计算机科学 ›› 2019, Vol. 46 ›› Issue (12): 237-241.doi: 10.11896/jsjkx.181102173
沈先宝, 宋余庆, 刘哲
SHEN Xian-bao, SONG Yu-qing, LIU Zhe
摘要： 针对集成过程中基分类器的集成优先性缺少精确化度量而导致的模型选择严谨性不高、系统精简性设计难以实现的问题,文中提出了一种基于排序选择度量方式、自适应权重设置的集成分类方法。首先,利用K折交叉验证及设计的误差熵与分类器互补性相结合的组合指数度量方法,选出集成优先性最高的两个分类器;然后,通过构造的以组合指数为基础的整体组合指数度量方法,实现对不同模型的优先性排序选择;最后,通过设置自适应权重的方式为不同模型找到最佳权重进行集成分类。在UCI数据集上的实验结果表明,所提方法与其他分类模型相比,各项分类评价指标均有提高,验证了该集成方法的可行性。该方法通过设计的模型选择定量性依据及自适应权重设置机制,使得整个集成分类系统具有模型选择分层性、可自适应精简化的特点。
中图分类号:
| [1]FUMERA G,FABIO R,ALESSANDRA S.A theoretical analysis of bagging as a linear combination of classifiers[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,2008,30(7):1293-1311.[2]FARID D M,AL-MAMUN M A,MANDERICK B,et al.An adaptive rule-based classifier for mining big biological data[J].Expert Systems with Applications,2016,64(C):305-316.[3]KUNCHEVA L I.A theoretical study on six classifier fusion strategies[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,2002,24(2):281-286.[4]CERNADAS E,AMORIM D.Do we need hundreds of classifiers to solve real world classification problems?[J].Journal of Machine Learning Research,2014,15(1):3133-3181.[5]POLIKAR R.Ensemble based systems in decision making[J].IEEE Circuits & Systems Magazine,2006,6(3):21-45.[6]JR A S B,SABOURIN R,OLIVEIRA L E S.Dynamic selection of classifiers－A comprehensive review[J].Pattern Recognition,2014,47(11):3665-3680.[7]RAYHAN F,AHMED S,SHATABDA S,et al.iDTI-ESBoost:Identification of Drug Target Interaction Using Evolutionary and Structural Features with Boosting[J].Scientific Reports,2017,7(1):17731.[8]CHITROUB S.Classifier combination and score level fusion: concepts and practical aspects[J].International Journal of Image and Data Fusion,2010,1(2):113-135.[9]LIN C,CHEN W,QIU C,et al.LibD3C:Ensemble classifiers with a clustering and dynamic selection strategy[J].Neurocomputing,2014,123(1):424-435.[10]CRUZ R M O,SABOURIN R,CAVALCANTI G D C.Analyzing different prototype selection techniques for dynamic classifier and ensemble selection[C]//International Joint Conference on Neural Networks.Anchorage,AK,USA:IEEE,2017:3959-3966.[11]DE SOUTO M C P,SOARES R G F,SANTANA A,et al.Empirical comparison of Dynamic Classifier Selection methods based on diversity and accuracy for building ensembles[C]//IEEE International Joint Conference on Neural Networks.Hong Kong,China:IEEE,2008:1480-1487.[12]CRUZ R M O,SABOURIN R,CAVALCANTI G D C.Prototype selection for dynamic classifier and ensemble selection[J].Neural Computing & Applications,2016,29(2):1-11.[13]FARID D M,ZHANG L,RAHMAN C M,et al.Hybrid decision tree and naive Bayes classifiers for multi-class classification tasks[J].Expert Systems with Applications An International Journal,2014,41(4):1937-1946.[14]SUN Z,SONG Q,ZHU X,et al.A novel ensemble method for classifying imbalanced data[J].Pattern Recognition,2015,48(5):1623-1637.[15]BRUN A L,JR A S B,OLIVEIRA L S,et al.Contribution of Data Complexity Features on Dynamic Classifier Selection[C]//International Joint Conference on Neural Networks.Vancouver,BC,Canada:IEEE,2016:4396-4403.