检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Jaafer, Amani Nilsson, Gustav Como, Giacomo Stockholm Sweden School of Electrical and Computer Engineering Georgia Institute of Technology AtlantaGA United States Department of Mathematical Sciences Politecnico di Torino Italy Department of Automatic Control Lund University Sweden

Over the past years, interest in classifying drivers’ behavior from data has surged. Such interest is particularly relevant for car insurance companies who, due to privacy constraints, often only have access to data from Inertial Measurement Units (IMU) or similar. In this paper, we present a semi-supervised learning solution to classify portions of trips according to whether drivers are driving aggressively or normally based on such IMU data. Since the amount of labeled IMU data is limited and costly to generate, we utilize Recurrent Conditional Generative Adversarial Networks (RCGAN) to generate more labeled data. Our results show that, by utilizing RCGAN-generated labeled data, the classification of the drivers is improved in 79% of the cases, compared to when the drivers are classified with no generated data. Copyright © 2020, 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

Enhanced phase sensitivity in a Mach-Zehnder interferometer via photon recycling

arXiv

引用

arXiv 2023年

作者： Li, Dong Yuan, Chun-Hua Ma, Xiaoping Wang, Qingle Lee, Hwang Yao, Yao Zhang, Weiping Microsystem and Terahertz Research Center China Academy of Engineering Physics Sichuan Chengdu610200 China Institute of Electronic Engineering China Academy of Engineering Physics Sichuan Mianyang621999 China State Key Laboratory of Precision Spectroscopy Quantum Institute of Atom and Light Department of Physics East China Normal University Shanghai200062 China College of Mathematical and Physical Sciences Qingdao University of Science and Technology Qingdao China School of Control and Computer Engineering North China Electric Power University Beijing102206 China CAS Key Laboratory of Quantum Information University of Science and Technology of China Hefei230026 China Hearne Institute for Theoretical Physics Department of Physics and Astronomy Louisiana State University Baton RougeLA70803 United States Department of Physics Shanghai Jiao Tong University Tsung-Dao Lee Institute Shanghai200240 China Collaborative Innovation Center of Extreme Optics Shanxi University Shanxi Taiyuan030006 China

We propose an alternative scheme for phase estimation in a Mach-Zehnder interferometer (MZI) with photon recycling. It is demonstrated that with the same coherent-state input and homodyne detection, our proposal possesses a phase sensitivity beyond the traditional MZI. For instance, it can achieve an enhancement factor of ∼9.32 in the phase sensitivity compared with the conventional scheme even with a photon loss of 10% on the photon-recycled arm. From another point of view, the quantum Cramér-Rao bound (QCRB) is also investigated. It is found that our scheme is able to achieve a lower QCRB than the traditional one. Intriguingly, the QCRB of our scheme is dependent of the phase shift φ while the traditional scheme has a constant QCRB regardless of the phase shift. Finally, we present the underlying mechanisms behind the enhanced phase sensitivity (due to the improved number of photons inside the interferometer). We believe that our results may pave the way to enhance the phase sensitivity via photon recycling. © 2023, CC BY.

关键词： Photons

来源：评论

学校读者我要写书评

暂无评论

Disease transmission in dynamic social networks constructed by reinforcement learning-driven preventive game

引用

Chaos, Solitons & Fractals 2025年 199卷

作者： Yinuo Qian Dawei Zhao Chengyi Xia School of Control Science and Engineering Tiangong University Tianjin 300387 China Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan 250014 China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan 250014 China School of Artificial Intelligence Tiangong University Tianjin 300387 China

Reinforcement learning delves into the intrinsic behaviors of multi-agents, while complex networks reveal their interactive relationships. In real life, an individual can be considered as a sophisticated multi-agent, whose behavioral choices are influenced by a myriad of factors. When contagious diseases penetrate a population, the adoption of preventive measures represents a manifestation of behavioral selection. This paper introduces reinforcement learning into the multi-agent decision within the network, leveraging the Q-learning algorithm to train individual decision-making. At each time step, individuals select the next preventive strategy based on their utility and strategies, and these choices subsequently alter the network structure, thereby influencing the prevalence of the disease. In addition, the incorporation of additional government incentives prompts individuals to opt for advanced preventive strategies, effectively containing disease transmission within the population. The construction of this model not only showcases the co-evolutionary process between network structure and disease transmission but also validates its efficacy through theoretical analysis and applications in real-world networks, offering a novel perspective towards the epidemic control.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Twisting Sliding Mode control of an Electrostatic MEMS Micromirror for a Laser Scanning System

