检索结果-内蒙古大学图书馆

7th International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2024

作者： Zhang, Zeyu Todo, Yuki Kanazawa University Division of Electrical Engineering and Computer Science Kanazawa Japan Kanazawa University Faculty of Electrical Information and Communication Engineering Kanazawa Japan

ISBN: (纸本)9798350350890

The Self-attention mechanism was widely applied in computer Vision (CV) field. However, while Self-attention mechanism brings high accuracy to Transformer, it also brings a huge amount of calculation. To further enhance accuracy and decrease computational load, in this paper, two refinements were implemented. Firstly, two matrices were introduced to enhance the extraction of image information for Extended-attention method. The capacity of Transformer was enhanced by these matrices to capture crucial information in complex tasks, the final accuracy and generalization performance were significantly improved. Secondly, the impact of implementing the aforementioned Self-attention mechanism at various stages of the Transformer is investigated. Intriguingly, our findings reveal that selectively implementing this method at specific stages leads to a significant enhancement in the model's performance. © 2024 IEEE.

关键词： Deep learning Different Stages Self-attention Transformer

来源：评论

学校读者我要写书评

暂无评论

Visually-Aware Context Modeling for News Image Captioning

Visually-Aware Context Modeling for News Image Captioning

引用

2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL 2024

作者： Qu, Tingyu Tuytelaars, Tinne Moens, Marie-Francine Department of Computer Science KU Leuven Belgium Department of Electrical Engineering KU Leuven Belgium

ISBN: (纸本)9798891761148

News Image Captioning aims to create captions from news articles and images, emphasizing the connection between textual context and visual elements. Recognizing the significance of human faces in news images and the face-name co-occurrence pattern in existing datasets, we propose a face-naming module for learning better name embeddings. Apart from names, which can be directly linked to an image area (faces), news image captions mostly contain context information that can only be found in the article. We design a retrieval strategy using CLIP to retrieve sentences that are semantically close to the image, mimicking human thought process of linking articles to images. Furthermore, to tackle the problem of the imbalanced proportion of article context and image context in captions, we introduce a simple yet effective method Contrasting with Language Model backbone (CoLaM) to the training pipeline. We conduct extensive experiments to demonstrate the efficacy of our framework. We outperform the previous state-of-the-art (without external data) by 7.97/5.80 CIDEr scores on GoodNews/NYTimes800k. ©2024 Association for Computational Linguistics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dynamic Model Selection for Asynchronous Federated Learning in IoBT Scenarios

Dynamic Model Selection for Asynchronous Federated Learning ...

引用

2024 IEEE International Conference on Big Data, BigData 2024

作者： Tankard, Earl Haileselassie Hagos, Desta Rawat, Danda B. Howard University Department of Electrical Engineering and Computer Science WashingtonDC United States

ISBN: (纸本)9798350362480

This paper explores the potential of Dynamic Model Selection (DMS) combined with asynchronous Federated Learning (FL) to enhance military devices within the Internet of Battlefield Things (IoBT). While previous studies have primarily focused on synchronous FL, we argue this approach has limitations. Hence, this study addresses this research gap by investigating asynchronous FL and its advantages over synchronous methods. Our main contribution lies in developing a dynamic client selection algorithm that optimizes the utility function, incorporating communication delay or latency, available computational resources, and model accuracy. This algorithm ensures clients are selected based on their potential contribution to the global model's performance, thereby improving the efficiency and effectiveness of the training process. Through experimentation with standard datasets (MNIST, CIFAR-10) and our custom dataset (Common Objects in Battlefield (COBA)) tailored for battlefield scenarios, we demonstrate the effectiveness of asynchronous FL and dynamic client selection. By addressing this critical research gap and providing empirical evidence, our study advances the use of FL for battlefield decision-making, significantly contributes to developing IoBT, and offers practical insights for military applications. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Latent Variable and Classification Performance Analysis of Bird-Drone Spectrograms with Elementary Autoencoder

IEEE Transactions on Radar Systems

引用

IEEE Transactions on Radar Systems 2024年 3卷 115-123页

作者： White, Daniel Jahangir, Mohammed Mishra, Amit Kumar Baker, Chris J. Antoniou, Michail University Of Birmingham School Of Electrical Electronic And Systems Engineering United Kingdom Aberystwyth University Department Of Computer Science United Kingdom

