结合最优类别信息离散的细粒度超网络微阵列数据分类

摘要/Abstract

摘要：

针对传统演化超网络只能有效处理二值数据输入的问题，提出一种结合最优类别信息离散（Optimal Class-Dependent Discretization， OCDD)的细粒度演化超网络模型，对连续数据进行离散化生成细粒度二进制编码，并通过对其进行演化学习得到具备决策能力的超网络分类器.该方法避免了传统超网络模型对连续数据进行直接二值化后的高信息损失，使演化超网络的概率估计更接近于数据真实分布，提高了超网络的决策分类能力.对结肠癌、肺癌、前列腺癌和急性白血病4种DNA微阵列数据集进行实验的结果表明，结合OCDD的细粒度演化超网络具有比传统演化超网络更高的识别率和鲁棒性.

关键词: 模式识别, 机器学习, 超网络, 细粒度

Abstract:

To overcome the disadvantages in the traditional hypernetwork, an optimal class-dependent discretization (OCDD)based fine-grain evolutionary hypernetwork model was proposed, in which a continuous data was discretized as a fine-grain data and was used to evolve a hypernetwork classifier. With OCDD, the proposed fine-grain evolutionary hypernetwork lose less information than the traditional hypernetwork which directly convert a continuous data to a binary data. Moreover, fine-grain discrete data processing within the proposed hypernetwork model improves the quality of the probability estimation of a hypernetwork to the training data sets, and further enhances the performance of the hypernetwork classifier. The experimental results on colon, lung, prostate and Leukemia DNA microarray data sets show that the proposed method has a higher recognition rate and better robustness than the traditional evolutionary hypernetworks.

Key words: pattern recognition, machine learning, hypernetworks, fine-grain

中图分类号:

TP 391.4

王进，张军，胡白帆. 结合最优类别信息离散的细粒度超网络微阵列数据分类[J]. 上海交通大学学报（自然版）, 2013, 47(12): 1856-1862.

WANG Jin,ZHANG Jun,HU Baifan . Optimal Class-Dependent Discretization-Based Fine-Grain Hypernetworks for Classification of Microarray Data[J]. Journal of Shanghai Jiaotong University, 2013, 47(12): 1856-1862.

参考文献

［1］Zhang B T. Hypernetworks: A molecular evolutionary architecture for cognitive learning and memory［J］.

IEEE Computational Intelligence Magazine, 2008, 3(3): 4963.

［2］Bautu E, Kim S, Bautu A, et al. Evolving hypernetwork models of binary time series for forecasting price movements on stock markets ［C］∥Proceedings of the 11th IEEE Congress on Evolutionary Computation. USA: IEEE Press, 2009: 166173.

［3］Ha J W, Kim B H, Lee B, et al. Layered hypernetwork models for crossmodal associative text and image keyword generation in multimodal information retrieval ［C］∥Proceedings of the PRICAI 2010. Berlin: Springer Berlin Heidelberg, 2010: 7687.

［4］Choi S W, Lee C H. DNA computing hardware design and application to multiclass cancer data ［C］∥Proceedings of the ICONIP 2008. Berlin: Springer Berlin Heidelberg, 2008： 1072 1079.

［5］Liu L L, Wong A K C, Wang Y. A global optimal algorithm for classdependent discretization of continuous data ［J］. Intelligent Data Analysis, 2004, 8(2):151170.

［6］周世昊, 倪衍森. 基于类属性关联度的启发式离散化技术［J］.控制与决策, 2011, 26(10): 15041510.

ZHOU Shihao, NI Yanshen. Heuristic discretization technique based on the classattribute interdependence ［J］. Control and Decision, 2011, 26(10): 15041510.

［7］罗健旭, 邵惠鹤. 一种基于粗集的模糊神经网络［J］.上海交通大学学报, 2003, 37(11): 17021705.

LUO Jianxu, SHAO Huihe. A neurofuzzy system based on rough set theory［J］. Journal of Shanghai Jiaotong University, 2003, 37(11): 17021705.

［8］诸文智, 王靖程, 张彦斌，等. 应用有效信息比率的离散化算法［J］. 西安交通大学学报, 2011, 45(4): 1217.

ZHU Wenzhi, WANG Jingcheng, ZHANG Yanbin, et al. Discretization algorithm based on effective information ratio ［J］. Journal of Xi’an Jiaotong University, 2011, 45(4):1217.

［9］王进，孙开伟，李忠浩.超网络道路限速标志识别［J］. 小型计算机系统,2012,12(33):27092714.

