2022 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC)最新文献_第10页

Generation of SAR Images with Features for Target Recognition 具有目标识别特征的SAR图像的生成

2022 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC) Pub Date : 2022-10-25 DOI: 10.1109/ICSPCC55723.2022.9984374

Guobei Peng, Ming Liu, Shichao Chen, Yiyang Li, Fugang Lu

引用次数: 1

A Novel Imaging Algorithm with High Range Resolution based on Beidou Signal-Based Passive SAR 基于北斗信号的无源SAR高距离分辨率成像算法

2022 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC) Pub Date : 2022-10-25 DOI: 10.1109/ICSPCC55723.2022.9984512

Chong Han, Xinliang Niu, Cheng Jing

{"title":"A Novel Imaging Algorithm with High Range Resolution based on Beidou Signal-Based Passive SAR","authors":"Chong Han, Xinliang Niu, Cheng Jing","doi":"10.1109/ICSPCC55723.2022.9984512","DOIUrl":"https://doi.org/10.1109/ICSPCC55723.2022.9984512","url":null,"abstract":"As is well known, the Bistatic Synthetic Aperture Radar (BSAR) based on Global Navigation Satellite System (GNSS) which relies on its low cost and near real-time global coverage shows an more important character in remote sensing applications. Based on the conventional GNSS system, The novel low orbit augmentation system for Beidou navigation satellite (BDS) can provide higher resolution for the bistatic SAR system from the theoretical range with its wide signal bandwidth. In this paper, A improved high resolution scheme for BDS-BSAR is proposed, it applies the fractional Fourier Transform (FRFT) operator to rotate the range compression signal into the specific fractional domain. Meanwhile, we introduce Teager Kaiser (TK) operator as an equalizer in the preprocessing to compress the pulse in the tuning range, so that the time-varying steering vector becomes a time invariant vector and the wideband GNSS signal becomes a narrowband stationary signal. The proposed method effectively improved the imaging resolution with the irregular imaging grid caused by the bistatic geometry. And also, The proposed effectively mitigate the ambiguity caused by the side-lobes. Lastly, the scheme results demonstrate that the proposed method has more effectiveness and high estimation accuracy than the conventioal approach. At the same time, a high estimation accuracy can be achieved.","PeriodicalId":346917,"journal":{"name":"2022 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC)","volume":"82 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126466304","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Space-time Adaptive Processing via Fast Environment Sensing 基于快速环境感知的时空自适应处理

2022 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC) Pub Date : 2022-10-25 DOI: 10.1109/ICSPCC55723.2022.9984609

Youai Wu, B. Jiu, Zongxing Guo, Hongzhi Liu

{"title":"Space-time Adaptive Processing via Fast Environment Sensing","authors":"Youai Wu, B. Jiu, Zongxing Guo, Hongzhi Liu","doi":"10.1109/ICSPCC55723.2022.9984609","DOIUrl":"https://doi.org/10.1109/ICSPCC55723.2022.9984609","url":null,"abstract":"In the heterogeneous clutter environment, the traditional space-time adaptive processing (STAP) cannot accurately estimate the clutter covariance matrix (CCM) due to the lack of training samples, so its clutter suppression performance is seriously degraded. The STAP based on dynamic environment perception can obtain the accurate estimation of CCM under the condition of single training sample, which greatly improves the ability of STAP to suppress heterogeneous clutter, unfortunately, this method suffers from low computational efficiency. This paper proposes a STAP via fast environment sensing algorithm to solve the problem. This algorithm first estimates the number of strong clutter patches in the clutter scene by beam scanning and uses it as the iterative stopping condition of the OMP algorithm. Then the clutter scene is reconstructed using the OMP algorithm as clutter prior information. Finally, the clutter-plus-noise covariance matrix (CNCM) is constructed using clutter prior information for STAP. The simulation results show that, compared with the existing environment sensing algorithm, the method proposed in this paper greatly improves computational efficiency and simultaneously has exhilarant clutter suppression performance.","PeriodicalId":346917,"journal":{"name":"2022 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC)","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116076328","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A denoising method of seismic data based on self-supervised learning 一种基于自监督学习的地震数据去噪方法

2022 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC) Pub Date : 2022-10-25 DOI: 10.1109/ICSPCC55723.2022.9984626

Zhenbin Xia, Dawei Liu, Xiaokai Wang, Zhensheng Shi, Wenchao Chen

{"title":"A denoising method of seismic data based on self-supervised learning","authors":"Zhenbin Xia, Dawei Liu, Xiaokai Wang, Zhensheng Shi, Wenchao Chen","doi":"10.1109/ICSPCC55723.2022.9984626","DOIUrl":"https://doi.org/10.1109/ICSPCC55723.2022.9984626","url":null,"abstract":"Random noise adversely affects seismic signal resolution, subsequent interpretation, and reservoir prediction accuracy. In actual seismic exploration, it is often difficult and costly to obtain clean labels to train a denoising network. Compared with supervised learning, self-supervised learning does not need clean labels, but constructs supervised information according to the data itself. This paper presents a denoising network of seismic data based on self-supervised learning, which mainly includes four parts: data processing module, encoder, decoder, and residual noise separation module. The data processing module performs Bernoulli sampling on the input single 2D seismic signal to construct the supervision information. The encoder consists of four parts: partial convolution, dilated convolution, residual learning block, and down sampling. Dilated convolution can increase receptive fields and make the encoder better capture the features of useful signals. The decoder consists of up-sampling and standard convolution with a dropout strategy. The encoder and decoder use skip connections between the layers of the same height to realize the feature fusion of deep and shallow layers. The residual noise separation module obtains the predicted noise by calculating the residual between actual seismic data and predicted useful data, then uses the noise prior information as the regularization constraint to avoid the phenomenon of overfitting during training. The experimental results of synthetic and real seismic data indicate that our network not only suppresses random noise with effect, but also does have high fidelity.","PeriodicalId":346917,"journal":{"name":"2022 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129326981","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

