检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Cho, Wonguk Park, Jinha Kim, Taesup Graduate School of Data Science Department of Electrical and Computer Engineering Seoul National University Korea Republic of

Continual domain shift poses a significant challenge in real-world applications, particularly in situations where labeled data is not available for new domains. The challenge of acquiring knowledge in this problem setting is referred to as unsupervised continual domain shift learning. Existing methods for domain adaptation and generalization have limitations in addressing this issue, as they focus either on adapting to a specific domain or generalizing to unseen domains, but not both. In this paper, we propose Complementary Domain Adaptation and Generalization (CoDAG), a simple yet effective learning framework that combines domain adaptation and generalization in a complementary manner to achieve three major goals of unsupervised continual domain shift learning: adapting to a current domain, generalizing to unseen domains, and preventing forgetting of previously seen domains. Our approach is model-agnostic, meaning that it is compatible with any existing domain adaptation and generalization algorithms. We evaluate CoDAG on several benchmark datasets and demonstrate that our model outperforms state-of-the-art models in all datasets and evaluation metrics, highlighting its effectiveness and robustness in handling unsupervised continual domain shift learning. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Experimental Study of a MISO-VLC using two LED Luminaires

Experimental Study of a MISO-VLC using two LED Luminaires

引用

IEEE/LEOS International Conference on Optical MEMS

作者： David Esteban Farfán-Guillén Luis Carlos Vieira Alexandre De Almeida Prado Pohl Graduate Program in Electrical and Computer Engineering (CPGEI) Universidade TecnolÓgica Federal do Paraná (UTFPR) Curitiba Brazil

In this work, the multiple-input, single-output (MISO) technique is implemented with OFDM modulation and the variation of the cyclic prefix (CP) is used to optimize the performance of an indoor VLC link, while maintaining the lighting conditions within the recommended levels (300–500 lux). Results show that by increasing the number of luminaires and by selecting the appropriate value of the OFDM cyclic prefix, the system's bit error rate (BER ≤ 10– 3 ) is improved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ADMM-SRNet: Alternating Direction Method of Multipliers Based Sparse Representation Network for One-Class Classification

引用

IEEE Transactions on Image Processing 2023年 32卷 2843-2856页

作者： Chiou, Chien-Yu Lee, Kuang-Ting Huang, Chun-Rong Chung, Pau-Choo National Cheng Kung University Department of Electrical Engineering Tainan 701 Taiwan National Chung Hsing University Department of Computer Science and Engineering Taichung 402 Taiwan National Cheng Kung University Cross College Elite Program and Academy of Innovative Semiconductor and Sustainable Manufacturing Tainan 701 Taiwan

One-class classification aims to learn one-class models from only in-class training samples. Because of lacking out-of-class samples during training, most conventional deep learning based methods suffer from the feature collapse problem. In contrast, contrastive learning based methods can learn features from only in-class samples but are hard to be end-to-end trained with one-class models. To address the aforementioned problems, we propose alternating direction method of multipliers based sparse representation network (ADMM-SRNet). ADMM-SRNet contains the heterogeneous contrastive feature (HCF) network and the sparse dictionary (SD) network. The HCF network learns in-class heterogeneous contrastive features by using contrastive learning with heterogeneous augmentations. Then, the SD network models the distributions of the in-class training samples by using dictionaries computed based on ADMM. By coupling the HCF network, SD network and the proposed loss functions, our method can effectively learn discriminative features and one-class models of the in-class training samples in an end-to-end trainable manner. Experimental results show that the proposed method outperforms state-of-the-art methods on CIFAR-10, CIFAR-100 and ImageNet-30 datasets under one-class classification settings. Code is available at https://***/nchucvml/ADMM-SRNet. © 1992-2012 IEEE.

关键词： contrastive learning deep learning dictionary learning One-class classification sparse representation

来源：评论

学校读者我要写书评

暂无评论

Utilizing Battery Energy Storage Systems to Enhance the Integration of Photovoltaic Systems for Damping Oscillations

Utilizing Battery Energy Storage Systems to Enhance the Inte...

引用

IEEE Southeastcon

作者： Ilham Akbar Ariesa Budi Zakaria Mayur Basu Eduard Muliadi Suwarno Nanang Hariyanto Graduate Program PLN-ITB PLN Corporate University Auburn USA Electrical and Computer Engineering Auburn University Auburn USA School of Electrical Engineering and Informatics Institut Teknologi Bandung (ITB) Bandung Indonesia

