本文關(guān)鍵詞： 肝臟疾病分類 特征交互 最小絕對收縮和選擇算子 邏輯斯特回歸 交替方向乘子法　出處：《生物醫(yī)學(xué)工程學(xué)雜志》2017年03期 　論文類型：期刊論文

【摘要】：肝臟疾病特征及交互特征對于肝臟疾病的分類具有重要意義,本文在交互最小絕對收縮和選擇算子(LASSO)模型的基礎(chǔ)上,研究了廣義交互LASSO模型并與其他可用于肝臟疾病分類的方法比較。首先,本文建立了廣義交互邏輯斯特(logistic)分類模型,在模型參數(shù)中添加LASSO罰函數(shù),然后將模型參數(shù)通過交替方向乘子法(ADMM)求解,得到模型系數(shù)的稀疏解。最后將測試樣本代入模型,按照最大概率進(jìn)行分類結(jié)果統(tǒng)計。通過將本文方法應(yīng)用在肝臟失調(diào)數(shù)據(jù)集和印度肝病數(shù)據(jù)集的數(shù)據(jù)實驗結(jié)果表明,交互特征的模型系數(shù)不為零,這說明交互特征對分類存在貢獻(xiàn)。最終結(jié)果表明,本文提出的廣義交互LASSO方法的正確率要優(yōu)于交互LASSO方法,也優(yōu)于傳統(tǒng)模式識別方法,可將廣義交互LASSO方法推廣應(yīng)用到其他疾病的分類問題上。
[Abstract]:The characteristics of liver diseases and interactive features are of great significance to the classification of liver diseases. This paper is based on the interactive minimal absolute contraction and selection operator LASSO model. The generalized interactive LASSO model is studied and compared with other methods that can be used in the classification of liver diseases. Firstly, the generalized interactive logic logistic classification model is established, and the LASSO penalty function is added to the parameters of the model. Then the model parameters are solved by alternating direction multiplier method (ADMMM), and the sparse solution of the model coefficients is obtained. Finally, the test samples are substituted into the model. According to the maximum probability of classification, the experimental results show that the model coefficient of the interactive feature is not zero, by applying this method to the liver maladjusted data set and the Indian liver disease data set. The result shows that the generalized interactive LASSO method proposed in this paper is better than the interactive LASSO method and the traditional pattern recognition method. The generalized interactive LASSO method can be extended to the classification of other diseases.
【作者單位】： 燕山大學(xué)理學(xué)院;燕山大學(xué)信息科學(xué)與工程學(xué)院;
【基金】：國家自然科學(xué)基金(61273019,61473339) 河北省青年拔尖人才支持計劃([2013]17) 中國博士后科學(xué)基金面上項目(2014M561202) 燕山大學(xué)青年教師自主研究計劃課題(15LGA015)
【分類號】：O212.1;R575
，

本文編號：1529662