基于LEAP神經(jīng)網(wǎng)絡(luò)同步DS-CDMA偽碼序列盲估計(jì)
發(fā)布時(shí)間:2018-08-15 19:26
【摘要】:針對(duì)特征分解方法在實(shí)現(xiàn)非等功率同步直接序列碼分多址(DS-CDMA)信號(hào)偽碼序列盲估計(jì)時(shí)存在的處理數(shù)據(jù)向量不能太長(zhǎng)以及不能工作于非平穩(wěn)環(huán)境中的問(wèn)題,引入了一種由主分量分析實(shí)現(xiàn)自適應(yīng)特征提取的在線(xiàn)無(wú)監(jiān)督學(xué)習(xí)(LEAP)神經(jīng)網(wǎng)絡(luò)(NN)。首先將已分段的一周期DS-CDMA信號(hào)作為NN的輸入信號(hào),用NN各權(quán)值向量的符號(hào)函數(shù)代表DS-CDMA信號(hào)各用戶(hù)的偽碼序列,然后通過(guò)不斷輸入信號(hào)來(lái)反復(fù)訓(xùn)練權(quán)值向量直至收斂,最終DS-CDMA信號(hào)各用戶(hù)的偽碼序列就可以通過(guò)各權(quán)值向量的符號(hào)函數(shù)重建出來(lái)。此外,采用變步長(zhǎng)以提高收斂速度。理論分析與仿真實(shí)驗(yàn)表明,LEAP NN至少可以實(shí)現(xiàn)-20 d B信噪比下10個(gè)用戶(hù)的非等功率同步DS-CDMA偽碼序列盲估計(jì),并且比傳統(tǒng)的Sanger NN具有更快的收斂速度。
[Abstract]:Aiming at the problem that the processing data vector can not be too long and can not work in non-stationary environment when the eigen decomposition method realizes blind estimation of pseudo-code sequence of non-equal power synchronous direct sequence code division multiple access (DS-CDMA) signals, an on-line unsupervised learning (LEAP) neural network based on principal component analysis (PCA) for adaptive feature extraction is introduced. Network (NN). Firstly, the segmented one-cycle DS-CDMA signal is used as the input signal of NN, and the symbolic functions of the weighted vectors of NN are used to represent the pseudo-code sequences of the users of DS-CDMA signal. Then the weighted vectors are trained repeatedly until convergence through continuous input signals. Finally, the pseudo-code sequences of the users of DS-CDMA signal can pass through each weighted direction. In addition, the variable step size is used to improve the convergence rate. Theoretical analysis and simulation results show that LEAP NN can achieve at least 10 users'non-equal-power synchronous DS-CDMA pseudo-code sequence blind estimation under -20 D B SNR, and has faster convergence rate than the traditional Sanger NN.
【作者單位】: 重慶郵電大學(xué)信號(hào)與信息處理重慶市重點(diǎn)實(shí)驗(yàn)室;
【基金】:國(guó)家自然科學(xué)基金資助項(xiàng)目(61371164,61275099) 信號(hào)與信息處理重慶市市級(jí)重點(diǎn)實(shí)驗(yàn)室建設(shè)項(xiàng)目(CSTC2009CA2003) 重慶市杰出青年基金項(xiàng)目(CSTC2011jjjq40002) 重慶市教育委員會(huì)科研項(xiàng)目(KJ130524) 重慶市研究生科研創(chuàng)新項(xiàng)目(CYS14140)
【分類(lèi)號(hào)】:TP183;TN911.23
本文編號(hào):2185182
[Abstract]:Aiming at the problem that the processing data vector can not be too long and can not work in non-stationary environment when the eigen decomposition method realizes blind estimation of pseudo-code sequence of non-equal power synchronous direct sequence code division multiple access (DS-CDMA) signals, an on-line unsupervised learning (LEAP) neural network based on principal component analysis (PCA) for adaptive feature extraction is introduced. Network (NN). Firstly, the segmented one-cycle DS-CDMA signal is used as the input signal of NN, and the symbolic functions of the weighted vectors of NN are used to represent the pseudo-code sequences of the users of DS-CDMA signal. Then the weighted vectors are trained repeatedly until convergence through continuous input signals. Finally, the pseudo-code sequences of the users of DS-CDMA signal can pass through each weighted direction. In addition, the variable step size is used to improve the convergence rate. Theoretical analysis and simulation results show that LEAP NN can achieve at least 10 users'non-equal-power synchronous DS-CDMA pseudo-code sequence blind estimation under -20 D B SNR, and has faster convergence rate than the traditional Sanger NN.
【作者單位】: 重慶郵電大學(xué)信號(hào)與信息處理重慶市重點(diǎn)實(shí)驗(yàn)室;
【基金】:國(guó)家自然科學(xué)基金資助項(xiàng)目(61371164,61275099) 信號(hào)與信息處理重慶市市級(jí)重點(diǎn)實(shí)驗(yàn)室建設(shè)項(xiàng)目(CSTC2009CA2003) 重慶市杰出青年基金項(xiàng)目(CSTC2011jjjq40002) 重慶市教育委員會(huì)科研項(xiàng)目(KJ130524) 重慶市研究生科研創(chuàng)新項(xiàng)目(CYS14140)
【分類(lèi)號(hào)】:TP183;TN911.23
【相似文獻(xiàn)】
相關(guān)期刊論文 前7條
1 陳實(shí)如,張京娟,孫堯;直擴(kuò)系統(tǒng)偽碼序列串并組合捕獲方案[J];哈爾濱工程大學(xué)學(xué)報(bào);2003年01期
2 徐穎;封欣;吳嗣亮;;基于FPGA的任意時(shí)延偽碼序列產(chǎn)生方法[J];微計(jì)算機(jī)信息;2009年08期
3 金紅軍;戰(zhàn)術(shù)跳頻電臺(tái)偽碼序列的研究[J];電訊技術(shù);1998年06期
4 李軍偉;張?zhí)祢U;朱洪波;潘毅;;基于聚類(lèi)的多進(jìn)制擴(kuò)頻偽碼序列盲估計(jì)方法[J];科學(xué)技術(shù)與工程;2014年02期
5 韋永朋;劉洛琨;郭虹;楊正舉;;一種多徑信道直擴(kuò)信號(hào)偽碼序列盲估計(jì)方法[J];計(jì)算機(jī)工程與應(yīng)用;2013年12期
6 沈斌;王建新;;基于奇異值分解的直擴(kuò)信號(hào)偽碼序列及信息序列盲估計(jì)方法[J];電子與信息學(xué)報(bào);2014年09期
7 ;[J];;年期
,本文編號(hào):2185182
本文鏈接:http://sikaile.net/kejilunwen/xinxigongchenglunwen/2185182.html
最近更新
教材專(zhuān)著