检索结果-内蒙古大学图书馆

Annual International Conference of the IEEE engineering in Medicine and Biology Society (EMBC)

作者： Quoc Bao Phan Linh Nguyen Ngoc Thang Bui Dinh C. Nguyen Lan Zhang Tuy Tan Nguyen School of Informatics Computing and Cyber Systems Northern Arizona University Flagstaff AZ USA Department of Radiology Mayo Clinic Rochester MN USA Department of Electrical and Computer Engineering The University of Alabama in Huntsville Huntsville AL USA

ISBN: (数字)9798350371499

ISBN: (纸本)9798350371505

This paper presents a novel approach for classifying electrocardiogram (ECG) signals in healthcare applications using federated learning and stacked convolutional neural networks (CNNs). Our innovative technique leverages the distributed nature of federated learning to collaboratively train a high-performance model while preserving data privacy on local devices. We propose a stacked CNN architecture tailored for ECG data, effectively extracting discriminative features across different temporal scales. The evaluation confirms the strength of our approach, culminating in a final model accuracy of 98.6% after 100 communication rounds, significantly exceeding baseline performance. This promising result paves the way for accurate and privacy-preserving ECG classification in diverse healthcare settings, potentially leading to improved diagnosis and patient monitoring.

关键词： Data privacy Accuracy Protocols Federated learning Scalability Medical services Electrocardiography Feature extraction Robustness Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

An Actor-Critic Reinforcement Learning Scheme for Reactive 3D Optimal Motion Planning Based on Fluid Dynamics

An Actor-Critic Reinforcement Learning Scheme for Reactive 3...

引用

IEEE/RSJ International Conference on Intelligent Robots and systems (IROS)

作者： Marios Malliaropoulos Panagiotis Rousseas Charalampos P. Bechlioulis Kostas J. Kyriakopoulos School of Mechanical Engineering Control Systems Laboratory National Technical University of Athens Department of Electrical and Computer Engineering University of Patras Center of AI & Robotics (CAIR) New York University Abu Dhabi

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

This work proposes a novel and provably correct method for three-dimensional optimal motion planning in complex environments. Our approach models the 3D motion planning problem by solving streamlines of the potential fluid flow, filling a gap in traditional motion planning techniques by guaranteeing a closed-loop, smooth and natural-looking navigation solution. Special emphasis is given to an inherent challenge of artificial potential field (APF) methods, namely establishing proofs of safety and stability over the entire optimization process. A model-based actor-critic reinforcement learning algorithm is introduced to approximate the optimal solution to the Hamilton-Jacobi-Bellman equation and update the controller parameters in a deterministic manner. Through a series of ROS-Gazebo software-in-the-loop simulations the proposed methodology demonstrates robustness and outperforms widely used methods such as the RRT ∗ , highlighting its contribution to the field of 3D optimal motion planning.

关键词： Solid modeling Three-dimensional displays Navigation Reinforcement learning Mathematical models Stability analysis Robustness Planning Safety Optimization

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Model for Photovoltaic Generation: Comparison with Physical Models Using a Microgrid in Puerto Rico

Data-Driven Model for Photovoltaic Generation: Comparison wi...

引用

IEEE General Meeting Power& Energy Society

作者： Marcos R. Pesante Colón Alberto I. Cruz Salamán Dylan Cruz Figueroa Aditya Sundararajan Maximiliano Ferrari Electrical and Computer Engineering Department University of Puerto Rico Mayagüez USA Grid Systems Architecture Group Oak Ridge National Laboratory Oak Ridge TN USA

ISBN: (数字)9798350381832

ISBN: (纸本)9798350381849

Photovoltaic (PV) generation is a critical component of microgrids, but its accurate modeling is challenging due to the complex and dynamic interactions between solar irradiance, temperature, and PV system installation. This paper develops a multilayer perceptron (MLP) model that inputs solar irradiance and temperature to estimate the PV generation, and it compares the proposed data-driven model’s performance to two well-known physical models: the single-diode model and the inverter model. The results demonstrate that all the models can reach high levels of accuracy. However, the MLP model outperforms the physical models on average by 4.5 to 6.6 percent in R squared scores and 220 to 290 Watts in RMSE scores, and it does not require physical system parameters. Moreover, the data-driven model can overcome the limitations of the lack of real-time PV generation data.

