检索结果-内蒙古大学图书馆

Incremental Online Learning of Randomized Neural Network with Forward Regularization

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wang, Junda Hu, Minghui Li, Ning Al-Ali, Abdulaziz Suganthan, Ponnuthurai Nagaratnam The Key Laboratory of System Control and Information Processing Ministry of Education of China China The Department of Automation Shanghai Jiao Tong University Shanghai200240 China The Shanghai Engineering Research Center of Intelligent Control and Management Shanghai200240 China The School of Electrical and Electronic Nanyang Technological University Singapore The KINDI Computing Research Center College of Engineering Qatar University Qatar

Online learning of deep neural networks suffers from challenges such as hysteretic non-incremental updating, increasing memory usage, past retrospective retraining, and catastrophic forgetting. To alleviate these drawbacks and achieve progressive immediate decision-making, we propose a novel Incremental Online Learning (IOL) process of Randomized Neural Networks (Randomized NN), a framework facilitating continuous improvements to Randomized NN performance in restrictive online scenarios. Within the framework, we further introduce IOL with ridge regularization (-R) and IOL with forward regularization (-F). -R generates stepwise incremental updates without retrospective retraining and avoids catastrophic forgetting. Moreover, we substituted -R with -F as it enhanced precognition learning ability using semi-supervision and realized better online regrets to offline global experts compared to -R during IOL. The algorithms of IOL for Randomized NN with -R/-F on non-stationary batch stream were derived respectively, featuring recursive weight updates and variable learning rates. Additionally, we conducted a detailed analysis and theoretically derived relative cumulative regret bounds of the Randomized NN learners with -R/-F in IOL under adversarial assumptions using a novel methodology and presented several corollaries, from which we observed the superiority on online learning acceleration and regret bounds of employing -F in IOL. Finally, our proposed methods were rigorously examined across regression and classification tasks on diverse datasets, which distinctly validated the efficacy of IOL frameworks of Randomized NN and the advantages of forward regularization. Copyright © 2024, The Authors. All rights reserved.

关键词：

Quantifying Climate Change Impacts on Renewable Energy Generation: A Super-Resolution Recurrent Diffusion Model

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Dong, Xiaochong Dan, Jun Sun, Yingyun Liu, Yang Zhang, Xuemin Mei, Shengwei State Key Laboratory of Power System Operation and Control Department of Electrical Engineering Tsinghua University Beijing100084 China College of Information Science & Electronic Engineering Zhejiang University Hangzhou310058 China State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources North China Electric Power University Beijing102206 China Department of Engineering King’s College London LondonWC2R 2LS United Kingdom

Driven by global climate change and the ongoing energy transition, the coupling between power supply capabilities and meteorological factors has become increasingly significant. Over the long term, accurately quantifying the power generation of renewable energy under the influence of climate change is essential for the development of sustainable power systems. However, due to interdisciplinary differences in data requirements, climate data often lacks the necessary hourly resolution to capture the short-term variability and uncertainties of renewable energy resources. To address this limitation, a super-resolution recurrent diffusion model (SRDM) has been developed to enhance the temporal resolution of climate data and model the short-term uncertainty. The SRDM incorporates a pre-trained decoder and a denoising network, that generates long-term, high-resolution climate data through a recurrent coupling mechanism. The high-resolution climate data is then converted into power value using the mechanism model, enabling the simulation of wind and photovoltaic (PV) power generation on future long-term scales. Case studies were conducted in the Ejina region of Inner Mongolia, China, using fifth-generation reanalysis (ERA5) and coupled model intercomparison project (CMIP6) data under two climate pathways: SSP126 and SSP585. The results demonstrate that the SRDM outperforms existing generative models in generating super-resolution climate data. Furthermore, the research highlights the estimation biases introduced when low-resolution climate data is used for power conversion. Copyright © 2024, The Authors. All rights reserved.

