检索结果-内蒙古大学图书馆

Comparative Analysis between Three-Leg Interleaved and Conventional Bidirectional Converters Applied in Battery of Wind Power-Battery Unit Supplying an Islanded Microgrid

Comparative Analysis between Three-Leg Interleaved and Conve...

引用

IEEE General Meeting Power& Energy Society

作者： André C. Do Nascimento Giusep M. S. Ribeiro Lindemberg R. de Lima Pedro A. de Alcântara Luana C. S. Soares Luciano S. Barros Camila M. V. Barros Electrical Engineering Graduate Program Federal Institute of Pará Belém Brazil Electrical Engineering Graduate Program Federal University of Paraíba João Pessoa Brazil Mathematics and Computational Modeling Graduate Program Federal University of Paraíba João Pessoa Brazil Computer Systems Department Federal University of Paraíba João Pessoa Brazil

ISBN: (数字)9798350381832

ISBN: (纸本)9798350381849

Battery energy storage systems (BESS) are crucial for microgrids, enhancing dynamic performance and mitigating uncertainties inherent to isolated environments characterized by intermittent power generation. When microgrid is supplied by wind power in connection with BESS, the bidirectional DC-DC converter associated with BESS assumes a critical responsibility—ensuring the control of a wind power supplied DC-link. This permits the Voltage Source Inverter (VSI) to synthesize consistent voltages for the connected AC load. However, challenges emerge, particularly in arduous stress on switches of the bidirectional converter attributed to elevated current ripple. This stress does not only prejudice the overall system’s functioning but can also potentially leading it to shutdown in case of switch failure. Traditionally, the conventional buck-boost converter topology has been the go-to choice for this application, nevertheless, exploring novel converter topologies, such as interleaved bidirectional DC-DC converter (IBDC) has garnered attention, promising enhanced performance. This paper’s goal is to conduct a comparative analysis of the operation of these converters in an islanded microgrid supplied by a single Permanent Magnet Synchronous Generators (PMSG) small-scale wind turbine with a BESS system. Load variation with Maximum Power Point Tracking (MPPT) operation of the PMSG is performed during MATLAB/Simulink environment simulations. The results suggest significant advantages for the interleaved three-phase converter, such as reduced battery charging current ripple, switch disturbance, and voltage ripple in the DC-link.

关键词： Maximum power point trackers Magnetic separation Microgrids DC-DC power converters Wind power generation Permanent magnets Batteries Topology Wind turbines Stress

来源：评论

学校读者我要写书评

暂无评论

Corrections to 'Improved Renyi Entropy Benchmark for Performance Assessment of Common Cascade Control System'

引用

IEEE Access 2023年 11卷 61273-61273页

作者： Zhang, Qian Wang, Ya-Gang Lee, Fei-Fei Chen, Qiu Sun, Zhen University of Shanghai for Science and Technology School of Optical-Electrical and Computer Engineering Shanghai200093 China Kogakuin University Major of Electrical Engineering and Electronics Graduate School of Engineering Tokyo163-8677 Japan

In the above article [1], the affiliation of the coauthor Qiu Chen is currently listed incorrectly. His correct affiliation should be stated as 'Major of electrical engineering and Electronics, graduate School of engineering, Kogakuin University, Tokyo, Japan.' Furthermore, it is necessary to rectify the biographical details of the coauthor Qiu Chen as follows: © 2013 IEEE.

关键词： Cascade control systems

来源：评论

学校读者我要写书评

暂无评论

Multi-modal Multitask Learning Model for Simultaneous Classification of Two Epilepsy Biomarkers 27th

Multi-modal Multitask Learning Model for Simultaneous Classi...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Broti, Nawara Mahmood Sawada, Masaki Takayama, Yutaro Iijima, Keiya Iwasaki, Masaki Ono, Yumie Electrical Engineering Program Graduate School of Science and Technology Meiji University Kanagawa Kawasaki Japan Department of Neurosurgery Yokohama City University Hospital Kanagawa Yokohama Japan Department of Neurosurgery National Center Hospital National Center of Neurology and Psychiatry Tokyo Kodaira Japan Department of Electronics and Bioinformatics School of Science and Technology Meiji University Kanagawa Kawasaki Japan

