检索结果-内蒙古大学图书馆

DALTON - Deep Local Learning in SNNs via local Weights and Surrogate-Derivative Transfer

IEEE Transactions on Emerging Topics in Computing 2024年 1-12页

作者： Gaurav, Ramashish Do, Duy Anh Doan, Thinh Yi, Yang Department of Electrical and Computer Engineering Virginia Tech USA

Direct training of Spiking Neural Networks (SNNs) is a challenging task because of their inherent temporality. Added to it, the vanilla Back-propagation based methods are not applicable either, due to the non-differentiability of the spikes in SNNs. Surrogate-Derivative based methods with Backpropagation Through Time (BPTT) address these direct training challenges quite well;however, such methods are not neuromorphic-hardware friendly for the On-chip training of SNNs. Recently formalized Three-Factor based Rules (TFR) for direct local-training of SNNs are neuromorphic-hardware friendly;however, they do not effectively leverage the depth of the SNN architectures (we show it empirically here), thus, are limited. In this work, we present an improved version of a conventional three-factor rule, for local learning in SNNs which effectively leverages depth - in the context of learning features hierarchically. Taking inspiration from the Back-propagation algorithm, we theoretically derive our improved, local, three-factor based learning method, named DALTON (Deep LocAl Learning via local WeighTs and SurrOgate-Derivative TraNsfer), which employs weights and surrogate-derivative transfer from the local layers. Along the lines of TFR, our proposed method DALTON is also amenable to the neuromorphic-hardware implementation. Through extensive experiments on static (MNIST, FMNIST, & CIFAR10) and event-based (N-MNIST, DVS128-Gesture, & DVSCIFAR10) datasets, we show that our proposed local-learning method DALTON makes effective use of the depth in Convolutional SNNs, compared to the vanilla TFR implementation. IEEE

关键词： System-on-chip

来源：评论

学校读者我要写书评

暂无评论

Analysis of the effect of different scattering mechanisms on the excess noise behavior of Sb-based avalanche photodiodes

引用

Optics Express 2025年第4期33卷 7337-7344页

作者： Karimi, Hannaneh Herrera, Daniel J. Dadey, Adam A. Wei, Dongxia Mcarthur, Andrew Bank, Seth R. Campbell, Joe. C. Department of Electrical and Computer Engineering University of Virginia CharlottesvilleVA22903 United States Department of Electrical and Computer Engineering University of Texas AustinTX78758 United States

In optical applications where avalanche photodiodes (APDs) provide the benefit of high sensitivity, Sb-based materials systems such as AlInAsSb and AlGaAsSb have shown extremely low excess noise factors. The Monte Carlo (MC) model described in this work reveals the effect of high alloy scattering on the excess noise factor in these material systems. A comparison between the excess noise factor of different combinations of scattering rates is investigated. Furthermore, the ionization path length probability distribution is presented for AlInAsSb APDs with different scattering mechanisms. Good agreement is achieved between simulation results and experimental measurements. © 2025 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement.

关键词： III-V semiconductors

来源：评论

学校读者我要写书评

暂无评论

Virtual Power Plants for Grid Resilience: A Concise Overview of Research and Applications

引用

IEEE/CAA Journal of Automatica Sinica 2024年第2期11卷 329-343页

作者： Yijing Xie Yichen Zhang Wei-Jen Lee Zongli Lin Yacov A.Shamash IEEE Department of Electrical Engineering University of Texas at ArlingtonArlingtonTX 76019 USA Charles L.Brown Department of Electrical and Computer Engineering University of VirginiaCharlottesvilleVA 22904 USA Department of Electrical and Computer Engineering Stony Brook UniversityStony BrookNY 11794 USA

The power grid is undergoing a transformation from synchronous generators(SGs) toward inverter-based resources(IBRs). The stochasticity, asynchronicity, and limited-inertia characteristics of IBRs bring about challenges to grid resilience. Virtual power plants(VPPs) are emerging technologies to improve the grid resilience and advance the transformation. By judiciously aggregating geographically distributed energy resources(DERs) as individual electrical entities, VPPs can provide capacity and ancillary services to grid operations and participate in electricity wholesale markets. This paper aims to provide a concise overview of the concept and development of VPPs and the latest progresses in VPP operation, with the focus on VPP scheduling and control. Based on this overview, we identify a few potential challenges in VPP operation and discuss the opportunities of integrating the multi-agent system(MAS)-based strategy into the VPP operation to enhance its scalability, performance and resilience.

