用于不平衡数据分类的代价敏感超网络算法

doi:10.11772/j.issn.1001-9081.2014.05.1336

计算机应用 ›› 2014, Vol. 34 ›› Issue (5): 1336-1340.DOI: 10.11772/j.issn.1001-9081.2014.05.1336

用于不平衡数据分类的代价敏感超网络算法

郑燕¹,王杨²,郝青峰²,甘振韬³

1. 重庆工业职业技术学院信息工程学院，重庆 400050；
2. 重庆军代室，重庆 400030；
3. 第三军医大学教育技术中心，重庆 400038

收稿日期:2013-11-11 修回日期:2013-12-25 发布日期:2014-05-30 出版日期:2014-05-01
通讯作者: 郑燕
作者简介:郑燕（1981-），女，重庆人，讲师，硕士，主要研究方向：模式识别、嵌入式技术；王杨（1980-），男，四川阆中人，工程师，硕士，主要研究方向：机器学习、物联网；郝青峰（1976-），男，陕西西安人，工程师，硕士，主要研究方向：机器学习、物联网；甘振韬（1973-），男，重庆人，高级工程师，硕士，主要研究方向：人工智能、机器学习。
基金资助:
重庆市教育委员会2010年度科学技术研究资助项目

Cost-sensitive hypernetworks for imbalanced data classification

ZHENG Yan¹,WANG Yang²,HAO Qingfeng²,GAN Zhentao³

1. School of Information Engineering, Chongqing Industry Polytechnic College, Chongqing 400050, China;
2. Chongqing Military Representative Office, Chongqing 400030, China;
3. Education Technology Center, Third Military Medical University, Chongqing 400038, China

Received:2013-11-11 Revised:2013-12-25 Online:2014-05-30 Published:2014-05-01
Contact: ZHENG Yan

摘要/Abstract

摘要：

传统的超网络模型在处理不平衡数据分类问题时，具有很大的偏向性，正类的识别率远远高于负类。为此，提出了一种代价敏感超网络Boosting集成算法。首先，将代价敏感学习引入超网络模型，提出了代价敏感的超网络模型；同时，为了使算法能够自适应正类的错分代价，采用Boosting算法对代价敏感超网络进行集成。代价敏感超网络能很好地修正传统的超网络在处理不平衡数据分类问题时过分偏向正类的缺陷，提高对负类的分类准确性。实验结果表明，代价敏感超网络Boosting集成算法具有处理不平衡数据分类问题的优势。

Abstract:

Traditional hypernetwork model is biased towards the majority class, which leads to much higher accuracy on majority class than the minority when being tackled on imbalanced data classification problem. In this paper, a Boosting ensemble of cost-sensitive hypernetworks was proposed. Firstly, the cost-sensitive learning was introduced to hypernetwork model, to propose cost-sensitive hyperenetwork model. Meanwhile, to make the algorithm adapt to the cost of misclassification on positive class, cost-sensitive hypernetworks were integrated by Boosting. The proposed model revised the bias towards the majority class when traditional hypernetwork model was tackled on imbalanced data classification, and improved the classification accuracy on minority class. The experimental results show that the proposed scheme has advantages in imbalanced data classification.

中图分类号:

TP18

郑燕王杨郝青峰甘振韬. 用于不平衡数据分类的代价敏感超网络算法[J]. 计算机应用, 2014, 34(5): 1336-1340.

ZHENG Yan WANG Yang HAO Qingfeng GAN Zhentao. Cost-sensitive hypernetworks for imbalanced data classification[J]. Journal of Computer Applications, 2014, 34(5): 1336-1340.

