检索结果-内蒙古大学图书馆

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

作者： Datta, Gourav Liu, Zeyu Li, Anni Beerel, Peter A. Dept. of Electrical Computer & Systems Engineering Case Western Reserve University Cleveland United States Ming Hsieh Dept. of Electrical and Computer Engineering University of Southern California Los Angeles United States

ISBN: (纸本)9798350368741

Spiking Neural Networks (SNNs) have emerged as a popular spatio-temporal computing paradigm for complex vision tasks. Recently proposed SNN training algorithms have significantly reduced the number of time steps (down to 1) for improved latency and energy efficiency, however, they target only convolutional neural networks (CNN). These algorithms, when applied to the recently spotlighted vision transformers (ViT), either require a large number of time steps or fail to converge. Based on the analysis of the histograms of the ANN and SNN activation maps, we hypothesize that each ViT block has a different sensitivity to the number of time steps. We propose a novel training framework that dynamically allocates the number of time steps to each ViT module depending on a trainable score assigned to each timestep. In particular, we generate a scalar binary time step mask that filters spikes emitted by each neuron in a leaky-integrate-and-fire (LIF) layer. The resulting SNNs have high activation sparsity and require only accumulate operations (AC), except for the input embedding layer, in contrast to expensive multiply-and-accumulates (MAC) needed in traditional ViTs. This yields significant improvements in energy efficiency. We evaluate our training framework and resulting SNNs on image recognition tasks including CIFAR10, CIFAR100, and ImageNet with different ViT architectures. We obtain a test accuracy of 95.97% with 4.97 time steps with direct encoding on CIFAR10. © 2025 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

EMI-Silent Operation of Triple Active Bridge Converters with Online Model-Free ZVS Optimization and RMS Current Reduction

IEEE Open Journal of Industry Applications

引用

IEEE Open Journal of Industry Applications 2025年 6卷 249-261页

作者： Ibrahim, Ahmed A. Darisi, Michele Caldognetto, Tommaso Biadene, Davide Magnone, Paolo Mattavelli, Paolo Vicenza Italy Alexandria University Dept. of Electrical Engineering Faculty of Engineering Egypt

Triple active bridge (TAB) converter, an isolated multi-port converter (IMPC), connects three dc ports via a three-terminal high-frequency transformer, enabling zero voltage switching (ZVS) without the need for additional snubber circuits. However, under certain loading conditions ZVS is lost and rms currents increase. This paper introduces a model-free, online optimization method using multi-dimensional ripple correlation control (MD-RCC) to ensure ZVS operation while reducing rms currents. The MD-RCC is an online model-free approach, providing robust performance against parameter uncertainties or operational variations. Two distinct methods are utilized to evaluate the cost function online. The first method involves the oversampling of the transformer currents. The second approach relies on the correlation between the EMI noise level and the hard switching of the devices, providing a simpler alternative to oversampling techniques. The proposed MD-RCC technique has been validated through both simulation and experimental testing on a 5 kW prototype, demonstrating its efficacy in optimizing ZVS, reducing EMI noise, and rms currents. © 2020 IEEE.

关键词： Zero current switching

来源：评论

学校读者我要写书评

暂无评论

Comparative Study of Data Mining-Based State Determination Method for Smart EOCR

引用

Transactions of the Korean Institute of electrical Engineers 2025年第3期74卷 411-416页

作者： Lee, Kyung-Min Park, Chul-Won Dept. of Electrical Engineering Gangneung-Wonju National University Korea Republic of Korea Republic of

When a motor fault happens, the life and productivity of motor are reduced, and enormous recovery time and cost occur, so a protection plan must be established. Recently, the concept of predictive maintenance based on the prognosis according to the facility status has been attracting attention. In this paper, as part of the project to develop AI-based predictive maintenance technology for MCC's smart EOCR, state determination method using data mining is proposed. First, the data is collected from an electric motor system using an actual pump system, and then the training data and test data sets that can determine various states are configured. Among data mining technique, the state determination method is designed using the SVM model and the LSTM model, and implemented using the Python language. Finally, the performance of the two proposed data mining models are compared through evaluation metrics such as Precision, Recall, and F1_Score, etc. © The Korean Institute of electrical Engineers.

