摘要
基于粒子群优化(PSO)的增强型核极限学习机(KELM)提出了一种有效的预测模型PSO-KELM来辅助第二专业选择。在PSO-KELM中,PSO策略确定KELM的最佳参数。PSO-KELM与其他两个竞争方法在学生专业选择数据上通过10折交叉验证方案进行比较,这两个方法分别是支持向量机和网格搜索技术优化的KELM。结果表明了本文预测模型在分类精度、受试者工作特征曲线面积(AUC)、灵敏度和特异性方面的优越性。
This paper proposes an effective prediction model for choosing the second major based on the Particle Swarm Optimization(PSO)enhanced Kernel Extreme Learning Machine(KELM),which is called PSO-KELM model.In this model,the PSO strategy is adopted to adaptively determine the optimal parameters in KELM.The PSO-KELM model is compared with other two competitive methods,including Support Vector Machine(SVM)and a KELM is optimized by grid search technique,on a major selection dataset via a 10-fold cross validation scheme.The results clearly confirm the superiority of the proposed PSO-KELM model in classification accuracy,area under the receiver operating characteristic curve(AUC),sensitivity and specificity.
引文
[1]Kardan A A,Sadeghi H,Ghidary S S,et al.Prediction of student course selection in online higher education institutes using neural network[J].Computers and Education,2013,65:1-11.
[2]Guo W W.Incorporating statistical and neural network approaches for student course satisfaction analysis and prediction[J].Expert Systems with Applications,2010,37(4):3358-3365.
[3]Campagni R,Merlini D,Sprugnoli R,et al.Data mining models for student careers[J].Expert Systems with Applications,2015,42(13):5508-5521.
[4]Huang C,Xu J.Second major selection system based on data mining[J].Journal of Information and Computational Science,2009,6(6):2333-2340.
[5]Huang G B,Zhu Q Y,Siew C K.Extreme learning machine:theory and applications[J].Neurocomputing,2006,70(1-3):489-501.
[6]Huang G B,Zhou H,Ding X,et al.Extreme learning machine for regression and multiclass classification[J].IEEE Transactions on Systems Man&Cybernetics Part B Cybernetics,2012,42(2):513-529.
[7]Liu B,Tang L W,Wang J B,et al.2-D defect profile reconstruction from ultrasonic guided wave signals based on QGA-kernelized ELM[J].Neurocomputing,2014,128:217-223.
[8]Chen H L,Wang G,Ma C,et al.An efficient hybrid kernel extreme learning machine approach for early diagnosis of Parkinson's disease[J].Neurocomputing,2016,184(C):131-144.
[9]Liu T,Hu L,Ma C,et al.A fast approach for detection of erythemato-squamous diseases based on extreme learning machine with maximum relevance minimum redundancy feature selection[J].International Journal of Systems Science,2015,46(5):919-931.
[10]Chen H L,Yang B,Wang S J,et al.Towards an optimal support vector machine classifier using a parallel particle swarm optimization strategy[J].Applied Mathematics and Computation,2014,239:180-197.
[11]代琨,于宏毅,仇文博,等.基于SVM的网络数据无监督特征选择算法[J].吉林大学学报:工学版,2015,45(2):576-582.Dai Kun,Yu Hong-yi,Qiu Wen-bo,et al.Unsupervised feature selection algorithm based on support vector machine for network data[J].Journal of Jilin University(Engineering and Technology Edition),2015,45(2):576-582.
[12]赵东,臧雪柏,赵宏伟.基于果蝇优化的随机森林预测方法[J].吉林大学学报:工学版,2017,47(2):609-614.Zhao Dong,Zang Xue-bai,Zhao Hong-wei.Random forest prediction method based on Optimization of fruit fly[J].Journal of Jilin University(Engineering and Technology Edition),2017,47(2):609-614.
[13]Duan L,Dong S,Cui S,et al.Extreme learning machine with gaussian kernel based relevance feedback scheme for image retrieval[J].Springer International Publishing,2016,1:397-408.
[14]Chang C C,Lin C J.LIBSVM:a library for support vector machines[J].ACM Transactions on Intelligent Systems and Technology,2011,2(3):1-27.