检索结果-内蒙古大学图书馆

IEEE International Conference on Big Data

作者： Nicholas Josselyn Biao Yin Ziming Zhang Elke Rundensteiner Department of Data Science Worcester Polytechnic Institute Worcester MA Department of Electrical and Computer Engineering Worcester Polytechnic Institute Worcester MA Department of Computer Science Worcester Polytechnic Institute Worcester MA

ISBN: (纸本)9781665480468

Deep learning often relies on the availability of a large amount of high-quality labeled data, which can be very limited in novel domains. To address such data scarcity, domain adaptation is one promising approach that allows for deep networks to leverage large amounts of available data from a source domain to enhance the model’s efficacy on the target domain of interest. However, while there is a plethora of alternate models for domain adaptation proposed over many years in the literature, there is a dearth of studies that objectively compare the relative effectiveness of these models in a rigorous, empirical study. To fill this gap, we provide a thorough, unbiased, empirical study of five state-of-the-art (SOTA) deep domain adaptation models proposed over the past 6 years whose codes are publicly available. Models are evaluated on the complex and diverse domain adaptation tasks featured in the DomainNet benchmark dataset as well as the popular Office-31 dataset. Our results suggest that (1) all 5 models perform similarly, on average, and do not even significantly beat the oldest model, and (2) counter to their intended purpose, the transfer loss functions in the literature do not contribute significantly to learning transferable representations. Our observations suggest that domain adaptation research needs to more thoroughly compare newly proposed models against existing works, along with assessing their loss functions’ utility thoroughly. Our code and data splits are made public for reproducibility of results by the community.

关键词： Deep learning Adaptation models Codes Big Data Benchmark testing Reproducibility of results Data models

来源：评论

学校读者我要写书评

暂无评论

Text-dependent Speaker Verification Challenge 2024: Exploring Shared and User-defined Passphrases

Text-dependent Speaker Verification Challenge 2024: Explorin...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Zeinali, Hossein Lee, Kong Aik Alam, Jahangir Burget, Lukáš Department of Computer Engineering Amirkabir University of Technology Tehran Iran Department of Electrical and Electronic Engineering The Hong Kong Polytechnic University Kowloon Hong Kong Department of Computer Graphics and Multimedia Brno University of Technology Brno Czech Republic Computer Research Institute of Montreal Montreal Canada

ISBN: (纸本)9798350368741

In contrast to text-independent speaker verification, which has received significant attention from researchers and has many competitions dedicated to it, text-dependent speaker verification (TdSV) has been less explored recently. The TdSV Challenge 2024 was organized to analyze and explore novel methods for this type of speaker verification and aims to motivate participants to develop new approaches to TdSV, conduct comprehensive analyses, and investigate advanced techniques such as self-supervised learning. This challenge builds on the achievements of the short-duration speaker verification (SdSV) Challenges held in 2020 and 2021 and focuses specifically on TdSV in two distinct scenarios. The first scenario involves conventional TdSV, while the second focuses on speaker enrollment using user-defined passphrases. This paper provides a detailed description of both tasks, introduces the evaluation rules, and presents a comprehensive analysis of the results obtained from this challenge. © 2025 IEEE.

关键词： DeepMine dataset TdSV Challenge Text-dependent Speaker Verification User-defined passphrase

来源：评论

学校读者我要写书评

暂无评论

An Efficient Shortest Path Optimized Algorithm for Vehicle Adhoc Networks System 7

An Efficient Shortest Path Optimized Algorithm for Vehicle A...

引用

7th International Conference on Circuit Power and Computing Technologies, ICCPCT 2024

作者： Shalini, K. Reddy, K. Harinath Punati, Kondalarao Kavin, K.S. Veena, P. Pushpalatha, K. Vardhaman College of Engineering Department of Artificial Intelligence and Data Science Shamshabad India Annamacharya Institute of Technology and Sciences Department of Electrical and Electronics Engineering Rajampet India Hyderabad Institute of Technology and Management Faculty of Electronics and Communication Engineering Hyderabad500090 India Government College of Engineering Department of Electrical and Electronics Engineering Tamilnadu Tirunelveli India N. S. S. Polytechnic College Department of Computer Engineering Pandalam Pathanamthitta India Coimbatore Institute of Engineering and Technology Department of Computer Science and Engineering Coimbatore641109 India

ISBN: (纸本)9798350372816

VANET (Vehicular ad-hoc network) is a network of advanced automobiles designed to solve the problem of mobility and, as a result, reduce the number of accidents. Because VANET is a type of MANET (mobile ad hoc network) surrounded by human-driven nodes, the social concept can be used to explain VANET routing decisions. This motivates academics to look into the possibilities of using Social Network Analysis (SNA) to create routing strategies. The most critical problem in any system is parcel drop. Social characteristics-based architectures encounter comparable challenges, resulting in inefficient message delivery. In this research, the dragonfly method is used to the shortest path methodology for fixed line VANET with the purpose of reducing package drop and increasing network reliability. This is made achievable by sculpted system of values centralization analysis, which improves the decision via dragonfly optimization methodology. The behavior of the using nodes capability then be determined by the importance computation. In this study, the sustainability of the optimized shortest path system is measured in terms of End to End delay, Energy Consumption, Packet Loss, and Throughput. The dragonfly algorithm's throughput evaluation is 650 kbps as compared to the traditional way. © 2024 IEEE.

