检索结果-内蒙古大学图书馆

Cooperative System Identification via Correctional Learning ⁎

IFAC-PapersOnLine 2021年第7期54卷 19-24页

作者： Inês Lourenço Robert Mattila Cristian R. Rojas Bo Wahlberg Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm Sweden

We consider a cooperative system identification scenario in which an expert agent (teacher) knows a correct, or at least a good, model of the system and aims to assist a learner-agent (student), but cannot directly transfer its knowledge to the student. For example, the teacher’s knowledge of the system might be abstract or the teacher and student might be employing different model classes, which renders the teacher’s parameters uninformative to the student. In this paper, we propose correctional learning as an approach to the above problem: suppose that in order to assist the student, the teacher can intercept the observations collected from the system and modify them to maximize the amount of information the student receives about the system. We formulate a general solution as an optimization problem, which for a multinomial system instantiates itself as an integer program. Furthermore, we obtain finite-sample results on the improvement that the assistance from the teacher results in (as measured by the reduction in the variance of the estimator) for a binomial system. In numerical experiments, we illustrate the proposed algorithms and verify the theoretical results that have been derived in the paper.

关键词： Cooperative system identification assisted learning correctional learning student-expert transfer learning

来源：评论

学校读者我要写书评

暂无评论

Research on Target Detection Method Based on Improved YOLOv5 19th

Research on Target Detection Method Based on Improved YOLOv5

引用

19th International Conference on Web Information Systems and Applications, WISA 2022

作者： Wang, Rongzhuang Liu, Jun Zhang, Hualiang School of Computer Science and Technology Shenyang University of Chemical Technology Shenyang110142 China Liaoning Key Laboratory of Intelligent Technology for Chemical Process Industry Shenyang110142 China Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang110016 China Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang110169 China

ISBN: (纸本)9783031203084

At present, various target detection algorithms are used in detection and classification. It is a problem to improve the accuracy and speed of target detection by using deep learning and neural network model to train the parameters of the data set. Aiming at the problems of insufficient detection, inaccurate detection of complex background and loss of small target feature information in yolov5 target detection, an improved method combining hole convolution, moving exponential average and retraining of positive samples is proposed in this paper. This method effectively solves the problems of complex background, occlusion and incomplete feature extraction, reduces the loss rate of target features, and improves the detection accuracy of each category. The improved yolov5 target detection algorithm in this paper can not only use multi feature fusion and accelerate positive sample matching, but also use cavity convolution to increase receptive field, improve the detection effect of small targets and reduce the occurrence of missed detection and false detection. Experiments show that the improved yolov5 algorithm has better detection rate and lower loss rate than many existing target detection algorithms. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

On state-space representations of general discrete-time dynamical systems

arXiv

引用

arXiv 2022年

作者： Rojas, Cristian R. Wachel, Pawel The School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm100 44 Sweden The Department of Control Systems and Mechatronics Wroclaw University of Science and Technology Wroclaw Poland

In this paper we establish that every (deterministic) non-autonomous, discrete-time, causal, time invariant system has a state-space representation, and discuss its minimality. Copyright © 2022, The Authors. All ... 详细信息

关键词： Nonlinear dynamical systems

来源：评论

学校读者我要写书评

暂无评论

A Method for Recognition of Mixed Gas Composition Based on PCA and KNN 19

A Method for Recognition of Mixed Gas Composition Based on P...

