检索结果-内蒙古大学图书馆

9th NAFOSTED Conference on Information and computer Science, NICS 2022

作者： Nham, Do-Hai-Ninh Nguyen, Viet-Dung Trinh, Minh-Nhat Pham, Van-Truong Tran, Thi-Thao School of Applied Mathematics and Informatics Hanoi University of Science and Technology Hanoi Viet Nam School of Electrical and Electronic Engineering Hanoi University of Science and Technology Department of Automation Engineering Hanoi Viet Nam

ISBN: (纸本)9781665454223

Fish statistics and measurements are important for aqua-environment nowadays. While physical approaches might be expensive and prone to be erroneous, some automatic methods are dependent on the necessity of full annotations for supervised segmentation process;which is time-consuming and required manual labors. Inspired by the deep-learning methods and weakly-supervised approaches, we develop an efficient network for dataset with point-level supervision that fishes are labeled in a single mouse-click. With one branch containing our proposed baseline network output, the other branch includes the affinity matrix output that both of them are concatenated before being fed into a random walk architecture to attain the final. Additionally, the proposed architecture is trained with a new loss function based on the localization-based counting fully convolutional neural network (LCFCN);before being validated on the FishSeg testing part of the DeepFish dataset. Experimental results have confirmed the validity of our proposed affinity-LCFCN (A-LCFCN) solution on such a cheap fish dataset conbining both point-labeled and fully-masked images. © 2022 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

SACR: Self-training with Saliency-Augmented Consistency Regularization for Few-Shot Learners

SACR: Self-training with Saliency-Augmented Consistency Regu...

引用

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

作者： Feng, Yanyan Zhou, Yue Xue, Yun Li, Fenghuan Lin, Zehong School of Electronics and Information Engineering South China Normal University Foshan China Department of Artiffcial Intelligence School of Informatics Xiamen University Xiamen China School of Computer Science and Technology Guangdong University of Technology Guangzhou China

ISBN: (纸本)9798350368741

Pre-trained language models have made significant strides in natural language processing tasks, enabling flexible fine-tuning for downstream applications. However, in few-shot learning scenarios, pre-trained models face challenges related to overfitting due to limited training samples, which hinders their ability to capture data diversity and robustly handle input variations. To overcome these limitations, we propose the Saliency-Augmented Consistency Regularization (SACR) framework, a novel self-training strategy designed to improve few-shot learning performance and robustness. SACR consists of three key components: (1) Saliency-guided Data Perturbation, which uses saliency analysis to identify and perturb words that significantly influence model predictions, generating semantically consistent pseudo-samples;(2) Semantic-equivalent Sample Mining, which employs K-means clustering to select semantically similar samples and prevent semantic shift;and (3) Consistency Training, where regularization ensures consistency between the semantics and prediction distributions of the original and perturbed samples. We conducted extensive experiments on 15 public datasets to evaluate our approach. SACR significantly outperforms strong baseline models and demonstrates superior generalization capabilities compared to state-of-the-art methods, achieving an average 1.0% improvement in classification accuracy. © 2025 IEEE.

关键词： consistency regularization few-shot learning saliency self-training

来源：评论

学校读者我要写书评

暂无评论

Distributed Optical Fiber Acoustic Sensing Signal Enhancement and Fading Suppression Based on Multi-channel CNN 5

Distributed Optical Fiber Acoustic Sensing Signal Enhancemen...

引用

5th International Conference on Artificial Intelligence and Electromechanical Automation, AIEA 2024

作者： Xie, Haoshen Liao, Yongqing Huang, Hongbin Li, Ximing Liu, Weiping Jinan University School of Information Science and Technology Department of Electronic Engineering Guangzhou China China Mobile Internet Co. Ltd Guangzhou China South China Agricultural University School of Mathematics and Information Department of Computer Science Guangzhou China

ISBN: (纸本)9798350366174

In conventional distributed acoustic sensing (DAS) system using phase-sensitive optical time-domain reflectometry (Φ-OTDR), the signal-to-noise ratio (SNR) of demodulated phase signals is seriously limited due to the influence of laser phase noise, laser frequency drift and interference fading. To improve the SNR of the demodulated phase and restore the original acoustic signal, we propose a multi-channel convolutional neural network based on the time domain, which fully utilizes the spatial information of adjacent multi-channels. Four different multichannel model structures are compared to determine the optimal solution. Using a large number of real noises and three types of simulated acoustic signals to generate a dataset, the model is trained to establish a mapping relationship between the multichannel noisy phases and the clean phase. The experimental results on 11 km optical fiber show that the average SNR of piezoelectric transducer (PZT) vibration signals with five different frequencies is improved from 11.4 dB to 55.9 dB after enhancement. The method can effectively suppress interference fading and restore the acoustic signal with high fidelity. © 2024 IEEE.

