检索结果-内蒙古大学图书馆

International Wireless communications and Mobile Computing Conference, IWCMC

作者： Yi Hu Shuai Han Shiji Wang Cheng Li Communication Research Center Harbin Institute of Technology China Beijing Aerospace Measurement & Control Technology CO.LTD Beijing China Faculty of Engineering and Applied Science Memorial University Canada

ISBN: (数字)9798350361261

ISBN: (纸本)9798350361278

The widespread adoption of deep learning models has inspired an urgent need for their generalization capabilities. Despite their impressive performance on training data, achieving high accuracy on deployed untouched data remains a daunting challenge. To address this problem, improving the model’s adaptability to new samples is imperative. In this paper, we delve into the metrics of deep learning models, pointing out that the upper bound of the generalization error is a quantitative measure of their generalization ability. Outlining methods to enhance this ability, we subsequently improve the LSTM model for modulation recognition using the identified upper bound on the generalization error and the outlined enhancement strategy, significantly improving the accuracy. Finally, an outlook on future research is provided.

关键词： Deep learning Wireless communication Adaptation models Upper bound Accuracy Recurrent neural networks measurement uncertainty

来源：评论

学校读者我要写书评

暂无评论

Primary User Adversarial Attacks on Deep Learning-Based Spectrum Sensing and the Defense Method

引用

China communications 2021年第12期18卷 94-107页

作者： Shilian Zheng Linhui Ye Xuanye Wang Jinyin Chen Huaji Zhou Caiyi Lou Zhijin Zhao Xiaoniu Yang Science and Technology on Communication Information Security Control Laboratory Jiaxing314000China College of Information Engineering Zhejiang University of TechnologyHangzhou310012China Institute of Cyberspace Security Zhejiang University of TechnologyHangzhou310012China School of Communication Engineering Hangzhou Dianzi UniversityHangzhou310018China

The spectrum sensing model based on deep learning has achieved satisfying detection per-formence,but its robustness has not been *** this paper,we propose primary user adversarial attack(PUAA)to verify the robustness of the deep learning based spectrum sensing *** adds a care-fully manufactured perturbation to the benign primary user signal,which greatly reduces the probability of detection of the spectrum sensing *** design three PUAA methods in black box *** or-der to defend against PUAA,we propose a defense method based on autoencoder named *** apply the long short-term memory network and the convolutional neural network together to DeepFilter,so that it can extract the temporal and local features of the input signal at the same time to achieve effective *** experiments are conducted to eval-uate the attack effect of the designed PUAA method and the defense effect of *** show that the three PUAA methods designed can greatly reduce the probability of detection of the deep learning-based spectrum sensing *** addition,the experimen-tal results of the defense effect of DeepFilter show that DeepFilter can effectively defend against PUAA with-out affecting the detection performance of the model.

关键词： spectrum sensing cognitive radio deep learning adversarial attack autoencoder defense

来源：评论

学校读者我要写书评

暂无评论

Covid-19 Epidemic Trend Prediction Based on CNN-StackBiLSTM 11

Covid-19 Epidemic Trend Prediction Based on CNN-StackBiLSTM

引用

11th IEEE Data Driven control and Learning Systems Conference, DDCLS 2022

作者： Li, Zhenyu Wang, Yang Wang, Yanwei Zheng, Ying Su, Housheng School of Artificial Intelligence and Automation Huazhong University of Science and Technology China-Belt and Road Joint Laboratory On Measurement and Control Technology Wuhan430074 China School of Mechanical & Electrical Engineering Wuhan Institute of Technology Hubei Wuhan430073 China

ISBN: (数字)9781665496759

ISBN: (纸本)9781665496759

In late 2019, the novel coronavirus (COVID-19) became a major health hazard around the world. Recently, the COVID-19 has spread widely in most countries and regions and the number of infected people continues to grow rapidly. Therefore, it is essential to research the development trend of the epidemic. The prediction of the number of infections and deaths is critical and helpful for developing health and epidemic prevention strategies and even curbing the epidemic. In this paper, a one-dimensional convolutional neural network combined with the stacked long-short-term-memory network model (CNN-StackBiLSTM) is proposed for the time-series prediction of cumulative cases and daily new cases. The local feature is extracted by CNN. The stacked BiLSTM captures the deeper characteristics of the time-series data. By combining the two networks, the proposed method simultaneously considers the information of temporal and spatial domains and can achieve accurate prediction results. Examples in Taiwan and Italy demonstrate the effectiveness of the proposed method. The proposed method is compared with LSTM, BiLSTM, and GRU. The mean absolute error, mean square error, R2 score, and root mean square error are calculated to quantificationally measure the different models. The results indicate the proposed method performs well in the prediction of both new daily confirmed cases and cumulative confirmed cases. © 2022 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Two Algorithms Based on Iterative Optimization for UAV Path Planning

Two Algorithms Based on Iterative Optimization for UAV Path ...

引用

IEEE International Conference on Unmanned Systems (ICUS)

作者： Biao Chen Shengming Li Zongyang Lv School of Control Science and Engineering Dalian University of Technology Dalian China School of Information and Communication Engineering Dalian University of Technology Dalian China

In this paper, we propose two algorithms based on iterative optimization for UAV path planning. In the first one, a nonlinear programming (NLP) problem of unmanned aerial vehicle (UAV) path planning is transformed into a general quadratically constrained quadratic programming (QCQP) problem by a numerical optimization method and solved through iteration. This method can converge to the optimal solution without giving the initial value. It overcomes the problems that NLP solvers are dependent on the initial guess, slow to converge, and sometimes can't converge to a feasible solution. In the second one, we improve the optimized rapidly exploring random tree algorithm (RRT*) and add UAV flight constraints to it. The improved RRT* algorithm reduces the length of the path and makes the path smoother.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Realizing number recognition with simulated quantum semi-restricted Boltzmann machine

引用

communications in Theoretical Physics 2022年第9期74卷 33-38页

作者： Fuwen Zhang Yonggang Tan Qing-yu Cai School of Physics Zhengzhou UniversityZhengzhou 450001China Innovation Academy for Precision Measurement Science and Technology Chinese Academy of SciencesWuhan 430071China School of Physics and Electronic Information Luoyang Normal UniversityLuoyang 471934China Center for Theoretical physics Hainan UniversityHaikou 570228China School of Information and Communication Engineering Hainan UniversityHaikou 570228China

Quantum machine learning based on quantum algorithms may achieve an exponential speedup over classical algorithms in dealing with some problems such as *** this paper,we use the method of training the lower bound of the average log likelihood function on the quantum Boltzmann machine(QBM)to recognize the handwritten number datasets and compare the training results with classical *** find that,when the QBM is semi-restricted,the training results get better with fewer computing *** shows that it is necessary to design a targeted algorithm to speed up computation and save resources.

关键词： machine learning quantum Boltzmann machine quantum algorithm

来源：评论

学校读者我要写书评

暂无评论

A Prototypical Networks-based Multi-task Model for Few-shot Fault Diagnosis 11

A Prototypical Networks-based Multi-task Model for Few-shot ...

引用

11th IEEE Data Driven control and Learning Systems Conference, DDCLS 2022

作者： Huo, Zhihao Yang, Xiaoyu Yang, Tao Fan, Huijin Su, Housheng Zheng, Ying School of Artificial Intelligence and Automation Huazhong University of Science and Technology China-Belt and Road Joint Laboratory On Measurement and Control Technology Wuhan430074 China School of Energy and Power Engineering Huazhong University of Science and Technology Wuhan430074 China

