检索结果-内蒙古大学图书馆

Deep Learning Aided SCL Decoding of Polar Codes with Shifted-Pruning

China communications 2023年第1期20卷 153-170页

作者： Yang Lu Mingmin Zhao Ming Lei Chan Wang Minjian Zhao College of Information Science and Electronic Engineering Zhejiang UniversityHangzhou 310027China Zhejiang Provincial Key Laboratory of Information Processing Communication and Networking(IPCAN)Hangzhou 310027China

Recently,a generalized successive cancellation list(SCL)decoder implemented with shiftedpruning(SP)scheme,namely the SCL-SP-ωdecoder,is presented for polar codes,which is able to shift the pruning window at mostωtimes during each SCL re-decoding attempt to prevent the correct path from being *** candidate positions for applying the SP scheme are selected by a shifting metric based on the probability that the elimination ***,the number of exponential/logarithm operations involved in the SCL-SP-ωdecoder grows linearly with the number of information bits and list size,which leads to high computational *** this paper,we present a detailed analysis of the SCL-SP-ωdecoder in terms of the decoding performance and complexity,which unveils that the choice of the shifting metric is essential for improving the decoding performance and reducing the re-decoding attempts ***,we introduce a simplified metric derived from the path metric(PM)domain,and a custom-tailored deep learning(DL)network is further designed to enhance the efficiency of the proposed simplified *** proposed metrics are both free of transcendental functions and hence,are more hardware-friendly than the existing *** results show that the proposed DL-aided metric provides the best error correction performance as comparison with the state of the art.

关键词： polar codes successive cancellation list decoding deep learning shifted-pruning path metric

来源：评论

学校读者我要写书评

暂无评论

Contour extraction model introducing contrast adaptive characteristics based on visual pathway

引用

Multimedia Tools and Applications 2024年第15期84卷 14693-14717页

作者： Fang, Tao Cai, Zhefei Fan, Yingle College of Electronics and Information Hangzhou Dianzi University Hangzhou310018 China Zhejiang Provincial Key Laboratory of Information Processing Communication and Networking Hangzhou310027 China Laboratory of Pattern Recognition and Image Processing Hangzhou Dianzi University Hangzhou310018 China

Effectively extracting image subject contours holds significant importance for subsequent image processing tasks. Recognizing the pivotal role of contrast features in contour characterization, this paper proposes a novel contour extraction model with contrast adaptive characteristics, inspired by visual perception simulation visual pathways. Firstly, leveraging the color antagonism traits of retinal ganglion cells, we construct a color image contrast calculation model to enhance the representation of visual information contrast. Furthermore, drawing upon the feed-forward impact of the retina on Lateral Geniculate Nucleus (LGN) cells, we introduce a contrast gain control mechanism to extract multi-directional primary contour responses. Secondly, employing the LIF neuron network to simulate the lateral geniculate body's information flow processing mechanism, we encode visual information via pulse firing to eliminate redundant contour details. Then, by considering the primary visual cortex (V1) cell's receptive field size variation with contrast, we devise a contrast-adaptive dynamic receptive field model. Additionally, we develop a texture suppression model based on the orientation/contrast disparity between the receptive field model's center and periphery. Finally, integrating the primary contour response and the image obtained through the inhibition model, we fuse features to derive the final image subject target contour. This study employs the BSDS500 dataset and the RuG40 dataset for experimentation. Comparative analysis against mainstream methods demonstrates our approach's superior ability to retain the main image outline while suppressing non-edge textures, with P-value indicators for contour detection of 0.58 and 0.50, respectively. Furthermore, visual analysis using box and whisker plots confirms the robustness of our proposed method. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

Delay-Optimal Random Access in Large-Scale Energy Harvesting IoT Networks Based on Mean Field Game

引用

China communications 2022年第4期19卷 121-136页

作者： Dezhi Wang Wei Wang Zhaoyang Zhang Aiping Huang College of Information Science and Electronic Engineering Zhejiang UniversityHangzhou 310027China Zhejiang Provincial Key Laboratory of Information Processing Communication and Networking Zhejiang UniversityHangzhou 310027China