关键词： Climate change renewable energy resources resilience smart grids virtual power plants(VPPs)

来源：评论

学校读者我要写书评

暂无评论

Nonlinear observer-based state-of-charge balancing of networked battery energy storage systems

引用

Journal of Control and Decision 2025年第1期12卷 49-64页

作者： Tingyang Meng Zongli Lin Yan Wan Yacov A.Shamash Charles L.Brown Department of Electrical and Computer Engineering University of VirginiaCharlottesvilleVAUSA Department of Electrical Engineering University of Texas at ArlingtonFort WorthTXUSA Department of Electrical and Computer Engineering Stony Brook UniversityStony BrookNYUSA

In this paper,we propose an observer-based algorithm for balancing the state-of-charge(SoC)among battery units in a battery energy storage system(BESS).The dynamical behaviour of a battery unit is approximated by an equivalent circuit model,based on which a nonlinear SoC observer can be *** distribution laws are designed for the battery units according to the states of the battery units,the average battery state,and the average power *** estimation algorithms for the average battery state and the average power demand,as well as SoC observers,are constructed to implement *** BESS is shown to achieve SoC balancing among all its battery units while satisfying the power demand,as long as mild conditions on the underlying communication network and on the power demand are *** results are presented to demonstrate the effectiveness of the proposed algorithm.

关键词： Microgrids networked battery energy storage systems power distribution state-of-charge balancing equivalent circuit model nonlinear observer

来源：评论

学校读者我要写书评

暂无评论

Global Sensitivity Analysis for Rare Events in Probabilistic Power Flow Using Subset Simulation

引用

IEEE Transactions on Power Systems 2025年第2期40卷 1969-1972页

作者： Li, Yibo Xu, Yijun Gu, Wei Lu, Shuai Mili, Lamine Southeast University Electrical Engineering Department Nanjing210096 China Virginia Tech Bradley Department of Electrical and Computer Engineering Falls ChurchVA22043 United States

Traditionally, global sensitivity analysis (GSA) measures the importance of renewables and loads that will affect all probabilistic density functions (PDF) of operating states in power systems. However, when it comes to the rare events that better quantify the risk probabilities in the PDF tails, the traditional GSA is no longer applicable. In addition, the model uncertainties of the input PDFs are ignored in the traditional GSA. To overcome these challenges, we propose a novel GSA framework that addresses the probability of rare events associated with the distribution parameters of the input PDFs. Moreover, we propose to accelerate the expensive rare event-based GSA (REGSA) via the subset simulation (SS) method. The simulation results reveal the excellent performance of the proposed method. © 1969-2012 IEEE.

关键词： Load flow optimization

来源：评论

学校读者我要写书评

暂无评论

Flexible fibres take fabrics into the information age

引用

NATURE 2024年第7997期626卷 38-39页

作者： Jia, Xiaoting Parrott, Alex Xiaoting Jia is in the Bradley Department of Electrical and Computer Engineering the Department of Materials Science and Engineering and the School of Neuroscience Virginia Tech Blacksburg Virginia 24061 USA. Alex Parrott is in the Bradley Department of Electrical and Computer Engineering Virginia Tech Blacksburg Virginia 24061 USA.

A technique for embedding fibres with semiconductor devices produces defect-free strands that are hundreds of metres long. Garments woven with these threads offer a tantalizing glimpse of the wearable electronics of t... 详细信息

关键词： engineering Materials science Technology

来源：评论

学校读者我要写书评

暂无评论

Practical autoencoder based anomaly detection by using vector reconstruction error

引用

Cybersecurity 2023年第2期6卷 1-13页

作者： Hasan Torabi Seyedeh Leili Mirtaheri Sergio Greco Department of Electrical and Computer Engineering Faculty of EngineeringKharazmi UniversityTehranIran Department of Informatics ModelingElectronics and System EngineeringUniversity of CalabriaArcavacataItaly.

Nowadays,cloud computing provides easy access to a set of variable and configurable computing resources based on user demand through the *** computing services are available through common internet protocols and network standards.n addition to the unique benefits of cloud computing,insecure communication and attacks on cloud networks cannot be *** are several techniques for dealing with network *** this end,network anomaly detection systems are widely used as an effective countermeasure against network *** anomaly-based approach generally learns normal traffic patterns in various ways and identifies patterns of *** anomaly detection systems have gained much attention in intelligently monitoring network traffic using machine learning *** paper presents an efficient model based on autoencoders for anomaly detection in cloud computing *** autoencoder learns a basic representation of the normal data and its reconstruction with minimum ***,the reconstruction error is used as an anomaly or classification *** addition,to detecting anomaly data from normal data,the classification of anomaly types has also been *** have proposed a new approach by examining an autoencoder's anomaly detection method based on data reconstruction *** the existing autoencoder-based anomaly detection techniques that consider the reconstruction error of all input features as a single value,we assume that the reconstruction error is a *** enables our model to use the reconstruction error of every input feature as an anomaly or classification *** further propose a multi-class classification structure to classify the *** use the CIDDS-001 dataset as a commonly accepted dataset in the *** evaluations show that the performance of the proposed method has improved considerably compared to the existing ones in terms of accuracy,recall,false-positive rate,and F1-score

关键词： Cloud Practical Anomaly detection Autoencoder Reconstruction error Machine learning

来源：评论

学校读者我要写书评

暂无评论

A 500 kHz Wide Output LLC-T Resonant Converter With Narrow Frequency Range, Reduced Circulating Energy, and Low Voltage Stress

引用

IEEE Transactions on Power Electronics 2025年第8期40卷 11749-11762页

作者： Hou, Zhengming Jiao, Dong Lai, Jih-Sheng Virginia Polytechnic Institute and State University Bradley Department of Electrical and Computer Engineering BlacksburgVA24061 United States

