检索结果-内蒙古大学图书馆

11th International Conference on Learning Representations, ICLR 2023

作者： Hu, Jiachen Zhong, Han Jin, Chi Wang, Liwei School of Computer Science Peking University China Center for Data Science Peking University China Department of Electrical and Computer Engineering Princeton University United States National Key Laboratory of General Artificial Intelligence School of Intelligence Science and Technology Peking University Center for Data Science Peking University Beijing Institute of Big Data Research China

Sim-to-real transfer, which trains RL agents in the simulated environments and then deploys them in the real world, has been widely used to overcome the limitations of gathering samples in the real world. Despite the empirical success of the sim-to-real transfer, its theoretical foundation is much less understood. In this paper, we study the sim-to-real transfer in continuous domain with partial observations, where the simulated environments and real-world environments are modeled by linear quadratic Gaussian (LQG) systems. We show that a popular robust adversarial training algorithm is capable of learning a policy from the simulated environment that is competitive to the optimal policy in the real-world environment. To achieve our results, we design a new algorithm for infinite-horizon average-cost LQGs and establish a regret bound that depends on the intrinsic complexity of the model class. Our algorithm crucially relies on a novel history clipping scheme, which might be of independent interest. © 2023 11th International Conference on Learning Representations, ICLR 2023. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

PZT-based Multi-Mode Cantilever for Viscosity Sensing

PZT-based Multi-Mode Cantilever for Viscosity Sensing

引用

IEEE International Frequency Control Symposium

作者： Javed N Priyanka Singh Sudhanshu Tiwari Pavitra Jain Kongbrailatpam Sandeep Rudra Pratap Gayathri Pillai Center for Nanoscience and Engineering Indian Institute of Science Bengaluru India The Elmore Family School of Electrical and Computer Engineering Purdue University

We report a thin film Lead Zirconate Titanate (PZT) on Silicon-on-Insulator (SOI) based microcantilever for fluid dynamic viscosity (η fluid ) sensing using optical and electrical characterization schemes. The viscosity of the medium is modulated by adding glycerol to deionized (DI) water. The measurements are carried over a viscosity range of 0.98-24.24 cP, which covers the operational range for biomedical applications. The fundamental cantilever mode yields a quality factor (Q) of 630 and 15 in air and DI water, respectively, whilst the second mode exhibits a Q of 840 and 30 in air and DI water, respectively. Sensor characterization using Laser Doppler Vibrometer (LDV) shows a power law relation between Q and η fluid $\left( {Q = a\eta _{fluid}^b} \right)$. A high relative responsivity of 0.38 and 0.41 with respect to η fluid is observed for the first and second flexural modes of the microcantilever, respectively. These results indicate the development of a good platform for on-chip viscosity measurements for biomedical and industrial applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

EEG based stress classification by using difference plots of variational modes and machine learning

引用

Journal of Ambient Intelligence and Humanized Computing 2023年第12期14卷 16347-16360页

作者： Salankar, Nilima Qaisar, Saeed Mian School of Computer Science University of Petroleum and Energy Studies Dehradun India Persistent System Limited IT Park Maharashtra Nagpur India Department of Electrical and Computer Engineering EFfat University Jeddah22332 Saudi Arabia Communication and Signal Processing Lab Energy and Technology Research Center Effat University Jeddah22332 Saudi Arabia

The recent trend in healthcare is to use the automated biomedical signals processing for an augmented and precise diagnosis. In this context, an original approach is presented for categorization of stress and non-stress classes by processing the multichannel Electroencephalogram (EEG) signals. The EEG signals are decomposed by using the "Empirical Mode Decomposition" (EMD) and "Variational Mode Decomposition" (VMD), respectively render the "Intrinsic Mode Functions" (IMFs) and Modes. The Second Order Difference Plots (SODPs) are traced for each IMF and Mode. Shapes of SODPs are used to discriminate the two intended categories. The feature space includes areas, Central Tendency Measures (CTMs) and means of SODPs. It is derived from first 7 IMFs and Modes. The identification of stress and non-stress categories is performed by using the robust machine learning algorithms namely, the Support Vector Machine (SVM), Boosting with Random Forest (RF) and Multilayer Perceptron Neural Network (MLPNN). The applicability is tested by using a publicly available EEG signals dataset, recorded during mental arithmetic test. A detailed evaluation is carried out at the subset, individual channel and lobes wise. Noteworthy highest accuracies of subset wise 99.89%, channel wise 98.89% and lobe wise 99.99% are obtained respectively. © 2022, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Empirical mode decomposition