With energy harvesting capability, the Internet of things(IoT) devices transmit data depending on their available energy, which leads to a more complicated coupling and brings new technical challenges to delay optimization. In this paper,we study the delay-optimal random access(RA) in large-scale energy harvesting IoT networks. We model a two-dimensional Markov decision process(MDP)to address the coupling between the data and energy queues, and adopt the mean field game(MFG) theory to reveal the coupling among the devices by utilizing the large-scale property. Specifically, to obtain the optimal access strategy for each device, we derive the Hamilton-Jacobi-Bellman(HJB) equation which requires the statistical information of other ***, to model the evolution of the states distribution in the system, we derive the Fokker-PlanckKolmogorov(FPK) equation based on the access strategy of devices. By solving the two coupled equations,we obtain the delay-optimal random access solution in an iterative manner with Lax-Friedrichs method. Finally, the simulation results show that the proposed scheme achieves significant performance gain compared with the conventional schemes.

关键词： wireless communications energy harvesting random access mean field game

来源：评论

学校读者我要写书评

暂无评论

3D Human Reconstruction from A Single Depth Image

3D Human Reconstruction from A Single Depth Image

引用

2023 International Conference on Intelligent Perception and Computer Vision, CIPCV 2023

作者： Li, Rihui Li, Dongxiao Zhang, Ming Zhejiang University College of Information Science and Electronic Engineering China Communication and Networking Zhejiang Provincial Key Laboratory of Information Processing China

ISBN: (纸本)9798350323382

This paper presents a pioneering work on 3D human reconstruction from a single depth image only. Most of previous works were proposed to use RGB or RGBD images as input, which however suffers from bad illumination and violates privacy protection. Graph convolution network is introduced in our work to fully exploit the topological correlation between the neighboring vertices of graph-structured human body mesh. Parametric Skinned Multi-Person Linear (SMPL) model is further obtained via a regression network. As few datasets contain depth images as well as 3D ground truth, the constraints of 2D keypoints and 2D silhouette, inferred from the given depth image, are combined in loss function to supervise the training of the proposed network. Quantitative and qualitative evaluation on a challenging dataset demonstrated promising performance. And, the effectiveness of main components in our method is validated through a series of ablation studies. © 2023 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Multi-Task Lycium barbarum Recognition and Pedicel Localization Network Based on Improved YOLOv8 9

Multi-Task Lycium barbarum Recognition and Pedicel Localizat...

引用

9th International Conference on Image, Vision and Computing, ICIVC 2024

作者： Li, Fen Li, Dongxiao Huang, Le Zhang, Ming College of Information Science and Electronic Engineering Zhejiang University Hangzhou China Zhejiang Provincial Key Laboratory of Information Processing Communication and Networking Hangzhou China Jinhua Institute Zhejiang University Jinhua China

ISBN: (纸本)9798350385991

Given the unique indeterminate inflorescence trait of Lycium barbarum, traditional indiscriminate harvesting techniques like vibration, comb-brush, or airflow methods, fail to selectively harvest mature fruits, leading to an unsatisfactory picking rate and considerable damage. While a vision system might provide assistance for precise picking, the intricate task of harvesting Lycium barbarum remains challenging due to aspects like their diminutive size, compact distribution, and the presence of various complex occlusions. The three-stage method proposed in this paper facilitates precise object recognition and semantic segmentation of Lycium barbarum and provides individually targeted segmentation of each stem on branches with mature fruits, achieved by organically arranging three operational components based on improved YOLOv8. Moreover, the proposed method has been validated with the LyciumSeg dataset, yielding respective mean average precision (mAP) scores of 97.8% for Lycium barbarum recognition and 99.5% for pedicel segmentation. © 2024 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Deep Neural Network Based Matched-Field Geoacoustic Inversion 15

Deep Neural Network Based Matched-Field Geoacoustic Inversio...

