检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Hou, Wenzheng Xu, Qianqian Yang, Zhiyong Bao, Shilong He, Yuan Huang, Qingming Key Laboratory of Intelligent Information Processing Institute of Computing Technology CAS Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China State Key Laboratory of Information Security Institute of Information Engineering CAS Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Alibaba Group Beijing China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China Artificial Intelligence Research Center Peng Cheng Laboratory Shenzhen China

It is well-known that deep learning models are vulnerable to adversarial examples. Existing studies of adversarial training have made great progress against this challenge. As a typical trait, they often assume that the class distribution is overall balanced. However, long-tail datasets are ubiquitous in a wide spectrum of applications, where the amount of head class instances is larger than the tail classes. Under such a scenario, AUC is a much more reasonable metric than accuracy since it is insensitive toward class distribution. Motivated by this, we present an early trial to explore adversarial training methods to optimize AUC. The main challenge lies in that the positive and negative examples are tightly coupled in the objective function. As a direct result, one cannot generate adversarial examples without a full scan of the dataset. To address this issue, based on a concavity regularization scheme, we reformulate the AUC optimization problem as a saddle point problem, where the objective becomes an instance-wise function. This leads to an end-to-end training protocol. Furthermore, we provide a convergence guarantee of the proposed algorithm. Our analysis differs from the existing studies since the algorithm is asked to generate adversarial examples by calculating the gradient of a min-max problem. Finally, the extensive experimental results show the performance and robustness of our algorithm in three long-tail datasets. © 2022, CC BY.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Analyzing Impact of Time on Early Detection of Rainfall Event

Analyzing Impact of Time on Early Detection of Rainfall Even...

引用

Progress in Electromagnetic research Symposium (PIERS)

作者： Muhammad Salman Pathan Mayank Jain Avishek Nag Tarek Al Skaif Soumyabrata Dev ADAPT SFI Research Centre Dublin Ireland School of Computer Science University College Dublin Ireland School of Electrical and Electronic Engineering University College Dublin Ireland Information Technology Group Wageningen University and Research The Netherlands Beijing-Dublin International College Beijing China

ISBN: (纸本)9781665409889

Rainfall is a critical feature of a climatic system, which has a chaotic impact on agriculture, water resource management and biological systems. An early and accurate prediction of rainfall is a very important task and has vital effects on human life. However rainfall prediction is a challenging task in meteorology. Rainfall data mostly have high inconstancy and irregular patterns which are rare in other time series data. The rainfall data changes greatly with time, so the time factor has a high importance in such time series data. In order to develop efficient forecast models, one should deeply analyze the effect of time on prediction accuracy. Therefore, in this paper, we analyze how early we can predict a rainfall event with accuracy. We have performed the experiments on a 5-year daily rainfall data obtained from National Oceanic and Atmospheric Administration (NOAA) at 1-, 2-, 3-, and 4-day prior forecasting horizons using a machine learning technique to observe the trends in the prediction accuracy. Furthermore, we have also identified some most important input features from the dataset which plays a major role in the prediction of a rainfall event. Our results conclude that average wind speed and minimum temperature are most important weather variables in classifying rainfall events. We also observe that the forecasting error gradually increases with increasing lead times.

关键词： Atmospheric modeling Wind speed Time series analysis Weather forecasting Predictive models US Government agencies Time factors

来源：评论

学校读者我要写书评

暂无评论

Security boundaries of an optical power limiter for protecting quantum key distribution systems

arXiv

引用

arXiv 2023年

作者： Peng, Qingquan Gao, Binwu Zaitsev, Konstantin Wang, Dongyang Ding, Jiangfang Liu, Yingwen Liao, Qin Guo, Ying Huang, Anqi Wu, Junjie Institute for Quantum Information State Key Laboratory of High Performance Computing College of Computer Science and Technology National University of Defense Technology Changsha410073 China School of Automation Central South University Changsha410083 China China Greatwall Research Institute China Greatwall Technology Group Co. Ltd. Shenzhen518057 China Russian Quantum Center Skolkovo Moscow121205 Russia NTI Center for Quantum Communications National University of Science and Technology MISiS Moscow119049 Russia Vigo Quantum Communication Center University of Vigo Vigo Spain Escuela de Ingeniería de Telecomunicación Department of Signal Theory and Communications University of Vigo Vigo Spain atlanTTic Research Center University of Vigo Vigo Spain College of Computer Science and Electronic Engineering Hunan University Changsha410082 China School of Computer Science Beijing University of Posts and Telecommunications Beijing100876 China

Unauthorized light injection has always been a vital threat to the practical security of a quantum key distribution (QKD) system. An optical power limiter (OPL) based on the thermo-optical defocusing effect has been proposed and implemented, limiting the injected hacking light. As a hardware countermeasure, the performance of the OPL under various light-injection attacks shall be tested to clarify the security boundary before being widely deployed. To investigate the OPL’s security boundary in quantum cryptography, we comprehensively test and analyse the behavior of OPL under continuous-wave (c.w.) light-injection attacks and pulse illumination attacks with pulses’ repetition rate at 0.5-Hz, 40-MHz, and 1-GHz. The testing results illuminate the security boundary of the OPL, which allows one to properly employ the OPL in the use cases. The methodology of testing and analysis proposed here is applicable to other power-limitation components in a QKD system. Copyright © 2023, The Authors. All rights reserved.

