检索结果-内蒙古大学图书馆

8th IEEE International Forum on Research and Technologies for Society and Industry Innovation, RTSI 2024

作者： Pe, Samuele Nicora, Giovanna Guerra, Bruna Maria Vittoria Sozzi, Stefania Parimbelli, Enea University of Pavia Dept. of Electrical Computer and Biomedical Engineering Pavia Italy

ISBN: (纸本)9798350362138

Human Activity Recognition (HAR) is pivotal for automating the detection and classification of human movements. Technological advances in data collection from sensors and cameras is making automatic HAR increasingly available to support robotics-assisted rehabilitation, where the detection of abnormal patterns in movement and gait can aid clinical evaluation of patients with diverse disorders. HAR typically employs Machine Learning (ML) or Deep Learning (DL) techniques to analyze sensor data patterns for various activities. However, the generalizability of ML/DL models remains underexplored, particularly concerning the impact of different training and evaluation settings. Overfitting is a common challenge, especially in medical applications where user-dependent training data hinder generalization. Investigating the performance of ML and DL algorithms after a cross-subject (CS) and a noncross-subject (NCS) division of the dataset into training and test sets is crucial. This study aims to systematically compare various ML and DL algorithms for HAR, evaluating their performance across the CS and NCS settings to discern the impact of inter-subject variability on model generalizability. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Fault Detection and Classification Methodology for Photovoltaic Systems Through AI-based Digital Twin 3

Fault Detection and Classification Methodology for Photovolt...

引用

3rd International Conference on Energy Transition in the Mediterranean Area, SyNERGY MED 2024

作者： Kothona, Despoina Kouliousis, Asterios Christoforidis, Georgios C. Univeristy of Wesern Macedonia Dept. of Electrical and Computer Engineering Kozani Greece

ISBN: (纸本)9798350375923

This paper presents a Fault Detection and Classification (FDC) methodology using an Artificial Intelligence-based (AI-based) Digital Twin (DT). Initially, the AI-based DT simulates the generated photovoltaic (PV) power under specific environmental conditions. Subsequently, the FDC methodology assesses the system state and classifies faults. The case study in the paper considers four types of faults (shading, open circuit in one string, open circuit in two strings, and open circuit in three strings). Additionally, the time series of PV power production used in this study were simulated using MATLAB Simulink, considering real meteorological conditions with a recording frequency of one hour. The simplicity of the proposed methodology ensures its applicability to large-scale PV systems, with results indicating up to 93.6% fault classification accuracy and 100% fault detection accuracy. © 2024 IEEE.

关键词： Photovoltaics

来源：评论

学校读者我要写书评

暂无评论

Project or Factorize? A Case Study of Multiview CCA and PARAFAC2 Tensor Factorization 58

Project or Factorize? A Case Study of Multiview CCA and PARA...

引用

58th Asilomar Conference on Signals, Systems and computers, ACSSC 2024

作者： Chen, Jia Papalexakis, Evangelos E. University of California Dept. of Electrical and Computer Engineering Riverside United States Uuniversity of Californiav Dept. of Computer Science and Engineering Riverside United States

ISBN: (纸本)9798350354058

Consider learning the shared representations from multiple unlabeled views. Previous work either projects different views to the same space while enforcing the agreement among the projected views such as multiview canonical correlation analysis (MCCA), or factorizes different views while ensuring the common latent components across the views such as PARAFAC2, a tensor decomposition method. In this paper we first investigate a fundamental question: 'Do these two approaches learn different representations?' Preliminary numerical results suggest that in practice they do, which, in turn, begs the question of how we can leverage this observation in order to compute a superior representation. In this paper, we present a simple proof-of-concept scheme which augments MCCA with PARAFAC2 representations and vice-versa, and we demonstrate on multiple real datasets that such scheme can improve upon the baseline representation, paving the way for future research on optimally combining the strengths of projection and factorization methods for multiview representation learning. © 2024 IEEE.

关键词： Tensors

来源：评论

学校读者我要写书评

暂无评论

Preserving Pre-trained Representation Space: On Effectiveness of Prefix-tuning for Large Multi-modal Models

Preserving Pre-trained Representation Space: On Effectivenes...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Kim, Donghoon Lee, Gusang Shim, Kyuhong Shim, Byonghyo Dept. of Electrical and Computer Engineering Seoul National University Korea Republic of

ISBN: (纸本)9798891761681

Recently, we have observed that Large Multi-modal Models (LMMs) are revolutionizing the way machines interact with the world, unlocking new possibilities across various multi-modal applications. To adapt LMMs for downstream tasks, parameter-efficient fine-tuning (PEFT) which only trains additional prefix tokens or modules, has gained popularity. Nevertheless, there has been little analysis of how PEFT works in LMMs. In this paper, we delve into the strengths and weaknesses of each tuning strategy, shifting the focus from the efficiency typically associated with these approaches. We first discover that model parameter tuning methods such as LoRA and Adapters distort the feature representation space learned during pre-training and limit the full utilization of pre-trained knowledge. We also demonstrate that prefix-tuning excels at preserving the representation space, despite its lower performance on downstream tasks. These findings suggest a simple two-step PEFT strategy called Prefix-Tuned PEFT (PT-PEFT), which successively performs prefix-tuning and then PEFT (i.e., Adapter, LoRA), combines the benefits of both. Experimental results show that PT-PEFT not only improves performance in image captioning and visual question answering compared to vanilla PEFT methods but also helps preserve the representation space of the four pre-trained models. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Analysis on the Contribution and Economic Feasibility of Pumped Storage Hydropower in Korea Power System Considering the Penetration of Renewable Energy Generation