关键词： Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Investigations and prospects of Fabry-Perot antennas:a review

引用

Journal of Systems engineering and electronics 2021年第4期32卷 731-747页

作者： LIU Zhiming BORNEMANN Jens LIU Shaobin KONG Xiangkun Department of Electrical and Computer Engineering University of VictoriaVictoria V8W 2Y2Canada College of Electronic and Information Engineering Nanjing University of Aeronautics and AstronauticsNanjing 210016China

Fabry-Perot(FP)antennas have characteristics of planar structures combined with high gain,and they have been widely used in wireless *** the progress of ongoing research,FP antennas have achieved various capabilities,but many of them are still under development,such as lowprofile,wideband,circular polarization,multi-band,low-radar cross section(RCS)and reconfigurable *** paper discusses the theoretical analysis methods and research progress of FP antennas,and explains the realization methods of different features of FP *** order to indicate different technologies for realizing various capabilities,the key technologies and features of some of the latest designs are ***,the research situation and prospects of FP antennas are summarized to guide their research directions in the future.

关键词： Fabry-Perot(FP)antenna partially reflective surface research situation research direction

来源：评论

学校读者我要写书评

暂无评论

Control Oriented Freeway Traffic Modelling by Physics-Regularized Machine Learning

Control Oriented Freeway Traffic Modelling by Physics-Regula...

引用

International Conference on Intelligent Transportation

作者： K. Binjaku E.K. Meçe C. Pasquale S. Sacone Department of Informatics Bioengineering Robotics and Systems Engineering University of Genova Italy Department of Computer Engineering Polytechnic University of Tirana Albania

A modelling framework for freeway traffic systems specifically oriented to the definition of suitable control schemes is developed in this paper. The traffic system includes different vehicle classes (passengers and freight vehicles) whose behaviour is explicitly modelled. Vehicles can enter the free-way arriving from the mainstream or through on-ramps on which traffic volumes may be regulated with ramp metering techniques. Moreover, Artificial Intelligence (AI) techniques and, specifically a Machine Learning (ML) approach, are the modelling methodology proposed in this work. More in detail, a hybrid model is defined in which a physics-based component, provided by a multi-class version of METANET model, is added to a machine learning model as a regularization component and the derived model is trained to reproduce the behavior of different classes of users. The effectiveness of the hybrid model is shown by training and testing it with real traffic data.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimizing Dense Visual Predictions Through Multi-Task Coherence and Prioritization

Optimizing Dense Visual Predictions Through Multi-Task Coher...

引用

IEEE Workshop on Applications of computer Vision (WACV)

作者： Maxime Fontana Michael Spratling Miaojing Shi Department of Informatics King's College London Department of Behavioural and Cognitive Sciences University of Luxembourg College of Electronic and Information Engineering Tongji University

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

Multi-Task Learning (MTL) involves the concurrent training of multiple tasks, offering notable advantages for dense prediction tasks in computer vision. MTL not only reduces training and inference time as opposed to having multiple single-task models, but also enhances task accuracy through the interaction of multiple tasks. However, existing methods face limitations. They often rely on suboptimal cross-task interactions, resulting in task-specific predictions with poor geometric and predictive coherence. In addition, many approaches use inadequate loss weighting strategies, which do not address the inherent variability in task evolution during training. To overcome these challenges, we propose an advanced MTL model specifically designed for dense vision tasks. Our model leverages state-of-the-art vision transformers with task-specific decoders. To enhance cross-task coherence, we introduce a trace-back method that improves both cross-task geometric and predictive features. Furthermore, we present a novel dynamic task balancing approach that projects task losses onto a common scale and prioritizes more challenging tasks during training. Extensive experiments demonstrate the superiority of our method, establishing new state-of-the-art performance across two benchmark datasets. The code is available at: https://***/Klodivio355/MT-CP

关键词： Training computer vision Visualization Semantics Coherence Benchmark testing Predictive models Multitasking Transformers Decoding

来源：评论

学校读者我要写书评

暂无评论

The Distortion of Threshold Approval Matching

arXiv

引用

arXiv 2024年

作者： Latifian, Mohamad Voudouris, Alexandros A. Department of Computer Science University of Toronto Canada School of Computer Science and Electronic Engineering University of Essex United Kingdom

We study matching settings in which a set of agents have private utilities over a set of items. Each agent reports a partition of the items into approvals sets of different threshold utility levels. Given this limited information on input, the goal is to compute an assignment of the items to the agents (subject to cardinality constraints depending on the application) that (approximately) maximizes the social welfare (the total utility of the agents for their assigned items). We first consider the well-known, simple one-sided matching problem in which each of n agents is to be assigned exactly one of n items. We show that with t threshold utility levels, the distortion of deterministic matching algorithms is (Equation presented) while that of randomized algorithms is (Equation presented). We then show that our distortion bounds extend to a more general setting in which there are multiple copies of the items, each agent can be assigned a number of items (even copies of the same one) up to a capacity, and the utility of an agent for an item depends on the number of its copies that the agent is given. Copyright © 2024, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Bottleneck-Minimal Indexing for Generative Document Retrieval

arXiv

引用

arXiv 2024年

作者： Du, Xin Xiu, Lixin Tanaka-Ishii, Kumiko Waseda Research Institute for Science and Engineering Waseda University Japan Department of Mathematical Informatics The University of Tokyo Japan Department of Computer Science and Engineering Waseda University Japan