[16]CRUZ R M O,SABOURIN R,CAVALCANTI G D C.On Meta-learning for Dynamic Ensemble Selection[C]//International Conference on Pattern Recognition.Stockholm,Sweden:IEEE Computer Society,2014:1230-1235.[17]PINTO F,SOARES C,MENDES-MOREIRA J.CHADE:Metalearning with Classifier Chains for Dynamic Combination of Classifiers[M]//Machine Learning and Knowledge Discovery in Databases.Springer International Publishing,2016:410-425.[18]CRUZ R M O,SABOURIN R,CAVALCANTI G D C.META-DES.Oracle:Meta-learning and feature selection for dynamic ensemble selection[J].Information Fusion,2017,38(1):84-103.[19]XIAO Z H,YU H,WANG Y C.Unsupervised Machine Learning Based on the Sun of Squares of the Dynamic Deviations.Journal of Chongqing University of Technology(Natural Science),2018,32(11):134-139,186.(in Chinses) 肖枝洪,于浩,王一超.基于动态离差平方和准则的无监督机器学习.重庆理工大学学报(自然科学),2018,32(11):134-139,186. |
| [1] | 赵亮, 张洁, 陈志奎. 基于双图正则化的自适应多模态鲁棒特征学习 Adaptive Multimodal Robust Feature Learning Based on Dual Graph-regularization 计算机科学, 2022, 49(4): 124-133. https://doi.org/10.11896/jsjkx.210300078 |
| [2] | 曹林, 于威威. 基于图像分割的自适应窗口双目立体匹配算法研究 Adaptive Window Binocular Stereo Matching Algorithm Based on Image Segmentation 计算机科学, 2021, 48(11A): 314-318. https://doi.org/10.11896/jsjkx.201200264 |
| [3] | 程中建, 周双娥, 李康. 基于多尺度自适应权重的稀疏表示目标跟踪算法 Sparse Representation Target Tracking Algorithm Based on Multi-scale Adaptive Weight 计算机科学, 2020, 47(6A): 181-186. https://doi.org/10.11896/JsJkx.190500093 |
| [4] | 杨婷, 罗飞, 丁炜超, 卢海峰. 一种自适应优化松弛量的装箱算法 Bin Packing Algorithm Based on Adaptive Optimization of Slack 计算机科学, 2020, 47(4): 211-216. https://doi.org/10.11896/jsjkx.190500132 |
| [5] | 赵青杰, 李捷, 于俊洋, 吉宏远. 基于动态自适应权重和柯西变异的蝙蝠优化算法 Bat Optimization Algorithm Based on Dynamically Adaptive Weight and Cauchy Mutation 计算机科学, 2019, 46(6A): 89-92. |
| [6] | 王慧研,张腾飞,马福民. 基于空间距离自适应权重度量的粗糙K-means算法 Rough K-means Algorithm with Self-adaptive Weights Measurement Based on Space Distance 计算机科学, 2018, 45(7): 190-196. https://doi.org/10.11896／j.issn.1002-137X.2018.07.033 |
| [7] | 廖星,袁景凌,陈旻骋. 一种自适应权重的并行PSO快速装箱算法 Parallel PSO Container Packing Algorithm with Adaptive Weight 计算机科学, 2018, 45(3): 231-234. https://doi.org/10.11896/j.issn.1002-137X.2018.03.036 |
| [8] | 张春云,秦鹏达,尹义龙. 基于卷积神经网络的自适应权重multi-gram语句建模系统 Self-adaptation Multi-gram Weight Learning Strategy for Sentence Representation Based on Convolutional Neural Network 计算机科学, 2017, 44(1): 60-64. https://doi.org/10.11896/j.issn.1002-137X.2017.01.011 |
| [9] | 郭京蕾,李伟,金聪. 基于中心块的多特征自适应图像检索算法 Adaptive Image Retrieval Algorithm with Multi-feature of Center Block 计算机科学, 2016, 43(6): 65-67. https://doi.org/10.11896/j.issn.1002-137X.2016.06.013 |
| [10] | 周 杨，苗夺谦，岳晓冬. 基于自适应权重的粗糙K均值聚类算法 Rough K-means Clustering Based on Self-adaptive Weights 计算机科学, 2011, 38(6): 237-241. |
| [11] | 薛卫,都思丹,叶迎宪. 小波变分辨率频谱特征静音检测和短时自适应混音算法 Voice Activity Detection Using Wavelets Multiresolution Spectrum and Short-time Adaptive Audio Mixing Algorithm 计算机科学, 2009, 36(7): 211-214. https://doi.org/10.11896/j.issn.1002-137X.2009.07.051 |
| [12] | 吴帆 叶懋 陈贵海. 广域网虚拟平台：网格计算和对等计算的融合 计算机科学, 2005, 32(5): 23-26. |
|
||
首页