Deep learning with convolutional neural networks has been widely utilised in radar research concerning automatic target recognition. Maximising numerical metrics to gauge the performance of such algorithms does not necessarily correspond to model robustness against untested targets, nor does it lead to improved model interpretability. Approaches designed to explain the mechanisms behind the operation of a classifier on radar data are proliferating, but bring with them a significant computational and analysis overhead. This work uses an elementary unsupervised convolutional autoencoder (CAE) to learn a compressed representation of a challenging dataset of urban bird and drone targets and subsequently if apparent quality of the representation via preservation of class labels leads to better classification performance after a separate supervised training stage. It is shown that a CAE that reduces the features output after each layer of the encoder gives rise to the best drone vs bird classifier. A clear connection between unsupervised evaluation via label preservation in the latent space and subsequent classification accuracy after supervised fine-tuning is shown, supporting further efforts to optimise radar data latent representations to enable optimal performance and model interpretability. © 2023 IEEE.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

Very-Short-Term Solar Power Prediction Using a Suboptimal Multiple Fading Kalman Filter

Very-Short-Term Solar Power Prediction Using a Suboptimal Mu...

引用

2025 IEEE Texas Power and Energy Conference, TPEC 2025

作者： Nazaralizadeh, Solmaz Banerjee, Paramarshi Karimi, Sepehr Srivastava, Anurag K. Famouri, Parviz West Virginia University Lane Department of Computer Science and Electrical Engineering Morgantown United States

ISBN: (纸本)9798331541125

The uncertain nature and variability in solar power generation requires the development of methods to further improve the solar forecasting, specifically in very short term to drive the system operational decisions. With regard to this issue, this paper provides an innovative approach for predicting solar power in very short term using a Suboptimal Multiple Fading Extended Kalman Filter (SMFEKF). In this method, the fading factors are adjusted dynamically resulting in the SMFEKF having reduced computational burden as compared to traditional Kalman Filters such as Uncented Kalman Filter (UKF) and Extended Kalman Filter (EKF). Improving estimation precision is achieved through dynamically updating the covariance of process noise and measurement noise. In the proposed method, the historical solar irradiance data, numerical weather predictions, and the real-time power measurements are used to optimize prediction precision. The proposed SMFEKF demonstrates slightly better accuracy but significantly reduced computational burden and time. © 2025 IEEE.

关键词： Extended Kalman filters

来源：评论

学校读者我要写书评

暂无评论

Development of a String Transfer Assist Device for Electric Bass Picking 13

Development of a String Transfer Assist Device for Electric ...

引用

13th IEEE Global Conference on Consumer Electronic, GCCE 2024

作者： Marutsuka, Ryo Tsurumi, Kazuki Koutaki, Gou Kumamoto University Department of Computer Science and Electrical Engineering Kumamoto860-8555 Japan

ISBN: (纸本)9798350355079

This laboratory is developing a semi-automatic performance robot that involves human interaction. The robot is designed to provide an active performance experience. It is not fully automated, but rather semi-automated to allow for human involvement. While there have been robots in the past that assist with string pressing, playing the bass guitar can be challenging for beginners due to the need to pluck the strings separately with single notes. This presentation discusses the development of a device that facilitates picking motions in electric bass playing. © 2024 IEEE.

关键词： User centered design

来源：评论

学校读者我要写书评

暂无评论

Absorptive Microwave Filters: From Narrowband to Wideband Operation

Absorptive Microwave Filters: From Narrowband to Wideband Op...

引用

2024 International Applied Computational Electromagnetics Society Symposium, ACES-China 2024

作者： Cui, Jiaqian Zhu, Lei University of Macau Faculty of Science and Technology Department of Electrical and Computer Engineering Macau China

ISBN: (纸本)9798350355581

This paper presents a method to control the out-ofband performance of absorptive filters in both narrowband and wideband cases. To verify the method, a narrowband absorptive filter is designed with wideband matching, and a wideband one is proposed to achieve an infinite low-reflection range. Finally, the narrowband filter is implemented in microstrip-line platform, not only attaining symmetrical geometry but also improving impedance-matching performance. © 2024 IEEE.

关键词： Wiener filtering

来源：评论

学校读者我要写书评

暂无评论

Negative Differential Resistance Regime of Field Emitter Arrays 82

Negative Differential Resistance Regime of Field Emitter Arr...