引用

15th IEEE International Conference on Wireless communications and Signal processing, WCSP 2023

作者： Xu, Ruopeng Chen, Hongnan Zhang, Ting Zhejiang University College of Information Science and Electronic Engineering Hangzhou China Zhejiang Provincial Key Laboratory of Information Processing Communication and Networking Hangzhou China

ISBN: (纸本)9798350324662

Acoustic field inversion offers an efficient approach for estimating geoacoustic parameters and acquiring valuable geoacoustic characteristics. The matched-field inversion technique aligns the measured acoustic field with a copy acoustic field generated by an acoustic propagation model. By employing optimization algorithms in a high-dimensional parameter space, the technique searches for the best matching acoustic parameters, and Bayesian theory is then applied to further determine the parameter uncertainties. However, the traditional global optimization process and posterior probability density sampling in matched-field inversion require multiple calls of the acoustic propagation model, resulting in a considerable computational time cost. Although using a surrogate model can enhance time efficiency, it often compromises inversion accuracy. To address this challenge, we propose intergrating a deep learning-based pre-screening process into the conventional matched-field inversion. This innovative approach significantly reduces the number of calls, thereby reducing time costs without sacrificing accuracy. In this paper, we conduct experiments on matched-field inversion based on Deep Neural Networks with simulated data and measured data to validate its efficacy. © 2023 IEEE.

关键词： Matched-field inversion Pre-screening, DNN Surrogate model

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of RIS Assisted NOMA Networks over Rician Fading Channels

引用

Computer Modeling in Engineering & Sciences 2023年第6期135卷 2531-2555页

作者： Xianli Gong Chongwen Huang Xinwei Yue Zhaohui Yang Feng Liu School of Electronic and Information Engineering Beihang UniversityBeijing100191China College of Information Science and Electronic Engineering Zhejiang UniversityHangzhou310027China International Joint Innovation Center Zhejiang UniversityHaining314400China Zhejiang Provincial Key Laboratory of Information Processing Communication and Networking(IPCAN)Hangzhou310027China School of Information and Communication Engineering Beijing Information Science and Technology UniversityBeijing100101China Zhejiang Laboratory Hangzhou311121China

In this paper,we consider a downlink non-orthogonal multiple access(NOMA)network assisted by two reconfigurable intelligent surfaces(RISs)over Rician fading channels,in which each user communicates with the base station by the virtue of a RIS to enhance the reliability of the received *** evaluate the system performance of our proposed RIS-NOMA network,we first derive the exact and asymptotic expressions for the outage probability and ergodic rate of two ***,we derive the exact and asymptotic upper bound expressions for the ergodic rate of the nearby *** on asymptotic analytical results,the diversity orders for the outage probability and the high signal-to-noise ratio(SNR)slopes for the ergodic rate of the two users are obtained in the high SNR ***,we derive the system throughputs of the proposed RIS-NOMA network in delay-limited and delay-tolerant transmission *** results confirm our analysis and demonstrate that:1)The outage probability and ergodic rate of RIS-NOMA networks are superior to that of RIS-assisted orthogonalmultiple access(OMA)networks;2)The RIS-NOMA networks have ability to achieve a larger system throughput compared to RIS-OMA networks;and 3)The system performance of RIS-NOMA networks can be significantly improved as the number of reflecting elements and Rician factor increases.

关键词： Non-orthogonal multiple access reconfigurable intelligent surface outage probability ergodic rate

来源：评论

学校读者我要写书评

暂无评论

Media Access Control Protocol for Submarine Static Target Detection with a Multi-AUV Cluster

Media Access Control Protocol for Submarine Static Target De...

