基于特征选择的决策树方法在磷酸铝AlPO4-5定向合成中的应用

doi:10.3866/PKU.WHXB20110831

物理化学学报 >> 2011, Vol. 27 >> Issue (09): 2111-2117.doi: 10.3866/PKU.WHXB20110831

基于特征选择的决策树方法在磷酸铝AlPO₄-5定向合成中的应用

霍卫峰, 高娜, 颜岩, 李激扬, 于吉红, 徐如人

吉林大学无机合成与制备化学国家重点实验室, 长春 130012

收稿日期:2011-04-26 修回日期:2011-06-09 发布日期:2011-08-26
通讯作者: 李激扬 E-mail:lijiyang@jlu.edu.cn
基金资助:
国家自然科学基金(20871051)资助项目

Decision Trees Combined with Feature Selection for the Rational Synthesis of Aluminophosphate AlPO₄-5

HUO Wei-Feng, GAO Na, YAN Yan, LI Ji-Yang, YU Ji-Hong, XU Ru-Ren

State Key Laboratory of Inorganic Synthesis and Preparative Chemistry, Jilin University, Changchun 130012, P. R. China

Received:2011-04-26 Revised:2011-06-09 Published:2011-08-26
Contact: LI Ji-Yang E-mail:lijiyang@jlu.edu.cn
Supported by:
The project was supported by the National Natural Science Foundation of China (20871051).

摘要/Abstract

摘要： 分子筛类开放骨架材料的合成与结构关系研究对实现这类材料的定向合成起着至关重要的作用. 本文在建立开放骨架磷酸铝合成反应数据库的基础上, 提出了利用基于特征选择的决策树(C5.0)方法, 考察了不同反应条件(即各反应特征参数)对磷酸铝分子筛AlPO₄-5 生成的影响. 基于决策树模型, 利用8 个反应特征参数,可以有效预测磷酸铝分子筛AlPO₄-5的生成, 准确率达到88.18%, 接收者操作特性(ROC)曲线下面积(AUC)达到90%. 研究结果表明, 在众多的反应特征参数中, 有机模板剂的几何尺寸参数, 特别是模板剂的次长距离, 是影响AlPO₄-5分子筛合成的重要因素.

关键词: 磷酸铝, 定向合成, 数据挖掘, 决策树, 特征选择

Abstract: The relationship between the synthetic features and the types of final product is critical for the rational synthesis of zeolite-type open-framework materials. In this paper, an AlPO₄-5 prediction system based on C5.0 combined with a feature selection is proposed on the basis of the establishment of a database of AlPO syntheses. 26 synthetic parameters associated with gel composition, an organic amine template and a solvent were used as input to predict the formation of AlPO₄-5. The effects of different synthetic parameters on the formation of AlPO₄-5 were also studied. The performance of the method was evaluated using classification accuracy and a receiver operating characteristic (ROC) curve. The results show that the highest area under the ROC curve (90%) and the classification accuracy (88.18%) was obtained for the decision tree model that contains eight input features and some useful rules with high confidence degrees were extracted from the model. Among the various synthetic parameters the geometric size of the organic template, particularly the second longest distance of the template plays an important role in the formation of AlPO₄-5.

Key words: Aluminophosphate, Rational synthesis, Data mining, Decision tree, Feature selection

霍卫峰, 高娜, 颜岩, 李激扬, 于吉红, 徐如人. 基于特征选择的决策树方法在磷酸铝AlPO₄-5定向合成中的应用[J]. 物理化学学报, 2011, 27(09): 2111-2117.

HUO Wei-Feng, GAO Na, YAN Yan, LI Ji-Yang, YU Ji-Hong, XU Ru-Ren. Decision Trees Combined with Feature Selection for the Rational Synthesis of Aluminophosphate AlPO₄-5[J]. Acta Phys. -Chim. Sin., 2011, 27(09): 2111-2117.

