检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Wang, Vivienne Huiling Wang, Tinghuai Yang, Wenyan Kämäräinen, Joni-Kristian Pajarinen, Joni Department of Electrical Engineering and Automation Aalto University Finland Huawei Helsinki Research Center Finland Computing Sciences Tampere University Finland

In goal-conditioned hierarchical reinforcement learning (HRL), a high-level policy specifies a subgoal for the low-level policy to reach. Effective HRL hinges on a suitable subgoal representation function, abstracting state space into latent subgoal space and inducing varied low-level behaviors. Existing methods adopt a subgoal representation that provides a deterministic mapping from state space to latent subgoal space. Instead, this paper utilizes Gaussian Processes (GPs) for the first probabilistic subgoal representation. Our method employs a GP prior on the latent subgoal space to learn a posterior distribution over the subgoal representation functions while exploiting the long-range correlation in the state space through learnable kernels. This enables an adaptive memory that integrates long-range subgoal information from prior planning steps allowing to cope with stochastic uncertainties. Furthermore, we propose a novel learning objective to facilitate the simultaneous learning of probabilistic subgoal representations and policies within a unified framework. In experiments, our approach outperforms state-of-the-art baselines in standard benchmarks but also in environments with stochastic elements and under diverse reward conditions. Additionally, our model shows promising capabilities in transferring low-level policies across different tasks. © 2024, CC BY.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Probabilistic subgoal representations for hierarchical reinforcement learning 24

Probabilistic subgoal representations for hierarchical reinf...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Vivienne Huiling Wang Tinghuai Wang Wenyan Yang Joni-Kristian Kämäräinen Joni Pajarinen Department of Electrical Engineering and Automation Aalto University Finland Huawei Helsinki Research Center Finland Computing Sciences Tampere University Finland

关键词：

来源：评论

学校读者我要写书评

暂无评论

Real-time behavior recognition of animal: an IoT-based system design using acceleration data

引用

Multimedia Tools and Applications 2024年 1-26页

作者： Tran, Duc-Nghia Manh, Do Viet Van Thanh, Pham Shankar, A. Achyut Joshi, Kireet Tran, Duc-Tan Institute of Information Technology Vietnam Academy of Science and Technology Hanoi Viet Nam University of Fire Prevention and Fighting Hanoi100000 Viet Nam Department of Cyber Systems Engineering WMG University of Warwick CoventryCV74AL United Kingdom Department of CSE University Centre for Research & ampDevelopment Chandigarh University Punjab Mohali140413 India School of Computer Science Engineering Lovely Professional University Punjab Phagwara144411 India Department of Computer Science and Engineering Graphic Era Deemed to be University Dehradun248002 India Center of Research Impact and Outcome Chitkara University Punjab Chandigarh India Department of Computer Science & amp Engineering Graphic Era Deemed to be University Uttarakhand Dehradun248002 India Faculty of Electrical and Electronic Engineering Phenikaa University Hanoi12116 Viet Nam

By analyzing large amounts of animal behavior data, humans can assess cattle’s condition. It leads to research and development a field using accelerometers and machine learning algorithms to ‘study’ behavior from acceleration data. It is challenging to analyze animal behavior due to the activity complexity. For example, acceleration data of some cow behaviors (e.g., feeding and standing) are similar if these behaviors contain similar gestures. In practical, real-time applications even bring more challenging since it is necessary to minimize a data window for behavior consideration. Using short data window often reduces the performance of classification algorithms. This study proposes a new solution for the mentioned challenges by combining neck-mounted and leg-mounted accelerometers, then using the vector of the dynamic body acceleration (VeDBA) and Mean features of synchronized acceleration data for the Decision Tree algorithm. The proposed method is demonstrated that performs well (0.94 accuracy, 0.91 sensitivity, 0.90 positive predictive value) within a low computational complexity algorithm and short data window (3-second data window, at the rate of one sample per second). It is particularly suited for the case of a real-time IoT-based system. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Accelerometers

来源：评论

学校读者我要写书评

暂无评论

A Digital Decoupling Control Scheme for Synchronous-Frame Current Regulators in High-Speed Motor Drives

A Digital Decoupling Control Scheme for Synchronous-Frame Cu...

