基于布谷鸟算法优化支持向量机应用于胸痛三联征的分类诊断研究
|
摘要
胸痛三联征在临床上有相似的胸痛症状,误诊率居高,其确切病因尚不十分明确。针对经典支持向量机不适用于胸痛三联征此类非平衡数据集分类的缺点,本研究结合径向基核函数、布谷鸟算法以及支持向量机,提出一种基于布谷鸟算法优化支持向量机的分类识别模型,用于胸痛三联征的分类诊断。在收集到的735例有效样本数据集上,采用Java程序抽取平衡数据集。实验结果显示,基于平衡数据集,该模型的平均正确率为80.667%;基于非平衡数据集,其平均正确率为97.767%,相比经典支持向量机、粒子群算法-支持向量机、遗传算法-支持向量机均有不同程度的提高。因此,本研究模型对胸痛三联征的分类诊断具有一定的参考价值。
The triad of chest pain has similar symptoms of chest pain in the clinic, the rate of misdiagnosis is high. The exact cause is not very clear. In view of the disadvantage that classical support vector machine is not suitable for the classification of unbalanced data sets such as chest pain triad, we proposed a classification based on Cuckoo algorithm to optimize support vector machine based on radial basis kernel function, Cuckoo algorithm and support vector machine. The identification model proposed could be used for the classification diagnosis of triad of chest pain. In the collected 735 valid sample data sets, the balanced data set was extracted by Java program. The experimental results showed that the average accuracy of the model was 80.667% based on the balanced data set and 97.767% based on the imbalanced data set, which was higher than that of the classical support vector machine(SVM),particle swarm optimization-SVM(PSO-SVM), genetic algorithm SVM(GA-SVM). Therefore, this model has certain reference value for the classification diagnosis of triad of chest pain.
The triad of chest pain has similar symptoms of chest pain in the clinic, the rate of misdiagnosis is high. The exact cause is not very clear. In view of the disadvantage that classical support vector machine is not suitable for the classification of unbalanced data sets such as chest pain triad, we proposed a classification based on Cuckoo algorithm to optimize support vector machine based on radial basis kernel function, Cuckoo algorithm and support vector machine. The identification model proposed could be used for the classification diagnosis of triad of chest pain. In the collected 735 valid sample data sets, the balanced data set was extracted by Java program. The experimental results showed that the average accuracy of the model was 80.667% based on the balanced data set and 97.767% based on the imbalanced data set, which was higher than that of the classical support vector machine(SVM),particle swarm optimization-SVM(PSO-SVM), genetic algorithm SVM(GA-SVM). Therefore, this model has certain reference value for the classification diagnosis of triad of chest pain.
引文
[1]Henzler T,Gruettner J,Meyer M,et al.Coronary computed tomography and triple rule out CT in patients with acute chest pain and an intermediate cardiac risk for acute aoronary syndrome:Part2:Economic aspects[J].European Journal of Radiology,2013,82(1):106-111.
[2]Bojan Mihaljevi,Ruth Benavides-Piccione,Luis Guerra,et al.Classifying GABAergic interneurons with semi-supervised projectedmodel-based clustering Bojan[J].Artificial Intelligence in Medicine,2015,65(1):49-59.
[3]戴明锋,孟群.医疗健康大数据挖掘和分析面临的机遇与挑战[J].中国卫生信息管理杂志,2017,14(2):126-130.
[4]宗慧.通过数据挖掘手段对非创伤性急诊胸痛疾病进行分类[D].北京协和医学院,2016.
[5]邹芳,张世明,严守春.基于决策树的胸痛辅助诊断研究[J].中国数字医学,2017,12(6):118-120.
[6]李红丽,许春香,马耀锋.基于多核学习SVM的图像分类识别算法[J].现代电子技术,2018,41(6):50-52.
[7]李幼军,钟宁,黄佳进,等.基于高斯核函数支持向量机的脑电信号时频特征情感多类识别[J].北京工业大学学报,2018,44(2):234-243.
[8]梅恒荣,殷礼胜,刘冬梅,等.改进粒子群算法优化的SVM模拟电路故障诊断[J].电子测量与仪器学报,2017,31(8):1239-1246.
[9]Batuwita R,Palade V.Class imbalance learning methods for support vector machines[M].Imbalanced Learning:Foundations,Algorithms,and Applications,2013.
[10]Barua S,Islam M M,Yao X,et al.MWMOTE-majority weighted minority oversampling technique for imbalanced data set learning[J].IEEE Trans on Konwledge and Data Engineering,2014,26(2):405-425.
[11]Chawla N V,Bowyer K W,Hall L O,et,al.SMOTE:synthetic minority over-sampling technique[J].Journal of Artificial Intelligence Research,2011,16(1):321-357.
[12]Liu X Y,Wu J,Zhou Z H.Exploratory under sampling for class-imbalance learning[J].IEEE Transactions on Systems,Man,and Cybernetics–Part B:Cybernetics,2009,39(2):539-550.
[13]Yang X S.A new metaheuristic bat-inspired algorithm[J].Computer Knowledge & Technology,2010,284:65-74.
[2]Bojan Mihaljevi,Ruth Benavides-Piccione,Luis Guerra,et al.Classifying GABAergic interneurons with semi-supervised projectedmodel-based clustering Bojan[J].Artificial Intelligence in Medicine,2015,65(1):49-59.
[3]戴明锋,孟群.医疗健康大数据挖掘和分析面临的机遇与挑战[J].中国卫生信息管理杂志,2017,14(2):126-130.
[4]宗慧.通过数据挖掘手段对非创伤性急诊胸痛疾病进行分类[D].北京协和医学院,2016.
[5]邹芳,张世明,严守春.基于决策树的胸痛辅助诊断研究[J].中国数字医学,2017,12(6):118-120.
[6]李红丽,许春香,马耀锋.基于多核学习SVM的图像分类识别算法[J].现代电子技术,2018,41(6):50-52.
[7]李幼军,钟宁,黄佳进,等.基于高斯核函数支持向量机的脑电信号时频特征情感多类识别[J].北京工业大学学报,2018,44(2):234-243.
[8]梅恒荣,殷礼胜,刘冬梅,等.改进粒子群算法优化的SVM模拟电路故障诊断[J].电子测量与仪器学报,2017,31(8):1239-1246.
[9]Batuwita R,Palade V.Class imbalance learning methods for support vector machines[M].Imbalanced Learning:Foundations,Algorithms,and Applications,2013.
[10]Barua S,Islam M M,Yao X,et al.MWMOTE-majority weighted minority oversampling technique for imbalanced data set learning[J].IEEE Trans on Konwledge and Data Engineering,2014,26(2):405-425.
[11]Chawla N V,Bowyer K W,Hall L O,et,al.SMOTE:synthetic minority over-sampling technique[J].Journal of Artificial Intelligence Research,2011,16(1):321-357.
[12]Liu X Y,Wu J,Zhou Z H.Exploratory under sampling for class-imbalance learning[J].IEEE Transactions on Systems,Man,and Cybernetics–Part B:Cybernetics,2009,39(2):539-550.
[13]Yang X S.A new metaheuristic bat-inspired algorithm[J].Computer Knowledge & Technology,2010,284:65-74.