采用基于密度加權(quán)和偏好信息的K均值聚類(lèi)的胸阻抗信號(hào)自動(dòng)檢測(cè)算法
doi: 10.11999/JEIT140903 cstr: 32379.14.JEIT140903
基金項(xiàng)目:
國(guó)家自然科學(xué)基金(61108086)，重慶市自然科學(xué)基金(CSTC2011BB5066, CSTC2012jjA0612)，重慶市科技攻關(guān)計(jì)劃項(xiàng)目(CSTC2012gg-yyjs0572)，中央高?；?CDJZR10160003, CDJZR13160008)，軍隊(duì)博士后基金和重慶市博士后基金資助課題
Automatic Detection Algorithm for Transthoracic Impedance Signal Using K-means Clustering Based on Density Weighting and Preference Information
-
摘要: 為了自動(dòng)識(shí)別胸阻抗(TransThoracic Impedance, TTI)信號(hào)中的按壓和通氣波形，完成相關(guān)重要參數(shù)的計(jì)算，從而實(shí)現(xiàn)對(duì)心肺復(fù)蘇質(zhì)量的監(jiān)測(cè)評(píng)估，該文提出一種基于密度加權(quán)與偏好信息的胸阻抗信號(hào)自動(dòng)檢測(cè)算法。該方法針對(duì)實(shí)驗(yàn)采集的豬的電誘導(dǎo)心臟驟停模型TTI信號(hào)，通過(guò)預(yù)處理和多分辨率窗口搜索法完成潛在按壓和通氣波形的標(biāo)記；接著，提取每個(gè)標(biāo)記波形的寬度、幅值以及相鄰波形特征差作為特征，并按標(biāo)記波形寬度對(duì)信號(hào)進(jìn)行分段；之后，再對(duì)信號(hào)進(jìn)行小波分解，提取其小波系數(shù)每段的能量與原始波形幅值之比作為特征；最后采用基于密度加權(quán)與偏好信息的K均值聚類(lèi)分析法對(duì)標(biāo)記的波形進(jìn)行分類(lèi)識(shí)別。實(shí)驗(yàn)結(jié)果表明，該算法對(duì)TTI信號(hào)中按壓波形和波形分析識(shí)別的正確率和敏感度均較高，魯棒性好，且運(yùn)行時(shí)間(0.43 s0.07 s)滿(mǎn)足實(shí)時(shí)性要求。
-
關(guān)鍵詞:
- 自動(dòng)識(shí)別 /
- 胸阻抗 /
- K均值 /
- 密度加權(quán) /
- 偏好信息
Abstract: In order to recognize automatically the compression and ventilation waveforms of the TransThoracic Impedance (TTI) signal, and obtain the important parameters, for evaluating the CardioPulmonary Resuscitation (CPR) quality, this paper proposes an automatic detection algorithm for TTI signal based on density weighting and preference information. The TTI signals that come from the pig model based on electrically induced cardiac arrest are preprocessed, and the potential compression and ventilation waveforms are marked by using the searching algorithm of multiresolution window after the pretreatment. After that, the width, amplitude and the difference between the adjacent waveforms of the marked waveforms are selected as the features and the signal is divided into several sections according to the width of marked waveforms. Then the original signal is decomposed by wavelet transform. The ratio of the power of each section to the amplitude of the original one is taken as one feature. Finally, k-means clustering algorithm based on density weighting and preference information is used to recognize and classify the compression and ventilation of the marked waveforms. The experimental results show the accuracy and sensitivity of the recognition are high, the robustness is good and the running time (0.430.07 s) can meet the requirement of clinical application. -
計(jì)量
- 文章訪問(wèn)數(shù): 1891
- HTML全文瀏覽量: 145
- PDF下載量: 562
- 被引次數(shù): 0
下載:
