检索结果-内蒙古大学图书馆

27th International Conference on Domain Decomposition Methods in Science and engineering, DD 2022

作者： Dolean, Victorita Heinlein, Alexander Mishra, Siddhartha Moseley, Ben University of Strathclyde 26 Richmond Street GlasgowG1 1XH United Kingdom Faculty of Electrical Engineering Mathematics & Computer Science Delft University of Technology Delft Institute of Applied Mathematics Mekelweg 4 Delft2628 CD Netherlands Computational and Applied Mathematics Laboratory/ETH AI Center ETH Zurich Ramistrasse 101 Zurich8092 Switzerland

The success and advancement of machine learning (ML) in fields such as image recognition and natural language processing has lead to the development of novel methods for the solution of problems in physics and enginee... 详细信息

ISBN: (纸本)9783031507687

关键词： Domain decomposition methods

来源：评论

学校读者我要写书评

暂无评论

Open-Source Heterogeneous SoCs for AI The PULP Platform Experience

arXiv

引用

arXiv 2024年

作者： Conti, Francesco Garofalo, Angelo Rossi, Davide Tagliavini, Giuseppe Benini, Luca The Department of Electrical Electronic and Information Engineering University of Bologna Bologna40123 Italy The Department of Computer Science and Engineering University of Bologna Bologna40123 Italy The Integrated Systems Laboratory ETH Zürich Zurich8005 Switzerland

Since 2013, the PULP (Parallel Ultra-Low Power) Platform project has been oneof the most active and successful initiatives in designing research IPs andreleasing them as open-source. Its portfolio now ranges from processor cores tonetwork-on-chips, peripherals, SoC templates, and full hardware *** this article, we focus on the PULP experience designing heterogeneous AIacceleration SoCs - an endeavour encompassing SoC architecture definition;development, verification, and integration of acceleration IPs;front- andback-end VLSI design;testing;development of AI deployment software. Copyright © 2024, The Authors. All rights reserved.

关键词： System-on-chip

来源：评论

学校读者我要写书评

暂无评论

Transmission Loss of a Millimeter Wave Pulse Through a Waveguide Window 23

Transmission Loss of a Millimeter Wave Pulse Through a Waveg...

引用

23rd International Vacuum Electronics Conference, IVEC 2022

作者： Jao, Ruei-Fu Aranganadin, Kaviya Hsu, Hua-Yi Verboncoeur, John P. Lin, Ming-Chieh School of Information Technology Guangdong Industry Polytechnic Guangdong510300 China Hanyang University Multidisciplinary Computational Laboratory Department of Electrical and Biomedical Engineering Seoul04763 Korea Republic of National Taipei University of Technology Department of Mechanical Engineering Taipei10608 Taiwan Michigan State University Department of Electrical and Computer Engineering East LansingMI48824 United States

ISBN: (纸本)9781665443258

Millimeter waves have become increasingly important in wireless communication today. It is well known that a waveguide window exhibits almost perfect transmission for the center frequency of millimeter waves. However, this might not be true for a pulsed wave. In this work, we study the transmission loss of a millimeter wave pulse centered at 35 GHz traveling through a rectangular waveguide window. The transmission function of a continuous wave within the bandwidth from 0 to 100 GHz has been obtained using the transfer matrix method. The millimeter wave of 35 GHz pulsed from 100 ps to 1 us in time domain has been Fourier transformed to the frequency domain so that the transmittance of the pulsed wave in the frequency domain can be calculated. The transmission loss has been analyzed for various pulse durations. After inverse Fourier transform of the transmittance in the frequency domain back to the time domain, one can compare the result with the incident pulse to see the pulse distortion and transmission loss. A finite difference time domain simulation has been performed to verify the calculated results by the transfer matrix method combined with Fourier transform. Detailed methodology and analysis of the study will be presented. © 2022 IEEE.