引用

19th International Conference on Optical Communications and Networks, ICOCN 2021

作者： Xia, Wanyu Song, Tingting Yan, Zhanwei Song, Kai Chen, Deyun Chen, Yinsheng National Experimental Teaching Demonstration Center for Measurement and Control Technology and Instrumentation Harbin University of Science and Technology Harbin150080 China Postdoctoral Research Station of Computer Science and Technology Harbin University of Science and Technology Harbin150080 China School of Electrical Engineering and Automation Harbin Institute of Technology Harbin150080 China

ISBN: (纸本)9781665424462

In the mining process of coal, oil, and natural gas, there are often a large number of toxic, hazardous and explosive gases, which pose a greater safety hazard. These gases usually exist in the form of mixtures. Accurately identifying the composition of the mixed gas is of great significance to the prevention of safety accidents. In order to improve the accuracy of the component recognition of the mixed gas, this paper proposes a mixed gas component recognition algorithm based on the combination of principal component analysis (PCA) and k-nearest neighbor algorithm (KNN). PCA is used to extract the characteristics of the sensor array signal to obtain the characteristic value of the gas, and then KNN is used to realize the recognition of the gas type. The results show that the recognition rate of the feature quantity after dimensionality reduction as input is higher than that before dimensionality reduction. Finally, PCA and KNN algorithm and PCA and support vector machine (SVM) algorithm are compared for the recognition rate of mixed gas. Experimental results show that the proposed method has a recognition rate of 96.88% for mixed gas components. © 2021 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

A Model-Based Approach for Voltage and State-of-Charge Estimation of Lithium-ion Batteries

A Model-Based Approach for Voltage and State-of-Charge Estim...

引用

Sustainable Power and Energy Conference (iSPEC)

作者： Milad Andalibi Seyed Saeed Madani Carlos Ziebert Farshid Naseri Mojtaba Hajihosseini Department of Control and Computer Engineering Faculty of Electrical Engineering and Computing University of Zagreb Zagreb Croatia Institute of Applied Materials-Applied Materials Physics Karlsruhe Institute of Technology Karlsruhe Germany Electrical and Computer Engineering Department Electrical Energy Technology Aarhus University Aarhus Denmark

ISBN: (纸本)9781665485234

Electric vehicles are equipped with a large number of lithium-ion battery cells. To achieve superior performance and guarantee safety and longevity, there is a fundamental requirement for a Battery Management System (BMS). In the BMS, accurate prediction of the State-of-Charge (SOC) is a crucial task. The SOC information is needed for monitoring, controlling, and protecting the battery, e.g. to avoid hazardous over-charging or over-discharging. Nonetheless, the SOC is an internal cell variable and cannot be straightforwardly obtained. This paper presents a Kalman Filter (KF) approach based on an optimized second-order Rc equivalent circuit model to carefully account for model parameter changes. An effective machine learning technique based on Proximal Policy optimization (PPO) is applied to train the algorithm. The results confirm the high robustness of the proposed method to varying operating conditions.

关键词： Lithium-ion batteries Machine learning algorithms Computational modeling Estimation Voltage Safety State of charge

来源：评论

学校读者我要写书评

暂无评论

Kinetic discretization of one-dimensional nonlocal flow models

引用

IFAC-PapersOnLine 2022年第20期55卷 67-72页

作者： Mihály A. Vághy Mihály Kovács Gábor Szederkényi Faculty of Information Technology and Bionics Pázmány Péter Catholic University H-1444 Budapest Hungary Department of Mathematical Sciences Chalmers University of Technology and University of Gothenburg SE-41296 Gothenburg Sweden Systems and Control Laboratory Institute for Computer Science and Control (SZTAKI) H-1111 Budapest Hungary

We show that one-dimensional nonlocal flow models in PDE form with Lighthill-Whitham-Richards flux supplemented with appropriate in- and out-flow terms can be spatially discretized with a finite volume scheme to obtain formally kinetic models with physically meaningful reaction graph structure. This allows the utilization of the theory of chemical reaction networks, as demonstrated here via the stability analysis of a flow model with circular topology. We further propose an explicit time discretization and a Courant-Friedrichs-Lewy condition ensuring many advantageous properties of the scheme. Additional characteristics, including monotonicity and the total variation diminishing property are also discussed.

关键词： control of hyperbolic systems conservation laws kinetic modeling modeling for control stability of distributed parameter systems stability of nonlinear systems

来源：评论

学校读者我要写书评

暂无评论

On Solar Photovoltaic Parameter Estimation: Global Optimality Analysis and a Simple Efficient Differential Evolution Method

On Solar Photovoltaic Parameter Estimation: Global Optimalit...