关键词： Vehicular ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

A Fair Multi-Partner Profit Allocation for Islanded Micro-grid 2

A Fair Multi-Partner Profit Allocation for Islanded Micro-gr...

引用

2nd International Conference on Machine Learning and Data engineering, ICMLDE 2023

作者： Oladejo, Ismaheel O. Folly, Komla A. Brahma, Biswajit Ajagbe, Sunday Adeola Bandyopadhyay, Anjan Awotunde, Joseph Bamidele Department of Electrical Engineering The Polytechnic Ibadan Nigeria Department of Electrical Engineering University of Cape Town South Africa McKesson Corporation 32559 Lake Bridgeport St FremontCA94555 United States Department of Computer Engineering First Technical University Ibadan200255 Nigeria School of Computer Engineering Kalinga Institute of Industrial Technology Bhubaneswar India Department of Computer Science Faculty of Information and Communication Sciences University of Ilorin Nigeria

A micro-grid (MG) is regarded as a localized small-scale power supply system designed for providing electrical power for a remote community, which may be connected to the grid. The paper considers six participants' sites in a remote community. The peak energy consumption patterns for these participants must be different to ensure coalition for mutual benefits and this would facilitate efficient utilization of energy resources. This community concerned may include rural communities having participants such as schools, housing estates, industrial sites, etc. The propose approach would ensure that many participants and their needs are captured and optimized profit of the participants would ensure mutual benefits. In islanded MG, most of the cost/profit distributions in energy trading problems are done based on the self-interest of the participants. Some consider a fair (acceptable or reasonable) cost/profit distribution using the cooperative game theory (CGT) based on the Nash bargaining solution (NBS). However, this method leads to a high degree of dissatisfaction. To improve the fairness and mutual benefits for all MG participants, a new flexible approach is developed. Specifically, CGT which uses a generalized NBS (GNBS) has been proposed, which relaxes certain axiom of the NBS to ensure that fairness of game theory is achieved. The approach allows the profit of the MG participants to be shared using a mechanism based on the negotiation power (i.e. weighted fairness) so that the MG would attain an improved economic outcome. Empirical evaluation of the approach indicates that overall profits using CGT is higher when compared with an independent approach. Moreover, different in negotiation power is achieved in which higher profit is allocated to any participant based on participant's mutual agreement in achieving fair profit distribution. A robust optimization algorithm called Teaching-Learning-Based-Optimization (TLBO) is developed to obtain optimal results. The heur

关键词： Profitability

来源：评论

学校读者我要写书评

暂无评论

Triboelectric nanogenerator based on electrospun molecular ferroelectric composite nanofibers for energy harvesting

RSC Applied Polymers

引用

RSC Applied Polymers 2024年第4期2卷 634-641页

作者： Deswal, Swati Arab, Shima He, Nanfei Gao, Wei Lee, Bongmook Misra, Veena Department of Electrical and Computer Engineering North Carolina State University Raleigh NC United States Department of Textile Engineering Chemistry and Science North Carolina State University Raleigh 27606 NC United States College of Engineering SUNY Polytechnic Institute Utica NY United States

Ceramic-based ferroelectric materials have long been used as functional ferroelectric materials for applications in triboelectric-energy harvesting. However, their drawbacks (brittleness, energy-intensive fabrication methods, and minimal mechanical flexibility) have intensified the search for alternatives where flexible form factors are needed. Molecular ferroelectrics are an emerging class of multifunctional materials. To date, the intriguing piezo/ferroelectric properties of these materials have led to the construction of piezoelectric nanogenerators. However, their numerous advantages warrant their expansion towards triboelectric nanogenerators (TENGs). We aimed to demonstrate the potential of a molecular ferroelectric, diisopropylammonium bromide (DIPAB), in the realm of triboelectric-energy harvesting. Combining ferroelectric properties with enhanced surface modification, we designed an electrospun-based TENG comprising DIPAB/P(VDF-TrFE) as an active negative layer. The synergistic effects emanating from highly aligned polymeric chains and ferroelectric particles in conjunction with a high surface area of the as-designed TENG generated an output voltage of 203.8 V and resulted in a maximum power density of 416.2 mW m⁻² when operated in contact separation mode. Its practical application as a sustainable power supply for low-power electronics was demonstrated through powering of commercial electrolytic capacitors and LEDs. This study presents a reliable, cost-effective, and readily scalable method for enhancing TENG performance. This strategy holds potential for application of TENGs in wearable biomechanical-energy harvesting, and paves the way for further advances involving a sustainable energy solution for wearable electronics. © 2024 RSC.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Packaging of 15-kV Silicon Carbide Half-Bridge Module Enabled by a Nonlinear Resistive Polymer Nanocomposite Field-Grading Coating 10

