检索结果-内蒙古大学图书馆

Detecting lithium plating dynamics in a solid-state battery with operando X-ray computed tomography using machine learning

引用

npj Computational Materials 2023年第1期9卷 1402-1410页

作者： Ying Huang David Perlmutter Andrea Fei-Huei Su Jerome Quenum Pavel Shevchenko Dilworth Y.Parkinson Iryna V.Zenyuk Daniela Ushizima Department of Materials Science&Engineering University of California IrvineIrvineCaliforniaUSA National Fuel Cell Research Center University of California IrvineIrvineCaliforniaUSA Applied Math and Computational Research Division Lawrence Berkeley National LaboratoryBerkeleyCaliforniaUSA Department of Chemical&Biomolecular Engineering University of California IrvineIrvineCaliforniaUSA Department of Electrical Engineering and Computer Sciences College of EngineeringUniversity of California BerkeleyBerkeleyCaliforniaUSA Advanced Photon Source Argonne National Laboratory9700 South Cass AvenueLemontIllinoisUSA Advanced Light Source Lawrence Berkeley National LaboratoryBerkeleyCaliforniaUSA Berkeley Institute for Data Science University of California BerkeleyBerkeleyCaliforniaUSA

Operando X-ray micro-computed tomography(µCT)provides an opportunity to observe the evolution of Li structures inside pouch *** is an essential step to quantitatively analyzingµCT datasets but is challenging to achieve on operando Li-metal battery datasets due to the low X-ray attenuation of the Li metal and the sheer size of the ***,we report a computational approach,batteryNET,to train an Iterative Residual U-Net-based network to detect Li *** resulting semantic segmentation shows singular Li-related component changes,addressing diverse morphologies in the *** addition,visualizations of the dead Li are provided,including calculations about the volume and effective thickness of electrodes,deposited Li,and redeposited *** also report discoveries about the spatial relationships between these *** approach focuses on a method for analyzing battery performance,which brings insight that significantly benefits future Li-metal battery design and a semantic segmentation transferrable to other datasets.

关键词： battery lithium state

来源：评论

学校读者我要写书评

暂无评论

Enhancing 3D Human Pose Estimation Amidst Severe Occlusion with Dual Transformer Fusion

arXiv

引用

arXiv 2024年

作者： Ghafoor, Mehwish Mahmood, Arif Bilal, Muhammad Department of Computer Science Information Technology University Lahore Pakistan Center of Excellence in Intelligent Engineering Systems Department of Electrical and Computer Engineering Faculty of Engineering King Abdulaziz University Jeddah21589 Saudi Arabia

In the field of 3D Human Pose Estimation from monocular videos, the presence of diverse occlusion types presents a formidable challenge. Prior research has made progress by harnessing spatial and temporal cues to infer 3D poses from 2D joint observations. This paper introduces a Dual Transformer Fusion (DTF) algorithm, a novel approach to obtain a holistic 3D pose estimation, even in the presence of severe occlusions. Confronting the issue of occlusion-induced missing joint data, we propose a temporal interpolation-based occlusion guidance mechanism. To enable precise 3D Human Pose Estimation, our approach leverages the innovative DTF architecture, which first generates a pair of intermediate views. Each intermediate-view undergoes spatial refinement through a self-refinement schema. Subsequently, these intermediate-views are fused to yield the final 3D human pose estimation. The entire system is end-to-end trainable. Through extensive experiments conducted on the Human3.6M and MPI-INF-3DHP datasets, our method’s performance is rigorously evaluated. Notably, our approach outperforms existing state-of-the-art methods on both datasets, yielding substantial improvements. The code is available here: https://***/MehwishG/DTF. © 2024, CC BY-NC-ND.

关键词： 3D modeling

来源：评论

学校读者我要写书评

暂无评论

Probabilistic Device Scheduling for Over-the-Air Federated Learning 23

Probabilistic Device Scheduling for Over-the-Air Federated L...