来源：评论

学校读者我要写书评

暂无评论

Design and Optimization of Single-Shunt Diode RF Rectifier Using Electromagnetic Co-Simulation 12

Design and Optimization of Single-Shunt Diode RF Rectifier U...

引用

12th International electrical engineering Congress, iEECON 2024

作者： Arpanutud, Kirote Pongthavornkamol, Tiwat Akkaraekthalin, Prayoot Chalermwisutkul, Suramate Kasetsart University Sriracha Campus Faculty Of Engineering At Sriracha Chonburi Thailand National Electronics And Computer Technology Center The National Science And Technology Development Agency Pathumthani Thailand King Mongkut's University Of Technology North Bangkok Faculty Of Engineering Department Of Electrical And Computer Engineering Bangkok Thailand The Sirindhorn International Thai-German Graduate School Of Engineering King Mongkut's University Of Technology North Bangkok Bangkok Thailand

ISBN: (纸本)9798350383591

In this paper, an efficient design process for a single-shunt diode RF rectifier is proposed. The technique focuses on tuning microstrip line sections in electromagnetic and circuit co-simulation. The design study can achieve an RF-to-DC conversion efficiency of 51.27% at the center frequency of 950 MHz with -10 dBm input power. Good agreement between full wave electromagnetic simulation and electromagnetic/ circuit co-simulation is demonstrated, providing substantial support for the proposed RF rectifier design technique. © 2024 IEEE.

关键词： Conversion efficiency

来源：评论

学校读者我要写书评

暂无评论

Synergistic Swarm Optimization Algorithm

引用

computer Modeling in engineering & sciences 2024年第6期139卷 2557-2604页

作者： Sharaf Alzoubi Laith Abualigah Mohamed Sharaf Mohammad Sh.Daoud Nima Khodadadi Heming Jia Faculty of Computer Sciences and Informatics Amman Arab UniversityAmman11953Jordan Computer Science Department Al Al-Bayt UniversityMafraq25113Jordan Department of Electrical and Computer Engineering Lebanese American UniversityByblos13-5053Lebanon Hourani Center for Applied Scientific Research Al-Ahliyya Amman UniversityAmman19328Jordan MEU Research Unit Middle East UniversityAmman11831Jordan Applied Science Research Center Applied Science Private UniversityAmman11931Jordan School of Computer Sciences Universiti Sains MalaysiaPulau Pinang11800Malaysia School of Engineering and Technology Sunway University MalaysiaPetaling Jaya27500Malaysia Department of Industrial Engineering College of EngineeringKing Saud UniversityP.O.Box 800Riyadh11421Saudi Arabia College of Engineering Al Ain UniversityAbu Dhabi112612United Arab Emirates Department of Civil and Architectural Engineering University of MiamiCoral Gables1251USA School of Information Engineering Sanming UniversitySanming365004China

This research paper presents a novel optimization method called the Synergistic Swarm Optimization Algorithm(SSOA).The SSOA combines the principles of swarmintelligence and synergistic cooperation to search for optimal solutions efficiently.A synergistic cooperation mechanism is employed,where particles exchange information and learn from each other to improve their search *** cooperation enhances the exploitation of promising regions in the search space while maintaining exploration ***,adaptive mechanisms,such as dynamic parameter adjustment and diversification strategies,are incorporated to balance exploration and *** leveraging the collaborative nature of swarm intelligence and integrating synergistic cooperation,the SSOAmethod aims to achieve superior convergence speed and solution quality performance compared to other optimization *** effectiveness of the proposed SSOA is investigated in solving the 23 benchmark functions and various engineering design *** experimental results highlight the effectiveness and potential of the SSOA method in addressing challenging optimization problems,making it a promising tool for a wide range of applications in engineering and *** codes of SSOA are available at:https://***/matlabcentral/fileexchange/153466-synergistic-swarm-optimization-algorithm.