关键词： Clean energy

DiffRoad: Realistic and Diverse Road Scenario Generation for Autonomous Vehicle Testing

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhou, Junjie Wang, Lin Meng, Qiang Wang, Xiaofan Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai200240 China Department of Automation Shanghai Jiao Tong University School of Mechatronic Engineering and Automation Shanghai University School of Electrical and Electronic Engineering Shanghai Institute of Technology Shanghai201418 China Department of Civil and Environmental Engineering National University of Singapore Singapore117576 Singapore

Generating realistic and diverse road scenarios is essential for autonomous vehicle testing and validation. Nevertheless, owing to the complexity and variability of real-world road environments, creating authentic and varied scenarios for intelligent driving testing is challenging. In this paper, we propose DiffRoad, a novel diffusion model designed to produce controllable and high-fidelity 3D road scenarios. DiffRoad leverages the generative capabilities of diffusion models to synthesize road layouts from white noise through an inverse denoising process, preserving real-world spatial features. To enhance the quality of generated scenarios, we design the Road-UNet architecture, optimizing the balance between backbone and skip connections for high-realism scenario generation. Furthermore, we introduce a road scenario evaluation module that screens adequate and reasonable scenarios for intelligent driving testing using two critical metrics: road continuity and road reasonableness. Experimental results on multiple real-world datasets demonstrate DiffRoad’s ability to generate realistic and smooth road structures while maintaining the original distribution. Additionally, the generated scenarios can be fully automated into the OpenDRIVE format, facilitating generalized autonomous vehicle simulation testing. DiffRoad provides a rich and diverse scenario library for large-scale autonomous vehicle testing and offers valuable insights for future infrastructure designs that are better suited for autonomous vehicles. Copyright © 2024, The Authors. All rights reserved.

关键词： Automobile testing

Performance Optimization for Multicast Mm Wave MIMO Networks with Mobile Users

学校读者我要写书评

暂无评论

Performance Optimization for Multicast Mm Wave MIMO Networks...

IEEE International Conference on Communications Workshops, ICC

作者： Songling Zhang Mingzhe Chen Wenjing Zhang Zhaohui Yang Danpu Liu Zhilong Zhang Kai-Kit Wong Beijing Key Laboratory of Network System Architecture and Convergence Beijing University of Posts and Telecommunications Beijing China Department of Electrical and Computer Engineering Institute for Data Science and Computing University of Miami Coral Gables FL USA Zhejiang Lab Hangzhou China Zhejiang University Hangzhou China Department of Electronic and Electrical Engineering University College London London UK

ISBN: (数字)9798350304053

ISBN: (纸本)9798350304060

In this paper, the problem of maximizing the sum rate of mobile users in a multi-base station (BS) cooperative millimeter-wave (mmWave) multicast communication system is studied. In the considered model, due to the real-time mobility of users, the users being served by a given BS and beamforming of BSs and users are dynamic. Multiple BSs must cooperate to serve dynamic requests of multiple mobile users. This problem is posed as an optimization framework whose goal is to maximize the sum rate of all mobile users by jointly optimizing the number of users served by all BSs and beamforming matrices of both BSs and users. To solve this non-convex optimization problem, we first introduce a value decomposition based reinforcement learning (VD- RL) algorithm to determine the users to be served by each BS. Then, we use the block diagonalization method to obtain the fully digital transmit beamforming matrices of all BSs as well as the receive beamforming matrices of the users. Finally, a fast optimization algorithm is used to optimize the hybrid beamforming matrices of both BSs and users. Simulation results show that, the proposed algorithm can achieve up to 51 % gain in terms of the sum rate of all mobile users compared to baseline multi-agent algorithms.

关键词： Multicast algorithms Array signal processing Heuristic algorithms Simulation Conferences Multicast communication Real-time systems

Development and prospect of direct‐current circuit breaker in China

学校读者我要写书评

暂无评论

High Voltage 2021年第1期6卷 1-15页

作者： Weijiang Chen Rong Zeng Junjia He Yi Wu Xiaoguang Wei Taixun Fang Zhanqing Yu Zhao Yuan Yifei Wu Wandi Zhou Bing Yang Lu Qu STATE GRID Corporation of China BeijingChina Department of Electrical Engineering Key Laboratory of Control and Simulation of Power System and Generation EquipmentTsinghua UniversityBeijingChina School of Electric and Electronic Engineering Huazhong University of Science&TechnologyWuhanChina School of Electrical Engineering Xi'an Jiaotong UniversityXi'anChina Global Energy Interconnection Research Institute Co. LtdBeijingChina NR Electric Co. LtdNanjingChina