引用

IEEE Conference on Decision and control

作者： Shuhua Gao Cheng Xiang Ming Yu Kuan Tak Tan Tong Heng Lee School of Control Science and Engineering Shandong University Jinan China Department of Electrical and Computer Engineering National University of Singapore Singapore Power Automation Pte Ltd Singapore Engineering Cluster Singapore Institute of Technology Singapore

The literature presents a vast array of advanced metaheuristic methods for photovoltaic parameter estimation. However, the focus of this study is not to introduce another new method into this already crowded field. Instead, we examine two important but often overlooked questions: (i) are existing results globally optimal, and (ii) can a simpler method achieve comparable performance. We conduct case studies using two widely used I-V curve datasets. To address the first issue, we develop a branch and bound algorithm that, despite its sluggishness, either certifies the global minimum or provides a tight upper bound. These values serve as useful benchmarks for fair metaheuristic evaluation and further development. To answer the second question, our extensive examination and comparison surprisingly reveal that a basic differential evolution (DE) algorithm can achieve the certified global minimum or obtain the best known result. Additionally, the DE algorithm's runtime is much shorter than that of current state-of-the-art metaheuristic methods, making it a great choice for time-sensitive applications. This remarkable finding suggests that using increasingly complex metaheuristics in ordinary PV parameter estimation problems might be unnecessary. Finally, we discuss the implications of these outcomes and propose the simple DE method as the premier choice for industrial applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

QUADFormer: Learning-based Detection of Cyber Attacks in Quadrotor UAVs

arXiv

引用

arXiv 2024年

作者： Wang, Pengyu Yang, Zhaohua Yang, Nachuan Wang, Zikai Li, Jialu Zhang, Fan Wang, Chaoqun Wang, Jiankun Meng, Max Q.-H. Shi, Ling Shenzhen Key Laboratory of Robotics Perception and Intelligence The Department of Electronic and Electrical Engineering Southern University of Science and Technology Shenzhen China Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Hong Kong Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Hong Kong The School of Control Science and Engineering Shandong University Shandong China Jiaxing Research Institute Southern University of Science and Technology Jiaxing China Department of Electronic Engineering The Chinese University of Hong Kong Hong Kong Department of Electrical and Computer Engineering The University of Alberta Canada

Safety-critical intelligent cyber-physical systems, such as quadrotor unmanned aerial vehicles (UAVs), are vulnerable to different types of cyber attacks, and the absence of timely and accurate attack detection can lead to severe consequences. When UAVs are engaged in large outdoor maneuvering flights, their system constitutes highly nonlinear dynamics that include non-Gaussian noises. Therefore, the commonly employed traditional statistics-based and emerging learning-based attack detection methods do not yield satisfactory results. In response to the above challenges, we propose QUADFormer, a novel Quadrotor UAV Attack Detection framework with transFormer-based architecture. This framework includes a residue generator designed to generate a residue sequence sensitive to anomalies. Subsequently, this sequence is fed into a transformer structure with disparity in correlation to specifically learn its statistical characteristics for the purpose of classification and attack detection. Finally, we design an alert module to ensure the safe execution of tasks by UAVs under attack conditions. We conduct extensive simulations and real-world experiments, and the results show that our method has achieved superior detection performance compared with many state-of-the-art methods. (Video1) Copyright © 2024, The Authors. All rights reserved.