关键词： Temperature measurement Solar irradiance Photovoltaic systems Adaptation models Accuracy Voltage measurement Predictive models Multilayer perceptrons Data models Inverters

来源：评论

学校读者我要写书评

暂无评论

Invertible Voice Conversion with Parallel Data

Invertible Voice Conversion with Parallel Data

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Zexin Cai Ming Li Department of Electrical and Computer Engineering Duke University Durham NC USA Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems Duke Kunshan University Kunshan PR China

This paper introduces an innovative deep learning framework for parallel voice conversion to mitigate inherent risks associated with such systems. Our approach focuses on developing an invertible model capable of countering potential spoofing threats. Specifically, we present a conversion model that allows for the retrieval of source voices, thereby facilitating the identification of the source speaker. This framework is constructed using a series of invertible modules composed of affine coupling layers to ensure the reversibility of the conversion process. We conduct comprehensive training and evaluation of the proposed framework using parallel training data. Our experimental results reveal that this approach achieves comparable performance to non-invertible systems in voice conversion tasks. Notably, the converted outputs can be seamlessly reverted to the original source inputs using the same parameters employed during the forwarding process. This advancement holds considerable promise for elevating the security and reliability of voice conversion.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Electric Vehicle Charging Management in Smart Energy Communities to Increase Renewable Energy Hosting Capacity

Electric Vehicle Charging Management in Smart Energy Communi...

引用

International Conference on Power Electronics (ICPE)

作者： Hyunwoo Song Yeongsang Lee Gab-Su Seo Dongjun Won Department of Electrical and Computer Engineering Inha University Incheon South Korea Power Systems Engineering Center National Renewable Energy Laboratory Golden CO USA

Abnormal climates due to global warming have emerged as a big concern in the global community. To mitigate climate change and achieve sustainability, distributed energy resources (DERs), including solar and wind, have been recently deployed in power systems. As the penetration level of DERs has increased, however, it caused a multitude of issues in the power systems, such as voltage fluctuation in the distribution network limiting renewable hosting capacity. On the other hand, the electric vehicle (EV) industry is rapidly growing to facilitate the transition to a carbon-neutral community, illuminating the potential of EVs as a flexible grid asset to mitigate some of the issues and improve grid operation, if properly exploited. To explore the potential of EVs, this paper proposes an EV scheduling strategy. By using an optimal EV charging scheduling proposed, distribution system operators (DSOs) can minimize their operating costs and stably operate the system with a high level of DERs. To validate the method, a modified IEEE 33-bus system with DERs is developed. The case study shows the proposed scheduling strategizes EV charging to reduce the cost of PV curtailment. In the study, the method outperforms the renewable-only case with curtailment by 4.97% in DSO cost. It also demonstrates its potential to increase the renewable hosting capacity by harmonizing EV charging with renewables.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fusion protein localization predicted by AlphaFold2 17

Fusion protein localization predicted by AlphaFold2

引用

17th International Conference on Photonics and Imaging in Biology and Medicine, PIBM 2024

作者： Wu, Zipei Li, Changjiang Xiao, Zeyu Zhang, Xiaoying Song, Haiying Peng, Xiao Yan, Wei Qu, Junle College of Physics and Optoelectronic Engineering Key Laboratory of Optoelectronic Devices and Systems of Ministry of Education and Guangdong Province Shenzhen University Shenzhen518060 China Department of Electrical and Computer Engineering Boston University BostonMA02215 United States College of Pharmacy Shenzhen Technology University Shenzhen518118 China Department of Nephrology The First Affiliated Hospital of Shenzhen University Shenzhen Second People's Hospital Shenzhen518035 China Medical Engineering and Technology College Xinjiang Medical University Urumqi810017 China

ISBN: (数字)9781510688070

ISBN: (纸本)9781510688063

Currently, rapid and accurate prediction of targeting expression of a fluorescent protein tagged fusion protein remains a great challenge. Molecular docking simulation methods have been widely used to predict molecular binding targets in previous studies. However, these prediction methods rely on the existing protein structures and prior structural predictions, leading to an unsatisfied accuracy. Here, we combined Alphafold2 with molecular docking simulations to predict the targeting effect of fluorescent proteins EGFP or mCherry fused to cytoskeleton protein. The prediction results showed that the fusion of mCherry with β-actin did not affect its expression in the cytoskeleton. In contrast, the fusion of EGFP with β-actin inhibited its efficient participation in cytoskeleton formation. Subsequently, the corresponding β-actin-mCherry and β-actin-EGFP expression vectors were constructed and transfected into cells. The transfected cells were then observed under a confocal microscope. Imaging results showed that β-actin-mCherry participated in the construction of the cytoskeleton, while β-actin-EGFP dispersed in the cytoplasm. This work demonstrated a method to predict whether the fusion of fluorescent protein with a target protein will affect its original targeting function, providing a new approach to optimize the design of fusion proteins. © 2025 SPIE.

