北京生物醫(yī)學(xué)工程

基于自適應(yīng)線性神經(jīng)網(wǎng)絡(luò)的胎兒心電信號(hào)提取

Fetal ECG Signals Extraction Based on Adaptive Linear Neural Network

作者：賈文娟楊春蘭鐘果程周夢(mèng)穎吳水才

單位：北京工業(yè)大學(xué)生命學(xué)院生物醫(yī)學(xué)工程中心（北京100124）

關(guān)鍵詞：胎兒心電；自適應(yīng)線性神經(jīng)網(wǎng)絡(luò)；W-H學(xué)習(xí)法則

分類號(hào)：

出版年·卷·期（頁(yè)碼）：2010·29·6（575-580）

摘要：

胎兒心電信號(hào)提取對(duì)胎兒監(jiān)護(hù)具有重要意義。本文介紹了一種基于自適應(yīng)線性神經(jīng)網(wǎng)絡(luò)的胎兒心電信號(hào)提取方法。該方法根據(jù)母體心電信號(hào)與母體腹部信號(hào)的相關(guān)性原理，以母體心電信號(hào)為網(wǎng)絡(luò)輸入，母體腹部信號(hào)為網(wǎng)絡(luò)目標(biāo)，采用W-H學(xué)習(xí)方法獲取的訓(xùn)練誤差即為提取出的胎兒心電信號(hào)。此外，通過(guò)增加網(wǎng)絡(luò)隱含層，對(duì)神經(jīng)網(wǎng)絡(luò)的結(jié)構(gòu)進(jìn)行改進(jìn)，增加網(wǎng)絡(luò)訓(xùn)練精度，從而得到更好的訓(xùn)練結(jié)果，提取出更易識(shí)別的胎兒心電信號(hào)。最后分別使用仿真數(shù)據(jù)和臨床數(shù)據(jù)對(duì)上述方法進(jìn)行測(cè)試，實(shí)驗(yàn)結(jié)果表明，利用自適應(yīng)線性神經(jīng)網(wǎng)絡(luò)可以提取出胎兒心電信號(hào)，通過(guò)改進(jìn)神經(jīng)網(wǎng)絡(luò)結(jié)構(gòu)，可以提取出更為清晰的胎兒心電信號(hào)。

Fetal ECG signals extraction has the vital significance for fetal monitoring. This paper introduces a method of extracting fetal ECG based on adaptive linear neural network. The method was due to the correlation between maternal ECG and the abdominal signals of pregnant woman, adopted the W-H learning rule, with maternal ECG as input signals and the abdominal ECG as target signals of network, so that the training error was obtained as the fetal ECG extracted. In addition, a better result was achieved by increasing the hidden layer for the network to improve neural network structure and enhance the network training accuracy. Thus, more easily identified fetal ECG would be extracted. Using simulated data and clinical data to test this method, experimental results showed that the adaptive linear neural network could be used to extract fetal ECG signals from maternal abdominal signals effectively. Furthermore, clearer fetal ECG signals could be extracted by improving neural network structure.

參考文獻(xiàn)：

［1］李紅波,方少元. 基于Internet的家庭遠(yuǎn)程胎兒監(jiān)護(hù)系統(tǒng)的研制［J］. 醫(yī)療衛(wèi)生裝備, 2006, 27(2): 17- 19.
［2］Khaled A. Adaptive neuro-fuzzy inference systems for extracting fetal electrocardiogram［J］. IEEE International Symposium on Signal Processing and Information Technology, 2006: 122-126.
［3］徐進(jìn). 胎兒心電的提取方法分析［J］.電子技術(shù)應(yīng)用, 2006, 32(6): 77-80.
［4］付榮申. 基于自適應(yīng)濾波的胎兒心電信號(hào)提取［D］. 鄭州：鄭州大學(xué), 2007.
［5］王家達(dá),劉祖望. 基于S3C2410的無(wú)線胎兒心電監(jiān)護(hù)儀的設(shè)計(jì)［J］. 中國(guó)醫(yī)療器械雜志, 2007, 31(1): 30 -33.
［6］Edmond Zahedi. Applicability of adaptive noise cancellation to fetal heart rate detection using photoplethysmography［J］. Computers in Biology and Medicine, 2008, 38(1): 31-41.
［7］劉世金,徐文，劉大利，等. 基于RLS-ANC自適應(yīng)濾波的FECG信號(hào)提取方法［J］. 北京生物醫(yī)學(xué)工程, 2005, 24 (6): 414-417.
［8］李智,沈漢聰，莫瑋. 基于DSP的自適應(yīng)胎兒心電圖儀研究［J］. 生物醫(yī)學(xué)工程學(xué)雜志, 2008, 25(2): 309-312.
［9］石巖巖,茍正品，張榆峰，等. 基于經(jīng)驗(yàn)?zāi)B(tài)分解自適應(yīng)濾波的胎兒心電信號(hào)提取［J］. 生物醫(yī)學(xué)工程與臨床, 2010, 14(1): 5-9.
［10］劉清欣. 胎兒心電信號(hào)提取的算法研究［D］. 鄭州：鄭州大學(xué)， 2007.
［11］Najafabadi FS, Zahedi E, Mohd Ali MA, et al. Fetal heart rate monitoring based on independent component analysis［J］. Computers in Biology and Medicine, 2006, 36(3): 241-252.
［12］李君. 基于獨(dú)立分量分析方法的胎兒心電提取的研究［D］. 重慶:重慶大學(xué), 2009.
［13］Yalan Ye, et al. A Non-invasive Fetal Electrocardiogram Extraction Algorithm Based on ICA Neural Network［C］. Proceedings of 2007 1st International Conference on Bioinformatics and Biomedical Engineering, 2007: 806-809.
［14］劉清欣,萬(wàn)紅. 基于獨(dú)立分量分析的胎兒心電信號(hào)提取［J］. 華北水利水電學(xué)院學(xué)報(bào), 2007, 28(3): 45-47.
［15］謝楊梅,吳小培. 獨(dú)立分量分析在胎兒心電提取中的應(yīng)用［J］. 池州學(xué)院學(xué)報(bào), 2009, 23(3): 14-17.
［16］蔡坤寶,冀志華. 應(yīng)用獨(dú)立分量分析的胎兒心電信號(hào)提取［J］. 重慶大學(xué)學(xué)報(bào), 2009, 32(3): 332- 336.
［17］段紅博. 基于模糊神經(jīng)網(wǎng)絡(luò)的胎兒心電提取［D］. 重慶：重慶大學(xué)， 2009.
［18］Tompkins WJ. 生物醫(yī)學(xué)數(shù)字信號(hào)處理［M］. 林家瑞，徐邦荃，等譯. 武漢: 華中科技大學(xué)出版社, 2001: 204-214.
［19］Lathauwer L. DaIsy: Database for the identification of systems: Biomedical Systems ［EB/OL］.http://homes.esat.kuleuven.be/~smc/daisy/, 2000-10-10/2010-4-27.

服務(wù)與反饋：

【文章下載】【加入收藏】

提示：您還未登錄，請(qǐng)登錄！點(diǎn)此登錄

51黑料吃瓜在线观看,51黑料官网|51黑料捷克街头搭讪_51黑料入口最新视频