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］ZHANG B T, JANG H Y. Molecular programming: evolving genetic programs in a test tube ［C］// Proceedings of the 2005 Conference on Genetic and Evolutionary Computation. New York: ACM, 2005:1761-1768.
［3］KIM S, HEO M O, ZHANG B T. Text classifiers evolved on a simulated DNA computer ［C］// Proceedings of the 2006 IEEE Congress on Evolutionary Computation. Piscataway: IEEE Press, 2006:2646- 2652.
［4］KIM E S, HA J W, JUNG W H, et al. Mutual information-based evolution of hypernetworks for brain data analysis ［C］// Proceedings of the 2011 IEEE Congress on Evolutionary Computation. Piscataway: IEEE Press, 2011:2611-2617.
［5］SUN Y, WONG A K C, KAMEL M S. Classification of imbalanced data: a review ［J］. International Journal of Pattern Recognition and Artificial Intelligence, 2009, 23(4):687-719.
［6］LING C X, YANG Q, WANG J, et al. Decision trees with minimal costs ［C］// Proceedings of the 21st International Conference on Machine Learning. New York: ACM, 2004:69-76.
［7］ZHOU Z H, LIU X Y. Training cost-sensitive neural networks with methods addressing the class imbalance problem ［J］. IEEE Transactions on Knowledge and Data Engineering, 2006,18(1):63-77.
［8］LEI Z, ZHANG S, XUE Z. Classification method for imbalanced data based on spherical boundary ［J］. Journal of Computer Applications, 2008,28(4):866-868 (雷治军,张素玲,薛贞霞.基于球边界的不平衡数据分类方法［J］.计算机应用,2008,28(4):866-868.)
［9］CHAWLA N V, LAZAREVIC A, HALL L O, et al. SMOTEBoost: improving prediction of the minority class in boosting ［C］// Proceedings of the 7th European Conference on Principles and Practice of Knowledge Discovery in Database. Berlin: Springer-Verlag, 2003:107-119.
［10］GUO H, VIKTOR H L. Learning from imbalanced data sets with boosting and data generation: the databoost-IM approach ［J］. ACM SIGKDD Explorations Newsletter, 2004,6(1):30-39.
［11］LI X, LI J, DONG Y, et al. A new learning algorithm for imbalanced data—PCBoost ［J］.Chinese Journal of Computers, 2012,35(2):202 -209. (李雄飞,李军, 董元方,等.一种新的不平衡数据学习算法PCBoost［J］.计算机学报,2012,35(2):202-209.)
［12］DANG C, ZHANG J, SHEN Z. Traffic incidents detection based on Boosting method and RBF neural network ［J］. Journal of Computer Applications, 2007,27(12):3105-3107. (党长青,张景辉,沈志远.基于Boosting算法和RBF神经网络的交通事件检测［J］.计算机应用,2007,27(12):3105-3107.)
［13］TING K M. A comparative study of cost-sensitive boosting algorithms ［C］// Proceedings of the 17th International Conference on Machine Learning. San Francisco: Morgan Kaufmann Publishers, 2000:983-990.
［14］KIM J-K, ZHANG B-T. Evolving hypernetworks for pattern classification ［C］// Proceedings of the 2007 IEEE Congress on Evolutionary Computation. Piscataway: IEEE Press, 2007:25-28.
［15］LIU 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.
［16］TANG Y, ZHANG Y-Q, CHAWLA N V, et al. SVMs modeling for highly imbalanced classification ［J］. IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics, 2009,39(1): 281-288.
［17］WU G, CHANG E Y. KBA: kernel boundary alignment considering imbalanced data distribution ［J］. IEEE Transactions on Knowledge and Data Engineering, 2005,17(6):786-795.
［18］LIU X-Y, WU J, ZHOU Z-H. Exploratory undersampling for class-imbalance learning ［J］. IEEE Transactions on Systems, Man and Cybernetics, Part B: Cybernetics, 2009,39(2):539-550 .

[1]	吕乐张博瀚荆军昌刘栋. 基于持久性的多目标节点隐藏方法[J]. 《计算机应用》唯一官方网站, 0, (): 0-0.
[2]	宫智宇王士同. 面向重尾噪声图像分类的残差网络学习方法[J]. 《计算机应用》唯一官方网站, 0, (): 0-0.
[3]	王虎王晓峰李可马云洁. 融合多头自注意力的标签语义嵌入联邦类增量学习方法[J]. 《计算机应用》唯一官方网站, 0, (): 0-0.
[4]	丁建立, 黄辉, 曹卫东. 航班链运行状态动态监控方法[J]. 《计算机应用》唯一官方网站, 2024, 44(12): 3941-3948.
[5]	刘晶鑫, 黄雯静, 徐亮胜, 黄冲, 吴建生. 字典学习与样本关联保持结合的无监督特征选择模型[J]. 《计算机应用》唯一官方网站, 2024, 44(12): 3766-3775.
[6]	宋逸飞, 柳毅. 基于数据增强和标签噪声的快速对抗训练方法[J]. 《计算机应用》唯一官方网站, 2024, 44(12): 3798-3807.
[7]	沈嫣然, 温昕, 张瑾昊, 张帅, 曹锐, 高保禄. 轻量级多尺度卷积网络的功能磁共振成像脑龄预测模型[J]. 《计算机应用》唯一官方网站, 2024, 44(12): 3949-3957.
[8]	张祖篡, 陈学斌, 高瑞, 邹元怀. 基于标签分类的联邦学习客户端选择方法[J]. 《计算机应用》唯一官方网站, 2024, 44(12): 3759-3765.
[9]	蒋权黄文清苟志勇. 基于等变图神经网络的拉格朗日粒子流模拟[J]. 《计算机应用》唯一官方网站, 0, (): 0-0.
[10]	李岚皓严皓钧周号益孙庆赟李建欣. 基于神经网络的多尺度信息融合时间序列长期预测模型[J]. 《计算机应用》唯一官方网站, 0, (): 0-0.
[11]	廖炎华鄢元霞潘文林. 基于YOLOv9的交通路口图像的多目标检测算法[J]. 《计算机应用》唯一官方网站, 0, (): 0-0.
[12]	张学飞张丽萍闫盛侯敏赵宇博. 知识图谱与大语言模型协同的个性化学习推荐[J]. 《计算机应用》唯一官方网站, 0, (): 0-0.
[13]	索晋贤张丽萍闫盛王东奇张雅雯. 可解释的深度知识追踪方法综述[J]. 《计算机应用》唯一官方网站, 0, (): 0-0.
[14]	陈丹阳张长伦. 多尺度去相关的图卷积网络[J]. 《计算机应用》唯一官方网站, 0, (): 0-0.
[15]	蒋沛宇王永光任亚亭李硕晨谭火彬. 基于测量不确定度表示指南的目标检测不确定度测量方案[J]. 《计算机应用》唯一官方网站, 0, (): 0-0.

用于不平衡数据分类的代价敏感超网络算法

Cost-sensitive hypernetworks for imbalanced data classification

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics