检索结果-内蒙古大学图书馆

SSRN 2025年

作者： Zhang, Ziyang Chen, Cheng Qin, Wentao Wu, Xue Liu, Yang Wu, Lijun Lv, Xiaoyi Chang, Chenjie Chen, Xinya Chen, Zhiyuan Xu, Qianxi Li, Zhuoyu Ma, Mengsi Chen, Chen Xinjiang University College of Software Urumqi830046 China Xinjiang Cloud Computing Application Laboratory Xinjiang University Karamay834099 China School of Computer Science and Technology Xinjiang University Urumqi830046 China Key Laboratory of signal detection and processing Xinjiang University Urumqi830046 China Department of Rheumatology＆Immunology People's Hospital of Xinjiang Uygur Autonomous Region Xinjiang Urumqi China Xinjiang Clinical Research Center for Rheumatoid arthritis Xinjiang Urumqi China

Abstracts IgG4-related disease (IgG4-RD) is a multi-organ immune disorder characterized by systemic involvement, diverse pathogenesis, and rarity, which complicates its diagnosis. Traditional medical diagnostic models, predominantly based on supervised learning in machine learning or deep learning frameworks, struggle to address the scarcity of labeled data due to the diagnostic challenges of IgG4-RD. To overcome this limitation, this study proposes a novel framework based on Feature-Consistent Cyclic Domain Adversarial Networks (FCCDAN). The framework first trains a classification model on the source domain for diagnosing source domain diseases under supervised conditions. Subsequently, leveraging the source domain model, the encoder is guided to extract semantic features, while feature consistency loss is integrated into both the generator and discriminator to align the semantic features of the target domain with those of the source domain. Finally, the aligned features are processed through a pre-trained linear mapping to achieve unsupervised classification and diagnosis in the target domain. The proposed model utilizes common autoimmune diseases as a knowledge source, enabling unsupervised transfer diagnosis for IgG4-RD, and demonstrates generalizability through experiments on other disease datasets, achieving an average diagnostic accuracy of 90.62%. This represents improvements of 4.14%, 9.82%, and 10.51% over baseline models, respectively. FCCDAN expands the applicability of Raman spectroscopy in disease diagnosis, maintaining high performance even in label-scarce environments. The overall research workflow also establishes a robust paradigm for the application and advancement of domain adaptation techniques in this context. © 2025, The Authors. All rights reserved.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

signal Detection in MIMO Systems with Hardware Imperfections: Message Passing on Neural Networks

arXiv

引用

arXiv 2022年

作者： Gao, Dawei Guo, Qinghua Liao, Guisheng Eldar, Yonina C. Li, Yonghui Yu, Yanguang Vucetic, Branka The Hangzhou Institute of Technology Xidian University Hangzhou311200 China The National Laboratory of Radar Signal Processing Xidian University Xi’an710071 China The School of Electrical Computer and Telecommunications Engineering University of Wollongong NSW2522 Australia The Faculty of Math and CS Weizmann Institute of Science Rehovot7610001 Israel The School of Electrical and Information Engineering University of Sydney SydneyNSW2006 Australia

In this paper, we investigate signal detection in multiple-input-multiple-output (MIMO) communication systems with hardware impairments, such as power amplifier nonlinearity and in-phase/quadrature imbalance. To deal with the complex combined effects of hardware imperfections, neural network (NN) techniques, in particular deep neural networks (DNNs), have been studied to directly compensate for the impact of hardware impairments. However, it is difficult to train a DNN with limited pilot signals, hindering its practical applications. In this work, we investigate how to achieve efficient Bayesian signal detection in MIMO systems with hardware imperfections. Characterizing combined hardware imperfections often leads to complicated signal models, making Bayesian signal detection challenging. To address this issue, we first train an NN to ‘model’ the MIMO system with hardware imperfections and then perform Bayesian inference based on the trained NN. Modelling the MIMO system with NN enables the design of NN architectures based on the signal flow of the MIMO system, minimizing the number of NN layers and parameters, which is crucial to achieving efficient training with limited pilot signals. We then represent the trained NN with a factor graph, and design an efficient message passing based Bayesian signal detector, leveraging the unitary approximate message passing (UAMP) algorithm. The implementation of a turbo receiver with the proposed Bayesian detector is also investigated. Extensive simulation results demonstrate that the proposed technique delivers remarkably better performance than state-of-the-art methods. Copyright © 2022, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