We apply an information-theoretic perspective to reconsider generative document retrieval (GDR), in which a document x ∈ X is indexed by t ∈ T , and a neural autoregressive model is trained to map queries Q to T . GDR can be considered to involve information transmission from documents X to queries Q, with the requirement to transmit more bits via the indexes T . By applying Shannon’s rate-distortion theory, the optimality of indexing can be analyzed in terms of the mutual information, and the design of the indexes T can then be regarded as a bottleneck in GDR. After reformulating GDR from this perspective, we empirically quantify the bottleneck underlying GDR. Finally, using the NQ320K and MARCO datasets, we evaluate our proposed bottleneck-minimal indexing method in comparison with various previous indexing methods, and we show that it outperforms those methods. © 2024, CC BY.

关键词： Signal distortion

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of Hybrid AC/DC Microgrids with Integrated Renewable Energy

Performance Evaluation of Hybrid AC/DC Microgrids with Integ...

引用

IEEE International Conference on Signal Processing, Information, Communication & Systems (SPICSCON)

作者： Md Abu Talha Md Salman Khan Mithil S. M. Tanbinul Hoque Shamim Forhad Tarifuzzaman Riyad Foisal Ahmed Suprio Himu Department of Electrical and Electronic Engineering Faculty of Engineering American International University-Bangladesh (AIUB) Dhaka Bangladesh Department of Electrical Engineering and Computer Science Electrical Engineering (MS) South Dakota School of Mines & Technology Rapid City SD United States Department of Electrical and Electronic Engineering Faculty of Engineering Leading University Sylhet Bangladesh

ISBN: (数字)9798331510213

ISBN: (纸本)9798331510220

This study examines the operational efficiency and stability of a hybrid-AC/DC microgrid integrated with renewable energy sources, addressing the need for sustainable power systems. Using the IEEE 14-bus system simulated in MATLAB/Simulink, it assesses microgrid performance under various load conditions, focusing on energy distribution and power quality. The research hypothesizes that advanced energy storage systems within microgrids smooth demand peaks, maintaining voltage stability between 0.9pu and 1pu, and Total Harmonic Distortion (THD) consistently below 5%. Analysis includes active and reactive power distributions, demand profiles, power losses, power factors, voltage levels, and harmonic distortions. Results show the hybrid microgrid maintains operational stability and efficiently manages power, with minor power quality variations during peak demand. Significant power losses were observed in low-voltage bus lines, especially lines 2 and 4, peaking at nearly 1.8kW/phase. This study offers valuable insights for designing efficient power systems, highlighting the importance of hybrid-microgrids in sustainable energy infrastructures.

关键词： Renewable energy sources Reactive power Total harmonic distortion Power quality Microgrids Voltage Power system stability Hybrid power systems Stability analysis Energy storage

来源：评论

学校读者我要写书评

暂无评论

Non-Uniform 3D Massive MIMO Arrays Topology Optimization for Near-Field Communications 35

Non-Uniform 3D Massive MIMO Arrays Topology Optimization for...

引用

35th IEEE International Symposium on Personal, Indoor and Mobile Radio Communications, PIMRC 2024

作者： Guo, Yunhui Zhang, Yang Pang, Lihua Liu, Yuanwei Ding, Zhiguo Xidian University State Key Laboratory of Integrated Service Networks Xi'an710071 China Queen Mary University of London School of Electronic Engineering and Computer Science LondonE1 4NS United Kingdom Xian University of Science and Technology School of Information Engineering Xian710054 China Khalifa University 6G Center Department of Computer and Communication Engineering Abu Dhabi United Arab Emirates

ISBN: (纸本)9798350362244

In this paper, the design of non-uniform antenna topology for 3D massive MIMO arrays in near-field communications is investigated. Specifically, the near-field spherical wavefront radiation characteristics are considered to accurately model the variations of signal phase across array elements. Subsequently, the closed-form expressions of the per-user signal-to-interference noise ratio (SINR) and achievable sum rate for a multi-user MIMO system with maximum-ratio transmission (MRT) precoding are derived. The focus is on the maximization of the achievable sum rate by optimizing the non-uniform 3D antenna array topology. Since the optimization problem exhibits highly nonlinear and nonconvex characteristics, an enhanced particle swarm optimization (EPSO) algorithm is proposed to effectively solve it. Numerical results demonstrate the superiority of the proposed non-uniform 3D array topology in near-field communications for enhancing the achievable sum rate. © 2024 IEEE.

关键词： Signal to noise ratio

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：