检索结果-内蒙古大学图书馆

Network completion via deep metric learning

Journal of Physics: Conference Series 2020年第1期1656卷

作者： Qiang Wei School of Information and Communication Engineering University of Electronic Science and Technology of China Chengdu 611731 China National Key Laboratory of Science and Technology on Blind Signal Processing Chengdu 610041 China

Completing networks is often a necessary step when dealing with problems arising from applications in incomplete network data mining. This paper investigates the network completion problem with node attributes. We proposed a new method called DeepMetricNC by exploiting the correlation between node attributes and the underlying network structure. In DeepMetricNC, the correlation is modeled as a nonlinear mapping from node attributes to the probability of edge existence. To obtain the mapping, deep metric learning is applied with batch training and random negative sampling. DeepMetricNC has linear training time complexity and can adapt to large-scale network completion tasks. Experiments of real networks show that DeepMetricNC completes network structures better than other methods, and is more suitable when the portion of the observed part is small.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DOA Estimation for UCAs Based on Virtual Subarray Beamforming Technique

DOA Estimation for UCAs Based on Virtual Subarray Beamformin...

引用

2018 2nd International Conference on Electronic Information technology and Computer Engineering (EITCE 2018)

作者： Bo Xu Zhigang Huang Key Laborartory of Science and Technology for National Defence on Blind Signal Processing

Direction-of-arrival(DOA) estimation is always a hotspot research in the fields of radar, sonar, communication and so on. And uniform circular arrays(UCAs) are more attractive in the context of DOA estimation since their symmetrical structures have potential to provide two directions coverage. This paper proposed a new DOA estimation method for UCAs via virtual subarray beamforming technique. The method would provide an acceptable DOA estimate even if the number of sources is great than the number of array elements. Also, the performance of the proposed method would hold good when the snapshot length or the signal-to-noise ratio(SNR) is small. Simulations show that the proposed technique offers significantly improved estimation resolution, capacity, and accuracy relative to the existing techniques.

关键词： DOA Estimation for UCAs Based on Virtual Subarray Beamforming Technique Virtual

来源：评论

学校读者我要写书评

暂无评论

Dynamic HypE for solving single objective optimisation problems

引用

International Journal of Innovative Computing and Applications 2019年第1期10卷 51-58页

作者： Zhang, Qing Zhao, Fei Zeng, Sanyou School of Computer Science Huanggang Normal University Huanggang Hubei438000 China Science and Technology on Blind Signal Processing Laboratory Southwest Electronics and Telecommunication Technology Research Institute Chengdu Sichuan610041 China School of Mechanical Engineering and Electronic Information China University of Geosciences Wuhan Hubei430074 China

One difficulty in solving optimisation problems is the handling many local optima. The usual approaches to handle the difficulty are to introduce the niche-count into evolutionary algorithms (EAs) to increase population diversity. In this paper, we introduce the niche-count into the problems, not into the EAs. We construct a dynamic multi-objective optimisation problem (DMOP) for the single optimisation problem (SOP) and ensure both the DMOP and the SOP are equivalent to each other. The DMOP has two objectives: the original objective and a niche-count objective. The second objective aims to maintain the population diversity for handling the local optima difficulty during the search process. A dynamic version of a multi-objective evolutionary algorithm (DMOEA), specifically, HypE-DE, is used to solve the DMOP;consequently the SOP is solved. Experimental results show that the performance of the proposed method is significantly better than the state-of-the-art competitors on a set of test problems. Copyright © 2019 Inderscience Enterprises Ltd.

关键词： Evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

An Online Updating Multi-Threshold Method for Mobility Relationship Mining 9

An Online Updating Multi-Threshold Method for Mobility Relat...