21-cm foreground removal using AI and frequency-difference technique

arXiv

引用

arXiv 2023年

作者： Shi, Feng Chang, Haoxiang Zhang, Le Shan, Huanyuan Zhang, Jiajun Zhou, Suiping Jiang, Ming Wang, Zitong School of Aerospace Science And Technology Xidian University Xi’an710126 China Peng Cheng Laboratory No.2 Xingke 1st Street Shenzhen518000 China School of Physics and Astronomy Sun Yat-sen University 2 Daxue Road Tangjia Zhuhai519082 China CSST Science Center for the Guangdong-Hong Kong-Macau Greater Bay Area Zhuhai519082 China Nandan Road 80 Shanghai200030 China University of Chinese Academy of Sciences Beijing100049 China National Key Laboratory of Radar Signal Processing Xidian University Xi’an710126 China

The deep learning technique has been employed in removing foreground contaminants from 21-cm intensity mapping, but its effectiveness is limited by the large dynamic range of the foreground amplitude. In this study, we develop a novel foreground removal technique grounded in U-Net networks. The essence of this technique lies in introducing an innovative data preprocessing step specifically, utilizing the temperature difference between neighboring frequency bands as input. Combining with the frequency difference, we refer to our method as the UNet-fd (UNet frequency-difference), where the U-Net structure is the same as that in deep21. Based on our tests, we demonstrate that this frequency-difference preprocessing technique can substantially reduce the dynamic range of foreground amplitudes by approximately two orders of magnitude. This reduction proves to be highly advantageous for the U-Net foreground removal. We observe that the HI signal can be reliably recovered, as indicated by the cross-correlation power spectra showing unity agreement at the scale of k 0.3 hMpc−1 in the absence of instrumental effects. Moreover, accounting for the systematic beam effects, our reconstruction displays consistent auto-correlation and cross-correlation power spectrum ratios at the 1σ level across scales k 0.1 hMpc−1, with only a 10% reduction observed in the cross-correlation power spectrum at k 0.2 hMpc−1. The effects of redshift-space distortion are also reconstructed successfully, as evidenced by the quadrupole power spectra matching with the target truth. In order to test how thermal noise affects the performance of our method, we simulated various white noise levels in the map. This shows the mean cross-correlation ratio R¯cross 0.8 when the level of the thermal noise is smaller than or equal to that of the HI signal. In comparison, our method outperforms the traditional Principal Component Analysis (PCA) method. The PCA-derived cross-correlation ratios are underestimated by

关键词： Power spectrum

来源：评论

学校读者我要写书评

暂无评论

Accelerating evolutionary neural architecture search via multi-fidelity evaluation

arXiv

引用

arXiv 2021年

作者： Yang, Shangshang Tian, Ye Xiang, Xiaoshu Peng, Shichen Zhang, Xingyi Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Artificial Intelligence Anhui University Hefei230039 China Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Institutes of Physical Science and Information Technology Anhui University Hefei230601 China

Evolutionary neural architecture search (ENAS) has recently received increasing attention by effectively finding high-quality neural architectures, which however consumes high computational cost by training the architecture encoded by each individual for complete epochs in individual evaluation. Numerous ENAS approaches have been developed to reduce the evaluation cost, but it is often difficult for most of these approaches to achieve high evaluation accuracy. To address this issue, in this paper we propose an accelerated ENAS via multifidelity evaluation termed MFENAS, where the individual evaluation cost is significantly reduced by training the architecture encoded by each individual for only a small number of epochs. The balance between evaluation cost and evaluation accuracy is well maintained by suggesting a multi-fidelity evaluation, which identifies the potentially good individuals that cannot survive from previous generations by integrating multiple evaluations under different numbers of training epochs. For high diversity of neural architectures, a population initialization strategy is devised to produce different neural architectures varying from ResNetlike architectures to Inception-like ones. Experimental results on CIFAR-10 show that the architecture obtained by the proposed MFENAS achieves a 2.39% test error rate at the cost of only 0.6 GPU days on one NVIDIA 2080TI GPU, demonstrating the superiority of the proposed MFENAS over state-of-the-art NAS approaches in terms of both computational cost and architecture quality. The architecture obtained by the proposed MFENAS is then transferred to CIFAR-100 and ImageNet, which also exhibits competitive performance to the architectures obtained by existing NAS approaches. The source code of the proposed MFENAS is available at https://***/DevilYangS/MFENAS/.MSC Codes 68W50, 68T07 © 2021, CC BY.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Complementary Mismatch Filter Group Design for Joint radar and Communications Waveforms

Complementary Mismatch Filter Group Design for Joint Radar a...