关键词： Predictive maintenance

来源：评论

学校读者我要写书评

暂无评论

A Study on Selecting Specialized Areas for Distributed Energy and Developing Business Models

引用

Transactions of the Korean Institute of electrical Engineers 2025年第3期74卷 392-403页

作者： Kim, Hyeon-Jin Kim, Chi-Yeon Yoon, Ah-Yun Kim, Young-Jin Heo, Jae-Haeng Dept. of Energy and Electrical Engineering Tech University of Korea Korea Republic of Dept. RaonFriends Korea Republic of Korea Republic of

With climate change mitigation and carbon neutrality becoming global policy priorities, expanding renewable energy is a critical challenge. However, the conventional centralized power system faces significant limitations, including power losses from long-distance transmission, public opposition near generation and transmission facilities, and the intermittency and unpredictability of renewable energy sources. To address these challenges, the Korean government enacted the Distributed Energy Activation Special Act in June 2024, aiming to foster a transition towards a distributed energy system centered on renewable energy. Despite this legislative initiative, the lack of standardized procedures for selecting candidate sites for distributed energy-specialized regions has impeded systematic implementation. This study proposes an eight-step selection process to identify candidate sites for distributed energy-specialized regions and validates its applicability through a case study in Pohang. The framework evaluates regional energy demand and self-reliance potential while suggesting tailored distributed energy business models that address local characteristics. By providing a structured and replicable methodology, this study supports the realization of national energy self-reliance goals and the establishment of sustainable distributed energy systems, offering actionable strategies and guidelines for widespread adoption across diverse regions. © The Korean Institute of electrical Engineers.

关键词： Distributed energy

来源：评论

学校读者我要写书评

暂无评论

Evaluating Visual Transformers for Wafer Defect Detection: A Feasibility Study

Evaluating Visual Transformers for Wafer Defect Detection: A...

引用

2025 IEEE SoutheastCon, SoutheastCon 2025

作者： Lafrance, Samantha Bernadin, Shonda FAMU-FSU College of Engineering Dept. of Electrical and Computer Engineering Tallahassee United States

ISBN: (纸本)9798331504847

Wafer defect detection is a critical aspect of semi-conductor manufacturing, where even minor defects can lead to significant performance issues or device failures. Traditional methods, such as rule-based approaches and Convolutional Neural Networks (CNNs), have achieved moderate success but face limitations in scalability, adaptability, and the ability to model complex spatial patterns in high-resolution wafer imagery. These limitations make it critical to investigate advanced architectures that can accurately capture complex spatial relationships. Vision Transformers (ViTs) have emerged as a promising alternative within computer vision, offering global attention techniques that are particularly effective in recognizing long-range dependencies. This study evaluates the feasibility of ViTs for wafer defect detection through a literature-based empirical validation approach, synthesizing findings from prior research on ViT-based classification, defect localization, and industrial feasibility. Results indicate that ViTs offer superior accuracy and interpretability compared to CNN s, particularly in detecting rare and mixed-type defects. However, challenges remain in terms of computational cost and real-time deployment in high-throughput manufacturing settings. The findings of this study underscore the potential of ViTs as a transformative technology for semiconductor defect inspection while highlighting key areas for further development. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Innovative Solutions For Oil Well Monitoring: Data-Driven Multiphase Virtual Flow Metering Using Ensemble Machine Learning And Historical Field Data

Journal of Applied Science and Engineering

引用

Journal of Applied Science and engineering 2025年第12期28卷 2427-2438页

作者： Farag, Wael A. Ismail, Hussein H. Nadeem, Muhammad Electrical Power Engineering Dept. Cairo University Giza Egypt College of Engineering and Technology American University of the Middle East Kuwait

By combining data-driven ensemble machine-learning algorithms and historical oil field portable test reports, this paper proposes a Data-Drive Multiphase Virtual Flow Meter (DD-MVFM) that estimates oil, gas, and water flow rates and provides real-time monitoring, and predicts future production with appropriate accuracy. The proposed DD − MVFM utilizes the existing hardware used for measurements of basic variables such as temperature, and pressure at different locations at the well-head structure. The DD − MVFM can be employed in three ways. The first way is to be used as a verification tool for multiphase physical flow meters (MPFMs), making sure they are working properly and increasing confidence in the collected readings. The second way is to use the DD − MVFM as a redundant tool when the MPFMs are not available or going through maintenance. The third way, which is the main objective of our research, is to employ the proposed DD MVFM as a standalone for the complete replacement of current and future MPFM installments. This, significantly lowers the operating cost, reducing the required portable field tests, and saving the need to build a major infrastructure for the set-up of MPFMs for new oil wells. Consequently, this contributes to the ambitious goal of reducing CO2 emissions. The development of the DD − MVFM encompasses the fusion of multiple data wrangling and machine learning algorithms to achieve the required performance. The testing results of the proposed DD − MVFM and the prediction experiments show that it successfully achieved a performance of 85%. These results will be significantly improved in the future after incorporating more data from the previous and coming field test reports. © The Author(’s).

