检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Liu, Jiayue Mao, Tianqi He, Dongxuan Yang, Yang Gao, Zhen Zheng, Dezhi Zhang, Jun State Key Laboratory of CNS/ATM Beijing Institute of Technology Beijing100081 China MIIT Key Laboratory of Complex-Field Intelligent Sensing Beijing Institute of Technology Beijing100081 China Jiaxing314019 China School of Information and Electronics Beijing Institute of Technology Beijing100081 China Beijing Key Laboratory of Network System Architecture and Convergence School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing100876 China

The escalating interests on underwater exploration/ reconnaissance applications have motivated high-rate data transmission from underwater to airborne relaying platforms, especially under high-sea scenarios. Thanks to its broad bandwidth and superior confidentiality, Optical wireless communication has become one promising candidate for water-air transmission. However, the optical signals inevitably suffer from deviations when crossing the highly-dynamic water-air interfaces in the absence of relaying ships/buoys. To address the issue, this article proposes one novel beam alignment strategy based on deep reinforcement learning (DRL) for water-air direct optical wireless communications. Specifically, the dynamic water-air interface is mathematically modeled using sea-wave spectrum analysis, followed by characterization of the propagation channel with ray-tracing techniques. Then the deep deterministic policy gradient (DDPG) scheme is introduced for DRL-based transceiving beam alignment. A logarithm-exponential (LE) nonlinear reward function with respect to the received signal strength is designed for high-resolution rewarding between different actions. Simulation results validate the superiority of the proposed DRL-based beam alignment scheme. Copyright © 2024, The Authors. All rights reserved.

关键词： Ray tracing

来源：评论

学校读者我要写书评

暂无评论

Approximation Methods for Simulation and Equivalence Checking of Noisy Quantum Circuits

arXiv

引用

arXiv 2025年

作者： Huang, Mingyu Guan, Ji Fang, Wang Ying, Mingsheng Key Laboratory of System Software Chinese Academy of Sciences State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences Beijing101408 China School of Informatics University of Edinburgh EdinburghEH8 9UR United Kingdom Centre for Quantum Software and Information University of Technology Sydney UltimoNSW2007 Australia

In the current NISQ (Noisy Intermediate-Scale Quantum) era, simulating and verifying noisy quantum circuits is crucial but faces challenges such as quantum state explosion and complex noise representations, constraining simulation, and equivalence checking to circuits with a limited number of qubits. This paper introduces an approximation algorithm for simulating and assessing the equivalence of noisy quantum circuits, specifically designed to improve scalability under low-noise conditions. The approach utilizes a novel tensor network diagram combined with singular value decomposition to approximate the tensors of quantum noises. The implementation is based on Google’s TensorNetwork Python package for contraction. Experimental results on realistic quantum circuits with realistic hardware noise models indicate that our algorithm can simulate and check the equivalence of QAOA (Quantum Approximate Optimization Algorithm) circuits with around 200 qubits, surpassing the state-of-the-art methods by noise number and execution time. © 2025, CC BY.

关键词： Qubits

来源：评论

学校读者我要写书评

暂无评论

MPC Implementation for Optimal Active Power Control of Large-Scale Wind-PV-Battery Hybrid system

MPC Implementation for Optimal Active Power Control of Large...

引用

Chinese Control Conference (CCC)

作者： Zihan Zhang Zhongwei Lin Ze Zhao Jiawei Zhou Chenzhi Qu State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources School of Control and Computer Engineering North China Electric Power University Beijing P. R. China

This paper investigates the operational strategy for real-time optimal active power control of large-scale wind-PV-battery hybrid system. The MPC strategy is established with objective, forecast models and constraints for active power control of wind-PV-battery hybrid system, which simultaneously maximizes tracking accuracy and minimizes settling time. To guarantee the industrial reliability, the corresponding optimization solver and control architecture have been specifically developed and designed. Hardware-in-loop (HIL) experiments are conducted using the real-time digital simulator (RTDS) and programmable logic controllers (PLCs). Under different operating scenarios, HIL-RTDS testing results demonstrate that the MPC strategy significantly improves the tracking speed and accuracy compared to the conventional strategy in both normal and abnormal operating scenarios, which also sustain the feasibility of industrial implementation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A New Paradigm of User-Centric Wireless Communication Driven by Large Language Models

arXiv

引用

arXiv 2025年

作者： Ding, Kuiyuan Guo, Caili Yang, Yang Hu, Wuxia Eldar, Yonina C. Beijing Key Laboratory of Network System Architecture and Convergence School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing100876 China Beijing Laboratory of Advanced Information Net works School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing100876 China Faculty of Mathematics and Computer Science Weizmann Institute of Science Rehovot7610001 Israel