引用

IEEE International Conference on radar

作者： Haichuan Li Yongjun Liu Guisheng Liao Yufeng Chen Wei Yin Chilian Chen National Laboratory of Radar Signal Processing Xidian University Xi'an China The 54th Research Institute of CETC Shijiazhuang China Key Laboratory of Technology on Datalink The 20th Research Institute of CETC Xi'an China

ISBN: (纸本)9781665468893

In the traditional joint radar and communications (JRC) system, the receive filter outputs for unambiguous returns have high sidelobe level (SLL), and the outputs of range ambiguity returns have high energy. These problems degrade the performance of the traditional JRC system. To solve these problems, we design the complementary mismatch filter group (CMFG) for the JRC system in this paper. Compared with the matched filter, the output of the CMFG has signal to noise ratio (SNR) loss. Hence, in this method, the SNR loss and the SLL of the summation of filter outputs of unambiguous returns as well as the energy of summation of filter outputs of range ambiguity returns in each CMFG are jointly minimized. To achieve this, the multi-objective optimization problem for CMFG design is established, and the Block Coordinate Descent algorithm is employed to solve this optimization problem. Finally, simulation results show that the output of the designed CMFG has low SLL, low energy of the range ambiguity output, and low SNR loss.

关键词： Matched filters Simulation radar Filtering algorithms Optimization signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

signal classification against repeat radar jammers with optimized MIMO radar waveforms

Signal classification against repeat radar jammers with opti...

引用

IET International radar Conference (IET IRC 2020)

作者： G. Dou S. Zhou H. Liu J. Liu L. Xu H. Ma P. Wang National Laboratory of Radar Signal Processing Xi’an China University of Science and Technology of China Department of Electronic Engineering and Information Science Hefei 230027 China

The digital radio frequency memory (DRFM) repeat jammer, which can transmit signals of close signature to real target returns, is a typical low-cost electronic attacker and poses threats to radar systems. One can optimize multiple-input multiple-output (MIMO) radar waveforms to magnify the difference between deceptive signals and real targets, and in this paper, we examine the performance improvement achieved by designing classification algorithms. The training samples are theoretical target returns and theoretical constant-modulus deceptive signals, both modulated with different Doppler frequencies. Three classifiers, namely the support vector machines (SVM), Naive Bayes and k-Nearest Neighbor (kNN), are considered and the SVM performs the best. With 128-chips phase-coded transmit signals, the waveform optimization algorithm achieves a 6dB signal-to-noise ratio (SNR) improvement at the 90% classification rate.

关键词： jamming radar signal processing support vector machines signal classification MIMO radar signal sampling Doppler radar naive Bayes methods nearest neighbour methods phase coding optimisation radar computing

来源：评论

学校读者我要写书评

暂无评论

A Self-Adaptive Modified Whale Optimization Algorithm for Optimizing the Linear Antenna Array

A Self-Adaptive Modified Whale Optimization Algorithm for Op...

引用

International Conference on Measuring technology and Mechatronics Automation, ICMTMA

作者： Wentao Feng Kekang Song National Key Laboratory of Science and Technology on Blind Signal Processing Chengdu China National Key Laboratory of Science and Technology on Blind Signal Processing Sichuan Chengdu China

ISBN: (数字)9781728170817

ISBN: (纸本)9781728170824

The whale optimization algorithm (WOA) is an effective algorithm for solving complex optimization problem. Its unique search mechanism results in better exploitation than exploration capability which means that it's easy to get trapped in the local optima. A self-adaptive modified whale optimization algorithm named of SAMWOA is proposed. A self-adaptive quasi-opposition method and novel population updating mechanism is integrated into the whale optimization algorithm to improve the solution accuracy. Finally, the proposed algorithm is utilized in optimizing the radiation pattern of a 16-element linear antenna array. The experimental results show that SAMWOA algorithm can reduce the sidelobe level obviously.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Heterogeneous influence of individuals’ behavior on mask efficacy in gathering environments

引用

Frontiers of Engineering Management 2022年第4期9卷 550-562页

作者： Haochen SUN Xiaofan LIU Zhanwei DU Ye WU Haifeng ZHANG Xiaoke XU College of Information and Communication Engineering Dalian Minzu UniversityDalian 116600China Web Mining Laboratory Department of Media and CommunicationCity University of Hong KongHong KongChina WHO Collaborating Centre for Infectious Disease Epidemiology and Control School of Public HealthLi Ka Shing Faculty of MedicineThe University of Hong KongHong KongChina Laboratory of Data Discovery for Health Hong Kong Science and Technology ParkHong KongChina Computational Communication Research Center Beijing Normal University(Zhuhai)Zhuhai 519087China School of Journalism and Communication Beijing Normal UniversityBeijing 100875China Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Mathematical ScienceAnhui UniversityHefei 230601China