引用

IEEE/CAA Journal of automatica Sinica 2019年第4期6卷 1060-1067页

作者： Hui Chen Zhendong Sun Weijie Sun John Tze Wei Yeow the School of Computer and Information Engineering Henan UniversityKaifeng 475000China the Key Laboratory of Systems and Control Academy of Mathematics and Systems ScienceChinese Academy of SciencesBeijing 100190 China the College of Automation Science and Engineering South China University of TechnologyGuangzhou 510641China the Systems Design Engineering University of WaterlooWaterloo N2L3G1Canada IEEE

In this paper,we present a twisting control scheme with proportional-integral-derivative(PID)sliding surface for a two-axis electrostatic torsional micromirror,and the utilization of the proposed scheme in a laser scanning *** experimental results of set-point regulation verify that the proposed scheme provides enhanced transient response and positioning performance as compared to traditional sliding mode *** evaluate the tracking performance of the closed-loop system,triangular waves with different frequencies are used as desired *** the proposed scheme the experimental results verified that the closed-loop controlled micromirror follows the given triangular trajectories precisely.A micromirror-based laser scanning system is developed to obtain *** compared with open-loop control,the experimental results demonstrated that the proposed scheme is able to reduce the distortion of the raster scan,and improve the imaging performance in the presence of cross-coupling effect.

关键词： Electrostatic micromirror imaging microelectromechanical system(MEMS) twisting algorithm

来源：评论

学校读者我要写书评

暂无评论

Stacked BNAS: Rethinking Broad Convolutional Neural Network for Neural Architecture Search

arXiv

引用

arXiv 2021年

作者： Ding, Zixiang Chen, Yaran Li, Nannan Zhao, Dongbin Chen, C.L. Philip State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China School of Computer Science & Engineering South China University of Technology Guangdong Guangzhou510006 China College of Navigation Dalian Maritime University Dalian116026 China

Different from other deep scalable architecture-based NAS approaches, Broad Neural Architecture Search (BNAS) proposes a broad scalable architecture which consists of convolution and enhancement blocks, dubbed Broad Convolutional Neural Network (BCNN), as the search space for amazing efficiency improvement. BCNN reuses the topologies of cells in the convolution block so that BNAS can employ few cells for efficient search. Moreover, multi-scale feature fusion and knowledge embedding are proposed to improve the performance of BCNN with shallow topology. However, BNAS suffers some drawbacks: 1) insufficient representation diversity for feature fusion and enhancement and 2) time consumption of knowledge embedding design by human experts. This paper proposes Stacked BNAS, whose search space is a developed broad scalable architecture named Stacked BCNN, with better performance than BNAS. On the one hand, Stacked BCNN treats mini BCNN as a basic block to preserve comprehensive representation and deliver powerful feature extraction ability. For multi-scale feature enhancement, each mini BCNN feeds the outputs of deep and broad cells to the enhancement cell. For multi-scale feature fusion, each mini BCNN feeds the outputs of deep, broad and enhancement cells to the output node. On the other hand, Knowledge Embedding Search (KES) is proposed to learn appropriate knowledge embeddings in a differentiable way. Moreover, the basic unit of KES is an over-parameterized knowledge embedding module that consists of all possible candidate knowledge embeddings. Experimental results show that 1) Stacked BNAS obtains better performance than BNAS-v2 on both CIFAR-10 and ImageNet, 2) the proposed KES algorithm contributes to reducing the parameters of the learned architecture with satisfactory performance, and 3) Stacked BNAS delivers a state-of-the-art efficiency of 0.02 GPU days. Copyright © 2021, The Authors. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Wide-angle giant photonic spin Hall effect

引用

Physical Review B 2022年第7期106卷 075409-075409页

作者： Zhihao Chen Yu Chen Yaodong Wu Xinxing Zhou Handong Sun Tony Low Hongsheng Chen Xiao Lin Key Laboratory of Low-Dimensional Quantum Structures and Quantum Control of Ministry of Education Synergetic Innovation Center for Quantum Effects and Applications School of Physics and Electronics Hunan Normal University Changsha 410081 China International Collaborative Laboratory of 2D Materials for Optoelectronics Science and Technology Engineering Technology Research Center for 2D Material Information Function Devices and Systems of Guangdong Province Institute of Microscale Optoelectronics Shenzhen University Shenzhen 518060 China Division of Physics and Applied Physics School of Physical and Mathematical Sciences Nanyang Technological University Singapore 637371 Singapore Centre for Disruptive Photonic Technologies (CDPT) School of Physical and Mathematical Sciences Nanyang Technological University Singapore 637371 Singapore Department of Electrical and Computer Engineering University of Minnesota Minneapolis Minnesota 55455 USA Interdisciplinary Center for Quantum Information State Key Laboratory of Modern Optical Instrumentation ZJU-Hangzhou Global Scientific and Technological Innovation Center College of Information Science and Electronic Engineering Zhejiang University Hangzhou 310027 China International Joint Innovation Center ZJU-UIUC Institute The Electromagnetics Academy at Zhejiang University Zhejiang University Haining 314400 China