引用

International Conference on electrical Machines and Systems (ICEMS)

作者： Daniel L. Mon-Nzongo Shengyu Lin Paul G. Ipoum-Ngome Chunyan Lai Department of Electrical and Computer Engineering Concordia University Canada College of Electrical Engineering and Automation Fuzhou University Fuzhou China Research and Development Department Peal Electric China

This paper introduces a digital current regulator with a dynamic decoupling scheme for three-phase AC motor drives that operate under low sampling to fundamental frequency ratios for high-speed motor drives. Cross-coupling terms introduced by the motor and inverter models in synchronous-frame are the main cause of poor dynamic performances. These disturbances cannot be mitigated due to the bandwidth frequency limitation under high-speed operations. This paper introduces a decoupling matrix emulated in the digital domain aiming to dynamically cancel these effects. In addition, two compensation methods are proposed to reduce the discretization due to low sampling ratio. The proposed approach allows the dynamic cancellation of the plant poles that change their location depending on the synchronous speed. The time delay effect of the plant is compensated using the phase-lead compensation method. Simulation results discussed in this paper demonstrated good decoupling performances with improved dynamic responses.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fractional order adaptive robust formation control of multiple quad-rotor UAVs with parametric uncertainties and wind disturbances

引用

Chinese Journal of Aeronautics 2022年第8期35卷 204-220页

作者： Nasim ULLAH Yasir MEHMOOD Jawad ASLAM Shaoping WANG Khamphe PHOUNGTHONG Environmental Assessment and Technology for Hazardous Waste Management Research Center Faculty of Environmental ManagementPrince of Songkla UniversitySongkhla 90112Thailand Department of Electrical Engineering College of Engineering Taif UniversityAl-HawiyahTaif P.O Box:888Kingdom of Saudi Arabia School of Mechanical and Manufacturing Engineering NUSTIslamabad 44000 Pakistan School of Automation Science and Electrical Engineering Beihang UniversityBeijing 100083China Faculty of Environmental Management Prince of Songkla UniversitySongkla90112Thailand

In recent times,multiple Unmanned Aerial Vehicles(UAVs)are being widely utilized in several areas of applications such as agriculture,surveillance,disaster management,search and rescue *** of robustness of applied control schemes determines how accurate a swarm of UAVs accomplish group *** and trajectory tracking controllers are required for the swarm of multiple *** like external environmental effects,parametric uncertainties and wind gusts make the controller design process as a challenging *** article proposes fractional order formation and trajectory tacking controllers for multiple quad-rotors using Super Twisting Sliding Mode Control(STSMC)*** compensate the effects of the disturbances due to parametric uncertainties and wind gusts,Lyapunov function based adaptive controllers are ***,Lyapunov theorem is used to guarantee the stability of the proposed *** types of controllers,namely fixed gain STSMC and fractional order Adaptive Super Twisting Sliding Mode Control(ASTSMC)methods are tested for the swarm of UAVs by performing the numerical simulations in MATLAB/Simulink *** the presented results,it is verified that in presence of wind disturbances and parametric uncertainties,the proposed fractional order ASTSMC technique showed improved robustness as compared to the fixed gain STSMC and integer order ASTSMC.

关键词： Adaptive robust control Fractional order control Nonlinear control Quad-rotor UAVs Swarm formation control

来源：评论

学校读者我要写书评

暂无评论

Modified Integrated Regulator Strategy for High Density Interleaved DC-DC Converter with Enhancement Conversion Ratio and Losses Mitigation

Modified Integrated Regulator Strategy for High Density Inte...

