检索结果-内蒙古大学图书馆

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

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

PARoute2: Enhanced Analog Routing via Performance-Drive Guidance Generation

引用

IEEE Transactions on computer-Aided Design of Integrated Circuits and systems 2025年

作者： Xu, Peng Tu, Jindong Chen, Guojin Zhu, Keren Chen, Tinghuan Ho, Tsung-Yi Yu, Bei The Chinese University of Hong Kong Department of Computer Science and Engineering NT Hong Kong The Chinese University of Hong Kong School of Science and Engineering Guangdong Shenzhen518172 Hong Kong Fudan University School of Microelectronics State Key Laboratory of Integrated Chips and Systems Shanghai200433 China

Analog routing is crucial for performance optimization in analog circuit design, but conventionally takes significant development time and requires design expertise. Recent research has attempted to use machine learning (ML) to generate guidance to preserve circuit performance after analog routing. These methods face challenges such as expensive data acquisition and biased guidance. This paper presents AnalogFold, a new paradigm of analog routing that leverages ML to provide performance-oriented routing guidance. Our approach learns performance-driven routing guidance and uses it to help automatic routers for performance-driven routing optimization. We propose to use a 3DGNN that incorporates cost-aware distance to make accurate predictions on post-layout performance. A pool-assisted potential relaxation process derives the effective routing guidance. The experimental results on multiple benchmarks under the TSMC 40nm technology node demonstrate the superiority of the proposed framework compared to the cutting-edge works. © 2025 IEEE. All rights reserved.

关键词： Analog circuits

来源：评论

学校读者我要写书评

暂无评论

CPS, Sustainability and Efficiency in an Aquaponic Greenhouse

Renewable Energy and Power Quality Journal

引用

Renewable Energy and Power Quality Journal 2022年 20卷 210-215页

作者： Galvão, J. Santos, P. Aires, L. Neves, F. Department of Electrical Engineering/ESTG Polytechnic of Leiria Leiria2411-901 Portugal LSRE-LCM-Laboratory of Separation and Reaction Engineering Laboratory of Catalysis and Materials Escola Superior de Tecnologia e Gestão Instituto Politécnico de Leiria Leiria2411-901 Portugal ALiCE-Associate Laboratory in Chemical Engineering Faculty of Engineering University of Porto Rua Dr. Roberto Frias Porto4200-465 Portugal R&D Unit Institute for Systems Engineering and Computers/INESC Coimbra Portugal Department of Computer Science Polytechnic of Leiria Leiria2411-901 Portugal

Nowadays the humanity needs to produce food in greater quantity and quality, in order to satisfy citizens and markets, supported by advanced technologies such as cyber-physical system (CPS) or intelligent systems where software and electronic devices and receivers of physical variables are mechanisms that control the management of multiple actions inherent to plant growth. Electronic devices and receivers of physical variables are mechanisms that involve a network of IoT components and control multiple actions inherent to plant growth in agricultural greenhouses, which in short, are intensive food production systems. In this context, this paper presents a case study that uses a monitoring and management system that considers environmental parameters measured inside a greenhouse, allowing the manager to assess the working status of an aquaponic systems, and detect critical conditions that require quick decisions in real time. It is intended to develop technology that can be used in greenhouses, close to consumer centres or cities, to mitigate the impact of transport, lowering CO2 emissions resulting from the distribution channels between the producers and consumers. © 2022, European Association for the Development of Renewable Energy, Environment and Power Quality (EA4EPQ). All rights reserved.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Machine Learning for Scalable and Optimal Load Shedding Under Power System Contingency

arXiv

引用

arXiv 2024年

作者： Zhou, Yuqi Zhu, Hao Power Systems Engineering Center National Renewable Energy Laboratory GoldenCO80401 United States Department of Electrical & Computer Engineering The University of Texas at Austin AustinTX78712 United States

Prompt and effective corrective actions in response to unexpected contingencies are crucial for improving power system resilience and preventing cascading blackouts. The optimal load shedding (OLS) accounting for network limits has the potential to address the diverse system-wide impacts of contingency scenarios as compared to traditional local schemes. However, due to the fast cascading propagation of initial contingencies, real-time OLS solutions are challenging to attain in large systems with high computation and communication needs. In this paper, we propose a decentralized design that leverages offline training of a neural network (NN) model for individual load centers to autonomously construct the OLS solutions from locally available measurements. Our learning-for-OLS approach can greatly reduce the computation and communication needs during online emergency responses, thus preventing the cascading propagation of contingencies for enhanced power grid resilience. Numerical studies on both the IEEE 118-bus system and a synthetic Texas 2000-bus system have demonstrated the efficiency and effectiveness of our scalable OLS learning design for timely power system emergency operations. Copyright © 2024, The Authors. All rights reserved.

关键词： Electric power plant loads

来源：评论

学校读者我要写书评

暂无评论

Analytical Model for Device Currents in 5-Level Active Neutral Point Clamped Converter

Analytical Model for Device Currents in 5-Level Active Neutr...