引用

Transactions of the Korean Institute of electrical Engineers 2023年第6期72卷 709-716页

作者： Kim, Hyun Joong Oh, Jae Young Yoon, Yong Tae Yoon, Yong Beum Dept. of Electrical and Computer Engineering Seoul National University Korea Republic of Dept. KEPCO International Nuclear Graduate School Korea Republic of

The government of South Korea proclaimed Energy Transition 3020 and the details thereupon with the generation mix. According to the Basic Plan for Long-term Electricity, additional Pump Storage Hydropower (PSH) were planned to be installed as measure for the variability from the Renewables. However, despite of the astronomical hard cost required for the PSHs, there has been a lack of assessments on the economic feasibility and effectiveness of the PSHs. According to the simulation, there were total three scenarios with high load variability due to the Renewables. The monitoring factors in each scenario were changes, in the generation cost, generation by fuel type, reserve capability by the PSHs, and emission of product gas. Furthermore, the economic feasibility was assessed from the perspectives of the PSHs. Based on the simulation, it was concluded that the additional PSHs decrease the daily generation cost and the ramping of the thermal generation, the greater reserve capabilities procured. On the other hand, emission of the product gas increases due to greater pumping load on the thermal generation. Moreover, it is economically infeasible for the PSHs to salvage their initial investment cost. Thus, this paper implicates the regulatory improvements for the formulation of the just market environment. Copyright © The Korean Institute of electrical Engineers.

关键词： Power markets

来源：评论

学校读者我要写书评

暂无评论

Power Quality Control and Comparison of a Micro Grid System Using Fuzzy MPPT Technique 5

Power Quality Control and Comparison of a Micro Grid System ...

引用

5th International Conference on Energy, Power, and Environment, ICEPE 2023

作者： Sahoo, Satyabrata Thokchom, Surmila Puhan, Pratap Sekhar Panda, Gayadhar NallaMallaReaddy Engineering College Dept. of Electrical and Electronics Engineering Hyderabad India National Institute of Technology Meghalaya Dept. of Computer Science and Engineering Meghalaya India Sreenidhi Institute of Science and Technology Dept. of Electrical and Electronics Engineering Hyderabad India National Institute of Technology Meghalaya Dept. of Electrical Engineering Meghalaya India

ISBN: (纸本)9798350313123

This paper presents a power quality control in a microgrid system using different Maximum Power Point Tracking (MPPT) techniques. The main aim of the study is to evaluate the performance of the microgrid system in terms of power quality parameters, such as harmonic distortion and voltage stability, when different MPPT techniques are employed. The microgrid system incorporates a hybrid power generation system consisting of solar panels, wind turbines, and energy storage systems, which are integrated and controlled using different MPPT techniques, including the Perturb & Observation (P&O) method and the Fuzzy MPPT technique. A single-phase sinusoidal pulse width modulation (SPWM) inverter, based on the PQ control strategy, is used to supply power to the grid and maintain a constant DC link voltage. Additionally, a fuel cell is employed to substantially reduce power fluctuations. A comparison of the power quality performance of the micro grid system using these MPPT techniques is carried out through simulation studies using MATLAB/Simulink platform. The results are analyzed and discussed in detail, and recommendations are provided for improving the power quality control of the microgrid system. © 2023 IEEE.

关键词： Wind turbines

来源：评论

学校读者我要写书评

暂无评论

Use of a Hybrid Storage System for Frequency Regulation Services from a Photovoltaic Plant: Emulating Synchronous Generator Dynamics 3

Use of a Hybrid Storage System for Frequency Regulation Serv...

引用

3rd International Conference on Energy Transition in the Mediterranean Area, SyNERGY MED 2024

作者： Papageorgiou, Pavlos G. Oureilidis, Konstantinos O. Christoforidis, Georgios C. University of Western Macedonia Dept. of Electrical & Computer Engineering Kozani Greece

ISBN: (纸本)9798350375923

The gradual decommissioning of grid-forming synchronous generators and the increasing penetration of grid-following renewable energy sources such as photovoltaics (PVs), undermine the reliable operation of the grid. In this sense, even small power imbalances can cause significant frequency deviations. To address such issues, the employment of standalone battery storage systems is usually proposed to alleviate the power imbalances by releasing/absorbing energy when needed. However, a standalone battery suffers from quick lifetime fading and it cannot effectively provide multiple grid services simultaneously. To this end, this study presents a controller for a hybrid storage system that consists of a power-type superconducting magnetic energy storage (SMES) and an energy-type battery. The hybrid storage system is AC-coupled and provides frequency regulation services on behalf of the PV plant without any modification on its inverter. Through proper control, SMES handles the short-term power fluctuations emulating the inertial properties of a synchronous generator, while battery cope with long-term demands imitating the primary frequency response of the generator. Thus, the distinct features of both SMES and battery are effectively exploited, ensuring minimal stress on battery. To evaluate the proposed method during grid frequency events, simulation results are presented. © 2024 IEEE.

