A Multi-Class Cost Sensitivity AdaBoost Algorithm Using Multi-Class Cost Exponential Loss Function

doi:10.7652/xjtuxb201708006

您当前的位置：

首页 >

文章列表页 >

A Multi-Class Cost Sensitivity AdaBoost Algorithm Using Multi-Class Cost Exponential Loss Function

更新时间：2025-07-09

- A Multi-Class Cost Sensitivity AdaBoost Algorithm Using Multi-Class Cost Exponential Loss Function
- Vol. 51, Issue 8, Pages: 33-39(2017)
- 作者机构：
  
  空军工程大学防空反导学院,西安,710051
- 作者简介：
- 基金信息：
- DOI：10.7652/xjtuxb201708006
  CLC： TP391
- Online First：10 August 2017，
  
  Published：2017
- 稿件说明：
移动端阅览
A Multi-Class Cost Sensitivity AdaBoost Algorithm Using Multi-Class Cost Exponential Loss Function[J]. 2017, 51(8): 33-39.
DOI：

A Multi-Class Cost Sensitivity AdaBoost Algorithm Using Multi-Class Cost Exponential Loss Function[J]. 2017, 51(8): 33-39. DOI： 10.7652/xjtuxb201708006.

摘要

为解决由多个二类代价敏感算法扩展而成的多类算法存在时间复杂度高和不能区分错分代价的问题

提出一种采用多类代价指数损失函数的多类代价敏感AdaBoost算法(MCCSADA)。为保证算法的代价敏感特性

首先设计一种满足代价敏感损失函数设计准则的多类代价敏感指数损失函数; 然后将此损失函数作为评价分类器性能的标准

以最小化损失函数为目的使用逐步叠加模型推导算法的最优基分类器加权系数; 最后使用多类代价损失函数和最优基分类器加权系数求解公式替换多类AdaBoost算法的损失数和加权系数求解公式

得到代价敏感的MCCSADA算法。使用UCI数据集对算法进行验证

实验结果表明:算法的稳定性得到了提升

退化现象被减弱; 相比于由两类代价敏感算法通过一对一方法扩展而来的多类代价敏感算法

MCCSADA算法在大多数情况下能够取得更低的代价

而且具有较低的时间复杂度

在3类数据集上的时间复杂度降低约40%

并且随着类别数的增多效率提升更加明显。

Abstract

A multi-class cost sensitivity AdaBoost algorithm is proposed to solve the problems of high time complexity and indistinguishable cost among different classes in using the existing multi-class algorithm

which is an extension of some binary cost sensitive AdaBoost algorithms. The new algorithm uses a multi-class exponential loss function

and is named as MCCSADA. A cost sensitive multi-class exponential loss function is designed to satisfy design guidelines of cost-sensitive loss function and to ensure the cost-sensitive characteristic. Then

the loss function is used as a criterion for the evaluation of basis classifiers and the optimal weighted coefficients of base classifiers are obtained by using the forward stack model to minimize the cost loss function. Subsequently

MCCSADA is obtained by using the new loss function and weighted coefficients to replace the original loss function and coefficients in AdaBoost algorithm. MCCSADA is verified by using UCI dataset

and the results and a comparison with the CSOVO expanding from binary algorithm show that MCCSADA has lower cost and lower time complexity in most cases. The time complexity reduces by about 40% when the dataset contains three classes and reduces more with increasing number of data categories. Moreover

the stability of the algorithm is promoted

and the degeneration is weakened.

关键词

Keywords

references

LOPEZ V, FERNANDEZ A, MORENO-TORRES J G, et al. Analysis of preprocessing vs. cost-sensitive learning for imbalanced classification [J]. Expert Systems with Applications, 2012, 39(7): 6585-6608.

FREUND Y, SCHAPIRE R E. A decision theoretic generalization of on-line learning and an application to boosting [M]∥ Lecture Notes in Computer Science: Vol 904. Berlin, Germany: Springer Verlag, 1995: 23-37.

TING K M, ZHENG Z. Boosting trees for cost-sensitive classification [M]∥ Lecture Notes in Computer Science: Vol 1398. Berlin, Germany: Springer Verlag, 1999: 190-195.

FAN W, STOLFO S J, ZHANG J, et al. AdaCost: misclassification cost-sensitive boosting [C]∥Proceedings of the 16th International Conference on Machine Learning. San Francisco, CA, USA: Morgan Kaufmann Publishers Inc., 1999: 97-105.

SUN Y, WONG A, WANG Y. Parameter inference of cost-sensitive boosting algorithms [C]∥Proceedings of the 4th International Conference on Machine Learning and Data Mining in Pattern Recognition. Berlin, Germany: Springer-Verlag, 2005: 21-30.

SUN Y, KAMEL M S, WONG A, et al. Cost-sensitive boosting for classification of imbalanced data [J]. Pattern Recognition, 2007, 40(12): 3358-3378.