关键词： Oil well testing

来源：评论

学校读者我要写书评

暂无评论

Geometric Interpretation of Sensitivity to Structured Uncertainties in Spintronic Networks

引用

IEEE Control Systems Letters 2025年 9卷 192-197页

作者： O'Neil, S.P. Jonckheere, E.A. Schirmer, S. United States Military Academy Department of Electrical Engineering and Computer Science NY United States University of Southern California Dept of Electrical and Computer Engineering CA United States Swansea University Faculty of Science and Engineering Physics United Kingdom

We present a geometric model of the differential sensitivity of the fidelity error for state transfer in a spintronic network based on the relationship between a set of matrix operators. We show an explicit dependence of the differential sensitivity on the fidelity (error), and we further demonstrate that this dependence does not require a trade-off between the fidelity and sensitivity. We prove that for closed systems, ideal performance in the sense of perfect state transfer is both necessary and sufficient for optimal robustness in terms of vanishing sensitivity. We demonstrate the utility of this geometric interpretation of the sensitivity by applying the model to explain the sensitivity versus fidelity error data in two examples. © 2017 IEEE.

关键词： Sensitivity analysis

来源：评论

学校读者我要写书评

暂无评论

K-Band QPSK PMCW Radar with Digital I/Q Constellation Phase Compensation and I/Q Imbalance Correction

K-Band QPSK PMCW Radar with Digital I/Q Constellation Phase ...

引用

2025 IEEE Topical Conference on Wireless Sensors and Sensor Networks, WiSNeT 2025

作者： Thompson, Derek Li, Changzhi Dept. of Electrical and Computer Engineering Texas Tech University LubbockTX United States

ISBN: (纸本)9798331507336

This paper presents a novel K-Band Quadrature Phase Shift Keying (QPSK) phase-modulated continuous-wave (PMCW) radar front end architecture with digital I/Q constellation phase compensation and I/Q channel imbalance correction. Although QPSK is a very common form of digital phase modulation, it is rarely reported for PMCW radar systems, especially those designed on printed circuit board (PCB) technology. A MATLAB simulation platform is also developed and presented to help verify the benefits of QPSK PMCW radar for range detection. © 2025 IEEE.

关键词： MATLAB

来源：评论

学校读者我要写书评

暂无评论

Observation-Transformed Distributed Detection in Sensor Networks 59

Observation-Transformed Distributed Detection in Sensor Netw...

引用

59th Annual Conference on Information Sciences and Systems, CISS 2025

作者： Cao, Lei Viswanathan, Ramanarayanan University of Mississippi Dept. of Electrical and Computer Engineering OxfordMS38677 United States

ISBN: (纸本)9798331513269

Distributed detection (DD) plays a crucial role in sensor networks, where sensors gather data from a region of interest and report their observations to a fusion center (FC). The FC then makes a decision regarding a specific task, such as determining the presence or absence of a target. Given the constraints imposed by the transmission power, bandwidth, and noise impact in both sensing and data reporting channels, what should be reported from the sensors significantly affects the final detection accuracy. Existing methods include observation-untransformed DD (UDD), codewords-based DD (CDD), and quantized-but-uncoded DD (QDD). In this paper, we attempt to find the optimal sensor decision rule, i.e., the best transform for the observed data to be reported, by formulating the task as a functional optimization problem. To bypass the difficulty of theoretically solving the problem, we present two methods: an approximation function and a numerical solution for the Gaussian noise case. Our simulation results demonstrate that a variation of the hyperbolic tangent function can be an effective approximation of the optimal transform. This work could lead to further studies on the optimal design for distributed detection. © 2025 IEEE.

关键词： Hyperbolic functions

来源：评论

学校读者我要写书评

暂无评论

Encoding Cyclic Redundancy Checked Sequences 5

Encoding Cyclic Redundancy Checked Sequences

引用

5th IEEE Middle East and North Africa COMMunications Conference, MENACOMM 2025

作者： Abdel-Ghaffar, Khaled A. S. University of California Dept. Electrical and Computer Engineering DavisCA95616 United States

ISBN: (纸本)9798331519957

The undetected error probability of cyclic redundancy checks (CRC) combined with an error-correcting code in a concatenated coding scheme is considered. It is shown that this probability depends very much on the encoding of the cyclic redundancy checked sequences into codewords in the error-correcting code. Furthermore, it is proved that the average undetected error probability of the concatenated code over all linear encoders of the error-correcting code is about 1/2 of that of the error-correcting code, where is the degree of the CRC polynomial. In particular, for any CRC polynomial of degree , there exists an encoding function of the error-correcting code such that the undetected error probability of the concatenated scheme is at most 1/2 of that of the error-correcting code. © 2025 IEEE.

关键词： Concatenated codes

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：