关键词： Synergistic swarm optimization algorithm optimization algorithm metaheuristic engineering problems benchmark functions

来源：评论

学校读者我要写书评

暂无评论

Formal Ethical Obligations in Reinforcement Learning Agents: Verification and Policy Updates 24

Formal Ethical Obligations in Reinforcement Learning Agents:...

引用

Proceedings of the 2024 AAAI/ACM Conference on AI, Ethics, and Society

作者： Colin Shea-Blymyer Houssam Abbas Georgetown University Center for Security and Emerging Technology Oregon State University School of Electrical Engineering and Computer Science

When designing agents for operation in uncertain environments, designers need tools to automatically reason about what agents ought to do, how that conflicts with what is actually happening, and how a policy might be modified to remove the conflict. These obligations include ethical and social obligations, permissions and prohibitions, which constrain how the agent achieves its mission and executes its policy. We propose a new deontic logic, Expected Act Utilitarian deontic logic, for enabling this reasoning at design time: for specifying and verifying the agent's strategic obligations, then modifying its policy from a reference policy to meet those obligations. Unlike approaches that work at the reward level, working at the logical level increases the transparency of the trade-offs. We introduce two algorithms: one for model-checking whether an RL agent has the right strategic obligations, and one for modifying a reference decision policy to make it meet obligations expressed in our logic. We illustrate our algorithms on DAC-MDPs which accurately abstract neural decision policies, and on toy gridworld environments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Scattering exceptional point in the visible

引用

Light(science & Applications) 2023年第10期12卷 2228-2235页

作者： Tao He Zhanyi Zhang Jingyuan Zhu Yuzhi Shi Zhipeng Li Heng Wei Zeyong Wei Yong Li Zhanshan Wang Cheng-Wei Qiu Xinbin Cheng MOE Key Laboratory of Advanced Micro-Structured Materials Shanghai 200092China Institute of Precision Optical Engineering School of Physics Science and EngineeringTongji UniversityShanghai 200092China Shanghai Institute of Intelligent Science and Technology Tongji UniversityShanghai 200092China Shanghai Frontiers Science Center of Digital Optics Shanghai 200092China Shanghai Professional Technical Service Platform for Full-Spectrum and High-Performance Optical Thin Film Devices and Applications Shanghai 200092China Department of Electronic Science and Technology Tongji UniversityShanghai 201804China Department of Electrical and Computer Engineering National University of SingaporeSingapore 117583Singapore Institute of Acoustics School of Physics Science and EngineeringTongji UniversityShanghai 200092China

Exceptional point (EP) is a special degeneracy of non-Hermitian systems. One-dimensional transmission systems operating at EPs are widely studied and applied to chiral conversion and sensing. Lately, two-dimensional systems at EPs have been exploited for their exotic scattering features, yet so far been limited to only the non-visible waveband. Here, we report a universal paradigm for achieving a high-efficiency EP in the visible by leveraging interlayer loss to accurately control the interplay between the lossy structure and scattering lightwaves. A bilayer framework is demonstrated to reflect back the incident light from the left side ( | r_(−1) | >0.999) and absorb the incident light from the right side ( | r_(+1) | < 10^(–4)). As a proof of concept, a bilayer metasurface is demonstrated to reflect and absorb the incident light with experimental efficiencies of 88% and 85%, respectively, at 532 nm. Our results open the way for a new class of nanoscale devices and power up new opportunities for EP physics.

关键词： visible exceptional incident

来源：评论

学校读者我要写书评

暂无评论

SLSNet: Weakly-Supervised Skin Lesion Segmentation Network with Self-attentions 20th

SLSNet: Weakly-Supervised Skin Lesion Segmentation Network w...