As the integration of Variable Renewable Energy (VRE) generators into power systems increases, there is a potential decrease in overall system reliability, particularly in terms of stability. This research suggests the integration of a Battery Energy Storage System (BESS) into a power system with Variable Renewable Energy sources, such as a utility-scale Photovoltaic (PV) plant, to accelerate the damping of post-fault oscillations following a short-circuit disturbance. The objective is for a Power Oscillation Damping (POD) within the PV plant to address post-fault oscillations within a specific timeframe. The POD in the PV plant is designed to supply additional active and reactive power, responding to the system's demands after a disturbance. The addition of BESS to the system is anticipated to enhance the time required for the system to achieve a stable state, resulting in quicker system stabilization. Simulations conducted through PSCAD software can effectively depict the post-fault conditions of short-circuit disturbances, considering the impact of the integrated BESS.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Open Wireless Digital Twin: End-to-End 5G Mobility Emulation in O-RAN Framework

arXiv

引用

arXiv 2025年

作者： Iye, Tetsuya Sakamoto, Masaya Takaya, Shohei Sato, Eisaku Susukida, Yuki Nagaoka, Yu Maruta, Kazuki Nakazato, Jin Kozo Keikaku Engineering Inc. Tokyo Japan Department of Electronics and Computer Systems Graduate School of Engineering Takushoku University Tokyo Japan Department of Electrical Engineering Graduate School of Engineering Tokyo University of Science Tokyo Japan Graduate School of Information Science and Technology The University of Tokyo Tokyo Japan

This paper presents an end-to-end wireless digital twin platform constructed using open-source software and open data to enhance the evaluation of mobile communication systems. The proposed open wireless digital twin (OWDT) integrates OpenAirInterface (OAI) for 5G NR protocol stack emulation and NVIDIA Sionna RT for high-resolution ray tracing based radio propagation modeling. This integration enables realistic emulation of vehicular mobility scenarios, leveraging real-world geographic and building data to bridge the gap between theoretical simulations and real-world deployments. The platform utilizes ORAN’s Near-RT RIC via OAI FlexRIC to dynamically monitor key performance indicators (KPIs) such as RSRP, MCS, BLER, and throughput in real time. Through extensive evaluation in urban environments, this study demonstrates the validity of the emulation framework, revealing its capability to replicate real-world communication dynamics with high fidelity. The results underscore the potential of OWDT in accelerating wireless system development, reducing experimental costs, and optimizing network configurations. Copyright © 2025, The Authors. All rights reserved.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

The Influence of Overcharging and Over-Discharging on the Capacity Degradation of Lithium-Ion Batteries

The Influence of Overcharging and Over-Discharging on the Ca...

引用

IEEE Conference on Vehicle Power and Propulsion (VPPC)

作者： Joelton Deonei Gotz Marco Antonio Simões Teixeira Fernanda Cristina Corrêa Emilson Ribeiro Viana Alceu André Badin Milton Borsato Graduate Program in Electrical and Computer Engineering Federal Technological University of Paraná (UTFPR-CT) Curitiba Brazil Graduate Program in Informatics (PPGIa) Pontifical Catholic University of Paraná (PUC-PR) Curitiba Brazil Graduate Program in Electrical Engineering Federal Technological University of Paraná (UTFPR-PG) Ponta Grossa Brazil Physics Department Graduate Program in Physics and Astronomy Federal Technological University of Paraná (UTFPR-CT) Curitiba Brazil Graduate Program in Mechanical Engineering Federal Technological University of Paraná (UTFPR-CT) Curitiba Brazil

ISBN: (数字)9798331541606

ISBN: (纸本)9798331541613

Lithium-ion batteries (LIB) are the best technology for supplying and storing energy for electric mobility systems. Despite that, this technology is sensitive to abuses that can compromise its lifetime and cause fire and explosion risks. In this context, if LIB is not correctly controlled, some abuses, such as overcharging (OC) and over-discharging (OD), can be observed and provoke a loss of capacity. Therefore, this work presented the application of several experiments in cells, of the NMC type, under OC and the combination of OC and OD. The results indicated that cells charged until 4.4 and 4.5 V and discharged until 3.0 V do not lose capacity for twenty-five cycles, but more cycles should be done to understand the impact over time. On the other side, the cell charged until 4.6 and 4.8 V had its security protection romped in the fourth charging cycle, and the cell charged until 5.0 V had its safety compromised in the first charging cycle. Conversely, cells with a combination of OC and OD were more compromised. In this context, while a cell is submitted only with OC and does not lose capacity, a cell under OC and then under OD had its protection romped in the third charging cycle. Cells under 4.6 V and 4.8 V lost capacity during the second charging cycle. In conclusion, OC provokes a high level of degradation in the cell, but the combination of OC and OD causes even more degradation.

关键词： Degradation Lithium-ion batteries Battery management systems Propulsion Security Reliability Protection Stress Monitoring Predictive maintenance

来源：评论

学校读者我要写书评

暂无评论

Into 3D-Reconstructed Apparel over Virtual Try-On with Virtual Reality

Into 3D-Reconstructed Apparel over Virtual Try-On with Virtu...

引用

IEEE International Conference on Consumer Electronics-Taiwan (ICCE-TW)

作者： Surasachai Doungtap Jirayu Petchhan Varinya Phanichraksaphong Jenq-Haur Wang International Graduate Program of Electrical Engineering and Computer Science Dept. of Electrical Engineering National Taiwan University of Science & Technology Taiwan R. O. C. Department of Computer Science and Information Engineering National Taipei University of Technology Taiwan R. O. C.