引用

International Conference on electrical systems for Aircraft, Railway, Ship Propulsion and Road Vehicles & International Transportation Electrification Conference (ESARS-ITEC)

作者： Daniel Zakzewski Rakesh Resalayyan Apurv Kumar Yadav Alireza Khaligh Department of Electrical and Computer Engineering Maryland Power Electronics Laboratory The Institute for Systems Research University of Maryland College Park United States Department of Electrical Engineering Indian Institute of Technology Roorkee Uttrakhand India

This paper presents a closed form analytical model for semiconductor and capacitor currents in a 5-Level Active Neutral Point Clamped Converter (5L-ANPC) topology. This model enables device selection, performance prediction, and design optimization of the topology. Models for the switch and FC currents are derived based on the topology's switching states. A model for input capacitor current is derived by analyzing the interaction of three phase legs of the topology. The model is verified using conventional time-domain switching simulation of the topology.

关键词： Semiconductor device modeling Analytical models Capacitors Transportation Stars Switches Predictive models

来源：评论

学校读者我要写书评

暂无评论

Explainable Application Intent for Zero-Touch Networking: An Incorporation of Hypergraph and Transformer

引用

IEEE Transactions on Communications 2025年

作者： Wu, Bing Zou, Sai Liwang, Minghui Ni, Wei Wang, Xianbin Guizhou University College of Big Data and Information Engineering China National Key Laboratory of Autonomous Intelligent Unmanned Systems Department of Control Science and Engineering China Tongji University Frontiers Science Center for Intelligent Autonomous Systems Ministry of Education Shanghai China Data61 CSIRO Australia Department of Electrical and Computer Engineering Western University Canada

The autonomous interpretation of application intent (APPI) represents the primary step towards achieving closed-loop autonomy in zero-touch networking (ZTN) and also a prerequisite for intent-based networking (IBN). However, understanding APPIs and invoking the corresponding network resources require network professionals with extensive technical expertise to customize network service requests (NSRs), which presents significant challenges for the large-scale deployment of ZTN. This paper investigates an interesting problem of autonomous interpretation of APPIs for ZTN, where a novel mechanism integrating hypergraph and transformer with completeness assurance (HyperTrans-CA) is proposed. In particular, we first involve the Bayesian theory to model APPIs interpretability as maximizing the correct transition probability, where hypergraph is used to describe the complex relationship between application characteristics (e.g., scenario function, and performance) and NSRs, including network devices, virtual network functions (VNFs), and resources. Then, the hypergraph is integrated into the encoder, decoder, and attention mechanisms of Transformer, and a completeness assurance mechanism is designed to improve the prediction accuracy. The convergence of HyperTrans-CA and the corresponding convergence speed of the hypergraph-boosted Transformer in the graph search process are also analyzed. Comprehensive simulations and empirical measurements regarding industrial internet demonstrate that HyperTrans-CA can effectively explain/understand APPIs. Compared to the state-of-the-art Transformer and ChatGPT3.5 models, HyperTrans-CA improves the prediction accuracy of APPIs mapped to VNFs by 23% and 46%, respectively, while raising the prediction accuracy of VNF locations by 8.6 and 17.3 times. © 2025 IEEE.

关键词： Bayesian networks

来源：评论

学校读者我要写书评

暂无评论

Near-Far Field Three-Stage Beam Training for RIS-Assisted Wideband OFDM Communications

Near-Far Field Three-Stage Beam Training for RIS-Assisted Wi...

引用

IEEE Conference on Wireless Communications and Networking

作者： Zhichao Cheng Shupei Zhang Shu Fu Boya Di School of Electronics Engineering and Computer Science Peking University Beijing China State Key Laboratory of Advanced Optical Communication Systems and Networks School of Electronics Peking University Beijing China Department of Microelectronics and Communication Engineering Chongqing University Chongqing China

ISBN: (数字)9798350368369

ISBN: (纸本)9798350368376

Large-scale reconfigurable intelligent surfaces (RISs) have emerged as a promising technology for signal strength enhancement and coverage extension in 6G networks. However, as the antenna scale and the bandwidth increase, large-scale RIS-assisted wideband orthogonal frequency division multiplexing (OFDM) communication systems face new challenges due to the near-field range expansion and the beam split effect, complicating the acquisition of channel state information (CSI). To tackle these challenges, in this paper, we present a wideband beam training scheme by utilizing the beam split effect to bypass the CSI acquisition. Specifically, by analyzing the beam split effect in RIS-assisted OFDM communication systems, we propose a beam-split-aware codebook capable of covering both the near and far fields. The coverage of codewords in the proposed codebook is expanded benefiting from the beam split effect, leading to fewer codewords compared to conventional narrow-band codebooks. Utilizing such a codebook, a three-stage beam training mechanism is performed to obtain the optimal codeword with low time overhead, thereby facilitating the beamforming. Simulation results demonstrate that the proposed scheme outperforms existing codebook-based beam training schemes in terms of training overhead and sum rate in the hybrid near-far field.

关键词： Training Upper bound Array signal processing OFDM Simulation Reconfigurable intelligent surfaces Broadband antennas Wideband Faces Channel state information

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：