Packaging of 15-kV Silicon Carbide Half-Bridge Module Enable...

引用

10th IEEE Workshop on Wide Bandgap Power Devices and Applications, WiPDA 2023

作者： Zhang, Zichen Lu, Shengchang Nicholas, Carl Lynch, Justin Morgan, Adam Sung, Woongje Ngo, Khai D.T. Lu, Guo-Quan Virginia Tech Blacksburg CPES The Bradley Department of Electrical and Computer Engineering United States College of Nanoscale Science and Engineering SUNY Polytechnic Institute Albany United States

ISBN: (纸本)9798350337136

Emerging medium-voltage silicon carbide devices offer the potential to achieve more efficient and compact power electronics for grid-Tied applications. However, the lack of an effective insulation solution for packaging the devices has slowed their widespread adoption. In this work, a 15-kV silicon carbide MOSFET half-bridge module was designed and fabricated. The module was built by silver-sintering the device chips on an aluminum nitride direct-bond-copper substrate with 1.0-mm thick ceramic. The insulation of the module was enhanced by coating a nonlinear resistive polymer nanocomposite along the electrode edges on the substrate prior to silicone-gel encapsulation. The field-grading effect of the coating was tested on aluminum nitride direct-bond-copper substrates. The coated substrates showed an average partial discharge inception voltage of 20.2 kVpeak, which is 85% higher than the uncoated ones and 33% higher than the devices' rated voltage. Finally, prototypes of the modules with functional 15-kV dice were fabricated and tested. The blocking capability of the devices were unchanged after packaging. The fabricated modules in this work will serve as testbed for evaluating the coating's effectiveness under fast pulse-width modulation excitations during switching tests. © 2023 IEEE.

关键词： Substrates

来源：评论

学校读者我要写书评

暂无评论

An In-depth Investigation on the Structure, Characteristics, and Potential Applications of GaN/SiC Mosfet-Based Systems 23

An In-depth Investigation on the Structure, Characteristics,...

引用

Proceedings of the 6th International Conference on Information Technologies and electrical engineering

作者： Yan Ren Department of Electrical Computer and Systems Engineering Rensselaer Polytechnic Institute USA

ISBN: (纸本)9798400708299

In an era of rapid technological innovation, this article provides a comprehensive examination of Gallium Nitride (GaN) Metal-Oxide-Semiconductor Field-Effect Transistors (MOSFETs). The background section highlights the emergence and application of GaN MOSFETs and their significant advantages over silicon-based and Silicon Carbide (SiC) MOSFETs, such as smaller size, faster switching speed, less heat generation, and optimum operation at high temperatures, indicating that GaN MOSFETs are leading us into a more advanced, digitized future. The article delves into the basic theory of GaN MOSFETs, detailing their unique structure and properties that demonstrate massive potential and practicality in real-world applications such as electric vehicles and 5G technology. The conclusion emphasizes that GaN MOSFETs have already shown their importance in a wider range of industrial sectors and are set to revolutionize various industries, thereby driving overall progress. With diversified applications and broad prospects, the impact and value of GaN MOSFETs have gone beyond single-component applications, and their societal significance is undergoing profound changes.

关键词： GaN MOSFETs Advancements GaN MOSFETs Performance High Temperature Electronics Wide Bandgap Semiconductors in EVs and 5G

来源：评论

学校读者我要写书评

暂无评论

Analysis of a PM-Assisted Synchronous Reluctance Machine for Electric Veihicles

Analysis of a PM-Assisted Synchronous Reluctance Machine for...

