检索结果-内蒙古大学图书馆

A Gradient-Guided Evolutionary Approach to Training Deep Neural Networks

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2022年第9期33卷 4861-4875页

作者： Yang, Shangshang Tian, Ye He, Cheng Zhang, Xingyi Tan, Kay Chen Jin, Yaochu Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Hefei China Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Institutes of Physical Science and Information Technology Anhui University Hefei China Department of Computer Science and Engineering Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation Southern University of Science and Technology Shenzhen China Department of Computing The Hong Kong Polytechnic University Hong Kong SAR Department of Computer Science University of Surrey Guildford U.K

It has been widely recognized that the efficient training of neural networks (NNs) is crucial to classification performance. While a series of gradient-based approaches have been extensively developed, they are criticized for the ease of trapping into local optima and sensitivity to hyperparameters. Due to the high robustness and wide applicability, evolutionary algorithms (EAs) have been regarded as a promising alternative for training NNs in recent years. However, EAs suffer from the curse of dimensionality and are inefficient in training deep NNs (DNNs). By inheriting the advantages of both the gradient-based approaches and EAs, this article proposes a gradient-guided evolutionary approach to train DNNs. The proposed approach suggests a novel genetic operator to optimize the weights in the search space, where the search direction is determined by the gradient of weights. Moreover, the network sparsity is considered in the proposed approach, which highly reduces the network complexity and alleviates overfitting. Experimental results on single-layer NNs, deep-layer NNs, recurrent NNs, and convolutional NNs (CNNs) demonstrate the effectiveness of the proposed approach. In short, this work not only introduces a novel approach for training DNNs but also enhances the performance of EAs in solving large-scale optimization problems.

关键词： Artificial neural networks Training Optimization Search problems Scalability Complexity theory Genetic algorithms Deep neural networks (DNNs) evolutionary algorithm (EA) genetic operator gradient descent sparsity

来源：评论

学校读者我要写书评

暂无评论

Coplanar waveguide multiband antenna based on open resonant ring

Coplanar waveguide multiband antenna based on open resonant ...

引用

2022 International Applied Computational Electromagnetics Society Symposium, ACES-China 2022

作者： Li, Minquan Qu, Xin Xiao, Shuang Li, Chen Zhang, Zufeng Zhang, Weiqiang Ministry of Education Anhui University Key Laboratory of Intelligent Computing and Signal Processing Liaoyang Province China

ISBN: (纸本)9781665452366

A compact coplanar waveguide multiband antenna based on an open resonant ring is proposed in this paper. The proposed antenna is fabricated on FR-4 substrate with a dielectric constant of 4.4 and a small size of 23 × 23 × 1.6mm3. In the design process of the antenna, the deformed circular split ring metamaterial (RSRR) is introduced to realize the broadband and multi frequency characteristics of the antenna. The two frequency bands of the antenna are 2.91-3.63GHz (relative bandwidth 22%), 4.19-9.32GHz (relative bandwidth 75.9%), covering WiMax (3.4/5.5GHz), lower C-band (4.41GHz), upper C-band (6.9GHz), WLAN (5.4/5.8GHz), lower X-band (8.7GHz) wireless standards, S11 ≤ -10dB. High frequency structure simulator (HFSS) is used to simulate the antenna structure, which has uniform radiation characteristics. © 2022 IEEE.

关键词： Coplanar waveguides

来源：评论

学校读者我要写书评

暂无评论

A Privacy Preservation Method for Attributed Social Network Based on Negative Representation of Information

引用

Computer Modeling in Engineering & Sciences 2024年第7期140卷 1045-1075页

作者： Hao Jiang Yuerong Liao Dongdong Zhao Wenjian Luo Xingyi Zhang Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and TechnologyAnhui UniversityHefei230601China Chongqing Research Institute School of Computer Science and Artificial IntelligenceWuhan University of TechnologyWuhan430070China Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies School of Computer Science and TechnologyHarbin Institute of TechnologyShenzhen518055China

Due to the presence of a large amount of personal sensitive information in social networks,privacy preservation issues in social networks have attracted the attention of many *** by the self-nonself discrimination paradigmin the biological immune system,the negative representation of information indicates features such as simplicity and efficiency,which is very suitable for preserving social network ***,we suggest a method to preserve the topology privacy and node attribute privacy of attribute social networks,called ***,a negative survey-based method is developed to disturb the relationship between nodes in the social network so that the topology structure can be kept ***,a negative database-based method is proposed to hide node attributes,so that the privacy of node attributes can be preserved while supporting the similarity estimation between different node attributes,which is crucial to the analysis of social *** evaluate the performance of the AttNetNRI,empirical studies have been conducted on various attribute social networks and compared with several state-of-the-art methods tailored to preserve the privacy of social *** experimental results show the superiority of the developed method in preserving the privacy of attribute social networks and demonstrate the effectiveness of the topology disturbing and attribute hiding *** experimental results show the superiority of the developed methods in preserving the privacy of attribute social networks and demonstrate the effectiveness of the topological interference and attribute-hiding components.