引用

2017 9th IEEE International Conference on Communication Software and Networks (ICCSN 2017)

作者： Zeng Chen Keren Wang Zhengguo Xu Jiaqi Yao National Key Laboratory of Science and Technology on Blind Signal Processing

ISBN: (纸本)9781509038237;9781509038220

With the popularity of the mobile phones and location-based social networks, rich location data has become widely available nowadays, enabling study on friendship detection based on human mobility. However, in some circumstances, limited by data collection techniques, only discrete location（such as location IDs） can be fetched which leads to methods of detecting friendship based on distance metric is unrealistic. This paper aims to detect friendship among users based on their mobility data where locations are represented by location IDs. By considering each user’s preference for location and each location’s popularity, the difference between friends and strangers gets larger than using merely frequency of meeting events. However, we discover that measure values obtained may vary greatly among different users and propose to maintain a threshold for each user. In addition, an online updating algorithm is presented to update thresholds when a new user’s mobility data is available. Experiments conducted on MIT Reality Mining project dataset show that the proposed updating method is practical and the proposed multi-threshold model outperforms the state-of-theart methods proposed by Wang et al.

关键词： friendship detection multi-threshold mobility spatiotemporal online update

来源：评论

学校读者我要写书评

暂无评论

Weighted Multidimensional Scaling Localization of a Known Altitude Object Using TOA Measurements

Weighted Multidimensional Scaling Localization of a Known Al...

引用

2018 International Conference on Computer, Electronic Information and Communications(CEIC 2018)

作者： Bing DENG Yu-cheng WENG Zheng-bo SUN National Key Laboratory of Science and Technology on Blind Signal Processing China Southern Airlines

This paper considers the problem of geolocating a target on the Earth surface whose altitude is known using the target signal time of arrival(TOA) measurements. The geolocation Cramer-Rao lower bound(CRLB) is derived and the performance improvement due to the availability of target altitude information is quantified. An weighted multidimensional scaling geolocation solution is developed. Its sensitivity to the target altitude error is also studied. Simulations verify the theoretical developments and illustrate the good performance of the proposed geolocation method.

关键词： Time of arrival Multidimensional scaling Target altitude

来源：评论

学校读者我要写书评

暂无评论

A Wideband Spectrum Sensing Based on ESPRIT Algorithm

A Wideband Spectrum Sensing Based on ESPRIT Algorithm

引用

2018 International Computers, signals and Systems Conference, ICOMSSC 2018

作者： Shen, Yanni Wan, Qun Xia, Changxiong Wan, Yihe University of Electronic Science and Technology of China School of Electronic Engineering Chengdu China Key Lab of Blind Signal Processing Chengdu China Technology Co. Ltd Jiangxi Province Engineering Research Center Special Wireless Communications Tongfang Electronic Jiujiang China

ISBN: (纸本)9781538667514

Spectrum sensing is a prerequisite for cognitive dio. This paper proposes a wideband spectrum sensing method based on ESPRIT algorithm for detecting active channels. In this method, it detects the occupied channels directly according to the relationship between the Fourier transform (FT) of the multicoset sampler's output sequences and the active channels, which can save a lot of sampling rate and reduce the computational complexity. And the performance of this method is evaluated by calculating the detection probabilities for different numbers of samples and different signals to noise ratios (SNRs). The simulation results show that the proposed method performs well in low SNR and less data samples. © 2018 IEEE.

关键词： signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Optimum Strategy of Reference Emitter Placement for Dual-Satellite TDOA and FDOA Localization

Optimum Strategy of Reference Emitter Placement for Dual-Sat...

引用

International Conference on Instrumentation, Measurement, Computer, Communication and Control (IMCCC)

作者： Kaiqiang Ren Zhengbo Sun National Key Laboratory of Science and Technology on Blind Signal Processing Southwest Institute of Electronic and Telecommunication Chengdu China

