检索结果-内蒙古大学图书馆

Reconfigurable and Multiband Graphene THz Antenna Design Optimized Using Machine Learning

学校读者我要写书评

暂无评论

Reconfigurable and Multiband Graphene THz Antenna Design Opt...

2024 International Conference on Advanced Technologies for Communications, ATC 2024

作者： Patel, Shobhit K. Agravat, Dhruvik Nguyen, Tien Dung Nguyen, Thi Thanh Kieu Nguyen, Truong Khang Marwadi University Department of Computer Engineering Gujrat Rajkot360003 India Marwadi University Department of Physics Gujrat Rajkot360003 India Electric Power University Faculty of Control and Automation Ha Noi Viet Nam Binh Thuan College Faculty of Engineering Binh Thuan Viet Nam School of Technology Van Lang University Faculty of Information Technology Ho Chi Minh City Viet Nam

ISBN: (纸本)9798350353983

This study investigates the concept of multiband graphene THz antennas. We investigate the advantages of graphene in THz antenna applications with standard materials. Using a graphene strip, we built a multiband GSSPlp-MIMO antenna in this study that achieves triple operating frequencies of 7.64 THz, 9.57 THz, and 10.90 THz. The reflection response (S11) of -29.2135 dB, which shows excellent signal confinement within the antenna, was greatly improved upon the inclusion of graphene. Superior impedance matching was the trade-off for this, even if the gain decreased slightly (10.41 dB) in comparison to the antenna without graphene (12.30 dB). The parameters are optimized using machine learning, yielding a maximum accuracy (R2) of 0.996622 and a mean square error of 5.3934 ×10-5. This indicates that high-performance terahertz antennas that balance gain and effective signal transmission can be designed using graphene. The antenna's capacity to handle multiple bands makes it ideal for future ultra-broadband wireless communication systems. This results in higher data transfer rates and supports emerging technologies such as 6G and beyond. © 2024 IEEE.

关键词： Data transfer rates

Reinforcement Learning of Threshold Policy for Dynamic Wireless Charging with Distributed Energy Resources

学校读者我要写书评

暂无评论

Reinforcement Learning of Threshold Policy for Dynamic Wirel...

IEEE General Meeting Power& Energy Society

作者： Liangliang Hao Yunjian Xu Lang Tong Department of Control Science and Engineering Shandong University Jinan China Department of Mechanical and Automation Engineering Chinese University of Hong Kong Hong Kong SAR School of Electrical and Computer Engineering Cornell University Ithaca NY USA

ISBN: (数字)9798350381832

ISBN: (纸本)9798350381849

We study dynamic wireless charging for Electric Vehicles (EVs) on electrified highways where EVs are charged while in motion. Our focus is on the cost-minimization scheduling of EV charging based on EV mobility states, charging demands, travel plans, available distributed renewables, and power constraints of the distribution systems. As a Markov decision process with uncountable action space that couples stochasticities in charging demands, vehicle mobilities, and renewable resources, standard dynamic programming and approximation approaches face exponentially growing complexity and modeling uncertainties. By exploiting the linear network topology when EVs are on a highway, this work reveals a threshold structure of the optimal charging policy and develops a reinforcement learning approach for uncertainty models, resulting in a scalable EV charging solution. The proposed EV charging algorithm outperforms multiple charging benchmarks by 4.7-52.4% cost reduction.

关键词： Road transportation Renewable energy sources Uncertainty Costs Markov decision processes Inductive charging Dynamic scheduling Electric vehicle charging Distributed power generation Vehicle dynamics

Channel-Aware Throughput Maximization for Cooperative Data Fusion in CAV

学校读者我要写书评

暂无评论

arXiv 2024年

作者： An, Haonan Fang, Zhengru Zhang, Yuang Hu, Senkang Chen, Xianhao Xu, Guowen Fang, Yuguang Department of Computer Science City University of Hong Kong Hong Kong Department of Automation Tsinghua University China Department of Electrical and Electronic Engineering The University of Hong Kong Hong Kong

Connected and autonomous vehicles (CAVs) have garnered significant attention due to their extended perception range and enhanced sensing coverage. To address challenges such as blind spots and obstructions, CAVs employ vehicle-to-vehicle (V2V) communications to aggregate sensory data from surrounding vehicles. However, cooperative perception is often constrained by the limitations of achievable network throughput and channel quality. In this paper, we propose a channel-aware throughput maximization approach to facilitate CAV data fusion, leveraging a self-supervised autoencoder for adaptive data compression. We formulate the problem as a mixed integer programming (MIP) model, which we decompose into two sub-problems to derive optimal data rate and compression ratio solutions under given link conditions. An autoencoder is then trained to minimize bitrate with the determined compression ratio, and a fine-tuning strategy is employed to further reduce spectrum resource consumption. Experimental evaluation on the OpenCOOD platform demonstrates the effectiveness of our proposed algorithm, showing more than 20.19% improvement in network throughput and a 9.38% increase in average precision (AP@IoU) compared to state-of-the-art methods, with an optimal latency of 19.99 ms. © 2024, CC BY.