关键词： Attributed social network topology privacy node attribute privacy negative representation of information negative survey negative database

来源：评论

学校读者我要写书评

暂无评论

A One-to-Two Filter Power Divider Based on LTCC 12

A One-to-Two Filter Power Divider Based on LTCC

引用

12th International Conference on Electronics, Communications and Networks, CECNet 2022

作者： Li, Yuanyuan Wu, Xianliang Hu, Yunfeng Dong, Mengying Ma, Yue Geng, Xiaolei Fang, Rongzhen Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University Hefei230001 China

ISBN: (纸本)9781643683683

In order to miniaturize microwave devices in RF systems, a power divider with filtering performance is designed. The filter power divider is based on the LTCC process, and miniaturization is achieved by cascading a bandpass filter and a one-to-two power divider. The band-pass filter adopts a fourth-order comb-line structure, and the one-to-two power divider adopts an LC lumped structure. The size of the one-to-two filter power divider designed is 10mm×4mm×5mm, which is working in 3.3GHz-3.6GHz. The simulation results show that the insertion loss(S21 and S31) are less than or equal to 4 dB, the return loss(S11) is greater than 15 dB, the isolation(S23) is greater than 17 dB, and the out-of-band suppression is greater than 18 dB in 3.8-4.3GHz and 22 dB in 0-3.2GHz and 4.3-6GHz. © 2022 The authors and IOS Press.

关键词： Bandpass filters

来源：评论

学校读者我要写书评

暂无评论

A single notch ultra-wideband filter with wide Stopband

A single notch ultra-wideband filter with wide Stopband

引用

2022 International Applied Computational Electromagnetics Society Symposium, ACES-China 2022

作者： Li, Minquan Li, Chen Qu, Xin Xiao, Shuang Anhui University Key Laboratory of Intelligent Computing & Signal Processing Ministry of Education Hefei230601 China

ISBN: (纸本)9781665452366

An ultra-wideband filter with wide stopband performance with single notch using E-shaped resonator is proposed. Based on a U-shaped MMR structure loaded by an open-circuited stub connected at its center, the loaded basic open-stub structure can generate transmission zeros on both sides of the passband to improve the in-band selectivity. Meanwhile, the symmetrical U-shaped open stub introduced not only strengthens the out-of-band suppression ability, but also optimizes the lower stopband. To suppress the in-band interference phenomenon, the proposed UWB BPF used E-shaped resonator coupled to the main transmission line of the basic UWB BPF to generate a notch band at 8GHz (Satellite communications X band). The filter has passband from 2.74 GHz to 11.5 GHz, the insertion loss is lower than 0.6dB and the filter has a relative high selectivity (30dB skirt factor is 0.891), Meanwhile, the filter has a wide stopband of up to 20.8GHz (S21 © 2022 IEEE.

关键词： Ultra-wideband (UWB)

来源：评论

学校读者我要写书评

暂无评论

A beamforming microstrip array antenna for K-band applications

A beamforming microstrip array antenna for K-band applicatio...

引用

2022 International Applied Computational Electromagnetics Society Symposium, ACES-China 2022

作者： Yu, Zijian Feng, Wenwen Song, Xiaodi Anhui University Key Laboratory of Intelligent Computing & Signal Processing Ministry of Education Hefei230601 China

ISBN: (纸本)9781665452366

A beamforming microstrip array antenna for K-band is proposed. The antenna array is a 4∗4 array, the array elements are composed of slotted rectangular microstrip antennas, and the feed network is a combination of series and parallel connections. The beamforming is achieved by using a microstrip phase shift network. The design results show that the VSWR of the antenna array is less than 1.8dB in the operating frequency bandwidth of 24.0 GHz-24.5 GHz. This antenna array can achieve a gain of more than 7.6dB in the beam range of 22.5° azimuth and 30° pitch. © 2022 IEEE.

关键词： Beamforming

来源：评论

学校读者我要写书评

暂无评论

Dielectric Resonator Magnetoelectric Dipole Arrays with Low Cross Polarization,Backward Radiation,and Mutual Coupling for MIMO Base Station Applications

引用

China Communications 2024年第6期21卷 290-304页

作者： Song Simin Da Yiran Qian Bingyi Huang Xiaoyu Chen Xiaoming Li Yingsong Ahmed A.Kishk School of Information and Communications Engineering Xi’an Jiaotong UniversityXi’an 710049China Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui UniversityHefei 230039China Department of Electrical and Computer Engineering Concordia UniversityMontrealQC H3G 1M8Canada

Dielectric resonator magnetoelectric dipole(DRMED)arrays with enhanced isolation,reduced cross-polarization,and backward radiation are proposed for base station(BS)*** proposed antenna comprises an elevated dielectric resonator antenna(DRA)on a small metal plate above a sizeable common ground *** DRA is designed in its T Eδ11 mode,acting like a magnetic *** surface current excited by the differential probes flowing on the small ground plane is equivalent to an electric *** these two equivalent dipoles are orthogonal,they have the magnetoelectric dipole characteristics with reduced backward ***,the small ground planes can be treated as decoupling structures to provide a neutralization path to cancel the original coupling path.A linearly-polarized 4-element prototype array was verified experimentally in previous ***,a dual-polarized DRMED antenna is presented to construct a 2-element and 4×4 array for BS *** investigate its MIMO performance,sophisticated multi-cell scenario simulations are carried *** using the proposed dualpolarized DRMED array,the cellular system capacityis improved by 118.6%compared to a conventional DRA *** significant MIMO system improvement is mainly due to the reduced backward radiation and,therefore,reduced inter-cell *** align well with the simulations.

