本文關(guān)鍵詞： 流式細(xì)胞術(shù) 自動(dòng)分群 核熵成分分析 K-means算法 余弦相似度　出處：《儀器儀表學(xué)報(bào)》2017年01期 　論文類型：期刊論文

【摘要】：針對(duì)多參數(shù)流式細(xì)胞數(shù)據(jù)傳統(tǒng)人工分群過程復(fù)雜、自動(dòng)化程度不高等問題,提出了一種基于核熵成分分析(KECA)的自動(dòng)分群方法。選取對(duì)瑞利(Renyi)熵具有最大貢獻(xiàn)的特征向量作為投影方向,對(duì)數(shù)據(jù)進(jìn)行特征提取;設(shè)計(jì)了一種基于余弦相似度和K-means算法的分類器,并采用一種基于向量夾角的最佳聚類數(shù)確定方法,最終獲得細(xì)胞的分類標(biāo)簽。對(duì)實(shí)驗(yàn)獲得的淋巴細(xì)胞免疫表型分析數(shù)據(jù)進(jìn)行處理,結(jié)果表明,該方法能夠?qū)崿F(xiàn)細(xì)胞的快速、自動(dòng)分群,整體分群準(zhǔn)確率能夠達(dá)到97%以上,操作簡單便捷,提高了細(xì)胞分析的效率。
[Abstract]:In view of the traditional artificial clustering process of multi-parameter flow cell data, the process is complex and the degree of automation is not high. An automatic clustering method based on Kernel Entropy component Analysis (KECA) is proposed. The feature vector which has the greatest contribution to Rayleigh Renyi entropy is selected as the projection direction to extract the feature of the data. A classifier based on cosine similarity and K-means algorithm is designed. Finally, the classification label of cells was obtained. The experimental data of lymphocyte immunophenotypic analysis were processed. The results show that this method can realize the rapid and automatic grouping of cells, and the accuracy of overall grouping can reach more than 97%. The operation is simple and convenient, and the efficiency of cell analysis is improved.
【作者單位】： 北京信息科技大學(xué)光電測(cè)試技術(shù)北京市重點(diǎn)實(shí)驗(yàn)室;
【基金】：教育部"長江學(xué)者與創(chuàng)新團(tuán)隊(duì)"發(fā)展計(jì)劃(IRT1212) 國家重大科學(xué)儀器設(shè)備開發(fā)專項(xiàng)基金(2011YQ030134) 國家自然科學(xué)基金(61605010)項(xiàng)目資助
【分類號(hào)】：Q2-3;TP311.13
，

本文編號(hào)：1508882