关键词： Integer programming

Demonstration-Guided Reinforcement Learning with Efficient Exploration for Task automation of Surgical Robot

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Huang, Tao Chen, Kai Li, Bin Liu, Yun-Hui Dou, Qi The Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong The Department of Mechanical and Automation Engineering The Chinese University of Hong Kong Hong Kong

Task automation of surgical robot has the potentials to improve surgical efficiency. Recent reinforcement learning (RL) based approaches provide scalable solutions to surgical automation, but typically require extensive data collection to solve a task if no prior knowledge is given. This issue is known as the exploration challenge, which can be alleviated by providing expert demonstrations to an RL agent. Yet, how to make effective use of demonstration data to improve exploration efficiency still remains an open challenge. In this work, we introduce Demonstration-guided EXploration (DEX), an efficient reinforcement learning algorithm that aims to overcome the exploration problem with expert demonstrations for surgical automation. To effectively exploit demonstrations, our method estimates expert-like behaviors with higher values to facilitate productive interactions, and adopts non-parametric regression to enable such guidance at states unobserved in demonstration data. Extensive experiments on 10 surgical manipulation tasks from SurRoL, a comprehensive surgical simulation platform, demonstrate significant improvements in the exploration efficiency and task success rates of our method. Moreover, we also deploy the learned policies to the da Vinci Research Kit (dVRK) platform to show the effectiveness on the real robot. Code is available at https://***/med-air/DEX. Copyright © 2023, The Authors. All rights reserved.

关键词： Demonstrations

Lie-algebra Adaptive Tracking Control for Rigid Body Dynamics

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Tang, Jiawei Li, Shilei Shi, Ling The Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Clear Water Bay Hong Kong The School of Automation Beijing Institute of Technology China

Adaptive tracking control for rigid body dynamics is of critical importance in control and robotics, particularly for addressing uncertainties or variations in system model parameters. However, most existing adaptive control methods are designed for systems with states in vector spaces, often neglecting the manifold constraints inherent to robotic systems. In this work, we propose a novel Lie-algebra-based adaptive control method that leverages the intrinsic relationship between the special Euclidean group and its associated Lie algebra. By transforming the state space from the group manifold to a vector space, we derive a linear error dynamics model that decouples model parameters from the system state. This formulation enables the development of an adaptive optimal control method that is both geometrically consistent and computationally efficient. Extensive simulations demonstrate the effectiveness and efficiency of the proposed method. We have made our source code publicly available to the community to support further research and collaboration1 © 2025, CC BY.

关键词： Adaptive control systems

Optimizing solar PV systems using fuzzy logic for Climate-Resilient Healthcare infrastructure in Kyrgyzstan

学校读者我要写书评

暂无评论

Green Technologies and Sustainability

Green Technologies and Sustainability 2025年第3期3卷

作者： Guler, Nivine Hazem, Zied Ben Gunes, Ali Department of Computer Science University of Central Asia Bishkek Kyrgyzstan Automation and Sustainability Research Centre (ASRC) Department of Mechatronics Engineering College of Engineering (COE) University of Technology Bahrain Salmabad Bahrain Department of Computer Engineering Istanbul Aydin University Istanbul Türkiye

Stable power infrastructure and access to electricity for hospital and clinic infrastructures remains a challenge in most rural and climatically sensitive areas. Though photovoltaic (PV) modules are commonly used for renewable energy generation, conventional methods are generally based on fixed tilt angles or high mathematical modeling techniques. They often do not consider varying weather conditions as well as uncertainties in the surrounding environment and therefore have poor energy capture efficiency and higher operational nonlinearities. To fill this gap, this study develops an intelligent MPPT algorithm that applies the FLC. FLC was chosen because of its ability to control systems having nonlinearities and adverse operating environment without necessarily requiring robust computational power. These tilt angles are proposed for seasonal adjustment to ensure high efficiency, more importantly for the healthcare facilities in Naryn area in Kyrgyzstan that strongly depends on stable power sources. Simulation data also show that the FLC-based model has 20% more power compared with fixed-angle system and approximately 15% compared with traditional MPPT technique. Also, the proposed scheme showed 3% prediction error when checked with the PVWatts calculator. Moreover, the proposed system avoids large computational complexity and miniaturization, which makes it more realistic in practice. Besides contributing to the MPPT optimization field, this research also helps in meeting the energy requirement of healthcare facilities present in remote locations. The results fall under SDG 3 — Good Health and Well-being and SDG 13 — Climate Action, highlighting the benefits of using intelligent solar PV systems to create climate adaptive health facilities. © 2025 The Authors