关键词： Transfer matrix method

来源：评论

学校读者我要写书评

暂无评论

A Unified Alternating Optimization Framework for Joint Sensor and Actuator Configuration in LQG Systems

arXiv

引用

arXiv 2025年

作者： Yang, Nachuan Li, Yuzhe Shi, Ling Chen, Tongwen Department of Electrical and Computer Engineering University of Alberta EdmontonABT6G 1H9 Canada State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang110004 China Department of Electronic and Computer Engineering Department of Chemical and Biological Engineering Hong Kong University of Science and Technology Clear Water Bay Hong Kong

This paper fills a gap in the literature by considering a joint sensor and actuator configuration problem under the linear quadratic Gaussian (LQG) performance without assuming a predefined set of candidate components. Different from the existing research, which primarily focuses on selecting or placing sensors and actuators from a fixed group, we consider a more flexible formulation where these components must be designed from scratch, subject to general-form configuration costs and constraints. To address this challenge, we first analytically characterize the gradients of the LQG performance with respect to the sensor and actuator matrices using algebraic Riccati equations. Subsequently, we derive first-order optimality conditions based on the Karush–Kuhn–Tucker (KKT) analysis and develop a unified alternating direction method of multipliers (ADMM)based alternating optimization framework to address the general-form sensor and actuator configuration problem. Furthermore, we investigate three representative scenarios: sparsity promoting configuration, low-rank promoting configuration, and structure-constrained configuration. For each scenario, we provide in-depth analysis and develop tailored computational schemes. The proposed framework ensures numerical efficiency and adaptability to various design constraints and configuration costs, making it well-suited for integration into numerical solvers. Copyright © 2025, The Authors. All rights reserved.

关键词： Matrix algebra

来源：评论

学校读者我要写书评

暂无评论

Performance Enhancement of Vehicular VLC Using Spherical Detector and Efficient Lens Design

Performance Enhancement of Vehicular VLC Using Spherical Det...

引用

IEEE Conference on Wireless Communications and Networking

作者： Selma Yahia Yassine Meraihi Tu Dac Ho Hossien B. Eldeeb List Laboratory University of M’Hamed Bougara Boumerdes Boumerdes Algeria Department of Electrical Engineering Faculty of Engineering Science and Technology UiT The Arctic University of Norway Department of Electrical Engineering and Computer Science Khalifa University Abu Dhabi UAE

The reliability of vehicle-to-vehicle (V2V) Visible Light Communication (VLC) systems is affected by several factors, such as car mobility and optics system design. Therefore, this paper focuses on the cars’ relative positions and the design of the optics on the receiving end. Instead of using the rectangle detector, commonly used in the literature, this paper proposes using the polar detector for V2V-VLC systems. We introduce using an imaging receiver with different kinds of optical lenses, such as Fresnel and Aspherical lenses to improve the performance of a V2V-VLC system. We perform a channel modeling study using the non-sequential ray-tracing approach, considering the possibility of horizontal and vertical movement between vehicles. A comprehensive performance comparison of these lenses assumes different vehicle positions on the road. We further investigate the impact of receiver type and lateral shift on the performance of the considered systems. The obtained results demonstrated that with a carefully chosen system and lens parameters, an enhancement of up to 7 dB in total received power could be achieved compared to the case without the lens.

关键词： Roads Vehicular ad hoc networks Detectors Ray tracing Reliability engineering Optical receivers Automobiles

来源：评论

学校读者我要写书评

暂无评论

Deep Multi-Instance Learning with Adaptive Recurrent Pooling for Medical Image Classification

Deep Multi-Instance Learning with Adaptive Recurrent Pooling...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Yi Ding Lu Zhao Liming Yuan Xianbin Wen School of Computer Science and Engineering Tianjin University of Technology Tianjin China Key Laboratory of Computer Vision and System Ministry of Education Tianjin China Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology Tianjin China School of Computer and Information Engineering Tianjin Chengjian University Tianjin China

