[1]林毅,蔡福营,袁宇熹,等.PCA-SVM模型在几丁质酶最适温度建模中的应用[J].华侨大学学报(自然科学版),2008,29(2):236-240.[doi:10.11830/ISSN.1000-5013.2008.02.0236]
 LIN Yi,CAI Fu-ying,YUAN Yu-xi,et al.A Uniform Design Based PCA-SVM Model for Predicting Optimum Temperature in Chitinase[J].Journal of Huaqiao University(Natural Science),2008,29(2):236-240.[doi:10.11830/ISSN.1000-5013.2008.02.0236]
点击复制

PCA-SVM模型在几丁质酶最适温度建模中的应用()
分享到:

《华侨大学学报(自然科学版)》[ISSN:1000-5013/CN:35-1079/N]

卷:
第29卷
期数:
2008年第2期
页码:
236-240
栏目:
出版日期:
2008-04-20

文章信息/Info

Title:
A Uniform Design Based PCA-SVM Model for Predicting Optimum Temperature in Chitinase
文章编号:
1000-5013(2008)02-0236-05
作者:
林毅蔡福营袁宇熹张光亚
华侨大学材料科学与工程学院; 华侨大学材料科学与工程学院 福建泉州362021; 福建泉州362021
Author(s):
LIN Yi CAI Fu-ying YUAN Yu-xi ZHANG Guang-ya
College of Material Science and Engineering, Huaqiao University, Quanzhou 362021, China
关键词:
几丁质酶 数学模型 主成分分析 支持向量机 最适温度
Keywords:
principle component analysis support vector machine chitinase optimum temperature
分类号:
Q55
DOI:
10.11830/ISSN.1000-5013.2008.02.0236
文献标志码:
A
摘要:
采用主成分分析法(PCA)对样本数据集进行预处理,将得到的新样本数据集输入支持向量机(SVM),籍助均匀设计(UD),构建几丁质酶氨基酸组成和最适温度的数学模型.当径向基核函数的3个参数,惩罚系数C为10,ε为0.5,γ为5时,模型对温度拟合的平均绝对百分比误差为5.06%,预测的平均绝对误差为1.83℃,说明具有良好的预测效果且优于神经网络的预测结果.
Abstract:
The principal component analysis was applied to the data processing in training sets,the new principal components were then used as input data of support vector machine modle.A prediction model for optimum temperature of chitinase was established based on uniform design.When the regularized constant C,ε and γ were 10,0.5 and 5,respectively,the calculated temperature fitted the reported optimum temperature of chitinase very well and the mean absolute percent error(MAPEs) was 5.06%.At the same time,the predicted temperature fitted the reported optimum temperature well and the mean absolute error(MAE) was 1.83 ℃.It was superior in fittings and predictions compared to the model based on back propagation neural network.

参考文献/References:

[1] BUSSIVK A P, VAN EIJK M. The Biology of the gaucher cell:The cradle of human chitinase [J]. A Survey of Cell Biology, 2006(2):71-128.
[2] 蒋红彬, 蒋千里. 几丁质酶的研究概况 [J]. 山东科学, 2000(3):41-45.
[3] CHANG Ming-Chun, LAI Pe-Lin, WU Mei-Li. Biochemical characterization and site-directed mutational analysis of the double chitin-binding domain from chitinase 92 of Aeromonas hydrophila JP101 [J]. FEMS Microbiology Letters, 2004(5):1-61.doi:10.1016/S0378-1097(04)00014-X.
[4] ALLEN S. Enzyme functionality:Design, engineering, and screening [M]. New York:Marcel Dekker, Inc, 2004.1-712.
[5] MILDVAN A S. Inverse thinking about double mutants of enzymes [J]. Biochemistry, 2004(2):14517-14520.
[6] ROBERT J H, JORG B, MARIE L A. Combining computational and experimental screening for rapid optimization of protein properties [J]. Proceedings of the National Academy of Sciences(USA), 2002(3):15926-15931.
[7] NAKASHIMA H, NISHIKAWA K, OOI T. The folding type of a protein is relevant to the amino acid composition [J]. Journal of Biochemistry, 1986(1):153-162.
[8] KLEIN P. Prediction of protein structural class by discriminate analysis [J]. Biochimica Et Biophysica Acta, 1986(2):205-275.
[9] CHOU K C, MAGGIORA G M. Domain structure prediction [J]. Protein Engineering, 1998(7):523-538.doi:10.1093/protein/11.7.523.
[10] CHOU K C. A key driving force in determination of protein structural classes [J]. Biochemical and Biophysical Research Communications, 1999(1):216-224.
[11] VAPNIK V. Statistical learning theory [M]. New York:wiley, 1998.1-736.
[12] CORTES C, VAPNIK V. Support vector machine networks [J]. Machine Learning, 1995(4):273-297.
[13] FANG K T. The uniform design application of number theoretic methods in experimental design [J]. Acta Mathematicae Applicatae Sinica, 1980(3):363-372.
[14] 张光亚, 方柏山. 木聚糖酶氨基酸组成与其最适pH的神经网络模型 [J]. 生物工程学报, 2005(4):658-661.doi:10.3321/j.issn:1000-3061.2005.04.029.