关键词： Fill factor MPPT Photovoltaic system Tilt angle

End-to-End Learning of Deep Visuomotor Policy for Needle Picking

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Lin, Hongbin Li, Bin Chu, Xiangyu Dou, Qi Liu, Yunhui Au, Kwok Wai Samuel Department of Mechanical and Automation Engineering The Chinese University of Hong Kong Hong Kong Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong

Needle picking is a challenging manipulation task in robot-assisted surgery due to the characteristics of small slender shapes of needles, needles’ variations in shapes and sizes, and demands for millimeter-level control. Prior works, heavily relying on the prior of needles (e.g., geometric models), are hard to scale to unseen needles’ variations. In this paper, we present the first end-to-end learning method to train deep visuomotor policy for needle picking. Concretely, we propose DreamerfD to maximally leverage demonstrations to improve the learning efficiency of a state-of-the-art model-based reinforcement learning method, DreamerV2;Since Variational Auto-Encoder (VAE) in DreamerV2 is difficult to scale to high-resolution images, we propose Dynamic Spotlight Adaptation to represent control-related visual signals in a low-resolution image space;Virtual Clutch is also proposed to reduce performance degradation due to significant error between prior and posterior encoded states at the beginning of a rollout. We conducted extensive experiments in simulation to evaluate the performance, robustness, in-domain variation adaptation, and effectiveness of individual components of our method. Our method, trained by 8k demonstration timesteps and 140k online policy timesteps, can achieve a remarkable success rate of 80%. Furthermore, our method effectively demonstrated its superiority in generalization to unseen in-domain variations including needle variations and image disturbance, highlighting its robustness and versatility. Codes and videos are available at https://***/view/DreamerfD. © 2023, CC BY.

关键词： Needles

Model Predictive Control Strategy for Three-Level Quasi-Z-Source Inverters

学校读者我要写书评

暂无评论

Model Predictive Control Strategy for Three-Level Quasi-Z-So...

Power Electronics and Power System Conference (PEPSC)

作者： Ji Zhang Tung-Chin Pan Department of Electronic and Computer Engineering National Taiwan University of Science and Technology Taipei Taiwan Department of Electric and Automation Engineering Changshu Institute of Technology Suzhou China

Model predictive control(MPC) strategy is pay more attention in power electronics applications. Inductor current, output current and capacitor voltage are selected as the factor of cost function for the proposed MPC. The discrete-time model of the MPC is designed to calculate inductor current, output current and capacitor voltage at next sampling time in each switching state, regulate the shoot-through duty cycle, and select the following switching vector for the Quasi-Z-Source inverter $(\text{qZSI})$ . The optimal switching vector is decided, which avoids the traditional complicated modulated process. The MPC strategy is designed to can achieve desired dynamic performance for the $\text{qZSI}$ , is beyond the traditional proportional-integral(PI)-type method.

关键词：

Learning a Typhoon Bayesian Network Structure from Natural Language Reports 5th

学校读者我要写书评

暂无评论

Learning a Typhoon Bayesian Network Structure from Natural...

5th IFIP TC 12 International Conference on Intelligence Science, ICIS 2022

作者： Yao, Zhangrui Chen, Junhan Pan, Yinghui Zeng, Yifeng Ma, Biyang Ming, Zhong Department of Automation and Xiamen Key Laboratory of Big Data Intelligent Analysis and Decision-Making Xiamen University Xiamen China College of Computer Science and Software Engineering Shenzhen University Shenzhen China Department of Computer and Information Sciences Northumbria University Newcastle upon Tyne United Kingdom School of Computer Science and Engineering Minnan Normal University Zhangzhou China

ISBN: (纸本)9783031149023

Given the huge toll caused by natural disasters, it is critically important to develop an effective disaster management and emergency response technique. In this article, we investigate relationships between typhoon-related variables and emergency response from natural language (NL) reports. A major challenge is to exploit typhoon state information for typhoon contingency plan generation, especially from unstructured text data based on NL input. To tackle this issue, we propose a novel framework for learning typhoon Bayesian network structures (FLTB), which can extract typhoon state information from unstructured NL, mine inter-information causal relationships and then generate Bayesian networks. We first extract information about typhoon states through NL processing (NLP) techniques, and then analyze typhoon reports by designing heuristic rules to identify causal relationships between states. We leverage these features to improve the learned structures and provide user-interaction mechanisms to finalize Bayesian networks. We evaluate the performance of our framework on real-world typhoon datasets and develop the Bayesian networks based typhoon emergency response systems. © 2022, IFIP International Federation for Information Processing.

关键词： Bayesian networks