The photonic spin Hall effect is a manifestation of the spin-orbit interaction of light and can be measured by a transverse shift δ of photons with opposite spins. The precise measurement of transverse shifts can enable many spin-related applications, such as precise metrology and optical sensing. However, this transverse shift is generally small (i.e., δ/λ<10−1, where λ is the wavelength), which impedes its precise measurement. To date, proposals to generate a giant spin Hall effect (namely, with δ/λ>102) have severe limitations, particularly its occurrence only over a narrow angular cone (with a width of Δθ<1∘). Here we propose a universal scheme to realize the wide-angle giant photonic spin Hall effect with Δθ>70∘ by exploiting the interface between free space and uniaxial epsilon-near-zero media. The underlying mechanism is ascribed to the almost-perfect polarization splitting between s and p polarized waves at the designed interface. Remarkably, this almost-perfect polarization splitting does not resort to the interference effect and is insensitive to the incident angle, which then gives rise to the wide-angle giant photonic spin Hall effect.

关键词： Light-matter interaction Photonics Spin Hall effect Spin-orbit coupling

来源：评论

学校读者我要写书评

暂无评论

Enhancing reliability and safety of uncertain grid-connected photovoltaic systems based on intelligent transient regime analysis

引用

Applied Energy 2025年 397卷

作者： Amal Hichri Mansour Hajji Majdi Mansouri Kais Bouzrara Noureddine Elboughdiri Hatem Gasmi Research Laboratory of Advanced Materials and Nanotechnologies Higher Institute of Applied Sciences and Technology of Kasserine Kairouan University Kairouan Tunisia Department of Electrical and Computer Engineering College of Engineering Sultan Qaboos University Muscat 123 Oman Laboratory of Automatic Signal and Image Processing National Engineering School of Monastir University of Monastir Monastir 5019 Tunisia Chemical Engineering Department College of Engineering University of Ha’il P.O. Box 2440 Ha’il 81441 Saudi Arabia Civil Engineering Department College of Engineering University of Ha’il P.O. Box 2440 Ha’il 81441 Saudi Arabia

Ensuring the uninterrupted operation of Grid-Connected Photovoltaic (GCPV) systems is crucial, as these systems are highly susceptible to faults and downtime caused by various factors, which can lead to significant system damage. To address these challenges, fault detection and diagnosis (FDD) methods are essential to maintain the reliability and safety of GCPV systems. This paper presents a transient regime based on the FDD approach of uncertain GCPV systems, employing deep learning techniques to detect and classify faults effectively. Furthermore, the proposed method takes advantage of the transition phase between healthy and faulty states in renewable energy systems to enable early fault detection by identifying anomalies in performance signals. By combining transient regime analysis with deep learning techniques, the approach facilitates rapid and accurate fault detection, thereby enhancing the reliability and extending the lifespan of photovoltaic systems. To handle uncertainties in the measured data, an interval-valued data representation is utilized, ensuring robust fault analysis under varying conditions. However, the hyperparameters of the proposed techniques are optimized using the Genetic Algorithm, improving their adaptability to diverse operating scenarios. The robustness of the methodology is further validated by introducing varying levels of noise into the data, simulating real-world perturbations and dynamic variations. The processed outputs are used to train deep learning classifiers to distinguish between various operating modes in GCPV systems. Experimental validation with real-world data demonstrates the efficacy and robustness of the proposed approach, enabling immediate decision-making and preventing fault propagation. The results highlight the strategy’s high accuracy and computational efficiency, contributing to improved reliability and safety of GCPV systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Randomised benchmarking for characterizing and forecasting correlated processes

arXiv

引用

arXiv 2023年

作者： Zhang, Xinfang Wu, Zhihao White, Gregory A.L. Xiang, Zhongcheng Hu, Shun Peng, Zhihui Liu, Yong Zheng, Dongning Fu, Xiang Huang, Anqi Poletti, Dario Modi, Kavan Wu, Junjie Deng, Mingtang Guo, Chu Institute for Quantum Information State Key Laboratory of High Performance Computing College of Computer Science and Technology National University of Defense Technology Changsha410073 China School of Physics and Astronomy Monash University VIC3800 Australia Dahlem Center for Complex Quantum Systems Freie Universität Berlin Berlin14195 Germany Institute of Physics Chinese Academy of Sciences Beijing100190 China Key Laboratory of Low-Dimensional Quantum Structures and Quantum Control of Ministry of Education Department of Physics Synergetic Innovation Center for Quantum Effects and Applications Hunan Normal University Changsha410081 China Science Mathematics and Technology Cluster and Engineering Product Development Pillar Singapore University of Technology and Design 8 Somapah Road 487372 Singapore Centre for Quantum Technologies National University of Singapore 117543 Singapore MajuLab CNRS-UNS-NUS-NTU International Joint Research Unit UMI 3654 Singapore Quantum for NSW Sydney2000 Australia