Virtualization technologies are still growing bigger and faster. Despite the greatness of its advancement, the costume industry is still very accessible when it comes to real trials. Off-the-shelf stuff are inadequate details for the desired individual to assess its in-depth utility for each garment trying on for a second, including custom stuff are much harder to try out right away. To this end, 2D image-based 3D reconstruction inclusive of touchable-virtualized space is accessible easier to stuff details for mans' decision making in purchasing. We establish the overall end-to-end pipeline from reconstruction until visualization for one instance to be triable on its stuff for a moment. As an expectation, our proposed approach can bring objects into the experimental area and use them immediately without any obstacle.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Q-Learning-Based Multi-Objective Global Path Planning for UGV Navigation*

Q-Learning-Based Multi-Objective Global Path Planning for UG...

引用

IEEE Latin American Robotics Symposium, LARS

作者： Hiago O. B. Batista Thayron M. Hudson Kevin B. de Carvalho Alexandre S. Brandão Department of Electrical Engineering Graduate Program in Computer Science Núcleo de Especialização em Robótica (NERo) Universidade Federal de Viçosa Viçosa - MG Brazil

ISBN: (数字)9798331508807

ISBN: (纸本)9798331508814

This paper presents an offline path planning strategy for unmanned ground vehicles (UGVs) using Q-learning. The proposed method addresses path optimization in warehouse-like environments, where tasks involve item pickup and delivery to specific locations. The Q-learning algorithm trains an agent to determine the most efficient routes, with validation conducted in an $8 \times 5$ meter workspace equipped with an Optitrack motion capture system. The workspace was discretized into a $16 \times 10$ grid, allowing the Q-learning to effectively navigate through complex obstacle-laden scenarios. Experimental results indicate that the Q-learning approach outperforms traditional methods such as Dijkstra, A-star, and Breadth-First Search in terms of path length, number of turns, planning time, and overall success rate; being up to 7 times faster to plan a path and reducing the number of bends by up to 41%. The Q-learning based paths feature more linear segments, which contribute to energy savings and improved navigational efficiency. Future work will explore applications in heterogeneous multi-agent systems and enhancements in training time and agent collaboration.

关键词： Training Meters Q-learning Navigation Path planning Motion capture Planning Robots Optimization Multi-agent systems

来源：评论

学校读者我要写书评

暂无评论

Multi-objective Optimal Power Scheduling of A Residential Microgrid Considering V2G and Demand Response Techniques

Multi-objective Optimal Power Scheduling of A Residential Mi...

引用

2022 IEEE Industry Applications Society Annual Meeting, IAS 2022

作者： Gamil, Mahmoud M. Masrur, Hasan Muttaqi, Kashem M. Huang, Yongyi Lotfy, Mohammed Elsayed Senjyu, Tomonobu Graduate School of Science and Engineering University of the Ryukyus Okinawa903-0213 Japan School of Electrical Computer and Telecommunications Engineering University of Wollongong NSW2522 Australia Zagazig University Department of Electrical Power and Machines Zagazig44519 Egypt

ISBN: (数字)9781665478151

ISBN: (纸本)9781665478151

electrical load reshaping plays an important role in optimal power scheduling and emission reduction. Vehicle-to-grid (V2G) strategies offer an appropriate control option for flatting load duration curves despite the high burden of electric vehicles on the utility grid. Charging EV s from renewable sources is the only solution for reducing electric grid's emissions, so establishing new microgrids which depend mainly on renewable energy is highly encouraged these days. The novelty of this paper demonstrated in studying the emission reduction and multi-objective optimal power scheduling of the residential microgrids considering EVs' charging/discharging management and demand response programs. Two case studies are discussed in this research;the first one is the system without EV integration, and the second case study represents the integration of controlled EV s. The obtained results show a significant reduction in the system cost by integrating EV s to the system. © 2022 IEEE.

关键词： Vehicle-to-grid

来源：评论

学校读者我要写书评

暂无评论

The shortest lengths and the enclosure method for time dependent problems

arXiv

引用

arXiv 2023年

作者： Kawashita, Mishio Kawashita, Wakako Mathematics Program Graduate School of Advanced Science and Engineering Hiroshima University Higashihiroshima739-8526 Japan Electrical Systems and Control Engineering Program Graduate School of Advanced Science and Engineering Hiroshima University Higashihiroshima739-8527 Japan

In this article, the role of "shortest length" is discussed concerning the inverse problems with the time dependent enclosure method. In the beginning, the inclusions embedded in a non-layered medium are handled. The argument for the above case reveals why the "shortest length" is important. Next, the case where the inclusions are embedded in a two-layered medium is explained in view of the previous works by Ikehata and the authors. In addition, the regularity assumptions for the boundaries of the inclusions are *** Codes 35R30, 35L05, 35B40, 78A46 Copyright © 2023, The Authors. All rights reserved.

关键词： Enclosures

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：