ISBN: (纸本)9783031781971

Accurate estimation of the epileptogenic zone is critical for surgical treatment of drug-resistant epilepsy. While epilepsy biomarkers detection for epileptogenic zone localization has traditionally relied on expert clinician knowledge, the use of deep learning in this context has recently gained appeal for objective diagnosis and reducing clinician burden. However, previously proposed classifiers for electrocorticogram data focused on only single biomarkers among many types, requiring separate models and large datasets for each. To minimize clinicians’ workload and patients’ sufferings, innovative methods to classify multiple biomarkers using small training datasets and minimal computation time is required. This research marks the first implementation of multi-modal multitask learning in epilepsy biomarker classification, proposing a model to automatically classify two biomarkers—high-frequency oscillations (HFO) and interictal epileptiform discharges (IED)—from separate datasets simultaneously. We validated the proposed model on 1500 annotated HFO and IED candidate signals each, obtained from 5 patients. Our proposed model can perform both HFO and IED classification simultaneously, with cross-validation accuracies of 90.99% and 93.99%;F1 scores were reported as 0.80 and 0.82, respectively. Our leave-one-patient-out experiments achieved 78.03% and 81.19% accuracy for HFO and IED classification, respectively. Compared to existing state-of-the-art classification architectures, our model is shown to be efficient and robust, yet simple and lightweight. The usefulness of sharing parameters between the two classifiers was confirmed in this practical clinical setting of epileptic biomarker detection, potentially contributing to minimizing the number of annotated datasets and realizing robust, accurate, and simultaneous identification of two biomarkers. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Verification of Animal External Ear Model-based Microphone Sensor for Hazardous Sound Detection 6

Verification of Animal External Ear Model-based Microphone S...

引用

6th International Symposium on Advanced Technologies and Applications in the Internet of Things, ATAIT 2024

作者： Yamada, Miho Kumaki, Takeshi Kageyama, Kyosuke Graduate School of Science and Engineering Kindai University 3-4-1 Kowakae Higashi-Osaka Osaka Japan Dept. of Electronic and Computer Engineering Ritsumeikan University 1-1-1 Noji-Higashi Shiga Kusatsu Japan Dept. of Electrical Electronic and Communication Engineering Kindai University 3-4-1 Kowakae Higashi-Osaka Osaka Japan

Hazardous sounds represent a particular type of danger signal and should be heard clearly to ensure safety. Hearing-impaired people can be involved in accidents. This is exacerbated by the fact that they may have difficulty hearing hazardous sounds. Therefore, they spend time with a hearing-assistance dog in their daily lives. However, the number of hearing-assistance dogs has decreased recently, and they are less known in society and they may even be prevented from entering public facilities. Therefore, an animal external ear model-based mobile device that can detect hazardous sounds has been proposed. This device can alert the hearing-impaired person. In this paper, the animal external attachment with a human- and a cat-external ear model-verified for hazardous sound detection accuracy by microphone sensor is presented. Microphone sensors with and without a human- and a cat-external ear model are used. An ambulance siren and a bicycle bell are used as the hazardous sounds, and the spectral envelopes of each recorded sound are compared. The results show that the animal external ear model-based microphone sensor can more effectively detect the frequency features of the ambulance siren and the bicycle bell. A microphone sensor attached an external attachment with a human-external ear model can detect 2 ∼ 3 kHz frequency features with the highest sound pressure compared to the other microphones, regardless of the distance between the microphone sensor and the sound source. Also, a microphone sensor attached an external attachment with a cat-external ear model can detect wide range of frequencies with the highest sound pressure compared to the other microphone sensors, regardless of the distance between the microphone sensor and the sound source. © 2024 Copyright for this paper by its authors.

关键词： Bicycles

来源：评论

学校读者我要写书评

暂无评论

A Simple Baseline with Single-encoder for Referring Image Segmentation

arXiv

引用

arXiv 2024年

作者： Yu, Seonghoon Jung, Ilchae Han, Byeongju Kim, Taeoh Kim, Yunho Wee, Dongyoon Son, Jeany AI Graduate School GIST Korea Republic of NAVER Cloud Korea Republic of Electrical Engineering and Computer Science GIST Korea Republic of