引用

23rd IEEE International Conference on Communication Technology, ICCT 2023

作者： Sun, Yuchang Lin, Zehong Mao, Yuyi Jin, Shi Zhang, Jun The Hong Kong University of Science and Technology Department of Electronic and Computer Engineering Hong Kong The Hong Kong Polytechnic University Department of Electrical and Electronic Engineering Hong Kong Southeast University National Mobile Communications Research Laboratory Nanjing210096 China

ISBN: (纸本)9798350325959

Federated learning (FL) is an emerging distributed training scheme where edge devices collaboratively train a model by uploading model updates instead of private data. To address the communication bottleneck, over-the-air (OTA) computation has been introduced to FL, which allows multiple edge devices to upload their gradient updates concurrently for aggregation. However, OTA computation is plagued by the communication error, which is critically affected by the device selection policy and impacts the performance of the output model. In this paper, we propose a probabilistic device selection scheme PO-FL, which effectively enhances the convergence performance of over-the-air FL. Specifically, each device is selected for OTA computation according to the predetermined probability, and its local update is scaled by this probability. By analyzing the convergence of PO-FL, we show that its convergence is determined by the device selection via the communication error and the variance of global update. Then, we propose a device selection algorithm that jointly considers the channel condition and gradient update importance of edge devices to optimize their selection probabilities. The experimental results on the MNIST dataset demonstrate that the proposed algorithm converges faster and learns better models than the baselines. © 2023 IEEE.

关键词： channel awareness device scheduling Federated learning (FL) gradient importance over-the-air computation (AirComp)

来源：评论

学校读者我要写书评

暂无评论

DFD-Net:lung cancer detection from denoised CT scan image using deep learning

引用

Frontiers of computer science 2021年第2期15卷 119-131页

作者： Worku J.SORI Jiang FENG Arero W.GODANA Shaohui LIU Demissie J.GELMECHA School of Electrical Engineering and Computing Department of Computer Science and EngineeringAdama Science and Technology UniversityAdama1888Ethiopia Faculty of Natural Computational Science Department of Mathematics Bule Hora UniversityBule HoraHagere Maryam144Ethiopia School of Computer Science and Technology Harbin Institute of TechnologyHarbin150001China Peng Cheng Laboratory Shenzhen518052China School of Electrical Engineering and Computing Department of Electronics and Communications EngineeringAdama Science and Technology UniversityAdama1888Ethiopia

The availability of pulmonary nodules in CT scan image of lung does not completely specify *** noise in an image and morphology of nodules,like shape and size has an implicit and complex association with cancer,and thus,a careful analysis should be mandatory on every suspected nodules and the combination of information of every *** this paper,we introduce a“denoising first”two-path convolutional neural network(DFD-Net)to address this *** introduced model is composed of denoising and detection part in an end to end ***,a residual learning denoising model(DR-Net)is employed to remove noise during the preprocessing ***,a two-path convolutional neural network which takes the denoised image by DR-Net as an input to detect lung cancer is *** two paths focus on the joint integration of local and global *** this end,each path employs different receptive field size which aids to model local and global *** further polish our model performance,in different way from the conventional feature concatenation approaches which directly concatenate two sets of features from different CNN layers,we introduce discriminant correlation analysis to concatenate more representative ***,we also propose a retraining technique that allows us to overcome difficulties associated to the image labels *** found that this type of model easily first reduce noise in an image,balances the receptive field size effect,affords more representative features,and easily adaptable to the inconsistency among nodule shape and *** intensive experimental results achieved competitive results.

关键词： medical image discriminant correlation analysis features fusion image detection denoising

来源：评论

学校读者我要写书评

暂无评论

Multi-agent Deep Reinforcement Learning Based Multi-objective Charging Control for Electric Vehicle Charging Station 7th

Multi-agent Deep Reinforcement Learning Based Multi-objectiv...