The next generation of wireless communications seeks to deeply integrate artificial intelligence (AI) with user-centric communication networks, with the goal of developing AI-native networks that more accurately address user requirements. The rapid development of large language models (LLMs) offers significant potential in realizing these goals. However, existing efforts that leverage LLMs for wireless communication often overlook the considerable gap between human natural language and the intricacies of real-world communication systems, thus failing to fully exploit the capabilities of LLMs. To address this gap, we propose a novel LLM-driven paradigm for wireless communication that innovatively incorporates the nature language to structured query language (NL2SQL) tool. Specifically, in this paradigm, user personal requirements is the primary focus. Upon receiving a user request, LLMs first analyze the user intent in terms of relevant communication metrics and system parameters. Subsequently, a structured query language (SQL) statement is generated to retrieve the specific parameter values from a high-performance real-time database. We further utilize LLMs to formulate and solve an optimization problem based on the user request and the retrieved parameters. The solution to this optimization problem then drives adjustments in the communication system to fulfill the user’s requirements. To validate the feasibility of the proposed paradigm, we present a prototype system. In this prototype, we consider user-request centric semantic communication (URC-SC) system in which a dynamic semantic representation network at the physical layer adapts its encoding depth to meet user requirements, such as improved data transmission quality or reduced data transmission latency. Additionally, two LLMs are employed to analyze user requests and generate SQL statements, respectively. Simulation results demonstrate the effectiveness of the prototype in personalizing and addressing user r

关键词： Structured Query Language

来源：评论

学校读者我要写书评

暂无评论

Aeroengine remaining useful life prediction via integrating enhanced inverted transformer and spatiotemporal graph learning

引用

ISA Transactions 2025年

作者： Sun, Shilong Ding, Hao Zhao, Zida Zhou, Yu Wang, Dong Xu, Wenfu School of Robotics and Advanced Manufacturing College of Artificial Intelligence Harbin Institute of Technology Shenzhen China Guangdong Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics Shenzhen China College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China State Key Laboratory of Mechanical System and Vibration Shanghai Jiao Tong University Shanghai200240 China

Accurate prediction of aeroengine Remaining Useful Life (RUL) is critical for ensuring flight safety, minimizing maintenance costs, and improving operational efficiency. This study proposes a novel model, the Fourier-Enhanced Inverted Transformer with Graph-Augmented Spatiotemporal Modeling (FIT-GSTM), to enhance RUL prediction performance. FIT-GSTM combines an inverted Transformer with a Spatiotemporal Graph Convolutional Network (STGCN) to effectively capture global spatiotemporal dependencies across multi-sensor data. To further enrich feature representation, the model incorporates Fast Fourier Transform (FFT) to extract frequency-domain information and fuses it with time-domain features, enhancing robustness to noise. Additionally, the integration of Memory Tokens and Reversible Instance Normalization (RevIN) strengthens the model's ability to retain long-term dependencies and adapt to heterogeneous data distributions. Experimental evaluations on the C-MAPSS dataset demonstrate that FIT-GSTM achieves superior RUL prediction accuracy and generalization compared to existing methods, highlighting its potential for real-world deployment in aeroengine health management. © 2025 ISA

关键词： Fast Fourier transforms

来源：评论

学校读者我要写书评

暂无评论

Deep Common Feature Mining for Efficient Video Semantic Segmentation

arXiv

引用

arXiv 2024年

作者： Zheng, Yaoyan Yang, Hongyu Huang, Di State Key Laboratory of Software Development Environment School of Computer Science and Engineering Beihang University Beijing100191 China Institute of Artificial Intelligence Beihang University Beijing100191 China Shanghai Artificial Intelligence Laboratory Shanghai201112 China Zhejiang Industrial Big Data and Robot Intelligent System Key Laboratory Hangzhou Innovation Institute Beihang University Hangzhou310051 China