ISBN: (数字)9781665468190

ISBN: (纸本)9781665468206

Recently, deep multi-instance neural networks have been successfully applied for medical image classification, where only image-level labels rather than fine-grained patch-level labels are available for use. One key issue for these multi-instance neural networks is how to aggregate all patch (instance) features into an entire image (bag) representation, referred to as multi-instance pooling, e.g., max, mean, and attention based pooling. Nevertheless, these multi-instance pooling operations do not take the structural information within an image into account. This is obviously inappropriate for medical image classification since there often exist certain dependencies among regional patches/lesions. We propose an adaptive recurrent pooling based deep multi-instance neural network in this paper. In this network, we first extract multi-view global structural features from every bag using the self-attention mechanism, and then aggregate these multi-view features into a whole bag representation based on the adaptive recurrent pooling operation in order to further capture the contextual information within the bag. Moreover, we introduce the cross-normalization operation used in the Unit Force Operated vision Transformer into the self-attention module to reduce its computational complexity. We have experimentally evaluated the performance of the proposed network on three medical image datasets, namely UCSB breast, Messidor, and Colon cancer. The results demonstrate the advantage of our network over current state-of-the-art deep multi-instance networks in terms of classification accuracy and interpretability.

关键词： Technological innovation Adaptive systems Aggregates Neural networks Force Feature extraction Transformers

来源：评论

学校读者我要写书评

暂无评论

Channel Estimation for Movable Antenna Communication Systems Based on Compressed Sensing

Channel Estimation for Movable Antenna Communication Systems...

引用

IEEE Conference on Wireless Communications and Networking

作者： Songqi Cao Lipeng Zhu Xiangyu Pi Zhenyu Xiao Boyu Ning School of Electronic and- Inforrmation Engineering Beihang University Beijing China Department of Electrical and Computer Engineering National University of Singapore Singapore National Key Laboratory of Science and Technology on Communications University of Electronic Science and Technology of China China

ISBN: (数字)9798350303582

ISBN: (纸本)9798350303599

This paper proposes a general channel estimation framework for movable antenna (MA) communication systems. In this framework, the channel state information between the entire transmitter (Tx) and receive (Rx) regions can be re-constructed, so as to find the optimal positions of the MAs for reaping performance gains. Specifically, the field-response channel structure is utilized to represent the channel response in terms of the angles of departure (AoDs), angles of arrival (AoAs), and complex coefficients of the multi-path components (MPCs). Then, the compressed sensing method is employed to jointly estimate the MPC information, i.e., the AoDs, AoAs, and complex coefficients of the paths, with a limited number of channel measurements. Notably, the measurement matrix under the proposed framework is fundamentally determined by the Tx-MA and Rx-MA measurement positions, which further affects the channel estimation performance. In this regard, four MA measurement position setups are proposed, and the channel estimation performance of each setup is further compared. Finally, simulation results show that the complete CSI between the entire Tx and Rx regions can be reconstructed by our proposed channel estimation framework with a high accuracy.

关键词： Antenna measurements Communication systems Atmospheric measurements Simulation Channel estimation Position measurement Particle measurements

来源：评论

学校读者我要写书评

暂无评论

Row-Column Decoupled Loss: A Probability-Based Geometric Similarity Framework for Aerial Micro-Target Detection

引用

IEEE Access 2025年 13卷 93593-93604页

作者： Xiaohui Chen Yunzhi Ling Lingjun Chen Li Liu Xuechen Cui Ziqiang Liu Zhenyu Wang Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering China Three Gorges University Yichang China College of Computer and Information Technology China Three Gorges University Yichang China Yichang Power Supply Company State Grid Hubei Electric Power Company Ltd. Yichang China