引用

2022 IEEE International Conference on "Power Electronics, Smart Grid, and Renewable Energy", PESGRE 2022

作者： Barman, Dwaipayan Chowdhury, Vikram Roy Iqbal, Mohammad Tauquir Barman, Debabrata Department of Electrical and Computer Engineering Concordia University Montreal Canada Department of Electrical and Computer Engineering Georgia Institute of Technology Atlanta United States School of Electrical and Electronic Engineering Nanyyang Tcehnological University Singapore Jalpaiguri Polytechnic Institute Department of Electrical Engineering India

ISBN: (纸本)9781665448376

although motors that use rare-earth permanent magnets (PM) typically provide high efficiency and power density, their cost is high. A high torque density ferrite permanent magnet assisted synchronous reluctance machine (PMASynRM) is presented to demonstrate its feasibility in electric vehicle (EV) applications considering productivity and a liquid cooling system is available. The performance of the proposed PMASynRM is evaluated based on finite element analysis (FEA). The parametric analysis of the PMASynRM is performed in terms of average torque and torque ripple by changing the web thickness and bridge thickness in the rotor. The performance of the PMASynRM is investigated with three different rotors and the rotor with sufficient average torque and lower torque ripple is selected as the best design. A high flux weakening range is achieved with a maximum speed of 9000 rpm. Also, a thermal analysis is performed. © 2022 IEEE

关键词： Thermoanalysis

来源：评论

学校读者我要写书评

暂无评论

Tuning of renewable energy bids based on energy risk management: Enhanced microgrids with pareto-optimal profits for the utility and prosumers

Energy Conversion and Economics

引用

Energy Conversion and Economics 2022年第3期3卷 156-169页

作者： Mohan, Vivek Antonis, Anjula Mary Jisma, M. Krishnakumar, Nila Bu, Siqi Department of Electrical and Electronics Engineering National Institute of Technology Tiruchirappalli Tamil Nadu Tiruchirappalli India Department of Electrical and Computer Engineering University of Toronto Toronto Canada Department of Electrical Sustainable Energy Faculty of Electrical Engineering Applied Mathematics and Computer Science Delft University of Technology Delft Netherlands Department of Electrical Engineering The Hong Kong Polytechnic University Kowloon SAR Hong Kong

The increasing penetration of renewable energy sources (RES) and electric vehicles (EVs) demands the building of a microgrid energy portfolio that is cost-effective and robust against generation uncertainties (energy risk). Energy risk may trigger financial risk in the local energy market, depending on bid values, cost of generation and price of upstream grid power. In this study, a microgrid energy portfolio is built based on adjustments to both the financial and energy risks. These risks are managed in two ways: (1) by pre-tuning and prioritizing the bid prices for wind and solar energy sources based on their relative levels of energy risk as quantified through a conditional value-at-risk (CVaR) approach;and (2) by co-optimizing the conflicting profits of the utility and prosumers using non-dominated sorting particle swarm optimization (NSPSO) to obtain a risk-adjusted Pareto-optimal energy mix. Thus, the utility predicts the net power balancing cost from the scheduling time horizon, thereby moderating the adverse effect that the uncertainties in renewable energy could have on the collective welfare. The proposed method is tested on a grid-connected CIGRE low-voltage (LV) benchmark microgrid with solar and wind sources, microturbines, and EVs. The results demonstrate that the obtained portfolio is realistic, welfare-optimized and cost-efficient. © 2022 The Authors. Energy Conversion and Economics published by John Wiley & Sons Ltd on behalf of The Institution of engineering and Technology and the State Grid Economic & Technological Research institute Co., Ltd.

关键词： Profitability

来源：评论

学校读者我要写书评

暂无评论

PFAS Incineration: Known Unknowns, Reaction Simulation, and ML to Predict Product Properties

PFAS Incineration: Known Unknowns, Reaction Simulation, and ...

引用

IEEE MIT Undergraduate Research Technology Conference (URTC)

作者： Duncan Soiffer Tuomas Pyorre David Kenney Andrew Teixeira Department of Computer Science and Mathematical Sciences Worcester Polytechnic Institute Worcester MA United States Department of Robotics Engineering Worcester Polytechnic Institute Worcester MA United States Department of Chemical Engineering Worcester Polytechnic Institute Worcester MA United States

ISBN: (数字)9798350309652

ISBN: (纸本)9798350309669

Per- and polyfluoroalkyl substances (PFAS) are a group of chemicals used for their impressive stability, a property which has also led them to be found polluting virtually every sector of the environment-including our own bodies. Presently, our ability to destroy PFAS is limited largely to incineration, whose products and side effects are poorly understood. Research on PFAS incineration is constrained by high experimental costs and difficulty in accurately measuring reaction products. This presents an opportunity for computer simulation and machine learning to provide valuable assistance. In this study, three kinds of thermal PFAS decomposition are simulated. Further, to broaden physical understanding of PFAS incineration products, a recent in-house machine learning model for predicting the octanol-water partition coefficient (LogP) of chemicals is improved and applied to simulation results. A decrease in LogP is observed in all treatments, with the most dramatic effect (-2 average LogP) observed in oxidative pyrolysis.

关键词： Costs Incineration computer simulation Thermal decomposition Machine learning Predictive models Stability analysis

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：