The direct‐current circuit breaker(DCCB)is the most ideal choice for DC fault isolation in DC *** a late start,China's research and development on the DCCB have made outstanding *** article provides a brief glance of current China's DCCB development *** begins by sorting out the technical route according to the topology of *** it systematically summarises both mechanical and hybrid DCCBs with focussing on the aspects of topology structure and principle,key technology and characteristics,prototype development and *** is apparent that Chinese scientists and engineers confronted the worldwide problem of large capacity DC breaking,and put forward a comprehensive solution which consists of an innovative topology structure based on coupled negative voltage circuit,breaking throughs on the key technologies such as highly controllable and reliable fault current commutation,millisecond‐level ultra‐fast and efficient electromagnetic repulsion mechanism,high tolerance and high stability power electronic switch,low residual voltage and fast response energy consumption device,*** article states that the world's first set of hybrid high‐voltage(HV)DCCB,and the first set of mechanical HV DCCB have been *** DCCBs will soon be deployed to the DC grids which have the highest voltage levels therefore require the strongest breaking *** achievements are leading the world in the development and application of *** article also discusses the overall development trends of DCCB in the areas of new topologies,key techno-logical breakthroughs and application scenarios,*** discussions serve as references for DCCB's future technological advancement and its ever‐expanding applications.

关键词： breaking breakthrough discussions

Quality Prediction of Injection Molding Process Using CNN and Parallel-Cascade LSTMs

学校读者我要写书评

暂无评论

Quality Prediction of Injection Molding Process Using CNN an...

第43届中国控制会议

作者： Yibo Zhang Dewei Li Yuanqiang Zhou Furong Gao Key Laboratory of System Control and Information Processing Shanghai Jiao Tong University College of Electronic and Information Engineering Tongji University Department of Chemical and Biological Engineering Hong Kong University of Science and Technology Clear Water Bay KowloonHong Kong and the Guangzhou HKUST Fok Ying Tung Research Institute

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

Quality prediction of plastic products has always been an important research topic in the injection molding production process. However, existing quality prediction methods struggle to handle both high-frequency data and statistical data generated during the injection molding production process. This paper introduces a novel quality prediction model for injection molding production, utilizing a combination of Convolutional Neural Networks(CNN) and Parallel-Cascade Long Short-Term Memory(PCLSTM) networks. The PCLSTM network is designed to handle the complexities of high-frequency data in injection molding,overcoming the limitations of traditional LSTM methods in processing long sequence data. By segmenting data into stages and utilizing a cascade mechanism, the PCLSTM architecture efficiently captures important temporal dynamics. Additionally, the CNN network is designed to extract statistical data features. The quality prediction results are obtained by fusing two types of data features and then passing them through a fully connected network. Experimental results on real production datasets show that the CNN-PCLSTM model outperforms existing models in prediction accuracy and training convergence speed.

关键词： LSTM CNN Quality Prediction Injection Molding Process

Pathological axonal enlargement in connection with amyloidosis,lysosome destabilization,and bleeding is a major defect in Alzheimer’s disease

学校读者我要写书评

暂无评论

Neural Regeneration Research 2026年第2期21卷 790-799页

作者： Hualin Fu Jilong Li Chunlei Zhang Guo Gao Qiqi Ge Xinping Guan Daxiang Cui Institute of Nano Biomedicine and Engineering School of Sensing Science and EngineeringSchool of Electronic Information and Electrical EngineeringShanghai Jiao Tong UniversityShanghaiChina Institute of Marine Equipment Shanghai Jiao Tong UniversityShanghaiChina National Center for Translational Medicine Shanghai Jiao Tong UniversityShanghaiChina Department of Automation Shanghai Jiao Tong UniversityShanghaiChina The Key Laboratory of System Control and Information Processing Ministry of EducationShanghaiChina

Alzheimer’s disease is a multi-amyloidosis disease characterized by amyloid-βdeposits in brain blood vessels,microaneurysms,and senile *** amyloid-βdeposition affects axon pathology has not been examined *** used immunohistochemistry and immunofluorescence staining to analyze the forebrain tissue slices of Alzheimer’s disease *** axonal amyloidosis with distinctive axonal enlargement was observed in patients with Alzheimer’s *** average,amyloid-β-positive axon diameters in Alzheimer’s disease brains were 1.72 times those of control brain ***,axonal amyloidosis was associated with microtubule-associated protein 2 reduction,tau phosphorylation,lysosome destabilization,and several blood-related markers,such as apolipoprotein E,alpha-hemoglobin,glycosylated hemoglobin type A1C,and *** destabilization in Alzheimer’s disease was also clearly identified in the neuronal soma,where it was associated with the co-expression of amyloid-β,Cathepsin D,alpha-hemoglobin,actin alpha 2,and collagen type *** suggests that exogenous hemorrhagic protein intake influences neural lysosome ***,the data showed that amyloid-β-containing lysosomes were 2.23 times larger than control ***,under rare conditions,axonal breakages were observed,which likely resulted in Wallerian *** summary,axonal enlargement associated with amyloidosis,micro-bleeding,and lysosome destabilization is a major defect in patients with Alzheimer’s *** finding suggests that,in addition to the well-documented neural soma and synaptic damage,axonal damage is a key component of neuronal defects in Alzheimer’s disease.

