检索结果-内蒙古大学图书馆

4th International Conference on Big Data and Artificial Intelligence and Software engineering, ICBASE 2023

作者： Cheng, Xing Xie, Heng He, Shanbao Beijing Information Science and Technology University Key Laboratory of Information and Communication Systems Ministry of Information Industry School of Information and Communication Engineering Beijing China

ISBN: (纸本)9798350329490

Remote sensing (RS) of sea ice types is of great significance for global climate research. A convolutional neural network (CNN) based sea ice type recognition method for delay Doppler map (DDM) of global navigation satellite system reflection (GNSS-R) is proposed in this paper. In the proposed method, the sea ice type recognition problem is transformed into an image recognition problem by utilizing the difference between the DDM images corresponding to the first-year and multi-year ice, and the CNN model is used to recognize the images. Experimental results show that our proposed CNN based method for identifying sea ice types has excellent performance. © 2023 IEEE.

关键词： Sea ice

来源：评论

学校读者我要写书评

暂无评论

A strategy for accurate prediction of dielectric permittivity and dielectric strength in polyimide

引用

High Voltage 2024年第6期9卷 1393-1401页

作者： Yu Wang Changhai Zhang Jiaqi Lin Hongguo Sun Ying Yang Wenlong Yang School of Electrical and Electronic Engineering Harbin University of Science and TechnologyHarbinChina School of Science Harbin University of Science and TechnologyHarbinChina Polymer Composites Engineering Laboratory Changchun Institute of Applied ChemistryChinese Academy of SciencesChangchunChina State Key Laboratory of Mechanics and Control of Mechanical Structures Nanjing University of Aeronautics and AstronauticsNanjingChina School of Measurement and Communication Engineering Harbin University of Science and TechnologyHarbinChina

A strategy was proposed to predict accurately the dielectric permittivity and dielectric strength based on the Onsager local field *** molecular dynamic simulation was utilised to analyse the dipole moment fluctuation in polyimide(PI)to reflect the polar-isation response of applied electric *** simulation results revealed that the optical dielectric permittivity and static dielectric permittivity were 2.62 and 3.34,showing that the electronic displacement polarisation of the PI acted as a major *** deviation between simulated and measured values of the frequency-dependent relative dielectric permittivity was no more than 5%,which exhibited high *** the polarisation response of the polar groups in the PI was at infrared frequencies,the conductive loss may be the dominant role in 102–106 Hz at room ***,the effect of Joule heat on the structure,dielectric permittivity and Young modulus was considered to accurately predict the dielectric strength of the PI(359 kV/mm),which was in agreement with experimental values in the *** results establish a clear correlation between structural characteristics and dielectric properties of the PI,which would be the theoretical insights into the design and synthesis of the PI with tailored dielectric properties.

关键词： dielectric strength permittivity

来源：评论

学校读者我要写书评

暂无评论

Attention-based deep learning approach for CSI feedback under 5G TDL channel

Attention-based deep learning approach for CSI feedback unde...

引用

2023 International Conference on Machine Learning and Automation, CONF-MLA 2023

作者： Peng, Hanli School of Information and Communication Engineering University of Electronic Science and Technology of China Sichuan Chengdu611731 China

In 5G communication systems, accurate channel state information (CSI) is indispensable for signal detection and regulation at the base station side. However, frequent CSI feedback from users leads to excessive system overhead. To tackle this challenge, this paper puts forward a novel deep learning framework - HCNet based on attention mechanism and autoencoder, aiming to efficiently compress and reconstruct the high-dimensional time-varying CSI matrices in an end-to-end approach. The proposed framework incorporates a self-attention module in the encoder to explicitly capture global dependencies within the CSI matrix. Meanwhile, the decoder adopts gated recurrent unit networks to fully exploit inter-feature correlations and redundancy. To evaluate the performance, simulations are conducted using datasets conforming to current 5G time-varying TDL channel models. Results demonstrate superior performance over existing deep learning based feedback networks. Specifically, the proposed framework can reduce the normalized mean square error of CSI reconstruction by 4 dB under various compression ratios which confirms the effectiveness of the attention-enhanced autoencoder structure for compressive CSI sensing and feedback in practical dynamic communication systems. © 2024 Institute of Physics Publishing. All rights reserved.