关键词： Pulse repetition rate

来源：评论

学校读者我要写书评

暂无评论

The Importance of Gender Specification for Detection of Driver Fatigue using a Single EEG Channel

The Importance of Gender Specification for Detection of Driv...

引用

Biomedical engineering International Conference (BMEiCON)

作者： Mohammad Shahbakhti Matin Beiramvand Erfan Nasiri Wei Chen Jordi Solé-Casals Michal Wierzchon Anna Broniec-Wójcik Piotr Augustyniak Vaidotas Marozas Biomedical Engineering Institute Kaunas University of Technology Kaunas Lithuania Faculty of Information Technology and Communication Tampere University Tempere Finland Faculty of Statistics Mathematics and Computer Allameh Tabataba’i University Tehran Iran Center for Intelligent Medical Electronics School of Information Science and Technology the Human Phenome Institute Fudan University Shanghai China Data and Signal Processing Research Group University of Vic-Central University of Catalonia Vic Spain Institute of Psychology Jagiellonian University Krakow Poland Department of Biocybernetics and Biomedical Engineering AGH University of Science and Technology Krakow Poland

ISBN: (纸本)9781665489041

Although detection of the driver fatigue using a single electroencephalography (EEG) channel has been addressed in literature, the gender differentiation for applicability of the model has not been investigated heretofore. Motivated accordingly, we address the detection of driver fatigue based the gender-segregated datasets, where each of them contains 8 subjects. After splitting the EEG signal into its sub-bands (delta, theta, alpha, beta, and gamma) using discrete wavelet transform, the log energy entropy of each band is computed to form the feature vector. Afterwards, the feature vector is randomly split into 50% for training and 50% for the unseen testing, and fed to a support vector machine model. When comparing the classification results of fatigue driving detection between the gender segregated and non-gender segregated datasets, the former achieved the accuracy 78% and 77% for male and female subjects, respectively, than the latter (71%). The obtained results show the importance of gender-specification for the driver fatigue detection.

关键词： Training Support vector machines Computational modeling Transforms Fatigue Brain modeling Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Efficient Forecasting of Precipitation Using LSTM

Efficient Forecasting of Precipitation Using LSTM

引用

Progress in Electromagnetic research Symposium (PIERS)

作者： Muhammad Salman Pathan Mayank Jain Yee Hui Lee Tarek Al Skaif Soumyabrata Dev ADAPT SFI Research Centre Dublin Ireland School of Computer Science University College Dublin Ireland School of Electrical and Electronic Engineering Nanyang Technological University Singapore Singapore Information Technology Group Wageningen University and Research The Netherlands Beijing-Dublin International College Beijing China

ISBN: (纸本)9781665409889

Precipitation is one of those many critical elements of the hydrological cycle that has a direct impact on human life in many aspects. An accurate and early detection of a future precipitation event can help in preventing human and financial losses. Therefore, it is vital to design a framework that can predict the precipitation with a significant accuracy. Accordingly, in this paper we have proposed a Long-Short-Term-Memory (LSTM) based forecast model which can predict the precipitation values efficiently using the historical values. The design of forecast model is made simple to avoid the heavy training time. Furthermore, a transformation technique was applied on the precipitation dataset to make the data more normal distribution-like. The proposed model was evaluated in terms of Root Mean Square Error (RMSE). The proposed model achieves a 6.186 RMSE and outperforms the traditional persistence and average forecast models.