引用

OCEANS 2024 - Singapore, OCEANS 2024

作者： Jin, Jiaming Chen, Huifang Xie, Lei Zhejiang University College of Information Science and Electronic Engineering Hangzhou310027 China Zhejiang Provincial Key Laboratory of Information Processing Communication and Networking Hangzhou310027 China Zhejiang University Zhoushan Ocean Research Center Zhoushan316021 China

Due to the challenges for the underwater acoustic channel, designing an efficient media access control (MAC) protocol to enhance the underwater transmission efficiency is very important. In this paper, we design a task-oriented MAC protocol, called as underwater ALOHA protocol adapted for submarine static target detection (UW-ALOHA-USTD) protocol, for submarine static target detection with a multi-AUV cluster. In the proposed MAC protocol, a frame is divided two sub-frames, where sub-frame 1 is used for the underwater localization and cluster state information exchange, sub-frame 2 is responsible for transmitting task data. By introducing a conflict avoidance mechanism and improving the UW-ALOHA protocol, the proposed protocol effectively reduces data transmission conflict and delay, as well as enhancing the data transmission success rate. Simulation result shows that the proposed UW-ALOHA-USTD protocol performs well, and provides an efficient and reliable data transmission solution for submarine static target detection with a multi-AUV cluster. © 2024 IEEE.

关键词： Medium access control

来源：评论

学校读者我要写书评

暂无评论

A Channel-estimation-Aided Underwater Acoustic Localization Method in the Integrated communication and Positioning System

A Channel-estimation-Aided Underwater Acoustic Localization ...

引用

OCEANS 2024 - Singapore, OCEANS 2024

作者： Li, Yida Wu, Xintao Chen, Huifang Xie, Lei Zhejiang University College of Information Science and Electronic Engineering Hangzhou310027 China Zhejiang Provincial Key Laboratory of Information Processing Communication and Networking Hangzhou310027 China Zhejiang University Zhoushan Ocean Research Center Zhoushan316021 China

Underwater localization is critical for in the marine exploration. However, the harsh underwater conditions, like the multipath effect, signal attenuation and Doppler effect, introduces numerous difficulties for the underwater localization. In this paper, we propose a channel-estimation-Aided underwater acoustic localization method in the underwater acoustic integrated communication and positioning (UWA-ICP) system. In the UWA-ICP system, a UWA-ICP device with a four-element hydrophone array and a transducer is equipped on each underwater node for acoustic positioning and communication. In order to mitigate the influence of multipath effect on the localization performance, an enhanced orthogonal matching pursuit algorithm is presented to perform the channel estimation. The estimated channel impulse response is used to compensate the received signal in order to mitigate the multipath effect. Numerical results show that the proposed localization method can effectively improve the localization performance. © 2024 IEEE.

关键词： Underwater acoustics

来源：评论

学校读者我要写书评

暂无评论

Experimental Verification of the Knowledge-Aided Approach for Active Target Localization in Reverberant Environments 15

Experimental Verification of the Knowledge-Aided Approach fo...

引用

15th IEEE International Conference on Wireless communications and Signal processing, WCSP 2023

作者： Wang, He Zhang, Ting Zhao, Hangfang Zhejiang University College of Information Science and Electronic Engineering Hangzhou China Communication and Networking Zhejiang Provincial Key Laboratory of Information Processing Hangzhou China Key Laboratory of Ocean Observation Imaging Testbed of Zhejiang Province Zhoushan China

ISBN: (纸本)9798350324662

A knowledge-aided approach for active target localization is presented and applied to the real-sea data to verify its feasibility in snapshot-deficient scenarios in the presence of reverberation. By leveraging the a priori reverberation covariance computed from a reverberation model, the knowledge-aided minimum variance distortionless response (KA-MVDR) is derived to facilitate adaptive processing and thus localize weak targets in reverberation. The KA-MVDR-based bearing-time record is employed to analyze the experimental data collected in the South China Sea, which verifies that the weak target echoes can be localized using single ping data with significantly reduced reverberation levels. Moreover, the impact of the bottom roughness mismatch on the model-based reverberation covariance and the performance of KA-MVDR are evaluated by the output signal-interference-plus-noise ratio, manifesting the robustness of this approach in real-sea applications. © 2023 IEEE.

关键词： active target localization reverberation knowledge-aided snapshot deficiency

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：