引用

7th Chinese Conference on Swarm Intelligence and Cooperative Control, CCSICC 2023

作者： Gong, Jiabao Fu, Weiming Kang, Yu Qin, Jiahu Xiao, Feng Department of Automation University of Science and Technology of China Hefei230027 China State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources School of Control and Computer Engineering North China Electric Power University Beijing102206 China

ISBN: (纸本)9789819733279

This paper proposes a multi-agent deep reinforcement learning (MADRL) based algorithm for charging control of multiple electric vehicles (EVs) in an electric vehicle charging station (EVCS) with dynamic operations. By taking the uncertainties of EV users’ behaviors and charging prices into consideration, a Markov game with multiple objectives is first established, where the individual objective of reducing EV charging costs and the collective objective of mitigating charging load fluctuations are both studied. Then, a multi-agent actor-double-critic (MAADC) algorithm with a unified advantage actor-critic framework is proposed, where two advantage functions are designed as the local and global critics, and the integrated actor is employed to balance the learning towards the individual and collective objectives. The simulation results obtained in a delicately built EVCS environment show the effectiveness of MAADC. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Extended state observer-based pressure control for pneumatic actuator servo systems

引用

Control Theory and Technology 2021年第1期19卷 64-79页

作者： John Mohorcic Lili Dong Delta Systems Inc. StreetsboroOH 44241USA Department of Electrical Engineering and Computer Science Cleveland State UniversityClevelandOH 44115.USA

A pneumatic actuator is a fast and economical tool that converts compressed air into mechanical *** this paper,an extended state observer(ESO)-based sliding mode controller(SMC)is developed to adjust the air pressure of the actua-tor for accurate position control,Specifically,an impedance control module is established to produce desired air pressure based on the relationship between forces and desired ***,the ESO-based SMC is implemented to adjust the air pressure to the required level despite the presence of system uncertainties and *** a result,the position of the actuator is controlled to a setpoint through the regulation of *** performance of ESO-based SMC is compared with that of a classic active disturbance rciection controller(ADRC)and a *** results demonstrate that the:ESO-based SMC shows comparable performance to ADRC in terms of precise pressure *** addition,it requires the least control effort ncessary to excite valves among the three *** stability of ESO based SMC is theoretically justifed through Lyapunov approach.

关键词： Pneumatic actuator Pressure control ESO-based SMC ADRC Impedance control module Stability proof Lyapunov approach

来源：评论

学校读者我要写书评

暂无评论

Straggler-Resilient Federated Learning: Leveraging the Interplay Between Statistical Accuracy and System Heterogeneity

Straggler-Resilient Federated Learning: Leveraging the Inter...

引用

作者： Reisizadeh, Amirhossein Tziotis, Isidoros Hassani, Hamed Mokhtari, Aryan Pedarsani, Ramtin Massachusetts Institute of Technology Laboratory for Information and Decision Systems CambridgeMA02139 United States The University of Texas at Austin Department of Electrical and Computer Engineering AustinTX78712 United States University of Pennsylvania Department of Electrical and Systems Engineering PhiladelphiaPA19104 United States University of California at Santa Barbara Department of Electrical and Computer Engineering Santa BarbaraCA93106 United States

Federated learning is a novel paradigm that involves learning from data samples distributed across a large network of clients while the data remains local. It is, however, known that federated learning is prone to multiple system challenges including system heterogeneity where clients have different computation and communication capabilities. Such heterogeneity in clients' computation speed has a negative effect on the scalability of federated learning algorithms and causes significant slow-down in their runtime due to slow devices (stragglers). In this paper, we propose FLANP, a novel straggler-resilient federated learning meta-algorithm that incorporates statistical characteristics of the clients' data to adaptively select the clients in order to speed up the learning procedure. The key idea of FLANP is to start the training procedure with faster nodes and gradually involve the slower ones in the model training once the statistical accuracy of the current participating nodes' data is reached, while the final model for each stage is used as a warm-start model for the next stage. Our theoretical results characterize the speedup provided by the meta-algorithm FLANP in comparison to standard federated benchmarks for strongly convex losses and i.i.d. samples. For particular instances, FLANP slashes the overall expected runtime by a factor of O((Ns)) , where N and s denote the total number of nodes and the number of samples per node, respectively. In experiments, FLANP demonstrates significant speedups in wall-clock time -up to 6 - compared to standard federated learning benchmarks. © 2020 IEEE.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Risk-Averse Learning with Delayed feedback

arXiv

引用

arXiv 2024年

作者： Wang, Siyi Wang, Zifan Johansson, Karl H. Hirche, Sandra Department of Electrical and Computer Engineering Technical University of Munich Munich80333 Germany Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm10044 Sweden