引用

Annual Conference of Industrial Electronics Society

作者： Mohsen Karimi Mohammad Farsijani Mohsin Jamil Iranian Research Institute for Electrical Engineering Academic Center for Education Culture and Research Tehran Iran Department of Electrical and Computer Engineering and Applied Science Memorial University of Newfoundland St John’s Canada Department of Electrical and Computer Engineering University of Illinois Chicago Chicago IL USA

ISBN: (数字)9781665464543

ISBN: (纸本)9781665464550

The high power DC-DC converters are widely used in industrial and renewable application due to variable dc source. For this purpose, the interleaved dual cascade DCDC converter (IDCC) is the most advantageous due to its and low ripple with high boosting factor and high potential efficiency. To optimize IDCC performance, an integrated regulator ensures equal current sharing between levels, with voltage cascading to boost the output voltage. The integrated regulator technique (IRT) is designed to control all regulators at each level to maintain an optimal switching period, thereby reducing switching dissipation and decreasing ripple. Its ability to handle high voltages conversion with a consistent low ripple output and modular structure enhance performance. It has demonstrated a 1.5% current ripple and up to 94% efficiency in high-power density applications. Simulation and experimental results of a 2 kW prototype validate the IRT's performance.

关键词： Industrial electronics Renewable energy sources Regulators Prevention and mitigation Prototypes Switches DC-DC power converters Control systems Voltage control Stress

来源：评论

学校读者我要写书评

暂无评论

Circularly Polarized Metasurface Superstrate Slot Antenna Array Fed by PRGW

Circularly Polarized Metasurface Superstrate Slot Antenna Ar...

引用

Antennas and Propagation & USNC/URSI National Radio Science Meeting

作者： Mahboubeh Taraji Elham Baladi Marco A. Antoniades Department of Electrical Computer and Biomedical Engineering Toronto Metropolitan University Toronto ON Canada Department of Electrical Engineering Poly-Grames Research Center Polytechnique Montreal Montreal QC Canada

ISBN: (数字)9798350369908

ISBN: (纸本)9798350369915

We present a wideband circularly-polarized 2-by-2 slot antenna array for X-band applications. The feeding network of the antenna is designed using printed ridge gap waveguide (PRGW) technology as a magnetic ground to suppress surface wave propagation and excite a quasi- TEM wave in the air along the ridge. Then, a single layer linear-to-circular polarization converter metasurface is designed and placed on top of the slot antenna array. The unit-cell of the converter contains two identical metallic layers with a combination of a connected Jerusalem cross (JC) and two parasitically coupled LC resonators. The antenna has a compact structure with a low profile, a −10-dB impedance bandwidth of 26% from 8.6 to 11.2 GHz, a 3-dB axial ratio bandwidth of 14% from 9.3 to 10.7 GHz, and an average gain of 13 dBi.

关键词： Surface impedance Slot antennas Surface waves Simulation Metasurfaces Broadband antennas Impedance

来源：评论

学校读者我要写书评

暂无评论

Improved Dictionary Learning for FMRI Data Analysis Capturing Common and Individual Activation Maps 58

Improved Dictionary Learning for FMRI Data Analysis Capturin...

引用

58th Asilomar Conference on Signals, Systems and computers, ACSSC 2024

作者： Xu, Shuai Jin, Rui Kim, Seung-Jun Adali, Tülay Calhoun, Vince D. University of Maryland Baltimore County Department of Computer Science and Electrical Engineering United States Tri-institutional Center for Translational Research in Neuroimaging and Data Science Georgia State University Georgia Institute of Technology United States Emory University United States

ISBN: (纸本)9798350354058

A dictionary learning (DL)-based method for mul-tisubject functional magnetic resonance imaging (fMRI) data analysis is proposed. The method can incorporate group attributes to find the neural activation maps that are common across groups as well as those that are explanatory of the group differences. The key contribution is to significantly improve the map estimation performance by mitigating undesirable local optima obtained from a supervised DL formulation for fMRI data analysis. We introduce two novel ideas, namely, developing a variant of Fisher's discriminant cost, which is imposed on the non-discriminative features, and optimally permuting the dictionary and the sparse factor such that the solution is not trapped to unwanted local optima. Preliminary tests on synthetic and real data sets verify the effectiveness of the proposed approach. © 2024 IEEE.