Recent advancements in video semantic segmentation have made substantial progress by exploiting temporal correlations. Nevertheless, persistent challenges, including redundant computation and the reliability of the feature propagation process, underscore the need for further innovation. In response, we present Deep Common Feature Mining (DCFM), a novel approach strategically designed to address these challenges by leveraging the concept of feature sharing. DCFM explicitly decomposes features into two complementary components. The common representation extracted from a key-frame furnishes essential high-level information to neighboring non-key frames, allowing for direct re-utilization without feature propagation. Simultaneously, the independent feature, derived from each video frame, captures rapidly changing information, providing frame-specific clues crucial for segmentation. To achieve such decomposition, we employ a symmetric training strategy tailored for sparsely annotated data, empowering the backbone to learn a robust high-level representation enriched with common information. Additionally, we incorporate a self-supervised loss function to reinforce intra-class feature similarity and enhance temporal consistency. Experimental evaluations on the VSPW and Cityscapes datasets demonstrate the effectiveness of our method, showing a superior balance between accuracy and efficiency. The implementation is available at https://***/BUAAHugeGun/DCFM. © 2024, CC BY-NC-SA.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Experimental Investigation on the Adiabatic Film Effectiveness for Counter-Inclined Simple and Laid-Back Film-Holes of Leading Edge

引用

Journal of Thermal Science 2020年第3期29卷 772-783页

作者： YE Lin LIU Cunliang XU Zhipeng ZHU Huiren LIU Haiyong ZHAI Yingni School of Power and Energy Northwestern Polytechnical UniversityXi'an 710072China Shaanxi Key Laboratory of Thermal Sciences in Aero-engine System Xi'an 710129China State Key Laboratory of Green Building in Western China Xi'an University of Architecture and TechnologyXi'an 710055China School of Mechanical&Electrical Engineering Xi'an University of Architecture and TechnologyXi'an 710055China

The adiabatic film effectivenessηof the counter-inclined film-holes fed by varying internal coolant intake on the turbine vane leading edge model was experimentally investigated.A semi-cylinder model was adopted to model the vane leading edge which was arranged with two-row holes,which located at±15°on both *** four Leading edge model with the combinations of hole-shape(simple holes and laid-back holes)and intake structure(plenum and impingement)were tested under four blowing ratios M of 0.5,1.0,1.5,and ***ηcontours were obtained by the transient measurement technique based on double thermochromic *** results present that theηis sensitive to the M for the four studied leading edge *** addition of impingement enhances theηfor the two studied *** film jets make the coolant-flow closed to the target surface,resulting in higherηunder lower *** core with higherηappears in the downstream area of ***ηenhancement can be provided to almost the identical level by adding the impingement-holes and improving the hole-exit shaping in most *** increasing M,the jets with stronger exit normal momentum penetrate into the *** impingement addition may be a more effective program to upgrade theηrelatively to the exit shaping under larger ***,the laid-back holes with impingement case produce the highest film cooling performance among the four cases,providing great potential in the leading edge especially under larger M.

关键词： turbine blade leading edge adiabatic film effectiveness counter-inclined holes impingement thermochromic liquid crystal transient measurement

来源：评论

学校读者我要写书评

暂无评论

Consistency-based Semi-supervised Learning Framework for Power Line Insulators Detection

Consistency-based Semi-supervised Learning Framework for Pow...