Wearing masks is an easy way to operate and popular measure for preventing *** masks can slow down the spread of viruses,their efficacy in gathering environments involving heterogeneous person-to-person contacts remains ***,we aim to investigate the epidemic prevention effect of masks in different real-life gathering *** study uses four real interpersonal contact datasets to construct four empirical networks to represent four gathering *** transmission of COVID-19 is simulated using the Monte Carlo simulation *** heterogeneity of individuals can cause mask efficacy in a specific gathering environment to be different from the baseline efficacy in general ***,the heterogeneity of gathering environments causes the epidemic prevention effect of masks to *** masks can greatly reduce the probability of clustered epidemics and the infection scale in primary schools,high schools,and ***,the use of masks alone in primary schools and hospitals cannot control *** high schools with social distancing between classes and in workplaces where the interpersonal contact is relatively sparse,masks can meet the need for *** the heterogeneity of individual behavior,if individuals who are more active in terms of interpersonal contact are prioritized for mask-wearing,the epidemic prevention effect of masks can be ***,asymptomatic infection has varying effects on the prevention effect of masks in different *** effect can be weakened or eliminated by increasing the usage rate of masks in high schools and ***,the effect on primary schools and hospitals cannot be *** study contributes to the accurate evaluation of mask efficacy in various gathering environments to provide scientific guidance for epidemic prevention.

关键词： COVID-19 masks behavioral heterogeneity asymptomatic infection

来源：评论

学校读者我要写书评

暂无评论

From early biological models to CNNs: Do they look where humans look? 25

From early biological models to CNNs: Do they look where hum...

引用

25th International Conference on Pattern Recognition, ICPR 2020

作者： Cadoni, Marinella Iole Lagorio, Andrea Grosso, Enrico Jia Huei, Tan Chee Seng, Chan Computer Vision Laboratory University of Sassari Sassari Italy Center of Image and Signal Processing Department of Artificial Intelligence Faculty of Computer Science and Information Technology University of Malaya Malaysia

ISBN: (纸本)9781728188089

Early hierarchical computational visual models as well as recent deep neural networks have been inspired by the functioning of the primate visual cortex system. Although much effort has been made to dissect neural networks to visualize the features they learn at the individual units, the scope of the visualizations has been limited to a categorization of the features in terms of their semantic level. Considering the ability humans have to select high semantic level regions of a scene, the question whether neural networks can match this ability, and if similarity with humans attention is correlated with neural networks performance naturally arise. To address this question we propose a pipeline to select and compare sets of feature points that maximally activate individual networks units to human fixations. We extract features from a variety of neural networks, from early hierarchical models such as HMAX up to recent deep convolutional neural netwoks such as Densnet, to compare them to human fixations. Experiments over the ETD database show that human fixations correlate with CNNs features from deep layers significantly better than with random sets of points, while they do not with features extracted from the first layers of CNNs, nor with the HMAX features, which seem to have low semantic level compared with the features that respond to the automatically learned filters of CNNs. It also turns out that there is a correlation between CNN's human similarity and classification performance. © 2020 IEEE

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

A real-time dereverberation algorithm combined with echo cancellation 12

A real-time dereverberation algorithm combined with echo can...

引用

12th International Conference on Measuring technology and Mechatronics Automation, ICMTMA 2020

作者： Wang, Xia Zhu, Shuangshuang Zhao, Li School of Information Science and Technology Nantong University Nantong226019 China Key Laboratory of Underwater Acoustic Signal Processing of Ministry of Education Southeast University Nanjing210096 China

ISBN: (纸本)9781728170817

In order to improve the output speech quality of the near-end signal collected in the real-time communication system, a reverberation suppression algorithm with low computation is proposed. Firstly, the algorithm uses the adaptive filter of the echo canceller to model the room response. Secondly, using the linear fitting method, the reverberation time is estimated according to the modeled impulse. Then, a adaptive filter is used to estimate the echo signal and thus the error signal is obtained. Finally, the spectral subtraction method is used to obtain the estimated pure signal. Experimental results validated the efficiency of the proposed algorithm. The near-end speech can be obtained with less amount of calculation comparing to other similar algorithms. © 2020 IEEE.

关键词： Echo suppression

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：