关键词： Synchronous generators

来源：评论

学校读者我要写书评

暂无评论

SOH Estimation of Batteries using Lithium-Ion Internal Parameters with Convolution Neural Network and Gated Recurrent

引用

Transactions of the Korean Institute of electrical Engineers 2023年第3期72卷 387-394页

作者： Park, Hyun-Yong Lim, Hee-Sung Lee, Kyo-Beum Dept. of Electrical and Computer Engineering Ajou University Korea Republic of Dept. of IT Convergence Engineering Ajou University Korea Republic of SK Signet Inc Korea Republic of

This paper proposes an estimation method for Lithium-Ion Batteries SOH by learning the batteries’ internal parameters using the Convolution Neural Network and the Gated Recurrent Unit. Various equivalent circuit models exist to represent the batteries’ internal parameters. Among these equivalent circuit models, the most representative model is the Randles model, and the data measured based on the Randles model is used as learning input data. The internal parameters of batteries change non-linearly depending on the operation condition and use time. So, nonlinear features are extracted using the CNN input as the batteries' parameters. The extracted features are used as an input of the GRU to learn the characteristics of change over time, and SOH is predicted through this. The learning dataset utilizes 17IND10 LibForSecUse of EMPIR, which validates the performance of the proposed model. Copyright © The Korean Institute of electrical Engineers.

关键词： Lithium-ion batteries

来源：评论

学校读者我要写书评

暂无评论

Using Semeru Cloud Compiler to Enhance Cloud-Native Java Application Performance 34

Using Semeru Cloud Compiler to Enhance Cloud-Native Java App...

引用

34th Annual International Conference on Collaborative Advances in Software and Computing, CASCON 2024

作者： Liu, Ryan Shinde, Shreya Tahvildari, Ladan Stoodley, Mark Sundaresan, Vijay Pirvu, Marius University of Waterloo Dept. of Electrical and Computer Engineering Canada IBM Canada

ISBN: (纸本)9798331504830

Java-based applications rely on just-in-time (JIT) compilation to convert bytecode into machine code at run-time to improve throughput. However, JIT compilation is achieved at the cost of additional CPU cycles and memory. In the context of modern cloud, where applications have limited computing resources due to containerization, JIT compilation may potentially become a pain-point. The Semeru Cloud Compiler (SCC) is a promising solution that offloads JIT compilation to a remote cloud compiler to reduce the local overhead of JIT compilation in containers. In this paper, we outline novel research directions to further leverage the advantages of remote cloud compilation by extending the SCC to achieve two goals: (i) reduce application start-up time and (ii) improve JIT compilation decision making. To reduce application start-up time, the proposed enhancement is to extract unused or unlikely to be used Java class files from container images. The SCC can still provide the extracted class files to the client JVM if any turn out to be needed. Our preliminary experiments show that this approach can potentially reduce container image sizes by up to 22.1% and start-up times by up to 9.2% for certain applications. To reduce JIT compilation overhead, the proposed enhancement is to perform dynamic analysis of the Java application using the additional resources on the server-side. In turn, the remote JIT compilation can make more informed decisions regarding which methods to compile and optimizations to apply. We are also developing a novel visualization tool designed to help JIT compiler developers identify pain points in current JIT compilation heuristics. Specifically, we have measured that up to 18.9% of JIT compilations for certain applications may be sub-optimal due to later method inlining, and we are investigating how the SCC could help to avoid these potentially wasted compile-time computations by using information learned from other JVM clients. © 2024 IEEE.

关键词： Program compilers

来源：评论

学校读者我要写书评

暂无评论

Hydrogen powered microgrid for EV charging stations load flow analysis and optimization 21

Hydrogen powered microgrid for EV charging stations load flo...

引用

21st International Learning and technology Conference, L and T 2024

作者： Alammari, Eithar Alamro, Joud Alashwali, Sara Hassan, Rana Muthanna, Lina Barkat, Enfel Effat University Dept. of Electrical & Computer Engineering Jeddah Saudi Arabia

ISBN: (纸本)9798350393569

This paper presents an exhaustive analysis of power flow optimization within an IEEE 33-bus microgrid system using Particle Swarm Optimization (PSO) and compares it with traditional Optimal Power Flow (OPF) methods. The PSO approach is evaluated based on its effectiveness in reducing real and reactive power losses and enhancing overall system efficiency, particularly when integrated with renewable energy sources. Our study delves into the intricacies of power system optimization, examining the system's adaptability to load variations and the integration of distributed generation. The performance metrics focus on energy conservation, operational cost, system reliability, and power quality. The results from the PSO are critically assessed against those obtained from the OPF, providing insights into the suitability and effectiveness of each optimization method for modern smart grid applications. © 2024 IEEE.

关键词： Reactive power

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：