链接本文: https://www.whxb.pku.edu.cn/CN/10.3866/PKU.WHXB20110831

https://www.whxb.pku.edu.cn/CN/Y2011/V27/I09/2111

参考文献

(1) Smit, B.; Maesen, T. L. M. Nature 2008, 451, 671.

(2) Chen, X.; Yang, H.; Gu, Z. Y.; Shao, Z. Z. J. Appl. Polym. Sci. 2001, 79, 1144.

(3) Rakoczy, R. A.; Traa, Y. Microporous Mesoporous Mat. 2003, 60, 69.

(4) Chang, C. F.; Chang, C. Y.; Chen K. H.; Tsai,W. T.; Shie, J. L.; Chen, Y. H. J. Colloid Interface Sci. 2004, 277 (1), 29.
(5) Shi, X. E.; Zhai, S. R.; Dai, L. Y.; Shan, Y. K.; He, M. Y.;Wei, W.;Wu, D.; Sun, Y. H. Acta Phys. -Chim. Sin. 2004, 20 (3), 265. [师希娥, 翟尚儒, 戴立益, 单永奎, 何鸣元, 魏伟, 吴东, 孙予罕. 物理化学学报, 2004, 20 (3), 265.]
(6) Wilson, S. T.; Lok, B. M.; Messina, C. A.; Cannan, T. R.; Flanigen, E. M. J. Am. Chem. Soc. 1982, 104, 1146.

(7) Witten, I. H.; Frank, E. Data Mining: Practical Machine Learning Tools and Techniques with Java Implementations; Morgan Kaufmann: San Francisco, 2000; p xix.
(8) Han, J.W.; Kamber, M. Data Mining: Concepts and Techniques; Morgan Kaufmann: San Francisco, 2001; p 7.
(9) Fletcher, D. A.; McMeeking, R. F.; Parkin, D. J. Chem. Inf. Comput. Sci. 1996, 36 (4), 746.
(10) Perola, E.; Xu, K.; Kollmeyer, T. M.; Kaufmann, S. H.; Prendergast, F. G.;. Pang, Y. P. J. Med. Chem. 2000, 43 (3), 401.
(11) Goto, S.; Nishioka, T.; Kanehisa, M. Bioinformatics 1998, 14, 591.

(12) Sandberg, M.; Eriksson, L.; Jonsson, J.; Sjöström M.;Wold, S. J. Med. Chem. 1998, 41 (14), 2481.
(13) Karelson, M.; Lobanov, V. S.; Katritzky, A. R. Chem. Rev. 1996, 96 (3), 1027.
(14) Karelson, M. Molecular Descriptors in QSAR/QSPR; John Wiley & Sons Ltd.: New York, 2000.
(15) Bennett, C. A.; Franklin, N. L. Statistical Analysis in Chemistry and the Chemical Industry; JohnWiley & Sons Ltd.: New York, 1954.
(16) Allen, F. H. Acta Cryst . B 2002, 58, 380.

(17) Kraeft,W. D.; Kremp, D.; Ebeling,W.; Ropke, G. Quantum Statistics of Charged Particle Systems; Akademie-Verlag: Berlin, 1986.
(18) Edwards, G.; Compton, P.; Malor, R.; Srinivasan, A.; Lazarus, L. Pathology 1993, 25 (1), 27.
(19) Rich, S. H.; Venkatasubramanian, V. Comput. Chem. Eng. 1987, 11 (2), 111.
(20) Barratt, M. D.; Basketter, D. A.; Chamberlain, M.; Admans, G. D.; Langowski, J. J. Toxicol. in Vitro 1994, 8 (5),1053.
(21) King, R. D.; Srinivasan, A.; Dehaspe, L. J. Comput.-Aided Mol. Des. 2001, 15 (2), 173.
(22) Zhang, J. H.;Wang, X. J. Acta Phys. -Chim. Sin. 2010, 26 (1), 188. [张家虎, 王秀军. 物理化学学报, 2010, 26 (1), 188.]
(23) Corma, A.; Diaz-Cabanas, M. J.; Jorda, J. L.; Martinez, C.; Moliner, M. Nature 2006, 443, 842.