关键词： Molecular docking

来源：评论

学校读者我要写书评

暂无评论

Efficient Model Training in Decentralized systems with Federated Learning 2

Efficient Model Training in Decentralized Systems with Feder...

引用

2nd IEEE International Conference on Communication, Security and Artificial Intelligence, ICCSAI 2023

作者： Rao, M.S. Srinivasa Saraswathy, S. Neela, V. Arun, M.R. Gupta, Sandeep Taqui, Syed Noeman Vignana Jyothi Institute of Engineering & Technology Vnr Department of Mechanical Engineering Telangana Hyderabad India Sri Sairam Engineering College Department of Computer Science and Business Systems Chennai India School of Computing and Information Technology Reva University Karnataka Bengaluru India Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Ece Chennai India Department of Electrical Engineering Dehradun India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Vlsi Microelectronics Tamil Nadu Chennai India

ISBN: (纸本)9798350369960

In the fast-changing field of machine learning, data privacy and model training efficiency are crucial. Federated Learning (FL) is a breakthrough method for training models on several decentralized devices or servers without centralizing raw data. This study examines Federated Learning's challenges in optimizing model training in dispersed systems. The first stage is to examine the Federated Learning (FL) framework and its merits, particularly in protecting data privacy and reducing server dependence. The next section will discuss communication overhead, stragglers, and non-IID (independent and identically distributed) data issues in a decentralized training model. We developed novel optimization methodologies and adaptive algorithms to improve Federated Learning (FL) efficiency. This includes updating asynchronous models, adaptability-based communication frequency, and non-IID data management. We also present a resilient aggregation method that mitigates Byzantine failures in participating nodes. We demonstrate that our methods improve convergence rate, communication costs, and model performance trained with Federated Learning (FL) by conducting a series of comprehensive experiments and analyzing real-world case studies. We show that these enhancements do not compromise data privacy, preserving Federated Learning (FL) principles. In conclusion, this study advances Federated Learning in decentralized systems. In an age of data sensitivity, this approach could help implement efficient, scalable, and privacy-preserving machine-learning methods. © 2023 IEEE.

关键词： Byzantine Failures Communication Efficiency Data Privacy Decentralized systems Federated Learning Model Training Non-IID Data

来源：评论

学校读者我要写书评

暂无评论

Cyber-Physical Reconfiguration for Disaster Resilience of Power Distribution systems

Cyber-Physical Reconfiguration for Disaster Resilience of Po...

引用

IEEE International Conference on Smart Grid Communications (SmartGridComm)

作者： Md. Zahidul Islam Yuzhang Lin Vinod M. Vokkarane Yiyun Yao Fei Ding Department of Electrical and Computer Engineering University of Massachusetts Lowell Lowell MA USA Power Systems Engineering Center National Renewable Energy Laboratory Golden CO

Cyber-physical distribution systems (CPDS) have emerged from the integration of information technology into distribution systems. While offering substantial benefits, this integration also introduces vulnerabilities. The interaction between cyber networks and distribution systems renders CPDS susceptible to disasters. To ensure critical load supply and system resilience, rapid post-disaster load restoration is required. The paper proposes a critical load restoration (CLR) framework in CPDS using a network reconfiguration approach that exploits the existing post-disaster resources to restore critical loads within the shortest possible time. Using graph theory, the cyber network and distribution system are integrated into a single digraph, minimizing the CLR complexity in CPDS. A cost metric is also defined to satisfy network-specific objectives and constraints. A heuristic is proposed to guide the load restoration process using the cost metric within the integrated digraph. Simulation results confirm the framework’s superiority over existing literature, which either overlooks cyber components or prolongs restoration with additional resource deployment.

