基于免疫克隆选择的最优ECOC编码输出

doi:10.3969/j.issn.0372-2112.2018.12.031

电子学报 ›› 2018, Vol. 46 ›› Issue (12): 3044-3049.DOI: 10.3969/j.issn.0372-2112.2018.12.031

基于免疫克隆选择的最优ECOC编码输出

雷蕾¹, 余晓东², 王晓丹¹, 罗玺³, 王艺菲¹

1. 空军工程大学防空反导学院, 陕西西安 710051;
2. 空军研究院系统工程研究所, 北京 100076;
3. 空军工程大学信息与导航学院, 陕西西安 710077

收稿日期:2017-03-16 修回日期:2017-12-14 出版日期:2018-12-25
- 作者简介:
- 雷蕾女,1988年生于四川南充.讲师,博士.主要研究方向为智能信息处理和目标识别.E-mail:wendyandpaopao@163.com;余晓东 男,1989年生于江西九江.工程师,博士.主要研究方向为目标识别、直觉模糊理论.E-mail:1438894571@qq.com;王晓丹 女,1966年生于陕西汉中.教授,博士.研究方向为模式识别、深度学习.E-mail:afeu_wang@163.com
- 基金资助:
- 国家自然科学基金 (No.61806219，No.61876189，No.61503407）

An Optimization Strategy of ECOC Coding Matrix-Based on Immune Clonal Selection Algorithm

LEI Lei¹, YU Xiao-dong², WANG Xiao-dan¹, LUO Xi³, WANG Yi-fei¹

1.The Air and Missile Defense Institute, Air Force Engineering University, Xi'an, Shaanxi 710051, China;
2.The Systems Engineering Institute, AIR Force Research Institute, Beijing 10076, China;
3.The Information and Navigation Institute, Air Force Engineering University, Xi'an, Shaanxi 710077, China

Received:2017-03-16 Revised:2017-12-14 Online:2018-12-25 Published:2018-12-25
- Supported by:
- National Natural Science Foundation of China (No.61806219, No.61876189, No.61503407)

摘要/Abstract

摘要： 纠错输出编码（Error Correcting Output Codes，ECOC）是解决模式识别领域多类分类问题的有效工具。在寻找最优编码输出的问题上，现有方法忽略了样本类别之间的相关性，导致学习效率和分类效果低下。为构造数据感知的编码矩阵，提出基于免疫克隆选择（Immune Clonal Selection Algorithm，ICSA）的最优纠错输出编码方法，将矩阵构造的多约束NP（Non-deterministic Polynomial，NP）难问题转换为优化搜索问题.首先基于分类精度和编码长度定义亲合度函数，然后结合样本知识改进变异交叉算子，根据约束性条件对矩阵进行搜索，从而快速有效地构建最优ECOC编码.实验表明该方法能够在提升多类分类精度的同时加快算法效率，而且输出的编码矩阵更加紧凑.

关键词: 多类分类, 纠错编码, 免疫克隆选择, 数据感知, 编码矩阵, 多约束优化

Abstract: Error correcting output codes (ECOC) is a powerful tool to solve multi-classification problem. The existing methods of seeking the optimal coding matrix ignore the correlation between classes, which leads to bad performance in learning speed and classification accuracy. In order to construct data-driven coding matrix, an optimization strategy of coding matrix based on immune clonal selection algorithm (ICSA) is presented. The strategy reduces the multiple constraints non-deterministic polynomial problem (NP) of finding the optimal coding matrix to a finite heuristic search problem. Firstly, the affinity function based on accuracy and coding length is defined. Then, the mutation, crossover and selection operator are modified respectively. Meanwhile, the validity constraints are combined to execute the quick search. The experiment results based on UCI and traffic data prove that the proposed strategy can enhance the classification performance and accelerated the speed. The output coding matrix is more compact as well.

Key words: multi-classification, ECOC, immune clonal selection algorithm, data driven, coding matrix, multiple constraints optimization

中图分类号:

TP391

雷蕾, 余晓东, 王晓丹, 等. 基于免疫克隆选择的最优ECOC编码输出[J]. 电子学报, 2018, 46(12): 3044-3049.

LEI Lei, YU Xiao-dong, WANG Xiao-dan, et al. An Optimization Strategy of ECOC Coding Matrix-Based on Immune Clonal Selection Algorithm[J]. Acta Electronica Sinica, 2018, 46(12): 3044-3049.