关键词： Channel state information

来源：评论

学校读者我要写书评

暂无评论

Resilient filtering for discrete-time system with multipath data packet dropout and quantization

引用

Asian Journal of control 2023年第4期25卷 3067-3082页

作者： Wang, Jian Chang, Xiao-Heng Xiong, Jun Li, Zhi-Min School of Information Science and Engineering Wuhan University of Science and Technology Wuhan Hubei China School of Electronic and Control Engineering North China Institute of Aerospace Engineering Langfang Hebei China

This paper proposes a two-step method to design a resilient filter and two dynamic quantizers for a class of discrete-time systems. In the first step, a filter is designed to make the discrete-time system stochastically stable, and make the (Figure presented.) norm between the filtering error and the external disturbance less than a given level. In the second step, two dynamic quantizers, which quantify the measurement output signal and the performance output signal, respectively, are designed under the condition that the filter gain matrices are obtained. In addition, the filter adopted in this paper takes the randomly occurring uncertainty into consideration, and the quantizers are designed by an inequality scaling technique which can reduce the complexity of linear matrix inequalities. Furthermore, this paper also considers the data packet dropout that may occur during network transmission. Finally, considering the data packet dropout and quantization of measurement output signal and performance output signal, the effectiveness of the proposed filter design method is demonstrated by two simulation examples. © 2023 Chinese Automatic control Society and John Wiley & Sons Australia, Ltd.

关键词： Linear matrix inequalities

来源：评论

学校读者我要写书评

暂无评论

On-chip spiking neural networks based on add-drop ring microresonators and electrically reconfigurable phase-change material photonic switches

引用

Photonics Research 2024年第4期12卷 755-766页

作者： QIANG ZHANG NING JIANG YIQUN ZHANG ANRAN LI HUANHUAN XIONG GANG HU YONGSHENG CAO KUN QIU School of Information and Communication Engineering University of Electronic Science and Technology of ChinaChengdu 611731China

We propose and numerically demonstrate a photonic computing primitive designed for integrated spiking neural networks (SNNs) based on add-drop ring microresonators (ADRMRs) and electrically reconfigurable phasechange material (PCM) photonic switches. In this neuromorphic system, the passive silicon-based ADRMR,equipped with a power-tunable auxiliary light, effectively demonstrates nonlinearity-induced dual neural dynamics encompassing spiking response and synaptic plasticity that can generate single-wavelength optical neural spikes with synaptic weight. By cascading these ADRMRs with different resonant wavelengths, weighted multiple-wavelength spikes can be feasibly output from the ADRMR-based hardware arrays when external wavelengthaddressable optical pulses are injected;subsequently, the cumulative power of these weighted output spikes is utilized to ascertain the activation status of the reconfigurable PCM photonic switches. Moreover, the reconfigurable mechanism driving the interconversion of the PCMs between the resonant-bonded crystalline states and the covalent-bonded amorphous states is achieved through precise thermal modulation. Drawing from the thermal properties, an innovative thermodynamic leaky integrate-and-firing (TLIF) neuron system is proposed. With the TLIF neuron system as the fundamental unit, a fully connected SNN is constructed to complete a classic deep learning task:the recognition of handwritten digit patterns. The simulation results reveal that the exemplary SNN can effectively recognize 10 numbers directly in the optical domain by employing the surrogate gradient algorithm. The theoretical verification of our architecture paves a whole new path for integrated photonic SNNs, with the potential to advance the field of neuromorphic photonic systems and enable more efficient spiking information processing.