ISBN: (数字)9781665496759

ISBN: (纸本)9781665496759

Due to the powerful classification performance, Prototypical Networks is widely used in few-shot fault diagnosis. However, insufficient feature extraction ability and negligence of inter-class distance in the Prototypical Networks may lead to the decrease of diagnosis accuracy. To solve the above problems, a Prototypical Networks-based multi-task model (PNBMTM) is proposed in this paper. Firstly, a convolutional autoencoder is built based on the feature extraction network of the Prototypical Networks, in which the optimization of the reconstruction loss is taken as a new task to obtain more efficient features. Secondly, a channel attention module (CAM) is designed to be applied to each layer of the encoder, which focuses on important features and suppresses useless features. Thirdly, relative distance loss is introduced while considering the effect of intra-class distance and inter-class distance to make inter-class distance larger and intra-class distance smaller, which helps to improve the quality of the features. And the optimization of relative distance loss is consequently taken as a new task to constitute a multi-task fault diagnosis model. Finally, a mechanical fault simulation experiment platform is built to verify the validity of the proposed model. The experimental results show that the proposed model has superior performance compared with other models. © 2022 IEEE.

关键词： Failure analysis

来源：评论

学校读者我要写书评

暂无评论

Receiver System Design for Universal Polyphase DFT Digital Channelization Algorithm 5

Receiver System Design for Universal Polyphase DFT Digital C...

引用

5th IEEE International Conference on Electronics technology, ICET 2022

作者： Lu, Shihang Su, Zhengyu Liao, Kaisheng Li, Chao Xiao, Zhuoling Yan, Bo Lin, Shuisheng Wu, Bo University of Electronic Science and Technology of China Science and Technology on Electronic Information Control Laboratory National Key Laboratory of Science and Technology on Blind Signal Processing School of Information and Communication Engineering China

ISBN: (纸本)9781665485081

Receiver plays a vital role in various electronic countermeasure systems and has always been a hot topic to research. Based on the traditional receiver digital channelization structure, this paper further researches and derives the high-efficiency digital channelization structure based on polyphase discrete Fourier transform corresponding to various application scenarios. Then we design a 256-sub-channel digital channelization system and implement it on a 64-channel parallel digital down converter to verify the structure. The system design relies on system on chip as the platform, and we verify the feasibility of it on field programmable gate array. © 2022 IEEE.

关键词： System-on-chip

来源：评论

学校读者我要写书评

暂无评论

Talent Flow Model Based on Graph Attention Network

Talent Flow Model Based on Graph Attention Network

引用

Big Data & Artificial Intelligence & Software engineering (ICBASE), International Conference on

作者： Baisen Liu Zongting Jia Lili Zhao Weili Kong School of Measurement and Communication Engineering Harbin University of Science and Technology China College of Electrical and Information Engineering Heilongjiang Institute of Technology Harbin China College of Information and Communication Engineering Harbin Engineering University Harbin China

Talent flow is a vital component of the region’s competitiveness and development. Accurately grasping talent trends can aid in the development of the region. Unlike text and image data, the characteristics of questionnaire data are more dependent on prior and potential correlations between each factor than on its order and position relationship. To efficiently extract features from questionnaire data and accurately predict talent flow, this paper proposes a novel talent flow prediction method based on the graph attention network. In our method, the data is transformed into graph data, the data feature is saved in the nodes, the adjacency matrix stores the link between the nodes, and an attention mechanism allocates the aggregate weight when the neighbor nodes are aggregated. The experiment demonstrates that the method proposed in this paper outperforms other algorithms for similar tasks both in accuracy and efficiency. It achieves an overall classification accuracy of 92.33% and more than 90% of the classification accuracy in each category prediction classification on our dataset.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Baseline Modeling and Anomaly Detection Method for Inertial Navigation System Based on Integrated 1DCNN

A Baseline Modeling and Anomaly Detection Method for Inertia...