WANG Jin, SUN Kaiwei, LI Zhonghao. Hypernetworks for road speed limit sign recognition ［J］. Journal of Chinese Computer Systems, 2012,12(33):27092714.

［10］Wang L, Zhu J, Zou H. Hybrid huberized support vector machines for microarray classification and gene selection ［J］. Bioinformatics, 2008, 24(3): 412419.

［11］Helman P, Veroff R, Atlas S R, et al. A bayesian network classification methodology for gene expression data ［J］. Journal of Computational Biology, 2004, 11(4): 581615.

［12］Tan A C, Gilbert D. Ensemble machine learning on gene expression data for cancer classification ［J］. Applied Bioinformatics, 2003, 2(Sup 3): 7583.

［13］Tang Y H, Zhang Y Q, Huang Z, et al. Granular SVMRFE gene selection algorithm for reliable prostate cancer classification on microarray expression data［C］∥Proceedings of the Fifth IEEE Symposium on Bioinformatics and Bioengineering. Washington:IEEE Computer Society, 2005: 290293.

［14］卢新国,林亚平,骆嘉伟,等.癌症识别中一种基于组合GCM 和CCM 的分类算法［J］.软件学报, 2010, 21(11): 28382851.

LU Xinguo, LIN Yaping, LUO Jiawei. Classification algorithm combined GCM with CCM in cancer recognition ［J］. Journal of Software, 2010, 21(11): 28382851.

［15］Cho S B, Won H. Cancer classification using ensemble of neural networks with multiple significant gene subsets ［J］. Applied Intelligence, 2007, 26(3): 243250.

[1]	舒俊清, 许昱晖, 夏唐斌, 潘尔顺, 奚立峰. 面向多故障模式的多尺度相似性集成寿命预测[J]. 上海交通大学学报, 2022, 56(5): 564-575.
[2]	贾岛, 陈磊, 朱志鹏, 余曜, 迟德建. 机器学习在引战系统设计中的应用研究[J]. 空天防御, 2022, 5(2): 27-31.
[3]	王卓鑫, 赵海涛, 谢月涵, 任翰韬, 袁明清, 张博明, 陈吉安. 反向传播神经网络联合遗传算法对复合材料模量的预测[J]. 上海交通大学学报, 2022, 56(10): 1341-1348.
[4]	李川, 聂熠文, 刘军伟, 孟凡钦, 沈晓静. 基于机器学习的多算法融合航迹稳健起始方法[J]. 空天防御, 2022, 5(1): 20-24.
[5]	周毅, 秦康平, 孙近文, 范栋琦, 郑义明. 台风气象环境电网设备风险量化预警及其N-m故障处置预案在线生成方法[J]. 上海交通大学学报, 2021, 55(S2): 22-30.
[6]	何夏维, 蔡云泽, 严玲玲. 一种合成残差式的反作用轮故障检测方法[J]. 上海交通大学学报, 2021, 55(6): 716-728.
[7]	祝颂, 钱晓超, 陆营波, 刘飞. 基于XGBoost的装备体系效能预测方法[J]. 空天防御, 2021, 4(2): 1-.
[8]	包清临, 柴华奇, 赵嵩正, 王吉林. 采用机器学习算法的技术机会挖掘模型及应用[J]. 上海交通大学学报, 2020, 54(7): 705-717.
[9]	屠恩美，杨杰. 半监督学习理论及其研究进展概述[J]. 上海交通大学学报（自然版）, 2018, 52(10): 1280-1291.
[10]	化存卿. 物联网安全检测与防护机制综述[J]. 上海交通大学学报（自然版）, 2018, 52(10): 1307-1313.
[11]	刘凯a，张立民b，周立军a. 随机受限玻尔兹曼机组设计[J]. 上海交通大学学报（自然版）, 2017, 51(10): 1235-1240.
[12]	李庆1,LIANG Steven Y1,2,杨建国1. 谐波小波样本熵与HMM模型的轴承故障模式识别[J]. 上海交通大学学报（自然版）, 2016, 50(05): 723-729.
[13]	赵秀亮，程勇，王丽梅. 利用模式识别技术提高燃烧激励响应信号信噪比[J]. 上海交通大学学报（自然版）, 2015, 49(05): 637-643.
[14]	刘书，王慈. 基于自适应非局部均值滤波的图像去块算法[J]. 上海交通大学学报（自然版）, 2013, 47(12): 1930-1933.
[15]	肖敏1, 廖少明1, 周松2. 基于Web的隧道盾构法施工动态监控系统[J]. 上海交通大学学报（自然版）, 2012, 46(01): 105-108.