Object detection, a fundamental research direction in the field of computer vision, serves as the basis for various complex visual tasks. However, detection performance for small targets remains significantly inferior compared to regular-sized targets. In conventional tiny object detection methods, the uniform distribution strategy adopted for bounding box regression during prediction processes tends to induce instability, particularly when handling small targets. To address this critical issue, this paper proposes Row-Column Decoupled Loss to enhance the stability of the prediction process and improve the accuracy of detection results. The proposed approach innovatively transforms the traditional regression paradigm by incorporating probabilistic modeling that better aligns with the spatial characteristics of small objects. Firstly, to address the challenge where the absence of overlap between predicted and ground-truth bounding boxes prevents distance computation in small object scenarios, this work introduces a probabilistic modeling framework based on Binomial distribution to characterize the spatial distribution of bounding boxes. This approach effectively captures the probabilistic attributes of pixel distributions within target regions. Secondly, we design a dual-channel evaluation mechanism, established a similarity evaluation strategy that better aligns with the target natural characteristics. Finally, Row-Column Decoupled Loss: A probability-Based Geometric Similarity Framework is proposed to optimize feature learning for minuscule targets. Experimental validation on the AI-TOD dataset demonstrates the efficacy of our method across multiple mainstream object detection frameworks and state-of-the-art small object detectors. Detectors equipped with Row-Column Decoupled Loss exhibit significant performance enhancements over baseline models, achieving a peak value of 60.5 in $AP_{0.5} $ and delivering a maximum improvement margin of 16.2 in $AP_{0.5} $ compare

关键词： Object detection Optimization Convergence Sensitivity Probabilistic logic Detectors Accuracy Probability distribution Predictive models Object recognition

来源：评论

学校读者我要写书评

暂无评论

Simulation Study on Broadband Hive Receiving Coil for Small-Loop Transient Electromagnetic Detection 11

Simulation Study on Broadband Hive Receiving Coil for Small-...

引用

11th International Conference on Environmental and engineering Geophysics, ICEEG 2024

作者： Wang, Shengjie Su, Guoying Sun, Yishu Jia, Wenfeng Wang, Weicheng Wang, Qingshan The First Monitoring and Application Center China Earthquake Administration Tianjin300180 China College of Computer and Electrical Engineering Hunan University of Arts and Science Changde415000 China Qingdao Zhongdian Zhongyi Intelligent Technology Development Co. Ltd Qingdao266108 China Key Laboratory of Geophysics Exploration Equipment Ministry of Education of PRC Jilin University Changchun130061 China

The multi-turn small-loop transient electromagnetic (TEM) receiving coils can be used for urban underground space survey and mine detection because of their versatility and adaptability to complex environments. However, reducing the size of the receiving coil increases the parasitic parameters while narrowing the frequency band, resulting in the loss of high-frequency signals that contains shallow geological information. We propose a hive-receiving coil, and use finite element simulation to compare multi-turn hive coils with circular receiving coils in the same size. It is proved that the hive coil has lower parasitic parameters and wider passband, which can meet the detection requirements of small-loop TEM. © 2024 Institute of Physics Publishing. All rights reserved.

关键词： Electromagnetic transients

来源：评论

学校读者我要写书评

暂无评论

Singular Perturbation: When the Perturbation Parameter Becomes a State-Dependent Function

引用

IFAC-PapersOnLine 2023年第1期56卷 294-300页

作者： Tengfei Liu Zhong-Ping Jiang State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang 110004 China Department of Electrical and Computer Engineering New York University 370 Jay Street Brooklyn NY 11201 USA

This paper introduces a new class of singularly perturbed systems in which the small, but constant, perturbation coefficient in standard singular perturbation theory is replaced by a state-dependent function. This generalization is aimed at broadening the applicability of singular perturbation theory in practice. For this class of singularly perturbed systems, it is assumed that the boundary-layer subsystem is globally asymptotically stable (GAS) at the origin and the reduced subsystem is input-to-state stable (ISS) with respect to the state of the boundary-layer subsystem. Under a mild monotonicity condition, sufficient conditions on the perturbation functions are given under which the singularly perturbed system is GAS at the origin. ISS and nonlinear small-gain techniques are exploited in the stability analysis. The efficacy of the proposed theoretical result is validated via its applications to tackling integral control and feedback optimization problems.

关键词： Singular perturbation perturbation functions global asymptotic stability

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：