关键词： Antennas

来源：评论

学校读者我要写书评

暂无评论

A Novel Deep Learning Approach Featuring Graph-Based Algorithm for Cell Segmentation and Tracking

A Novel Deep Learning Approach Featuring Graph-Based Algorit...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Zhao, Keliang Niyogisubizo, Jovial Xiao, Linxia Pan, Yi Wei, Dongqing Rosiyadi, Didi Wei, Yanjie Chinese Academy of Sciences Shenzhen Key Laboratory of Intelligent Bioinformatics and Center for High Performance Computing Shenzhen Institute of Advanced Technology Shenzhen518055 China Chinese Academy of Sciences College of Computer Science and Control Engineering Shenzhen Institutes of Advanced Technology Shenzhen518055 China Shanghai Jiao Tong University State Key Laboratory of Microbial Metabolism School of Life Sciences and Biotechnology Shanghai200240 China National Research and Innovation Agency Research Center for Artificial Intelligence and Cybersecurity Bandung Indonesia

ISBN: (纸本)9798350337488

The precise segmentation and tracking of cells in microscopy image sequences play a pivotal role in biomedical research, facilitating the study of tissue, organ, and organism development. However, manual segmentation and tracking of cells is time-consuming and often require professional experiences. Besides, segmenting cells in the images with a low signal-to-noise ratio remains difficult. While deep learning (DL) has become a common method for cell segmentation, few DL- based methods address concurrent cell segmentation and tracking. In this paper, we propose a novel DL approach featuring graph-based tracking for cell segmentation and tracking in microscopy images. We combine Deeplabv3+ for semantic segmentation and ResNet50 for enhanced feature extraction, enabling comprehensive cell detection and instance segmentation. Post-processing, involving non-maxima suppression and outlier detection, refines predictions and produces final segmentation. The tracking method is based on the relative position of graph nodes to track segmented cells, encompassing cell division and apoptosis. We conduct our experiments on the induced pluripotent stem (iPS) cell datasets, and the results show that the segmentation and tracking performance of our method yields superior performance compared to the benchmark models. More specifically, our approach achieved DET values of 0.955 and 0.913, TRA values of 0.951 and 0.906, and SEG values of 0.690 and 0.665 on two iPS dataset videos, respectively. Additionally, the performance assessment encompasses four real microscopy datasets from the Cell Tracking Challenge (CTC). Our method greatly reduces the cost of manual labeling and labor-intensive costs. © 2023 IEEE.

关键词： cell segmentation cell tracking deep learning Deeplabv3+ instance segmentation iPS cell reprogramming

来源：评论

学校读者我要写书评

暂无评论

4.6-Bit Quantization for Fast and Accurate Neural Network Inference on Cpus

SSRN

引用

SSRN 2023年

作者： Trusov, Anton Limonova, Elena Nikolaev, Dmitry Arlazarov, Vladimir V. Moscow Institute of Physics and Technology Dolgoprudny Russia Federal Research Center "Computer Science and Control" Russian Academy of Sciences Moscow Russia Smart Engines Service LLC Moscow Russia Institute for Information Transmission Problems Russian Academy of Sciences Moscow Russia

Quantization is a widespread method for reducing the inference time of neural networks on mobile Central Processing Units (CPUs).8-bit quantized networks demonstrate almost as high quality as full precision models and perfectly fit the hardware architecture with one-byte coefficients and 32-bit dot product *** precision quantizations usually suffer from noticeable quality loss and require specific computational algorithms to outperform 8-bit quantization. In this paper, we propose a novel 4.6-bit quantization scheme that allows for more efficient use of CPU *** scheme has more quantization bins than 4-bit quantization and is more accurate while preserving the computational efficiency of the later(it runs only 4% slower). Our multiplication uses a combination of 16- and 32-bit accumulators and avoids multiplication depth limitation, which the previous 4-bit multiplication algorithm *** experiments with different convolutional neural networks on CIFAR-10 and ImageNet datasets show, that 4.6-bit quantized networks are 1.5-1.6 times faster than 8-bit networks on the ARMv8 CPU. The quality loss in comparison to 8-bit and full precision models is also not high. Therefore, 4.6-bit quantization may serve as an intermediate solution between fast and inaccurate low-bit network quantizations and accurate but relatively slow 8-bit ones. © 2023, The Authors. All rights reserved.

关键词： Program processors

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：