. Subsequently, a discounted cost function, which includes the estimated fault, the formation error, and the control laws, is developed for each following agent. In order to solve the coupled Hamilton-Jacobi-Bellman equation of each follower, a critic-only structure is built to obtain the approximate fault tolerant formation control law. Furthermore, it is proved that the uniform ultimate boundedness of the formation error of each following agent is guaranteed under the developed observer-based fault tolerant formation control law. It means that all following agents are able to maintain a specified formation and catch up with the leader. Finally, a simulation example is employed to validate the effectiveness of the present control approach. © 2024 ieee.

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

Nonconvex Scenario Optimization for data-driven Reachability 6

Nonconvex Scenario Optimization for Data-Driven Reachability

引用

6th Annual learning for Dynamics and control conference

作者： Dietrich, Elizabeth Devonport, Rosalyn Alex Arcak, Murat Univ Calif Berkeley Dept Elect Engn & Comp Sci Berkeley CA 94720 USA

Many of the popular reachability analysis methods rely on the existence of system models. When system dynamics are uncertain or unknown, data-driven techniques must be utilized instead. In this paper, we propose an approach to data-driven reachability that provides a probabilistic guarantee of correctness for these systems through nonconvex scenario optimization. We pose the problem of finding reachable sets directly from data as a chance-constrained optimization problem, and present two algorithms for estimating nonconvex reachable sets: (1) through the union of partition cells and (2) through the sum of radial basis functions. Additionally, we investigate numerical examples to demonstrate the capability and applicability of the introduced methods to provide nonconvex reachable set approximations.

关键词： Reachability analysis scenario optimization data-driven methods

来源：评论

学校读者我要写书评

暂无评论

Input Mapping Design for Batch-to-Batch Optimization With Limited Memory

引用

ieee TRANSACTIONS ON CIRCUITS AND systems II-EXPRESS BRIEFS 2023年第1期70卷 171-175页

作者： Zhou, Yuanqiang Li, Dewei Gao, Furong Hong Kong Univ Sci & Technol Dept Chem & Biol Engn Hong Kong Peoples R China Shanghai Jiao Tong Univ Dept Automat Shanghai 200240 Peoples R China Shanghai Jiao Tong Univ Key Lab Syst Control & Informat Proc Minist Educ Shanghai 200240 Peoples R China Guangzhou HKUST Fok Ying Tung Res Inst Guangzhou 511458 Peoples R China

This brief discusses data-driven design techniques for batch-to-batch optimization problems and proposes a new input-mapping-based online uncertainty compensation method for optimization-based iterative learning control (ILC) with limited memory. Since process uncertainties are generally inevitable, we collect historical data that incorporates past inputs and outputs to provide more insight into plant uncertain dynamics, resulting in a more accurate optimization model for optimal ILC solution. Instead of learning from a single step, our proposed method maintains a memory of the latest executed steps and updates the ILC solution using a linear combination of the memory and quadratic programming. A rigorous theoretical analysis shows that such a design provides robust benefits as well as asymptotic and monotonic stability properties under mild conditions. Finally, we demonstrate our design through an illustrative numerical example.

关键词： Process control optimization data-driven control iterative learning control uncertainty

来源：评论

学校读者我要写书评

暂无评论

Comparative Study Based on a Reduced Dynamic data-driven Methods of Machine learning

Comparative Study Based on a Reduced Dynamic Data-driven Met...

引用

International conference on Advanced systems and Emergent Technologies (ICASET)

作者： Said, Maroua Taouali, Okba Univ Sousse Natl Sch Engn Sousse ENISO Dept Elect Sousse Tunisia Univ Tabuk Fac Comp & Informat Technol Dept Comp Engn Tabuk Saudi Arabia

ISBN: (纸本)9798350384901;9798350384895

Chemical and industrial processes are often overly complex and have thousands of process measurements, every day. In this context, data-driven methods are very interesting methods for the diagnosis of dynamic systems. More precisely, kernel methods have attracted attention for several years, for Fault Detection (FD). A performance comparison, in this paper, is presented between two dynamic monitoring methods. However, the two FD methods are based on the Reduced Kernel Partial Least Square (RKPLS). We compare in this case, the dynamic Moving Window RKPLS (MW-RKPLS) with the dunamique Online RKPLS (ORKPLS). In this comparison, we are mainly interested of the False Alarm Rate (FDR) and also the Good Detection Rate (GDR) to increase the FD performance. All this performances are presented through the Tennessee Eastman process.