相似文献/References:

[1]王全凤,施士升.50米以上高层建筑在地震荷载下剪力墙数量的确定[J].华侨大学学报(自然科学版),1982,3(1 ):96.[doi:10.11830/ISSN.1000-5013.1982.01.0096]
[2]王全凤.变刚度框架-剪力墙结构抗地震荷载剪力墙数量的优化分析[J].华侨大学学报(自然科学版),1982,3(2):43.[doi:10.11830/ISSN.1000-5013.1982.02.0043]
[3]方志成,陆丽华,程均琦.交流电位法裂纹深度测量仪[J].华侨大学学报(自然科学版),1982,3(2):61.[doi:10.11830/ISSN.1000-5013.1982.02.0061]
[4]方志成,陆丽华.裂纹深度刻度曲线的数学模型与计算机程序[J].华侨大学学报(自然科学版),1983,4(1):48.[doi:10.11830/ISSN.1000-5013.1983.01.0048]
[5]方志成,廖培福,陆丽华,等.不贯通裂纹深度测量的计算机自动修正[J].华侨大学学报(自然科学版),1983,4(2):72.[doi:10.11830/ISSN.1000-5013.1983.02.0072]
[6]周再发,陈文挺.场效应晶体管在低电平下变阻特性的数学模型[J].华侨大学学报(自然科学版),1983,4(2):79.[doi:10.11830/ISSN.1000-5013.1983.02.0079]
[7]方志成,陆丽华.用微型计算机实现不同材质的表面裂纹深度测量的自动修正[J].华侨大学学报(自然科学版),1984,5(1):77.[doi:10.11830/ISSN.1000-5013.1984.01.0077]
[8]王全凤.剪力墙刚度优化分析的计算机程序——为普及微型计算机而作[J].华侨大学学报(自然科学版),1984,5(2):65.[doi:10.11830/ISSN.1000-5013.1984.02.0065]
[9]陈希达,陈宝珊.工艺设备调整数学模型[J].华侨大学学报(自然科学版),1985,6(3):286.[doi:10.11830/ISSN.1000-5013.1985.03.0286]
 Chen Xida,Chen Baoshan.The Mathematical Model of the Adjustment of Technological Installations[J].Journal of Huaqiao University(Natural Science),1985,6(2):286.[doi:10.11830/ISSN.1000-5013.1985.03.0286]
[10]陈元霖.楔形滑块机构力分析和综合的新准则[J].华侨大学学报(自然科学版),1987,8(2):188.[doi:10.11830/ISSN.1000-5013.1987.02.0188]
 Chen Yuanlin.A New Criterion for Force Analysis and Synthesis of Wedge Slider Mechanism[J].Journal of Huaqiao University(Natural Science),1987,8(2):188.[doi:10.11830/ISSN.1000-5013.1987.02.0188]

备注/Memo

备注/Memo:
国家自然科学基金资助项目(40601046); 福建省高等学校新世纪优秀人才计划支持项目(2006); 福建省自然科学基金资助项目(B0510011)
更新日期/Last Update: 2014-03-23