关键词： neural networks precise

来源：评论

学校读者我要写书评

暂无评论

Optimized LDPC Matrices: Reducing and Redistributing 1 bits for Enhanced MAP Detection in Bit-Patterned Media Recording Systems

引用

IEEE Access 2025年 13卷 85745-85758页

作者： Nguyen, Thien An Lee, Jaejin Lee, Jong-Ho Soongsil University Department of Information Communication Convergence Technology Seoul06978 Korea Republic of Soongsil University School of Electronic Engineering Seoul06978 Korea Republic of

Bit-patterned media recording (BPMR) is increasingly recognized as a leading technology for next-generation storage systems due to its potential for achieving extremely high area density. In BPMR, data is stored on discrete magnetic islands arranged in a patterned layout, enabling greater storage capacity than traditional magnetic recording techniques. However, as area density increases to meet growing data demands, the magnetic islands are positioned closer together, leading to significant two-dimensional (2D) interference. This interference complicates signal interpretation, making accurate data recovery more challenging and necessitating advanced detection methods. To address these challenges, sophisticated algorithms such as maximum a posteriori (MAP) detection have shown promise in improving data recovery by accounting for the probabilistic nature of signals and noise. MAP detection can effectively mitigate 2D interference when it incorporates extrinsic information (additional data that enhances the detection process). One way to obtain this extrinsic information is through iterative algorithms that utilize the output of self-MAP detection or decoding. Low-density parity-check (LDPC) codes are commonly employed alongside MAP detection to exploit extrinsic information. However, previous studies have shown that suboptimal parity matrix structures in LDPC decoders degrade performance, particularly when using the sum-product algorithm. In this paper, we propose an optimized approach that integrates MAP detection with LDPC decoding for BPMR systems while refining the parity check matrix structure to enhance performance. Our modifications focus on reducing the number of 1-bits to maintain low density (consistent with LDPC standards) while strategically redistributing them throughout the matrix. This optimized parity matrix structure leads to improved performance compared to previous studies. © 2013 IEEE.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Point Cloud Based In-vehicle Occupancy Detection Method by Using 77GHz mmWave Radar 2

Point Cloud Based In-vehicle Occupancy Detection Method by U...

引用

2nd IEEE International Conference on Signal, information and Data Processing, ICSIDP 2024

作者： Cao, Xinda Liu, Jiangang Wu, Yulin Shao, Fengzhi Wang, Yubo Cui, Guolong Quzhou China University of Electronic Science and Technology of China School of Information and Communication Engineering Chengdu China

ISBN: (纸本)9798331515669

In recent years, with the introduction and development of vehicle-to-everything (V2X) and child presence detection (CPD), there's an increasing demand for in-vehicle perception systems. Millimeter-wave (mmWave) radar has become one of the mainstream sensors in this field for high accuracy, small size, and low power consumption. In this paper, we develop a real-time in-vehicle occupancy detection method based on 77GHz mmWave radar. Firstly, a pre-processing framework based on dual-path detection is used to obtain more point clouds from weak targets. Then density-based spatial clustering of applications with noise (DBSCAN) is applied to classify the occupants' point clouds. Finally, we propose a novel probabilistic population-assisted occupancy detection algorithm based on the long and short-term feedback results, which can suppress missed detection and false alarms well. Our algorithm has been successfully deployed onto the radar board and achieves an average accuracy rate of 99.10% under various complex scene experiments. © 2024 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Transmit Rate Enhancement for STAR-RIS-Assisted Uplink NOMA

引用

IEEE Transactions on Vehicular technology 2025年第5期74卷 7651-7665页

作者： Feng, Youhong Xu, Longzhu Li, Qiang Yan, Shihao Wang, Hong Ng, Derrick Wing Kwan Anhui Normal University School of Physics and Electronic information Wuhu241000 China Southeast University National Mobile Communications Research Laboratory Nanjing210096 China Nanjing University of Posts and Telecommunications Key Laboratory of Broadband Wireless Communication and Sensor Network Technology Nanjing210003 China University of Electronic Science and Technology of China School of Information and Communication Engineering Chengdu611731 China Edith Cowan University School of Science Security Research Institute JoondalupWA6027 Australia Nanjing University of Posts and Telecommunications School of Communication and Information Engineering Nanjing210003 China University of New South Wales School of Electrical Engineering and Telecommunications SydneyNSW2033 Australia

In this paper, a novel simultaneous transmitting and reflecting reconfigurable intelligent surface (STAR-RIS) enhanced uplink non-orthogonal multiple access (NOMA) communication network is investigated. Specifically, we tackle the transmit rate maximization problem for the strong user, subject to the constraints on total power consumption and the successive interference cancellation order, while guaranteeing the minimum quality-of-service requirement for the weak user. To address such a non-convex optimal problem, we introduce a novel, efficient, and low-complexity scheme. Specifically, the power allocation and receive beamforming optimization solutions are acquired in closed forms, and the transmission and reflection coefficients are obtained in semi-closed forms with a one-dimensional bisection search. Then, theoretical analysis demonstrates our proposed scheme has a lower complexity compared to the schemes with alternating direction method of multipliers (ADMM) and semidefinite relaxation (SDR) strategies, and the complexity advantage of our proposed scheme over the SDR and ADMM aided schemes becomes prominent when the number of RIS elements increase. Simulation results show that the proposed STAR-RIS-NOMA scheme achieves a better performance than the conventional STAR-RIS-aided orthogonal multiple access (OMA) scheme and STAR-RIS aided NOMA scheme adopting random phase shifts. More specifically, the proposed STAR-RIS-NOMA scheme outperforms the STAR-RIS-OMA scheme in terms of the strong user's rate, especially when the quality-of-service (QoS) requirements for weak user is high, or there is a significant difference channel quality between the reflecting and transmitting links. © 1967-2012 IEEE.

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

Design of De-tumbling Device for Improving the De-tumbling Performance of Uncooperative Space Target

引用

Space(Science & technology) 2024年第1期4卷 10-19页

作者： Lei Du Zhen Chen Hengzai Hu Xiangdong Liu Youguang Guo School of Automation Beijing Institute of TechnologyBeijingChina Key Laboratory of Drive and Control of Servo Motion System Ministry of Industry and Information TechnologyBeijingChina School of Electrical and Data Engineering University of Technology SydneySydneyAustralia

This article presents the design of an optimal coil structure for 2 de-tumbling devices, each is carried by a de-tumbling robot. The design is based on electromagnetic eddy current method and aims to reduce the angular velocity of uncooperative space targets. It proposes an optimization framework with the advantages of safety and high performance. The magnetic field analytical model is established by the designed coil’s structure parameters, and the optimal structure parameters of the coil are determined. To further ensure the maximum magnetic field at the target, the electromagnetic characteristics under different current directions in the 2 coils are analyzed based on magnetic field analytical model, and their accuracy is verified using finite element method (FEM). Additionally, an improved Maxwell’s stress tensor method is proposed to calculate the de-tumbling torque, and its accuracy is assessed using traditional Maxwell’s stress tensor and virtual displacement method. The proposed optimal coil structure and its optimization framework can de-tumble over 1 million targets of various sizes, demonstrating universality.

关键词： uncooperative space target optimal structure parameters detumbling optimization framework electromagnetic eddy current reduce angular velocity electromagnetic eddy current method coil structure

来源：评论

学校读者我要写书评

暂无评论

Quasi Neural Network assisted Channel Estimation for MIMO-OFDM 24

Quasi Neural Network assisted Channel Estimation for MIMO-OF...

引用

24th IEEE International Conference on communication technology, ICCT 2024

作者： Hu, Wanchen Liang, Xin Yang, Jie Ran, Rong Jiang, Yi Fudan University School of Information Science and Technology Dept. of Communication Science and Engineering Shanghai China

ISBN: (纸本)9798350363760

This paper presents a quasi-neural network (QuasiNN) based parametric channel estimation for multiple inputs and multiple outputs with orthogonal frequency division multiplexing (MIMO-OFDM) systems. This approach jointly considers time delay, multipath gain, direction-of-arrival (DOA), direction-of-departure (DOD), and the number of multipaths. We construct a Quasi-NN that accurately models the signal transmission process via a parametrized channel. By leveraging the layered structure of Quasi-NN, similar to that of artificial neural networks (ANNs), we can directly apply the backpropagation (BP) algorithm. To address parameter initialization in scenarios with clustered multipath distributions, we propose a low-complexity fast Fourier transform (FFT)-based initialization method. Furthermore, we propose a hypothesis testing based method for estimating number of multipaths during the optimization of the Quasi-NN. Simulation results verify that the proposed Quasi-NN assisted parametric channel estimation closely approaches the Cramér Rao Bound (CRB). © 2024 IEEE.

关键词： Orthogonal frequency division multiplexing

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：