参考文献

[1] Dietterich T G,Kong E.Error correcting output codes corrects bias and variance[A].Proceedings of the 21th International Conference on Machine Learning[C].S Prieditis,S Russell,UK:AAA,1995.313-321.
[2] Oriol P,Radeva P,Vitria J.Discriminate ECOC:A heuristic method for application dependent design of error correcting output codes[J].IEEE Trans on Pattern Analysis and Machine Intelligence,2006,28(6):1001-1007.
[3] Escalera S,David M J T,Oriol P,et al.Subclass problem-dependent design for error-correcting output codes[J].IEEE Trans on Pattern Analysis and Machine Intelligence,2008,30(6):1041-1054.
[4] ZHOU J D,YANG Y,ZHANG M J,et al.Constructing ECOC based on confusion matrix for multiclass learning problems[J].Science China Information Sciences,2016,59(1):1-14.
[5] LEI L,WANG X D.Hierarchical error-correcting output codes based on SVDD[J].Pattern Analysis and Applications,2016,19(1):163-171.
[6] Bautista M Á,Escalera S,Baró X,et al.On the design of an ECOC-compliant genetic algorithm[J].Pattern Recognition,2014,47(2):865-884.
[7] Crammer K,Singer Y.On the learnability and design of output codes for multiclass problems[A].Proceedings of the Thirteenth Annual Conference on Computational Learning Theory[C].Kluwer Academic Publishers,Boston:2000.896-909.
[8] DeCastro L N,VonZuben F J.Learning and optimization using the clonal selection principle[J].IEEE Trans on Evolutionary Computation,2002,6(3):239~251.
[9] Gou S P,Zhang X,Jiao L C.Quantum immune fast spectral clustering for SAR image segmentation[J].IEEE Geoscience and Remote Sensing Letters,2012,9(1):8-12.
[10] 马文萍,黄媛媛,李豪,等.基于粗糙集与差分免疫模糊聚类算法的图像分割[J].软件学报,2014,25(11):2675-2689. Ma Wen-ping,Huang Yuan-yuan,Li Hao.Image segmentation based on rough set and differential immune fuzzy clustering algorithm[J].Journal of Software,2014,25(11):2675-2689.(in Chinese)
[11] Miguel A B,Sergio E.Minimal design of error-correcting output codes[J].Pattern Recognition Letters,2012,33(10):693-702.
[12] ZHOU J D,WANG X D.Coding design for error-correcting output codes based on perception[J].Optical Engineering,2012,51(5):322-331.
[13] 雷英杰,余晓东,王睿,王毅.根据混合选择策略的直觉模糊核匹配追踪集成算法[J].控制理论与应用.2016,33(3).336-343. Lei Ying-jie,Yu Xiao-dong,Wang Rui,et al.Intuitionistic fuzzy kernel-matching pursuit ensemble algorithm based on hybrid selection strategy[J].Control Theory and Applications,2016,33(3):336-343.(in Chinese)

基于免疫克隆选择的最优ECOC编码输出

An Optimization Strategy of ECOC Coding Matrix-Based on Immune Clonal Selection Algorithm

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 8

编辑推荐

Metrics

[1]	钟兆根, 吴昭军, 刘杰, 张立民. 高误码率下归零Turbo码帧结构识别[J]. 电子学报, 2019, 47(10): 2089-2097.
[2]	盛凯, 刘忠, 周德超, 魏启航, 冯成旭. 一种基于证据理论的多类半监督分类算法[J]. 电子学报, 2018, 46(11): 2642-2649.
[3]	丁蕊, 董红斌, 邢薇, 刘文杰, 孔飞. 一种求解冰壶比赛对阵多约束问题的逐层优化算法[J]. 电子学报, 2017, 45(3): 632-637.
[4]	雷蕾, 王晓丹, 罗玺, 王玮. 带拒绝域的ECOC多类分类[J]. 电子学报, 2017, 45(11): 2779-2786.
[5]	雷蕾, 王晓丹, 罗玺, 周进登, 陈琴. ECOC多类分类研究综述[J]. 电子学报, 2014, 42(9): 1794-1800.
[6]	周进登, 周红建, 杨云, 郭长华, 胡洪宇. 基于神经网络的纠错输出编码方法研究[J]. 电子学报, 2013, 41(6): 1114-1121.
[7]	周进登;王晓丹;权文;许燕;姚旭. 加权解码在解决纠错输出编码Consistent-Diverse平衡问题的应用[J]. 电子学报, 2011, 39(7): 1514-1522.
[8]	李昆仑;黄厚宽;田盛丰. 模糊多类SVM模型[J]. 电子学报, 2004, 32(5): 830-832.