The development of fault-tolerant quantum processors relies on the ability to control noise. A particularly insidious form of noise is temporally correlated or non-Markovian noise. By combining randomized benchmarking with supervised machine learning algorithms, we develop a method to learn the details of temporally correlated noise. In particular, we can learn the time-independent evolution operator of system plus bath and this leads to (i) the ability to characterize the degree of non-Markovianity of the dynamics and (ii) the ability to predict the dynamics of the system even beyond the times we have used to train our model. We exemplify this by implementing our method on a superconducting quantum processor. Our experimental results show a drastic change between the Markovian and non-Markovian regimes for the learning accuracies. Copyright © 2023, The Authors. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Cerebrovascular Segmentation in MRA via Reverse Edge Attention Network 23rd

Cerebrovascular Segmentation in MRA via Reverse Edge Attenti...

引用

23rd International Conference on Medical Image Computing and computer-Assisted Intervention, MICCAI 2020

作者： Zhang, Hao Xia, Likun Song, Ran Yang, Jianlong Hao, Huaying Liu, Jiang Zhao, Yitian College of Information Engineering Capital Normal University Beijing China Cixi Institute of Biomedical Engineering Ningbo Institute of Industrial Technology Chinese Academy of Sciences Ningbo China School of Control Science and Engineering Shandong University Jinan China Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China International Science and Technology Cooperation Base of Electronic System Reliability and Mathematical Interdisciplinary Capital Normal University Beijing China Laboratory of Neural Computing and Intelligent Perception Capital Normal University Beijing China Beijing Advanced Innovation Center for Imaging Theory and Technology Capital Normal University Beijing China

ISBN: (纸本)9783030597245

Automated extraction of cerebrovascular is of great importance in understanding the mechanism, diagnosis, and treatment of many cerebrovascular pathologies. However, segmentation of cerebrovascular networks from magnetic resonance angiography (MRA) imagery continues to be challenging because of relatively poor contrast and inhomogeneous backgrounds, and the anatomical variations, complex geometry and topology of the networks themselves. In this paper, we present a novel cerebrovascular segmentation framework that consists of image enhancement and segmentation phases. We aim to remove redundant features, while retaining edge information in shallow features when combining these with deep features. We first employ a Retinex model, which is able to model noise explicitly to aid removal of imaging noise, as well as reducing redundancy within an image and emphasizing the vessel regions, thereby simplifying the subsequent segmentation problem. Subsequently, a reverse edge attention module is employed to discover edge information by paying particular attention to the regions that are not salient in high-level semantic features. The experimental results show that the proposed framework enables the reverse edge attention network to deliver a reliable cerebrovascular segmentation. © 2020, Springer Nature Switzerland AG.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

The conceptual approach of system for automatic vehicle accident detection and searching for life signs of casualties 5th

The conceptual approach of system for automatic vehicle acci...

引用

5th International Doctoral Symposium on Applied Computation and Security Systems, ACSS 2018

作者： Lupinska-Dubicka, Anna Tabedzki, Marek Adamski, Marcin Rybnik, Mariusz Omieljanowicz, Miroslaw Omieljanowicz, Andrzej Szymkowski, Maciej Gruszewski, Marek Klimowicz, Adam Rubin, Grzegorz Saeed, Khalid Faculty of Computer Science Bialystok University of Technology Bialystok Poland Faculty of Mathematics and Informatics University of Bialystok Bialystok Poland Faculty of Mechanical Engineering Department of Automatic Control and Robotics Bialystok University of Technology Bialystok Poland Faculty of Computer and Food Science Lomza State University of Applied Sciences Lomza Poland

ISBN: (纸本)9789811337017

The European eSafety initiative aims to improve the safety and efficiency of road transport. The main element of eSafety is the pan-European eCall project—an in-vehicle system which idea is to inform about road collisions or serious accidents. As estimated by the European Commission, the implemented system will reduce services’ response time by 40%. This will save 2,500 people a year. In 2015, the European Parliament adopted the legislation that from the end of March 2018 all new cars from the EU should be equipped with the eCall system. The limitation of this idea is that only small part of cars driven in UE are brand new (about 3.7% brand new cars were sold in 2015). This paper presents the first concept of an onboard eCall device which can be installed at the owners’ request in used vehicles. The proposed system will be able to detect a road accident, indicate the number of vehicle’s occupants, report their vital functions, and send that information to dedicated emergency services via duplex communication channel. © Springer Nature Singapore Pte Ltd. 2019.

关键词： Emergency services

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：