引用

20th Pacific Rim International Conference on Artificial Intelligence, PRICAI 2023

作者： Pei, Songwen Huang, Junjie School of Optical-Electrical and Computer Engineering University of Shanghai for Science and Technology Shanghai200093 China State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China Engineering Research Center of Software/Hardware Co-design Technology and Application Ministry of Education East China Normal University Shanghai200062 China

ISBN: (纸本)9789819970247

computer-aided skin lesion segmentation with high precision is crucial to diagnose skin cancers in the early stage. However, the lack of pixel-level labels makes the skin lesion segmentation tasks challenging. To tackle this problem, a new weakly-supervised skin lesion segmentation network with self-attentions named SLSNet is proposed. SLSNet contains two modules and uses image-level labels as supervision information. One module named Intra-image Self-attention Seed Expansion (ISE) digs intra-image self-attentions with an expansion loss and a confidence loss to expand seed areas. The other module named Inter-image Affinity-based Noise Suppression (IAS) suppresses the noise pixels in attention maps via inter-image correlations. Extensive experiments conducted on ISIC-2017 dataset show that SLSNet achieves relatively high performance while reducing human labeling efforts. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2024.

关键词： Expansion

来源：评论

学校读者我要写书评

暂无评论

Encrypted Finite-Horizon Energy-to-Peak State Estimation for Time-Varying Systems Under Eavesdropping Attacks: Tackling Secrecy Capacity

引用

IEEE/CAA Journal of Automatica Sinica 2023年第4期10卷 985-996页

作者： Lei Zou Zidong Wang Bo Shen Hongli Dong Guoping Lu College of Information Science and Technology Donghua UniversityShanghai 201620 Engineering Research Center of Digitalized Textile and Fashion Technology Ministry of EducationShanghai 201620China College of Electrical Engineering and Automation Shandong University of Science and TechnologyQingdao 266590China Department of Computer Science Brunel University LondonUxbridgeMiddlesex UB83PHUK Intelligence Energy Research Institute Northeast Petroleum UniversityDaqing 163318 Heilongjiang Provincial Key Laboratory of Networking and Intelligent Control Northeast Petroleum UniversityDaqing 163318 Sanya Offshore Oil&Gas Research Institute Northeast Petroleum UniversitySanya 572024China School of Electrical Engineering Nantong UniversityNantong 226019China

This paper is concerned with the problem of finitehorizon energy-to-peak state estimation for a class of networked linear time-varying *** to the inherent vulnerability of network-based communication,the measurement signals transmitted over a communication network might be intercepted by potential *** avoid information leakage,by resorting to an artificial-noise-assisted method,we develop a novel encryption-decryption scheme to ensure that the transmitted signal is composed of the raw measurement and an artificial-noise term.A special evaluation index named secrecy capacity is employed to assess the information security of signal transmissions under the developed encryption-decryption *** purpose of the addressed problem is to design an encryptiondecryption scheme and a state estimator such that:1)the desired secrecy capacity is ensured;and 2)the required finite-horizon–l_(2)-l_(∞)performance is *** conditions are established on the existence of the encryption-decryption mechanism and the finite-horizon state ***,simulation results are proposed to show the effectiveness of our proposed encryption-decryption-based state estimation scheme.

关键词： Artificial-noise-assisted technique eavesdropping encryption-decryption scheme energy-to-peak state estimation finitehorizon state estimation

来源：评论

学校读者我要写书评

暂无评论

Learning-based adaptive optimal output regulation of linear and nonlinear systems:an overview

引用

Control Theory and technology 2022年第1期20卷 1-19页

作者： Weinan Gao Zhong-Ping Jiang Department of Mechanical and Civil Engineering College of Engineering and Science Florida Institute of Technology150 W.University Blvd.MelbourneFL32901USA Department of Electrical and Computer Engineering Tandon School of EngineeringNew York UniversitySix MetroTech CenterBrooklynNY11201USA

This paper reviews recent developments in learning-based adaptive optimal output regulation that aims to solve the problem of adaptive and optimal asymptotic tracking with disturbance *** proposed framework aims to bring together two separate topics—output regulation and adaptive dynamic programming—that have been under extensive investigation due to their broad applications in modern control *** this framework,one can solve optimal output regulation problems of linear,partially linear,nonlinear,and multi-agent systems in a data-driven *** will also review some practical applications based on this framework,such as semi-autonomous vehicles,connected and autonomous vehicles,and nonlinear oscillators.

关键词： Adaptive optimal output regulation Adaptive dynamic programming Reinforcement learning Learning-based 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：