引用

82nd Device Research Conference, DRC 2024

作者： Shin, Y. Chern, W. Karaulac, N. Akinwande, A. Mit Department of Electrical Engineering and Computer Science CambridgeMA02139 United States

ISBN: (纸本)9798350373738

Silicon field emitter arrays (FEAs) -based cold cathodes have shown promise in many applications under harsh environments such as x-ray sources and high-power microwave devices due to the temperature independence of tunneling current and the property of ballistic transport [ 1 - 3 ]. We report an unexpected, yet reproducible Negative Differential Resistance (NDR) region within the device output characteristics of gated FEAs. These results were obtained by utilizing an on-chip flat silicon anode with etched stand-offs to define the anode-to-emitter distances of AE, is lower than the gate voltage, V GE. © 2024 IEEE.

关键词： Anodes

来源：评论

学校读者我要写书评

暂无评论

Implementation of Variable Capacitance to Improve Efficiency for Asymmetric LCC-LCC Compensated Wireless Power Transfer Systems

Implementation of Variable Capacitance to Improve Efficiency...

引用

2024 Energy Conversion Congress and Expo Europe, ECCE Europe 2024

作者： Zhu, Gangwei Dong, Jianning Wang, Jundong Deng, Zichen Li, Yongpeng Bauer, Pavol Delft University of Technology Mathematics and Computer Science Department of Electrical Engineering Delft Netherlands

ISBN: (纸本)9798350364446

This paper proposes a variable-capacitance-based control strategy to improve efficiency for asymmetric LCC-LCC compensated wireless power transfer (WPT) systems. While the existing triple-phase-shift (TPS) method can achieve power regulation and wide-range zero-voltage-switching (ZVS), it results in significantly increased reactive power under asymmetric LCC-LCC compensation topology. To this end, this paper incorporates a switch-controlled-capacitor (SCC) on the primary side. The impact of variable capacitance on the system characteristics is first investigated. Furthermore, the optimal capacitor tuning factor is derived to achieve the inverter ZVS with minimal reactive power. Through the implementation of variable capacitance, the primary inductor current is notably reduced within a wide range of power. Moreover, the turn-off currents of power switches are minimized. These factors contribute to a reduction in inductor and inverter losses, thus improving the overall efficiency. Experimental results confirm that the proposed method improves the efficiency of an asymmetric LCC-LCC compensated WPT prototype, with a maximum efficiency improvement of up to 1.8%. © 2024 IEEE.

关键词： Capacitor bank

来源：评论

学校读者我要写书评

暂无评论

Multi-Level-Resistance Gate Driver for SiC Motor Drives to Control dv/dt and Reduce Switching Loss 11

Multi-Level-Resistance Gate Driver for SiC Motor Drives to C...

引用

11th IEEE Workshop on Wide Bandgap Power Devices and Applications, WiPDA 2024

作者： Bose, Abhishek Jiang, Peiwen Higgins, Hayden Huang, Qingyun University of Missouri Department of Electrical Engineering and Computer Science ColumbiaMO United States

ISBN: (纸本)9798350375602

Designing an optimal gate driver resistance for SiC motor drive inverters to meet the maximum dv/dt requirement is extremely critical in prolonging the motor lifetime. However, for SiC MOSFETs, turn on voltage slew rate dv/dt, decreases with increasing switching current, leading to an additional and undesirable increase in switching turn-on losses. This paper investigates how gate driver could be optimized to meet the maximum voltage slew rate through a sinusoidal load current by changing external gate resistance in limited change levels. Therefore, the switching turn-on losses under the maximum dv/dt will be significantly reduced compared to using the fixed gate driver resistance. In the proposed approach, the dynamic turn-on behaviour of SiC MOSFETs with regards to increasing miller platform voltage and decreasing dv/dt, is taken into consideration. In this paper, We theoretically demonstrate the effectiveness of the proposed multi-level resistance gate driver for SiC motor drive based on the analytical dv/dt and power loss model. The results show that by adjusting gate resistances with a few changing levels while meeting the maximum specified dv/dt requirement, turn-on switching loss can be reduced from 10 mJ to 4.5 mJ at device transconductance 12 S. © 2024 IEEE.

关键词： MOSFET devices

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：