关键词： Training Predictive models Root mean square Forecasting Electromagnetics

来源：评论

学校读者我要写书评

暂无评论

Statistical Channel Modeling and Estimation for PMMA-Based Vehicle-Mounted Magnetic Communication Systems

引用

IEEE Transactions on Vehicular technology 2025年

作者： Chen, Mingtao Qu, Xinyu Liu, Erwu Ni, Wei Long, Qingming Ma, Honglei Tongji University School of Electronics and Information Engineering Shanghai China Tongji University School of Computer Science and Technology Shanghai China University of New South Wales School of Computer Science and Engineering Australia CSIRO D61 SydneyNSW2052 Australia China Coal Technology Engineering Group Chongqing Research Institute State Key Laboratory of Coal Mine Disaster Prevention and Control Chongqing China Shanghai University of Engineering Science School of Electronic and Electrical Engineering Shanghai China

In subterranean or disaster-stricken environments, unmanned vehicles demand robust communication systems capable of penetrating dense structural obstructions. Low-frequency permanent magnet mechanical antennas (PMMAs), employing rotating permanent magnets as compact antennas, demonstrate superior signal penetration in soil and water, along with advantages in miniaturization and power efficiency. However, vehicular magnetic communication (MC) utilizing mechanical antennas remains underdeveloped;Existing research predominantly assumes quasi-static antenna operation, overlooking realistic dynamic vibration scenarios inherent to mobile platforms. This paper establishes the statistical characterization of fast fading channels in MC systems via analytical derivation. We develop a boundary Chi-square distribution model based on vehicular vibration dynamics and formulate a corresponding channel estimation algorithm employing the Expectation-Maximization (EM) framework. Numerical validations confirm the channel's statistical properties and the algorithm's convergence behavior. The proposed algorithm demonstrates operational efficacy in dynamic environments, attaining sub-4% normalized root mean square error (NRMSE) at 15 dB signal-to-noise ratio (SNR). © 1967-2012 IEEE.

关键词： Channel estimation

来源：评论

学校读者我要写书评

暂无评论

CloudBrain-NMR: An Intelligent Cloud Computing Platform for NMR Spectroscopy Processing, Reconstruction and Analysis

arXiv

引用

arXiv 2023年

作者： Guo, Di Li, Sijin Liu, Jun Tu, Zhangren Qiu, Tianyu Xu, Jingjing Feng, Liubin Lin, Donghai Hong, Qing Lin, Meijin Lin, Yanqin Qu, Xiaobo School of Computer and Information Engineering Fujian Engineering Research Center for Medical Data Mining and Application Xiamen University of Technology Xiamen361024 China Department of Electronic Science Fujian Provincial Key Laboratory of Plasma and Magnetic Resonance Xiamen University Xiamen361005 China The Key Laboratory for Chemical Biology of Fujian Province MOE Key Laboratory of Spectrochemical Analysis & Instrumentation College of Chemistry and Chemical Engineering Xiamen University Xiamen361005 China Department of Applied Marine Physics and Engineering College of Ocean and Earth Sciences Xiamen University Xiamen361102 China The China Mobile Group Xiamen361005 China

Nuclear Magnetic Resonance (NMR) spectroscopy has served as a powerful analytical tool for studying molecular structure and dynamics in chemistry and biology. However, the processing of raw data acquired from NMR spectrometers and subsequent quantitative analysis involves various specialized tools, which necessitates comprehensive knowledge in programming and NMR. Particularly, the emerging deep learning tools is hard to be widely used in NMR due to the sophisticated setup of computation. Thus, NMR processing is not an easy task for chemist and biologists. In this work, we present CloudBrain-NMR, an intelligent online cloud computing platform designed for NMR data reading, processing, reconstruction, and quantitative analysis. The platform is conveniently accessed through a web browser, eliminating the need for any program installation on the user side. CloudBrain-NMR uses parallel computing with graphics processing units and central processing units, resulting in significantly shortened computation time. Furthermore, it incorporates state-of-the-art deep learning-based algorithms offering comprehensive functionalities that allow users to complete the entire processing procedure without relying on additional software. This platform has empowered NMR applications with advanced artificial intelligence processing. CloudBrain-NMR is openly accessible for free usage at https://***/***. © 2023, CC BY.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Performance Compensation Method for Spaceborne Active Phased Array Antennas under Thermal Loads

Performance Compensation Method for Spaceborne Active Phased...

引用

IEEE Asia-Pacific Conference on Antennas and Propagation (APCAP)

作者： Rong Yu Pengying Xu Xing Yang Guangda Chen Longyang Wang Congsi Wang Zhihai Wang Wenzhi Wu Kunpeng Yu Guojun Leng Meng Wang Yan Wang Key Laboratory of Electronic Equipment Structure Design Ministry of Education Xidian University Xi'an China CETC No.38 Research Institute Hefei China CETC No.29 Research Institute Hefei China Research Institute of Shaanxi Huanghe Group Co. Ltd. Xi'an China School of Information and Control Engineering Xi'an University of Architecture and Technology Xi'an China Zhejiang Fengfan CNC Machinery Co. Ltd Huzhou China

Thermal load causes the structural deformation of the spaceborne active phased array antenna (APAA), which could degrade electromagnetic performance of antenna. The phase com-pensation method and the amplitude-phase compensation method based on the least square method are applied to compensate the electrical performance of the deformed antenna under obtaining the excitation adjustment of antenna elements. Taking the $24 \times 32$ element microstrip array antennas designed in this paper as an example, the compensation effects of the two methods on different observation areas of the antenna are analyzed, which provides a theoretical direction for ensuring the electrical performance of spaceborne APAAs.