关键词： Functional neuroimaging

来源：评论

学校读者我要写书评

暂无评论

What Improves the Generalization of Graph Transformers? A Theoretical Dive into the Self-attention and Positional Encoding 41

What Improves the Generalization of Graph Transformers? A Th...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Li, Hongkang Wang, Meng Ma, Tengfei Liu, Sijia Zhang, Zaixi Chen, Pin-Yu Department of Electrical Computer and System Engineering Rensselaer Polytechnic Institute TroyNY United States Department of Biomedical Informatics Stony Brook University Stony BrookNY United States Department of Computer Science and Engineering Michigan State University East LansingMI United States MIT-IBM Watson AI Lab IBM Research MA United States Department of Computer Science and Engineering University of Science and Technology of China Anhui Hefei China IBM Thomas J. Watson Research Center Yorktown HeightsNY United States

Graph Transformers, which incorporate self-attention and positional encoding, have recently emerged as a powerful architecture for various graph learning tasks. Despite their impressive performance, the complex non-convex interactions across layers and the recursive graph structure have made it challenging to establish a theoretical foundation for learning and generalization. This study introduces the first theoretical investigation of a shallow Graph Transformer for semi-supervised node classification, comprising a self-attention layer with relative positional encoding and a two-layer perceptron. Focusing on a graph data model with discriminative nodes that determine node labels and non-discriminative nodes that are class-irrelevant, we characterize the sample complexity required to achieve a desirable generalization error by training with stochastic gradient descent (SGD). This paper provides the quantitative characterization of the sample complexity and number of iterations for convergence dependent on the fraction of discriminative nodes, the dominant patterns, and the initial model errors. Furthermore, we demonstrate that self-attention and positional encoding enhance generalization by making the attention map sparse and promoting the core neighborhood during training, which explains the superior feature representation of Graph Transformers. Our theoretical results are supported by empirical experiments on synthetic and real-world benchmarks. Copyright 2024 by the author(s)

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Interactive AI with Retrieval-Augmented Generation for Next Generation Networking

arXiv

引用

arXiv 2024年

作者： Zhang, Ruichen Du, Hongyang Liu, Yinqiu Niyato, Dusit Kang, Jiawen Sun, Sumei Shen, Xuemin Poor, H. Vincent The School of Computer Science and Engineering Nanyang Technological University Singapore The School of Automation Guangdong University of Technology China The Institute for Infocomm Research Agency for Science Technology and Research Singapore The Department of Electrical and Computer Engineering University of Waterloo Canada The Department of Electrical and Computer Engineering Princeton University PrincetonNJ08544 United States

With the advance of artificial intelligence (AI), the emergence of Google Gemini and OpenAI Q* marks the direction towards artificial general intelligence (AGI). To implement AGI, the concept of interactive AI (IAI) has been introduced, which can interactively understand and respond not only to human user input but also to dynamic system and network conditions. In this article, we explore an integration and enhancement of IAI in networking. We first comprehensively review recent developments and future perspectives of AI and then introduce the technology and components of IAI. We then explore the integration of IAI into the next-generation networks, focusing on how implicit and explicit interactions can enhance network functionality, improve user experience, and promote efficient network management. Subsequently, we propose an IAI-enabled network management and optimization framework, which consists of environment, perception, action, and brain units. We also design the pluggable large language model (LLM) module and retrieval augmented generation (RAG) module to build the knowledge base and contextual memory for decision-making in the brain unit. We demonstrate the effectiveness of the framework through case studies. Finally, we discuss potential research directions for IAI-based networks. © 2024, CC BY.

关键词： Decision making

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：