ISBN: (数字)9781538682463

ISBN: (纸本)9781538682470

An optimum strategy of reference emitter placement for dual-satellite time difference of arrival (TDOA) and frequency difference of arrival (FDOA) localization based on particle swarm optimization is proposed to improve localization accuracy. Firstly Cramer-Rao lower bound (CRLR) of dual-satellite TDOA and FDOA localization system with ephemeris error and system error is derived. Then, the optimum strategy of reference emitter placement is transformed to multidimensional constraint optimization problem by using CRLB as the criterion for performance of dual-satellite TDOA and FDOA localization system. Finally, optimum strategy of reference emitter placement is obtained by using particle swarm optimization (PSO) to solve the target function. Simulation results demonstrate that the proposed method can derive optimum strategy of reference emitter placement validly. Besides, when the optimum strategy of reference emitter placement is applied, only two reference emitters are demanded to eliminate the effect of ephemeris error and system error on localization accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Low Altitude, Slow Speed and Small Size Object Detection Improvement in Noise Conditions Based on Mixed Training

引用

Journal of Physics: Conference Series 2019年第1期1169卷

作者： J. F. Que H. F. Peng J. Y. Xiong National Key Laboratory of Science and Technology on Blind Signal Processing Chengdu China.

The low altitude, slow speed and small size object which we call LSS-object for short, such as small UAV (unmanned aerial vehicles) have become a hot issue of air defense security, which is difficult to detect and identify accurately from the image. In this paper, aiming at the problem of LSS-object detection under noise environment, the detection method based on deep learning is proposed. Firstly, a standard training dataset consisting 5 classes of typical objects is constructed. Then, the standard dataset is augmented with noise of different intensity. Finally, YOLO v3 algorithm is used to form a LSS-object detection system which can adapt to environment noise. The training and detection experiments were carried out on the GPU server. After only using the noise-free dataset for training, the mAP(mean Average Precision) of the noise-free test set detection reached 81.07%, but the mAP decreased to 20.68% when the noise variance was *** adopting the mixed training strategy of the dataset with noise variance of 0.01 and noise-free data, the mAP for the test set detection with noise variance of 0.03 was increased to 70.61%, and the mAP still reached 79.85% in noise-free test set detection. The experiment results show that the mixed training strategy can greatly improve the accuracy in the noisy images detection while maintaining a higher accuracy in noise-free images.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Direct Location for Multiple Passive Radars without and with Reference

引用

Journal of Physics: Conference Series 2019年第1期1169卷

作者： K. K. Song Y. X. Yang H. F. Peng National Key Laboratory of Science and Technology on Blind Signal Processing Chengdu China.

The problem of stationary target location by multiple passive radar sensors that using unknown and non-cooperative opportunity illuminator is considered. Traditional two-step approach which estimating the time difference of arrival (TDOA) and angle of arrival (AOA) firstly and locating using those parameters secondly. We explore the direct location with multiple passive radar sensors without estimating the intermediate parameters. As the reference path from the transmitter to receivers may be blocked in practice, we discuss the both cases that location without and with reference path. Two maximum likelihood algorithms of direct location are proposed for multiple passive radar sensors without and with reference. Monte Carlo simulations indicate that the direct location algorithm is superior to two-step approach with TDOA and AOA at low SNR for multiple passive radar sensors.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Method of Fast Extract signal Subspace Based on the Householder Transformation

A Method of Fast Extract Signal Subspace Based on the Househ...

引用

2018 International Computers, signals and Systems Conference, ICOMSSC 2018

作者： Chang, Yu Wan, Qun Xia, Changxiong Wan, Yihe University of Electronic Science and Technology of China School of Electronic Engineering Chengdu China Key Lab of Blind Signal Processing Chengdu China Special Wireless Communication Tongfang Electronic Techology Co. Ltd Jiangxi Province Engineering Research Center Jiujiang China

ISBN: (纸本)9781538667514

The technologies of array signal processing based on subspace decomposition can break the Rayleigh limit, and have great performance and angular resolution. However, in order to obtain signal subspace, traditional methods need to apply singular value decomposition on the signal covariance matrix. Because of the large amount of calculation of singular value decomposition, it is difficult to satisfy the requirements in real-time. Given that the signal covariance matrix is conjugate-symmetric, this paper proposes a new method that can fast compute signal subspace depending on repeatedly applying householder transformation to reduce the covariance matrix order based on the power method, and it has fewer iterations and less amount of calculation. © 2018 IEEE.

关键词： Covariance matrix

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：