关键词： Phased arrays Microstrip antenna arrays Antenna theory Microstrip antennas Directive antennas Brain modeling Thermal loading

来源：评论

学校读者我要写书评

暂无评论

RadioGAT: A Joint Model-based and Data-driven Framework for Multi-band Radiomap Reconstruction via Graph Attention Networks

arXiv

引用

arXiv 2024年

作者： Li, Xiaojie Zhang, Songyang Li, Hang Li, Xiaoyang Xu, Lexi Xu, Haigao Mei, Hui Zhu, Guangxu Qi, Nan Xiao, Ming Shenzhen Research Institute of Big Data The Chinese University of Hong Kong-Shenzhen Guangdong China College of Physics Nanjing University of Aeronautics and Astronautics Nanjing210016 China Department of Electrical and Computer Engineering University of Louisiana at Lafayette LafayetteLA70503 United States Research Institute China United Network Communications Corporation Beijing100048 China China Mobile Communications Group Jiangxi Co. Ltd 330038 China Key Laboratory of Dynamic Cognitive System of Electromagnetic Spectrum Space Nanjing University of Aeronautics and Astronautics Nanjing210016 China State Key Laboratory of Integrated Services Networks Xidian University Xi'An710071 China Department of Information Science and Engineering School of Electrical Engineering of KTH Royal Institute of Technology Stockholm Sweden

Multi-band radiomap reconstruction (MB-RMR) is a key component in wireless communications for tasks such as spectrum management and network planning. However, traditional machine-learning-based MB-RMR methods, which rely heavily on simulated data or complete structured ground truth, face significant deployment challenges. These challenges stem from the differences between simulated and actual data, as well as the scarcity of real-world measurements. To address these challenges, our study presents RadioGAT, a novel framework based on Graph Attention Network (GAT) tailored for MBRMR within a single area, eliminating the need for multiregion datasets. RadioGAT innovatively merges model-based spatial-spectral correlation encoding with data-driven radiomap generalization, thus minimizing the reliance on extensive data sources. The framework begins by transforming sparse multiband data into a graph structure through an innovative encoding strategy that leverages radio propagation models to capture the spatial-spectral correlation inherent in the data. This graph-based representation not only simplifies data handling but also enables tailored label sampling during training, significantly enhancing the framework's adaptability for deployment. Subsequently, The GAT is employed to generalize the radiomap information across various frequency bands. Extensive experiments using raytracing datasets based on real-world environments have demonstrated RadioGAT's enhanced accuracy in supervised learning settings and its robustness in semi-supervised scenarios. These results underscore RadioGAT's effectiveness and practicality for MBRMR in environments with limited data availability. Copyright © 2024, The Authors. All rights reserved.

关键词： Encoding (symbols)

来源：评论

学校读者我要写书评

暂无评论

EDOA: an efficient delay optimization approach for mixed-polarity Reed-Muller logic circuits under the unit delay model

引用

Frontiers of computer Science 2019年第5期13卷 1102-1115页

作者： Zhenxue HE Limin XIAO Fei GU Li RUAN Zhisheng HUO Mingzhe LI Mingfa ZHU Longbing ZHANG Rui LIU Xiang WANG College of Information Science and Technology Hebei Agricultural University Baoding 071001 China State Key Laboratory of Software Development Environment Beihang University Beijing 100083 China School of Computer Science and Engineering Beihang University Beijing 100083 China School of Electronic and Information Engineering Beihang University Beijing 100083 China State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China National Engineering Research Center for Science & Technology Resources Sharing Service Beijing 100083 China

Delay optimization has recently attracted signif-icant attention. However, few studies have focused on the delay optimization of mixed-polarity Reed-Muller (MPRM) logic circuits. In this paper, we propose an efficient delay op-timization approach (EDOA) for MPRM logic circuits under the unit delay model, which can derive an optimal MPRM logic circuit with minimum delay. First, the simplest MPRM expression with the fewest number of product terms is ob-tained using a novel Reed-Muller expression simplification approach (RMESA) considering don't-care terms. Second, a minimum delay decomposition approach based on a Huffman tree construction algorithm is utilized on the simplest MPRM expression. Experimental results on MCNC benchmark cir-cuits demonstrate that compared to the Berkeley SIS 1.2 and ABC, the EDOA can significantly reduce delay for most cir-cuits. Furthermore, for a few circuits, while reducing delay, the EDOA incurs an area penalty.

关键词： delay optimization mixed-polarity Reed-Muller logic circuits unit delay model don't-care terms,

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：