Referring image segmentation (RIS) requires dense vision-language interactions between visual pixels and textual words to segment objects based on a given description. However, commonly adapted dual-encoders in RIS, e.g. Swin transformer and BERT (uni-modal encoders) or CLIP (a multi-modal dual-encoder), lack dense multi-modal interactions during pretraining, leading to a gap with a pixel-level RIS task. To bridge this gap, existing RIS methods often rely on multi-modal fusion modules that interact two encoders, but this approach leads to high computational costs. In this paper, we present a novel RIS method with a single-encoder, i.e. BEiT-3, maximizing the potential of shared self-attention across all framework components. This enables seamless interactions of two modalities from input to final prediction, producing granularly aligned multimodal features. Furthermore, we propose lightweight yet effective decoder modules, a Shared FPN and a Shared Mask Decoder, which contribute to the high efficiency of our model. Our simple baseline with a single encoder achieves outstanding performances on the RIS benchmark datasets while maintaining computational efficiency, compared to the most recent SoTA methods based on dual-encoders. © 2024, CC BY.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Push4Rec: Temporal and Contextual Trend-Aware Transformer Push Notification Recommender

Push4Rec: Temporal and Contextual Trend-Aware Transformer Pu...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Chu-Chun Yu Ming-Yi Hong Chiok-Yew Ho Che Lin Graduate Institute of Communication Engineering National Taiwan University Taiwan Graduate Program of Data Science National Taiwan University and Academia Sinica Taiwan Department of Electrical Engineering National Taiwan University Taiwan

Push notifications efficiently deliver real-time messages, boosting user engagement and website traffic. However, users often passively receive notifications without active interaction in recommendation contexts. Consequently, for precise recommendations, Click-Through Rate (CTR) prediction for push notifications requires addressing challenges such as user temporal and contextual preferences, the dynamic nature of user click behavior, and limited interactions between users and items. We propose Push4Rec, a novel push notification recommendation model designed explicitly for news articles. Push4Rec integrates pivotal learners to extract information adeptly. It assesses click behavior, captures preferences, and comprehends trends’ influence. A fusion function and gating network ensure versatile extraction of user click preferences. We assessed Push4Rec using a real-world push notification dataset from our partnering company. Push4Rec outperformed benchmark models, delivering state-of-the-art results across all evaluation metrics. Thus, we believe that Push4Rec, with its novel approach, sets a new standard in push notification services, driving forward the field of personalized recommendation systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

BAQET: BRAM-aware Quantization for Efficient Transformer Inference via Stream-based Architecture on an FPGA 25

BAQET: BRAM-aware Quantization for Efficient Transformer Inf...

引用

Proceedings of the 2025 ACM/SIGDA International Symposium on Field programmable Gate Arrays

作者： Ling-Chi Yang Chi-Jui Chen Trung Le Bo-Cheng Lai Scott Hauck Shih-Chieh Hsu Institute of Electronics National Yang Ming Chiao Tung University Hsinchu Taiwan Graduate Degree Program of College of Electrical and Computer Engineering in National Yang Ming Chiao Tung University Hsinchu Taiwan Electrical and Computer Engineering in University of Washington Seattle USA Electrical and Computer Engineering University of Washington Seattle USA Physics University of Washington Seattle USA

ISBN: (纸本)9798400713965

FPGAs are a compelling substrate for supporting machine learning inference. Tools such as High-Level Synthesis and hls4ml can shorten the development cycle for deploying ML algorithms on FPGAs, but can struggle to handle the large on-chip storage needed for many of these models. In particular the high BRAM usage found in many of these flows can cause Place & Route failures during synthesis. In this paper we propose using a Simulated-Annealing based flow to perform BRAM-aware quantization. This approach trades off inference accuracy with BRAM usage, to provide a high-quality inference engine that still meets on-chip resource constraints. We demonstrate this flow for Transformer-based machine learning algorithms, which include Flash Attention in a Stream-based Dataflow architecture. Our system imposes minimal accuracy drops, yet can reduce BRAM usage by 20%-50%, and improve power efficiency by 264%-812% compared to existing Transformer-based accelerators on FPGAs

关键词： efficient transformer

来源：评论

学校读者我要写书评

暂无评论

Solution Processable Mos2 Based Memristive Synapse for Brain Inspired Computing

Solution Processable Mos2 Based Memristive Synapse for Brain...