The resonant converters are promising topologies for the electric vehicle charging applications due to the soft switching feature. However, the conventional LLC resonant converter regulates the wide output voltage through a wide frequency range, which leads to low efficiency with large circulating energy and the difficulty of the resonant tank optimization. This article proposes a novel LLC-T resonant converter, which parallels an auxiliary transformer with the LC resonant tank for the wide output applications. The proposed LLC-T resonant converter narrows the frequency range with less circulating energy, lower voltage stress on the resonant capacitor, and smaller flux linkage in the resonant inductor compared to the conventional LLC resonant converter. Meanwhile, the zero-voltage switching turn-on is maintained throughout the wide output voltage range and load range. Furthermore, a precise time-domain based analysis and the design methodology are proposed. A 500-kHz, 1.35 kW, 400 V input 250 V-450 V output prototype is built to verify the concepts of the proposed topology and demonstrates a 97.82% peak efficiency. © 1986-2012 IEEE.

关键词： Resonant converters

来源：评论

学校读者我要写书评

暂无评论

Output Feedback Q-Learning for a Non-Zero-Sum Game Problem in Building HVAC Control

引用

Journal of Systems Science & Complexity 2025年第2期38卷 739-755页

作者： ANWAR Junaid RIZVI Syed Ali Asad LIN Zongli Department of Electrical and Computer Engineering Tennessee Technological University Charles L.Brown Department of Electrical and Computer Engineering University of Virginia

Building heating, ventilating, and air conditioning(HVAC) systems have one of the largest energy footprint worldwide, which necessitates the design of intelligent control algorithms that improve the energy utilization while still providing thermal comfort. In this work, the authors formulate the HVAC equipment dynamics in the setting of a two-player non-zero-sum cooperative game, which enables two decision variables(mass flow rate and supply air temperature) to perform joint optimization of the control utilization and thermal setpoint tracking by simultaneously exchanging their policies. The HVAC zone serves as a game environment for these two decision variables that act as two players in a game. It is assumed that dynamic models of HVAC equipment are not available. Furthermore, neither the state nor any estimates of HVAC disturbance(heat gains, outside variations, etc.) are accessible,but only the measurement of the zone temperature is available for feedback. Under these constraints,the authors develop a new data-driven Q-learning scheme employing policy iteration and value iteration with a bias compensation mechanism that accounts for unmeasurable disturbances and circumvents the need of full-state measurement. The proposed algorithms are shown to converge to the optimal solution corresponding to the generalized algebraic Riccati equations(GAREs) in dynamic games.

关键词： Game theory HVAC control optimal control output feedback Q-learning

来源：评论

学校读者我要写书评

暂无评论

Near-sensor computing-assisted simultaneous viral antigen and antibody detection via integrated label-free biosensors with microfluidics

引用

InfoMat 2023年第10期5卷 80-95页

作者： Byungjoon Bae Yongmin Baek Jeongyong Yang Heesung Lee Charana S.S.Sonnadara Sangeun Jung Minseong Park Doeon Lee Sihwan Kim Gaurav Giri Sahil Shah Geonwook Yoo William APetri Kyusang Lee Department of Electrical and Computer Engineering University of VirginiaCharlottesvilleVirginiaUSA School of Electronic Engineering Soongsil UniversitySeoulRepublic of Korea Department of Electrical and Computer Engineering University of MarylandCollege ParkMarylandUSA Department of Chemical Engineering University of VirginiaCharlottesvilleVirginiaUSA Division of Infectious Diseases and International Health Department of MedicineSchool of MedicineUniversity of VirginiaCharlottesvilleVirginiaUSA Department of Material Science and Engineering University of VirginiaCharlottesvilleVirginiaUSA Department of Intelligent Semiconductors Soongsil UniversitySeoulRepublic of Korea

Precise diagnosis and immunity to viruses,such as severe acute respiratory syndrome coronavirus 2(SARS-CoV-2)and Middle East respiratory syndrome coronavirus(MERS-CoV)is achieved by the detection of the viral antigens and/or corresponding antibodies,***,a widely used antigen detection methods,such as polymerase chain reaction(PCR),are complex,expensive,and time-consuming Furthermore,the antibody test that detects an asymptomatic infection and immunity is usually performed separately and exhibits relatively low *** achieve a simplified,rapid,and accurate diagnosis,we have demonstrated an indium gallium zinc oxide(IGZO)-based biosensor field-effect transistor(bio-FET)that can simultaneously detect spike proteins and antibodies with a limit of detection(LOD)of 1 pg mL–1 and 200 ng mL–1,respectively using a single assay in less than 20 min by integrat-ing microfluidic channels and artificial neural networks(ANNs).The near-sensor ANN-aided classification provides high diagnosis accuracy(>93%)with significantly reduced processing time(0.62%)and energy consumption(5.64%)compared to the software-based *** believe that the development of rapid and accurate diagnosis system for the viral antigens and antibodies detec-tion will play a crucial role in preventing global viral outbreaks.

关键词： artificial intelligence biosensor edge-computing integration microfluidic

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：