DPTNet-based Beamforming for Speech Separation 基于dptnet的语音分离波束形成

2022 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC) Pub Date : 2022-10-25 DOI: 10.1109/ICSPCC55723.2022.9984356

Tongtong Zhao, C. Bao, Xue Yang, Xu Zhang

{"title":"DPTNet-based Beamforming for Speech Separation","authors":"Tongtong Zhao, C. Bao, Xue Yang, Xu Zhang","doi":"10.1109/ICSPCC55723.2022.9984356","DOIUrl":"https://doi.org/10.1109/ICSPCC55723.2022.9984356","url":null,"abstract":"Filter-and-sum beamforming framework could separate speech effectively from the complicated acoustic scenarios by using dual-path recurrent neural network (DPRNN) to estimate the beamforming filters. Since the concerned context information was modeled by recurrent layers of the intermediate states, only the suboptimal separation performance can be achieved. To increase the performance, the dual-path transformer network (DPTNet) is employed to estimate beamforming filters instead of DPRNN in this paper because the DPTNet takes advantage of self-attention mechanism and makes high dimension feature sequences interacted directly. Specifically, to provide the spatial and context information of multi-channel speech signals, the cosine similarities between different channels are first concatenated with the transformed speech signals to serve as the input. Then, the DPTNet and transform-averaged-concatenation operation are used to extract context information for estimating beamforming filter of each channel. Finally, the observed signal of each channel is filtered and added to obtain the desired speech. Compared with the existing FaSNet, the proposed method can achieve better separation performance.","PeriodicalId":346917,"journal":{"name":"2022 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC)","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129111146","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

A Reduced-Order Multiple-Model Adaptive Identification Algorithm of Missile Guidance Law 导弹制导律的降阶多模型自适应识别算法

2022 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC) Pub Date : 2022-10-25 DOI: 10.1109/ICSPCC55723.2022.9984362

Yunyan Zhang, Peichang Wang, Yao Yang, Mingang Wang

引用次数: 1

σ-threshold Bayes Filter in Unknown Birth Background with Multi-Bernoulli Finite Sets 多伯努利有限集未知出生背景下的σ-阈值贝叶斯滤波

2022 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC) Pub Date : 2022-10-25 DOI: 10.1109/ICSPCC55723.2022.9984566

Xiaolong Hu, Q. Zhang, Baojun Song, Pengfei Wan, Zhiquan Xia

引用次数: 0

Representation of Comprehensive Dynamic Characteristics of Electromagnetic Environment based on Fractal Theory 基于分形理论的电磁环境综合动态特性表征

2022 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC) Pub Date : 2022-10-25 DOI: 10.1109/ICSPCC55723.2022.9984453

Peiwei Gao, Yongfeng Zhi

{"title":"Representation of Comprehensive Dynamic Characteristics of Electromagnetic Environment based on Fractal Theory","authors":"Peiwei Gao, Yongfeng Zhi","doi":"10.1109/ICSPCC55723.2022.9984453","DOIUrl":"https://doi.org/10.1109/ICSPCC55723.2022.9984453","url":null,"abstract":"The dynamic characteristics of electromagnetic environment are the comprehensive characteristics formed by the combination of various electromagnetic interference signals with different types, different quantities and variable parameters in the electromagnetic environment. Due to the time-varying of different electromagnetic interference signals, the combined electromagnetic environment signals will be non-linearly superimposed in time and energy domain, resulting in extremely intense dynamic characteristics of electromagnetic environment, resulting in the performance decline of electronic information systems in the electromagnetic environment area. Aiming at the above problems, a method of characterizing the dynamic characteristics of electromagnetic environment based on fractal theory is proposed, and the dynamic characteristics of electromagnetic environment are characterized by fractal dimension. Firstly, the representation model of regional electromagnetic environment is established. Secondly, the calculation method of fractal dimension to characterize the dynamic characteristics of electromagnetic environment is given. Finally, the simulation analysis shows that the comprehensive dynamic characteristics of electromagnetic environment can be characterized by fractal dimension.","PeriodicalId":346917,"journal":{"name":"2022 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121160898","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Blind Recognition of Convolutional Codes: A Matrix Transformation-Aided Deep Learning Approach 卷积码的盲识别:矩阵变换辅助深度学习方法

2022 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC) Pub Date : 2022-10-25 DOI: 10.1109/ICSPCC55723.2022.9984596

Yao Wang, Hongyu You, Xiang Wang, Zhitao Huang

引用次数: 1

Efficient Backup Link Scheme of ECHO Protocol for Mobile Ad Hoc Networks 移动Ad Hoc网络中ECHO协议的高效备份链路方案

2022 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC) Pub Date : 2022-10-25 DOI: 10.1109/ICSPCC55723.2022.9984610

Huoyun Deng, Jinghang Ou, Chen-Han Yao, Xiangqun Lu, Weijie Tan, Shuwen Pan, J. Wang

引用次数: 0