MASNADI-SHIRAZI H, VASCONCELOS N. Asymmetric boosting [C]∥Proceedings of the 24th International Conference on Machine Learning. San Francisco, CA, USA: Margan Kaufmann Publishers Inc., 2007: 609-619.

MASNADI-SHIRAZI H, VASCONCELOS N. Cost-sensitive boosting [J]. Pattern Analysis and Machine Intelligence, 2010, 33(2): 294-309.

付忠良. 多标签代价敏感分类集成学习算法 [J]. 自动化学报, 2014, 40(6): 1075-1080.

FU Zhongliang. Cost-sensitive ensemble learning algorithm for multi-label classification problems [J]. Acta Auto Matica Sinica, 2014, 40(6): 1075-1080.

付忠良. 多分类代价敏感AdaBoost算法 [J]. 自动化学报, 2011, 37(8): 973-983.

FU Zhongliang. Cost-sensitive AdaBoost algorithm for multi-class classification problems [J]. Acta Auto Matica Sinica, 2011, 37(8): 973-983.

PAN Shirui, WU Jia, ZHU Xingquan. CogBoost: boosting for fast cost-sensitive graph classification [J]. Knowledge and Data Engineering, 2015, 27(11): 2933-2946.

YUAN Xiaohui, MOHAMED A. A multi-class boosting method for learning from imbalanced data [J]. Rough Sets and Intelligent Systems, 2015, 4(1): 13-28.

曹莹, 苗启广, 刘家辰, 等. 具有Fisher一致性的代价敏感Boosting算法 [J]. 软件学报, 2013, 24(11): 2584-2596.

CAO Ying, MIAO Qiguang, LIU Jiacheng, et al. Fisher consistent cost sensitive boosting algorithm [J]. Journal of Software, 2013, 24(11): 2584-2596.

ZHU J, ZOU H, ROSSET S, et al. Multi-class AdaBoost [J]. Statistics and Its Interface, 2009, 2(3): 349-360.

LU Hengyang, CHEN Feiyu, XU Ming, et al. Never ignore the significance of different anomalies: a cost-sensitive algorithm based on loss function for anomaly detection [C]∥Proceedings of the 27th International Conference on Tools with Artificial Intelligence. Piscataway, NJ, USA: IEEE, 2015: 1099-1105.

李秋洁, 赵亚琴, 顾洲. 代价敏感学习中的损失函数设计 [J]. 控制理论与应用, 2015, 32(5): 689-694.

LI Qiujie, ZHAO Yaqin, GU Zhou. Design of loss function for cost-sensitive learning [J]. Control Theory and Applications, 2015, 32(5): 689-694.

付学中,方宗德,关亚彬,等.采用NSGA-Ⅱ算法的面齿轮副小轮拓扑修形多目标优化.2017,51(7):98-104.[doi:10.7652/xjtuxb201707015]

李莉,冯林,吴俊,等.一种三结构描述子的图像检索方法.2017,51(6):86-91.[doi:10.7652/xjtuxb201706014]

杨扬,Chun-Ta LU,王菲菲,等.众筹项目的社交网络影响力预测与分析.2017,51(04):91-96.[doi:10.7652/xjtuxb2017 04014]

张国和,黄凯,张斌,等.最大稳定极值区域与笔画宽度变换的自然场景文本提取方法.2017,51(01):135-140.[doi:10.7652/xjtuxb201701021]

龚春园,梁晋,温广瑞,等.投影仪全参数平面线性估计的高精度标定方法.2016,50(11):36-42.[doi:10.7652/xjtuxb 201611006]

高智勇,董荣光,高建民,等.采用聚类特征的基本概率分配生成方法及应用.2016,50(10):8-14.[doi:10.7652/xjtuxb 201610002]

刘星,梅雪松,陶涛,等.一种零耦合滚齿全误差模型及其预测方法.2016,50(10):42-48.[doi:10.7652/xjtuxb201610 007]

杨源,库涛,查宇飞,等.快速多特征金字塔的尺度目标跟踪方法.2016,50(10):49-56.[doi:10.7652/xjtuxb201610008]

张胜杰,查宇飞,李运强,等.一种利用局部结构信息的加权哈希图像检索算法.2016,50(10):78-85.[doi:10.7652/xjtuxb201610012]

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Research on Railway Track Foreign Object Intrusion Detection Based on Multi-Scale Feature Fusion

Turbulent Kinetic Energy Dissipation Mechanism of Supercritical Carbon Dioxide Leakage Flow in a Scallop Bionic Seal Cavity

Numerical Simulation of the Energy Conversion Process in Thermoacoustic Engines with Different Stack Materials

A Fast Calculation Method for Thermal Flow Fields in Transformer Windings Based on PI-DeepONet

Effects of Expansion Angle Crater Film Hole on the Film Cooling Characteristics of a Double-Wall Structure

Related Author

WANG Nan

HOU Tao

NIU Hongxia

Related Institution

(School of Automation and Electrical Engineering, Lanzhou Jiaotong University,,)

⁰