关键词： Alzheimer’s disease amyloid-β amyloidosis axonal enlargement hemoglobin hemorrhage lysosome destabilization neuropil thread tau Wallerian degeneration

AnyBipe: An End-to-End Framework for Training and Deploying Bipedal Robots Guided by Large Language Models

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Yao, Yifei He, Wentao Gu, Chenyu Du, Jiaheng Tan, Fuwei Zhu, Zhen Lu, Junguo All authors are with Machine Vision and Autonomous System Laboratory Department of Automation School of Electrical Information and Electronic Engineering Shanghai Jiao Tong University Shanghai China Key Laboratory of System Control and Information Processing Ministry of Education of China China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai200240 China University of Michigan Shanghai Jiao Tong University Joint Institute Shanghai Jiao Tong University Shanghai China

Training and deploying reinforcement learning (RL) policies for robots, especially in accomplishing specific tasks, presents substantial challenges. Recent advancements have explored diverse reward function designs, training techniques, simulation-to-reality (sim-to-real) transfers, and performance analysis methodologies, yet these still require significant human intervention. This paper introduces an end-to-end framework for training and deploying RL policies, guided by Large Language Models (LLMs), and evaluates its effectiveness on bipedal robots. The framework consists of three interconnected modules: an LLM-guided reward function design module, an RL training module leveraging prior work, and a sim-to-real homomorphic evaluation module. This design significantly reduces the need for human input by utilizing only essential simulation and deployment platforms, with the option to incorporate human-engineered strategies and historical data. We detail the construction of these modules, their advantages over traditional approaches, and demonstrate the framework’s capability to autonomously develop and refine controlling strategies for bipedal robot locomotion, showcasing its potential to operate independently of human intervention. Copyright © 2024, The Authors. All rights reserved.

关键词： Reinforcement learning

Deep Learning-based Fire Alarmer for Underground Power Cable Tunnel with Multiple Information Sources

学校读者我要写书评

暂无评论

Deep Learning-based Fire Alarmer for Underground Power Cable...

International Conference on Intelligent systems Applications to Power systems (ISAP)

作者： Jinshuo Jia Zhengwen Huang Yuhang Xia Guoquan Li Yujie Zhang Laurentiu Lipan Ioana Pisica School of Communications and Information Engineering Chongqing University of Posts and Telecommunications Chongqing China Theme of System Optimization BRUNEL-CQUPT Innovation Centre Chongqing China Department of Electronic and Electrical Engineering Brunel University London U.K Engineering Project Management Center Chengdu Power Supply Company of Sichuan Electric Power Company Chengdu China Department of Electric Power Systems University Politehnica of Bucharest Bucharest Romania

ISBN: (数字)9798331531751

ISBN: (纸本)9798331531768

Regarding the issue of risk management and control of tunnel cable fires, a cable fire management and control scheme based on Gene Expression Programming (GEP) has been proposed. This scheme comprises three stages: firstly, a cable skin temperature rise model based on load variations has been established; secondly, a cable fire monitoring model based on YOLOv5 has been trained; and finally, a cable fire management and control scheme that integrates GEP has been proposed. Through the fusion analysis of data from the first two stages, the dynamic adjustment of the weight output of different parts is achieved to achieve automatic recognition of optimal states. Through experiments and analysis, the temperature variation patterns of cables under various loads and environmental conditions have been demonstrated, as well as the recognition performance of the fire monitoring model based on YOLOv5, and a dynamic planning scheme for the GEP model has been provided.

关键词： Adaptation models Analytical models Temperature distribution Power cables Computational modeling Predictive models Skin Data models Monitoring Load modeling