关键词：

来源：评论

学校读者我要写书评

暂无评论

JARVIS-Leaderboard:a large scale benchmark of materials design methods

引用

npj Computational Materials 2024年第1期10卷 2280-2296页

作者： Kamal Choudhary Daniel Wines Kangming Li Kevin F.Garrity Vishu Gupta Aldo H.Romero Jaron T.Krogel Kayahan Saritas Addis Fuhr Panchapakesan Ganesh Paul R.C.Kent Keqiang Yan Yuchao Lin Shuiwang Ji Ben Blaiszik Patrick Reiser Pascal Friederich Ankit Agrawal Pratyush Tiwary Eric Beyerle Peter Minch Trevor David Rhone Ichiro Takeuchi Robert B.Wexler Arun Mannodi-Kanakkithodi Elif Ertekin Avanish Mishra Nithin Mathew Mitchell Wood Andrew Dale Rohskopf Jason Hattrick-Simpers Shih-Han Wang Luke E.K.Achenie Hongliang Xin Maureen Williams Adam J.Biacchi Francesca Tavazza Material Measurement Laboratory National Institute of Standards and TechnologyGaithersburgMD20899USA Department of Materials Science and Engineering University of Toronto27 King’s College CirTorontoONCanada Department of Electrical and Computer Engineering Northwestern UniversityEvanstonIL 60208USA Lewis-Sigler Institute for Integrative Genomics Princeton UniversityPrincetonNJ 08544USA Ludwig Institute for Cancer Research Princeton UniversityPrincetonNJ 08544USA Department of Physics and Astronomy West Virginia UniversityMorgantownWV 26506USA Materials Science and Technology Division Oak Ridge National LaboratoryOak RidgeTN 37831USA Center for Nanophase Materials Science Oak Ridge National LaboratoryOak RidgeTN 37831USA Computational Sciences and Engineering Division Oak Ridge National LaboratoryOak RidgeTN 37831USA Department of Computer Science and Engineering Texas A&M UniversityCollege StationTX 77843USA Globus University of ChicagoChicagoIL 60637USA Data Science and Learning Division Argonne National LabLemontIL 60439USA Institute of Nanotechnology Karlsruhe Institute of TechnologyKaiserstraße 1276131 KarlsruheGermany Institute of Theoretical Informatics Karlsruhe Institute of TechnologyKaiserstraße 1276131 KarlsruheGermany Department of Chemistry and Biochemistry and Institute for Physical Science and Technology University of MarylandCollege ParkMD 20742USA Department of Physics Applied Physics and AstronomyRensselaer Polytechnic InstituteTroyNY12180USA Department of Materials Science and Engineering University of MarylandCollege ParkMD20742USA Department of Chemistry and Institute of Materials Science and Engineering Washington University in St.LouisSt.LouisMO63130USA School of Materials Engineering Purdue UniversityWest LafayetteIN47907USA Department of Mechanical Science and Engineering University of Illinois Urbana-ChampaignUrbanaIllinois 61801USA Materials Research Laboratory University of Illinois Urbana-ChampaignUrbanaIL 61801USA Theore

Lack of rigorous reproducibility and validation are significant hurdles for scientific development across many *** science,in particular,encompasses a variety of experimental and theoretical approaches that require careful *** efforts have been developed previously to mitigate these ***,a comprehensive comparison and benchmarking on an integrated platform with multiple data modalities with perfect and defect materials data is still *** work introduces JARVIS-Leaderboard,an open-source and community-driven platform that facilitates benchmarking and enhances *** platform allows users to set up benchmarks with customtasks and enables contributions in the form of dataset,code,and meta-data *** cover the following materials design categories:Artificial Intelligence(AI),Electronic Structure(ES).

关键词： rigorous perfect enable

来源：评论

学校读者我要写书评

暂无评论

Systolic Array Architecture for Educational Use

Systolic Array Architecture for Educational Use

引用

International Conference on System Theory, Control, and computing (ICSTCC)

作者： Flavius Opriţoiu Mircea Vlăduţiu Computer Science and Engineering Department Advanced Computing Systems and Architectures (ACSA) Laboratory Politehnica University Timisoara 2 V.Parvan Blvd Timisoara Romania

This paper presents a systolic array architecture for General Matrix Multiplication. The system was designed and verified using the Verilog description language. The architecture was constructed for educational use aiming to complement the practical activities of computer Architecture classes. The proposed solution can be used as a design space exploration tool for evaluation of matrix multiplication accelerators based on non-stationary systolic arrays. Both the width and format of the processed operands as well as the number of stages of the systolic array’s Processing Elements can be customized. As a case study, the design and performance of a systolic array for accelerating the multiplication of square matrices of signed, 8-bit integers, is presented. The overall architecture was synthesized for the Altera DE2 FPGA board in order to evaluate its performance.

关键词：

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：