(24) Li, J. Y.; Qi, M.; Kong J.;Wang, J. Z.; Yan, Y.; Huo,W. F.; Yu, J. H.; Xu, R. R.; Xu, Y. Microporous Mesoporous Mat. 2010, 129, 251.

(25) Chen, Y.W.; Lin, C. J. Combining SVMs with various feature selection strategies, 2005. http://www.csie.ntu.edu.tw/-cjlin/ papers/features.pdf (accessed Oct 20, 2009).
(26) Hanley, J. A.; McNeil, B. J. Radiology 1982, 143, 29.
(27) Quinlan, J. R. C4. 5: Programs for Machine Learning; Morgan Kaufmann: San Francisco, 1993.
(28) Breiman, L.; Friedman, J. H.; Olshen, R. A.; Stone, C. J. Classification and Regression Trees;Wadsworth: Belmont, 1984.
(29) Shafer, J. C.; Agrawal, R.; Mehta, M. SPRINT: A Scalable Parallel Classifier for Data mining. In Very Large Data Bases, Proceedings of 22nd International Conference on Very Large Data Bases, Bombay, India, September, 1996; Vijayaraman, T. M., Buchmann, A. P., Mohan, C., Sarda, N. L., Eds.; Morgan Kaufmann: San Francisco, 1996; pp 544-555.
(30) Gehrke, J.; Ramakrishnan, R.; Ganti, V. Data Min. Knowl. Disc. 2000, 4 (2/3), 127.
(31) Quinlan, J. R. Mach. Learn. 1986, 1, 81.
(32) Quinlan, J. R. Data Mining Tools See5 and C5. 0. http://www.rulequest.com/see5-info.html (accessed Nov 30, 2007).
(33) Hoste, V. Optimization Issues in Machine Learning of Coreference Resolution. Ph. D. Dissertation, University of Antwerp, Belgium, 2005.

[1]	刘钢, 杨录新, 吴淑杰, 贾明君, 张文祥. 磷酸铝负载钾催化剂表面酸碱性质对邻苯二酚O-单醚化催化性能的影响[J]. 物理化学学报, 2014, 30(6): 1163 -1168 .
[2]	王志明, 韩娜, 袁哲明, 伍朝华. 基于岭回归和SVM的高维特征选择与肽QSAR建模[J]. 物理化学学报, 2013, 29(03): 498 -507 .
[3]	代志军, 周玮, 袁哲明, . 基于支持向量机的高维特征非线性快速筛选与肽QSAR建模[J]. 物理化学学报, 2011, 27(07): 1654 -1660 .
[4]	刘洁翔, 张晓光, 段中余, 刘晓莉. NO_x分子在[Ag]-MAPO-5 (M=Si, Ti) 分子筛中的吸附[J]. 物理化学学报, 2010, 26(10): 2679 -2685 .
[5]	何月, 董梅, 李俊汾, 王建国, 樊卫斌. MeAPO-5分子筛的合成及其在肉桂醇选择氧化反应中的催化性能[J]. 物理化学学报, 2010, 26(05): 1305 -1310 .
[6]	赵瑞花, 董梅, 秦张峰, 丁建飞, 郭星翠, 王建国. 不同钴含量CoAPO-5分子筛的合成、表征及其催化环己烷氧化性能[J]. 物理化学学报, 2008, 24(12): 2304 -2308 .
[7]	汪哲明;阎子峰. 杂原子取代型磷酸铝分子筛上丁烯异构化反应[J]. 物理化学学报, 2003, 19(03): 216 -220 .
[8]	徐桦, 邵俊. 正磷酸铝高压下相变的分子动力学模拟[J]. 物理化学学报, 2000, 16(06): 512 -516 .

基于特征选择的决策树方法在磷酸铝AlPO₄-5定向合成中的应用

Decision Trees Combined with Feature Selection for the Rational Synthesis of Aluminophosphate AlPO₄-5

PDF

赞

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 8

Metrics

推荐阅读 0