关键词： backward radiation dielectric resonator antennas(DRAs) isolation magnetoelectric-dipole(ME-dipole)antennas

来源：评论

学校读者我要写书评

暂无评论

A RIS-Aided MIMO Secure Communication Scheme Based on Subarray Partition 9

A RIS-Aided MIMO Secure Communication Scheme Based on Subarr...

引用

9th International Conference on Computer and Communications, ICCC 2023

作者： Wang, Suzhen Zhi, Hui Anhui University Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Hefei China Anhui University School of Electronic and Information Engineering Hefei China

ISBN: (纸本)9798350317251

Subarray partition of reconfigurable intelligent surface (RIS) can significantly reduce the computational complexity of solving optimal reflection coefficients. However, there is no research about the RIS subarray partition of RIS-aided multiple-input multiple-output (MIMO) communication for the eavesdropper scenario. In this paper, we intend to solve the optimization subarray partition problem for the eavesdropper scenario, design a RIS-aided MIMO secure communication scheme based on subarray partition (RSC-SP). We consider minimizing the number of subarrays while satisfying secrecy rate requirements. First, this problem is described as a nonconvex combinatorial optimization problem, then we solve it by combining alternating optimization and bisection. In this scheme, we derive the closed expressions of the optimal transmit covariance matrix and the optimal reflection coefficients of RIS. The alternating optimization algorithm is used to jointly optimize the transmit covariance matrix and the reflection coefficients of RIS, the bisection method is used to calculate the minimum number of subarrays. Simulation results show that compared with the traditional scheme without subarray partition, RSC-SP can significantly reduce the computational complexity while meeting secrecy rate requirements. © 2023 IEEE.

关键词： Covariance matrix

来源：评论

学校读者我要写书评

暂无评论

Dual-Control Reconfigurable intelligent Metasurface: Design and Realization 6

Dual-Control Reconfigurable Intelligent Metasurface: Design ...

引用

6th IEEE International Conference on Electronic Information and Communication Technology, ICEICT 2023

作者： Zheng, Kangtai Chung, Kwok L. Li, Yuzhong Lai, Guoming Wang, Jianhai Li, Yingsong School of Computer Science and Engineering Huizhou University Huizhou516007 China Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education China

ISBN: (纸本)9798350399059

A dual-control reconfigurable intelligent metasurface (DC-RIMS) composed of 24× 22 symmetric cells in the 5G mid-band is proposed. The DC-RIMS of non-artificial-magnetic-conductor type provides a smaller phase resolution of 60° with 2 bits under normal incidence. Angular sensitivities of the RIMS under oblique incidence are investigated. Our results show that the reflection responses at elevation angles are more sensitive than the azimuth angles, whereas the maximum phase differences are differed from each polarization. The horizontal one increases to 220° whereas the vertical one reduces to 150° as compared with overlapped 180° under normal incidence. © 2023 IEEE.

关键词： Beamforming

来源：评论

学校读者我要写书评

暂无评论

A knowledge-enhanced interest segment division attention network for click-through rate prediction

引用

Neural computing and Applications 2024年第34期36卷 21817-21837页

作者： Liu, Zhanghui Chen, Shijie Chen, Yuzhong Su, Jieyang Zhong, Jiayuan Dong, Chen College of Computer and Data Science Fuzhou University Fujian Province Fuzhou350108 China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fujian Province Fuzhou350108 China

Click-through rate (CTR) prediction aims to estimate the probability of a user clicking on a particular item, making it one of the core tasks in various recommendation platforms. In such systems, user behavior data are crucial for capturing user interests, which has garnered significant attention from both academia and industry, leading to the development of various user behavior modeling methods. However, existing models still face unresolved issues, as they fail to capture the complex diversity of user interests at the semantic level, refine user interests effectively, and uncover users’ potential interests. To address these challenges, we propose a novel model called knowledge-enhanced Interest segment division attention network (KISDAN), which can effectively and comprehensively model user interests. Specifically, to leverage the semantic information within user behavior sequences, we employ the structure of a knowledge graph to divide user behavior sequence into multiple interest segments. To provide a comprehensive representation of user interests, we further categorize user interests into strong and weak interests. By leveraging both the knowledge graph and the item co-occurrence graph, we explore users’ potential interests from two perspectives. This methodology allows KISDAN to better understand the diversity of user interests. Finally, we extensively evaluate KISDAN on three benchmark datasets, and the experimental results consistently demonstrate that the KISDAN model outperforms state-of-the-art models across various evaluation metrics, which validates the effectiveness and superiority of KISDAN. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Contrastive Learning

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：