引用

IEEE Conference on Nanotechnology

作者： Hanrui Li Dayanand Kumar Nazek El-Atab Smart Advanced Memory Devices and Applications (SAMA) labs Electrical and Computer Engineering Program Computer Electrical Mathematical Science and Engineering (CEMSE) Division KAUST Thuwal Saudi Arabia

As a novel 2D material, MoS 2 has shown excellent electrical properties and resistive switching characteristics to work as a switching layer for non-volatile memory. In this work, we drop cast the MoS 2 solution to prepare the thin film and deposit an interfacial layer of Al 2 O 3 . We demonstrate the proposed memristive device with Cu/Al 2 O 3 /MoS 2 /Pt structure to work as an artificial synapse. The device shows a steady resistive switching behavior with the SET and RESET voltages of 1.3 V and -0.5 V, respectively. We further demonstrate the synapse behavior via a Hopfield Neural Network (HNN) and achieve image recognition and reconstruction with a high accuracy of 96% after 15 training epochs.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Informative and Long-Term Response Generation using Multiple Suggestions and User Persona Retrieval in a Dialogue System

引用

APSIPA Transactions on Signal and Information Processing 2024年第2期13卷

作者： Hsu, Jia-Hao Chen, Tsai-Yi Wu, Chung-Hsien Department of Computer Science and Information Engineering National Cheng Kung University Tainan Taiwan Graduate Program of Artificial Intelligence National Cheng Kung University Tainan Taiwan

Enhancing user satisfaction in dialogue systems relies on their ability to understand users and generate responses that meet their expectations. This study proposes a dialogue system that incorporates the Multi-Suggestions Transformer (MST) to generate informative and long-term responses. The MST combines empathy suggestions, system persona suggestions, and knowledge suggestions to produce comprehensive and informative responses. Additionally, the system employs a persona detection model and a persona extraction model to extract the user persona from current sentences and retrieve the most suitable user persona from the dialogue history. This facilitates long-term conversations by enabling the system to remember and respond to sentences relevant to the user persona. The proposed MST-based dialogue system outperforms the baseline in terms of informativeness, as evidenced by higher scores in BLEU, BERT-score, Distinct-n, and Perplexity on the Blended Skill Talk and Multi Session Chat datasets. Furthermore, two novel evaluation metrics, PerP and PerB, introduced in this study demonstrate the system’s effective utilization of the user persona for achieving long-term dialogue. Human subjective evaluation indicates that our model consistently outperforms the baseline, achieving superior scores of 68%, 56%, 52%, and 64% in the four subjective metrics. © 2024 J.-H. Hsu, T.-Y. Chen and C.-H. Wu.

关键词： Speech processing

来源：评论

学校读者我要写书评

暂无评论

Near-Far Field Boundary Analysis and Transmit Covariance Optimization for Dual-Polarized XL-MIMO Communications

Near-Far Field Boundary Analysis and Transmit Covariance Opt...

引用

2025 IEEE Wireless Communications and Networking Conference, WCNC 2025

作者： Zeng, Shuhao Di, Boya Zhang, Hongliang Han, Zhu Poor, H. Vincent School of Electronic and Computer Engineering Peking University Shenzhen Graduate School Shenzhen China Princeton University Department of Electrical and Computer Engineering United States School of Electronics Peking University Beijing China University of Houston Electrical and Computer Engineering Department United States Kyung Hee University Department of Computer Science and Engineering Korea Republic of

ISBN: (纸本)9798350368369

Extremely large-scale multiple-input multiple-output (XL-MIMO) is expected to play an important role in future sixth generation (6G) networks. Most existing works in this area focus on single-polarized XL-MIMO, where transceivers transmit and receive signals in only one polarization direction, leading to degraded data rates. To improve multiplexing performance, in this paper, we investigate downlink XL-MIMO networks with dual-polarized antennas. However, unlike conventional dual-polarized massive MIMO, the cross-polarization discrimination (XPD) of channels vary across base station antennas in dual-polarized XL-MIMO due to the enlarged antenna aperture, leading to following two challenges. First, conventional near-far field boundary is insufficient as it only accounts for phase differences across array elements while irrespective of XPD differences. Second, existing transmit covariance optimization methods developed for dual-polarized massive MIMO cannot be directly utilized, since they are developed based on uniform XPD and pathloss assumptions. To address these challenges, we model the variations of XPD across antennas, based on which a non-uniform XPD distance is introduced to complement existing near-far field boundary. Based on the new distance criterion, we propose an efficient scheme for optimizing the transmit covariance, which considers the non-uniform XPD and pathloss. Numerical results validate our analysis and demonstrate the effectiveness of the proposed algorithm. © 2025 IEEE.

关键词： Carrier communication

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：