In real-world scenarios, the impacts of decisions may not manifest immediately. Taking these delays into account facilitates accurate assessment and management of risk in real-world environments, thereby ensuring the efficacy of strategies. In this paper, we investigate risk-averse learning using Conditional Value at Risk (CVaR) as risk measure, while incorporating delayed feedback with unknown but bounded delays. We develop two risk-averse learning algorithms that rely on one-point and two-point zeroth-order optimization approaches, respectively. The regret achieved by the algorithms is analyzed in terms of the cumulative delay and the number of total samplings. The results suggest that the two-point risk-averse learning achieves a smaller regret bound than the one-point algorithm. Furthermore, the one-point risk-averse learning algorithm attains sublinear regret under certain delay conditions, and the two-point risk-averse learning algorithm achieves sublinear regret with minimal restrictions on the delay. We provide numerical experiments on a dynamic pricing problem to demonstrate the performance of the proposed algorithms. © 2024, CC0.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

PrivShape: Extracting Shapes in Time Series Under User-Level Local Differential Privacy

PrivShape: Extracting Shapes in Time Series Under User-Level...

引用

International Conference on Data engineering

作者： Yulian Mao Qingqing Ye Haibo Hu Qi Wang Kai Huang Department of Computer Science and Engineering Southern University of Science and Technology Department of Electrical and Electronic Engineering The Hong Kong Polytechnic University Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology School of Computer Science and Engineering Macau University of Science and Technology

ISBN: (数字)9798350317152

ISBN: (纸本)9798350317169

Time series have numerous applications in finance, healthcare, IoT, and smart city. In many of these applications, time series typically contain personal data, so privacy infringement may occur if they are released directly to the public. Recently, local differential privacy (LDP) has emerged as the state-of-the-art approach to protecting data privacy. However, existing works on LDP-based collections cannot preserve the shape of time series. A recent work, PatternLDP, attempts to address this problem, but it can only protect a finite group of elements in a time series due to ω-event level privacy guarantee. In this paper, we propose PrivShape, a trie-based mechanism under user-level LDP to protect all elements. PrivShape first transforms a time series to reduce its length, and then adopts trie-expansion and two-level refinement to improve utility. By extensive experiments on real-world datasets, we demonstrate that PrivShape outperforms PatternLDP when adapted for offline use, and can effectively extract frequent shapes.

关键词： Privacy Differential privacy Shape Smart cities Frequency-domain analysis Time series analysis Transforms

来源：评论

学校读者我要写书评

暂无评论

Dimensionality and dynamics for next-generation artificial neural networks

Patterns

引用

Patterns 2025年

作者： Wang, Ge Fan, Feng-Lei Department of Biomedical Engineering Department of Electrical Computer and Systems Engineering Department of Computer Science Center for Computational Innovations Biomedical Imaging Center Center for Biotechnology and Interdisciplinary Studies Rensselaer Polytechnic Institute TroyNY United States Department of Data Science City University of Hong Kong Kowloon Hong Kong

The recent awarding of the Nobel Prize in Physics to Geoffrey E. Hinton and John J. Hopfield highlights their profound impact on artificial neural networks. In this perspective, we explore how their foundational insights can drive the advancement of next-generation artificial intelligence (AI) models. We propose expanding beyond conventional architectures by introducing dimensionality through intra-layer links and dynamics via feedback loops. Network height and additional dimensions, alongside traditional width and depth, enhance learning capabilities, while entangled loops across scales induce emergent behaviors akin to phase transitions in physics. We discuss how these principles extend beyond transformers, fostering a new paradigm of intelligence inspired by physics-driven models and biological cognition mechanisms. © 2025 The Author(s)

关键词： Neural network models

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：