引用

International Conference on Electronic measurement and Instruments, ICEMI

作者： Wenjing Mo Chuanjin Han Yuan Wang Chengdu Aircraft Industrial (Group) Co. Ltd. Chengdu China School of Measurement-Control and Communication Engineering Harbin University of Science and Technology Harbin China School of Electronics and Information Engineering Harbin Institute of Technology Harbin China

Flight test is an essential step before aircraft delivery. Safe flight test can not only reduce the cost of aircraft research, but also has great significance for the study of aircraft performance. In order to ensure the safety of flight test, it is necessary to implement anomaly detection for aircraft systems. Inertial navigation system, as a complex system can provide accurate position, velocity, and attitude information for aircraft during flight test. It is very important to monitor the state of inertial navigation system for ensuring the safety of flight test. However, traditional single anomaly detection models perform poorly on different test data and have poor generalization capabilities. In order to improve the generalization ability of the anomaly detection model with inertial navigation data, this paper proposes a prediction-based anomaly detection method based on an integrated one-dimensional convolutional neural network (1DCNN). Firstly, multiple training sets are divided based on the bootstrap method, and then integrated 1DCNN prediction models are built for corresponding training sets. Finally, a static threshold judgment method based on the PauTa criterion is used to detect whether any abnormality occurs. This paper verifies the effectiveness of the proposed method through experiments with real inertial navigation data. The results show that compared with the traditional 1DCNN method, the proposed method significantly improves the performance of anomaly detection and has good generalization ability on different test conditions. The TPR of anomaly data detection reaches more than 97%, which proves that the method has effective anomaly data detection for inertial data.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Temperature and strain sensitivities of surface and hybrid acoustic wave Brillouin scattering in optical microfibers

引用

Chinese Physics B 2022年第9期31卷 333-339页

作者： Yi Liu Yuanqi Gu Yu Ning Pengfei Chen Yao Yao Yajun You Wenjun He Xiujian Chou Taiyuan University of Technology Key Laboratory of Advanced Transducers and Intelligent Control SystemMinistry of Education and Shanxi ProvinceTaiyuan 030024China Taiyuan University of Technology Institute of Optoelectronic EngineeringCollege of Physics and OptoelectronicsTaiyuan 030024China Strong Digital Technology Co. Ltd.(Thinvent)Nanchang 410000China North University of China Key Laboratory of Instrumentation Science and Dynamic Measurement Ministry of EducationTaiyuan 030051China North University of China College of Mechatronics EngineeringTaiyuan 030051China North University of China Science and Technology on Electronic Test and Measurement LaboratorySchool of Instrument and ElectronicsTaiyuan 030051China

Temperature and strain sensitivities of surface acoustic wave(SAW)and hybrid acoustic wave(HAW)Brillouin scat-tering(BS)in 1μm-1.3μm diameter optical microfibers are *** contrast to stimulated Brillouin scattering(SBS)from bulk acoustic wave in standard optical fiber,SAW and HAW BS,due to SAWs and HAWs induced by the coupling of longitudinal and shear waves and propagating along the surface and core of microfiber respectively,facilitate innovative detection in optical microfibers *** highest temperature and strain sensitivities of the hybrid acoustic modes(HAMs)are 1.082 MHz/℃and 0.0289 MHz/με,respectively,which is suitable for microfiber sensing applica-tion of high temperature and strain ***,the temperature and strain sensitivities of the SAMs are less affected by fiber diameter changes,ranging from 0.05 MHz/℃/μm to 0.25 MHz/℃/μm and 1×10^(-4) MHz/με/μm to 5×10^(-4) MHz/με/μm,*** can be found that that SAW BS for temperature and strain sensing would put less stress on manufacturing constraints for optical ***,the simultaneous sensing of temperature and strain can be realized by SAW and HAW BS,with temperature and strain errors as low as 0.30℃-0.34℃and 14.47με-16.25με.

关键词： Brllouin scatering surface acoustic waves hybrid acoustic waves optical microfiber sensing

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：