关键词： data-driven Fault Detection RKPLS MWRKPLS ORKPLS

来源：评论

学校读者我要写书评

暂无评论

Context-Aware Spatiotemporal Poisoning Attacks on Wearable-Based Activity Recognition

Context-Aware Spatiotemporal Poisoning Attacks on Wearable-B...

引用

ieee conference on Computer Communications (ieee INFOCOM)

作者： Shahid, Abdur R. Hasan, Syed Mhamudul Imteaj, Ahmed Badsha, Shahriar Southern Illinois Univ Carbondale Sch Comp Carbondale IL 62901 USA Secure & Trustworthy Intelligent Syst SHIELD Lab Carbondale IL 62901 USA GM Global Tech Ctr Warren MI USA

ISBN: (纸本)9798350384482;9798350384475

The rapid progress in wearable sensors, smartphones equipped with sensors, and seamless cloud integration has ignited significant research into the creation of IoT-driven intelligent systems designed for human activity recognition (HAR). However, the reliance on external data curation for training machine learning (ML)-based recognition models renders the system susceptible to adversarial attacks. The limited existing research in this area calls for extensive efforts to address its gaps, notably the absence of vital contextual information crucial for HAR systems. In this poster, we present our ongoing research effort on investigating context-aware spatiotemporal data poisoning attacks on the intelligence of HAR systems. These attacks involve attackers exploiting specific spatiotemporal patterns and conditions to manipulate the labels of activity data. This manipulation is strategically designed to mislead the recognition system, thereby highlighting the pressing need for improved security measures in this rapidly evolving domain.

关键词： data Poisoning Attack Adversarial Machine learning Wearable Sensors Human Activity Recognition Context-Awareness

来源：评论

学校读者我要写书评

暂无评论

PUROS: A Cpx-Ievered Framework for Ad Procurement in Autobidding Worlds 13

PUROS: A Cpx-Ievered Framework for Ad Procurement in Autobid...

引用

13th ieee data driven control and learning systems conference, DDCLS 2024

作者： Luo, Huixiang Gao, Longyu Huang, Pingchun Li, Tianning Alibaba Group Hangzhou China

ISBN: (纸本)9798350361674

Nowadays online advertisers acquire ad impressions from digital advertising channels through operating on their au-tobidding platforms: advertisers express high level ad performance constraints for ad procurement by specifying levers including budget and cpx (e.g. cpm: max cost-per-mille, cpc: max cost-per-click, cpa: target cost-per-action). Ad platforms procure impressions on behalf of advertisers soon afterwards, and feedback ad performances (e.g. cost) to advertisers. In practice, no procurement details but aggregated ad performences are access to advertisers, and they are usually unstable because of the non-stationary autobidding environment. As a result, it's challenging for advertisers to optimize levers by directly using 'Predict, then Optimize (PO)' Framework (i.e. use machine-learning model with history data to estimate ad performances, then optimize levers by solving the multi-constraint optimization problem), because poor estimation performance leads to unreliable lever so-lution and results in bad performances on ad procurement. Thus, online-learning-based frameworks are recommended for lever optimization, with large amounts of history data neglected. To upgrade both the estimating & optimizing procedure in PO for better use of history data, 'Predict with Uncertainty estimation, then RObust Satisficing'(PUROS), a cpx-levered framework is presented to handle the chain reaction of poor estimation performance. In particular, an uncertainty-aware forecasting model is used for cpx-oriented ad performance estimation. Then robust satisficing is applied in the optimizing procedure, so that cpx solutions with better Pareto efficiency and robustness are produced compared to those generated by PO. Experiment results on both open-source and real-world e-commerce datasets prove the effectiveness of PUROS over traditional PO ones. Further, PUROS performs better than the previous SOTA online-learning-based framework, and shows huge potential on performance improvement

关键词： Budget control

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：