引用

2022 International Conference on Electrical, Power and Grid systems, ICEPGS 2022

作者： Yao, Xu Lei, Longwu Zheng, Zhou Mo, Wenhao Wu, Han Li, Shufang Beijing Key Laboratory of Network System Architecture and Convergence Beijing University of Posts and Telecommunications Haidian District Beijing100876 China State Grid Fujian Electric Power Research Institute Fujian Province Fuzhou350007 China China Electric Power Research Institute or2 Haidian District Beijing100192 China

It is commonly believed that fast and accurate object detection is the prerequisite for power line insulators automatic fault diagnosis. While the insulators detection task requires a huge number of labeled images to guarantee its performance, placing bounding boxes for every object in each image is time-consuming and requires professional knowledge. To alleviate this problem, we propose CASD, a two-stage semi-supervised learning framework for power line insulators detection based on consistency regularization and data augmentation. Firstly, we train a teacher model on labeled images, then generate pseudo labels for unlabeled images using the trained model, and the confidence-based thresholding is introduced to control the quality of pseudo labels. In the second stage, we apply strong data augmentation to unlabeled images and use both the labeled and unlabeled images to train the CASD. Consistency regularization is introduced in the calculation of unsupervised loss to improve the accuracy and robustness of the model. Finally, we compare CASD with supervised learning, data augmentation and self-training methods on insulators aerial image dataset. The results show that the proposed method performs better than all the three baseline methods, and the detection accuracy of CASD is far better than the supervised learning method in the case of less available images. The comparison results further prove the efficacy of the proposed method. © Published under licence by IOP Publishing Ltd.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Characterizing and Detecting Python Version Incompatibilities Caused by Inconsistent Version Specifications

SSRN

引用

SSRN 2024年

作者： Li, Shuo Gao, Haocheng Chen, Wei Li, Yi Tian, Haoxiang Liu, Chengwei Ye, Dan Institute of Software University of Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Nanyang Technological University Singapore Key Laboratory of System Software Chinese Academy of Sciences State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences Beijing China Nanjing Institute of Software Technology Nanjing China

Python interpreter serves as the foundation for developing Python projects. Configuring compatible Python version is essential for packaging and reusing third-partylibraries (TPLs) in the Python ecosystem. Python version incompatibilities caused by inconsistent version specification frequently occur across software systems, leading to installation failures and run-time errors. We refer to such an error as a Python distribution version specification error (PDSpecErr). However, PDSpecErrs are not studied adequately and there still lacks a method to guarantee the correctness of Python version *** combat PDSpecErrs and mitigate their adverse impacts on downstream applications, we conducted the first exploratory study on 3,000 real-world TPLs to investigate PDSpecErrs about their prevalence, symptom categories, and diagnostic patterns. Based on the comprehensive study, we designed and implemented \textbf{PyChecker}, a tool to automatically detect PDSpecErrs in TPLs, locate root causes, and generate fixing solutions. We evaluated PyChecker on 3,000 TPL releases and PyChecker detected 842 PDSpecErrs, reporting their root causes and recommending fixing solutions. We have reported 52 PDSpecErrs to the concerned developers. So far, 32 issues have been confirmed and fixed according to our suggestions. © 2024, The Authors. All rights reserved.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

Towards Query-Efficient Decision-Based Adversarial Attacks Through Frequency Domain

Towards Query-Efficient Decision-Based Adversarial Attacks T...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Jianhao Fu Xiang Ling Yaguan Qian Changjiang Li Tianyue Luo Jingzheng Wu Intelligent Software Research Center Institute of Software Chinese Academy of Sciences University of Chinese Academy of Sciences Nanjing Nanjing Institute of Software Technology Key Laboratory of System Software (Chinese Academy of Sciences) State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences Zhejiang University of Science and Technology Stony Brook University

ISBN: (数字)9798350390155

ISBN: (纸本)9798350390162

Deep neural networks are vulnerable to adversarial examples, where decision-based attacks can generate adversarial examples based solely on the predicted labels. However, these attacks typically require excessive queries to attack one example. Considering this challenge, we propose FBA (Frequency based Boundary Attack), a decision-based attack against the limitation of query efficiency. FBA incorporates a novel search process, utilizing high-frequency based importance sampling for efficient gradient estimation. Empirical results confirm the superior query efficiency of our method. Specifically, FBA surpasses SOTA attacks by achieving a 54% average improvement in query efficiency, quantified by the reduction in perturbation size within the same number of queries.

关键词： Technological innovation Monte Carlo methods Frequency-domain analysis Perturbation methods Estimation Artificial neural networks

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：