一种基于旋转森林的甲状腺疾病分类方法

doi:10.3969/j.issn.1006-2475.2016.03.003

计算机与现代化

一种基于旋转森林的甲状腺疾病分类方法

(东华大学计算机科学与技术学院，上海 201620)

收稿日期:2015-11-13 出版日期:2016-03-17 发布日期:2016-03-17
作者简介:潘乔（1977-），男，陕西汉中人，东华大学计算机科学与技术学院副教授，博士，研究方向：数据挖掘，网络性能分析; 许腾（1990-），男，江苏徐州人，硕士研究生，研究方向：数据挖掘; 陈德华（1976-），男，福建福州人，副教授，博士，研究方向：数据库，数据仓库与智慧医疗; 徐光伟（1969-），男，湖南衡阳人，副教授，博士，研究方向：无线传感网络。
基金资助:
上海市自然科学基金资助项目(15ZR1400900); 上海市科委科技创新行动计划项目(13511504905)

A Classification Method of Thyroid Disease Based on Rotation Forest

(School of Computer Science and Technology, Donghua University, Shanghai 201620, China)

Received:2015-11-13 Online:2016-03-17 Published:2016-03-17

摘要/Abstract

摘要： 甲状腺疾病是内分泌领域的常见疾病，准确识别不同类型的甲状腺疾病是临床医疗诊断中的首要问题。针对甲状腺检测指标数据，提出一种新的甲状腺疾病分类方法，该方法首先采用主成分分析法对数据集进行特征选择，降低数据维度，然后基于旋转森林集成分类算法实现分类。旋转森林算法使基分类器的差异性更加明显，进而提高分类器的精度，同时可以减少处理时间。实验中，同时分析了UCI标准数据集和真实临床医疗数据集，结果表明该方法的分类准确率分别可以达到96.28%和96.37%。

关键词: 甲状腺疾病, 集成分类, 旋转森林, 特征选择, 主成分分析

Abstract: Thyroid disease is common in the field of endocrine, accurate identification of different types of thyroid disease is the primary problem of clinical treatment. By using the results of clinical experiments, this paper presents a new method for thyroid disease classification. The method uses principal component analysis to reduce data dimension, and then implements classification task based on rotation forest algorithm. Rotation forest algorithm can make the difference between the base classifiers more obvious, and then improve the accuracy of the classifier, and it can reduce the processing time at the same time. Experimental results show that the classification accuracy of this method can reach to 96.28% on the dataset from UCI machine learning repository. In order to verify the effectiveness of the method furthermore, this paper also chooses the real clinical medical data set, it is more complex than the UCI standard dataset in data quantity and data dimension. Compared with the other method, the classification accuracy of this method reaches to 96.37%.

Key words: thyroid disease, ensemble classification, rotation forest, feature selection, principal component analysis

中图分类号:

TP391

潘乔，许腾，陈德华，徐光伟. 一种基于旋转森林的甲状腺疾病分类方法[J]. 计算机与现代化, doi: 10.3969/j.issn.1006-2475.2016.03.003.

PAN Qiao, XU Teng, CHEN De-hua, XU Guang-wei. A Classification Method of Thyroid Disease Based on Rotation Forest[J]. Computer and Modernization, doi: 10.3969/j.issn.1006-2475.2016.03.003.

参考文献

[1] 刘丽华,杜双迎,许秉权. 甲状腺疾病的最新实验室诊断指标及各诊断指标的相关性[J]. 中国民康医学, 2013,25(3):62-63.

[2] Ozyilmaz L, Yildirim T. Diagnosis of thyroid disease using artificial neural network methods[C]// Proceedings of the 9th International Conference on Neural Information Processing. 2002,4:2033-2036.

[3] Temurtas F. A comparative study on thyroid disease diagnosis using neural networks[J]. Expert Systems with Applications, 2009,36(1):944-949.

[4] Isa I S, Saad Z, Omar S, et al. Suitable MLP network activation functions for breast cancer and thyroid disease detection[C]// Proceedings of the 2nd International Conference on Computational Intelligence, Modelling and Simulation. 2010:39-44.

[5] Keles Ali, Keles Aytürk. ESTDD: Expert system for thyroid diseases diagnosis[J]. Expert Systems with Applications, 2008,34(1):242-246.

[6] Uğuz H. A two-stage feature selection method for text categorization by using information gain, principal component analysis and genetic algorithm[J]. Knowledge-based Systems, 2011,24(7):1024-1032.

[7] Valle S, Li Weihua, Qin S J. Selection of the number of principal components: The variance of the reconstruction error criterion with a comparison to other methods[J]. Industrial & Engineering Chemistry Research, 1999,38(11):4389-4401.

[8] Jolliffe I T. Principal Component Analysis[M]. Springer Verlag, 1986:1-47.

[9] Webb G I. Decision tree grafting from the all tests but one partition[C]// Proceedings of the 16th International Joint Conference on Artificial Intelligence. 1999:702-707.

[10] Rodriguez J J, Kuncheva L I, Alonso C J. Rotation forest: A new classifier ensemble method[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2006,28(10):1619-1630.

[11] 韩敏,刘贲. 一种改进的旋转森林分类算法[J]. 电子与信息学报, 2013,35(12):2896-2900.

[12] 毛莎莎,熊霖,焦李成,等. 利用旋转森林变换的异构多分类器集成算法[J]. 西安电子科技大学学报(自然科学版), 2014,41(5):48-53.

[13] Breiman L. Bagging predictors[J]. Machine Learning, 1996,24(2):123-140.

[14] Freund Y, Schapire R E. Experiments with a new boosting algorithm[C]// Proceedings of the 13th International Conference on Machine Learning. 1996:148-156.

[15] Breiman L. Random forests[J]. Machine Learning, 2001,45(1):5-32.

[16] UCI Machine Learning Repository. Thyroid Disease Data Set[DB/OL]. https://archive.ics.uci.edu/ml/datasets/Thyroid+Disease, 1987-01-01.

[17]中华医学会检验分会. 甲状腺疾病诊断治疗中实验室检测项目的应用建议[J]. 中华检验医学杂志, 2012,35(6):484-492.

一种基于旋转森林的甲状腺疾病分类方法

A Classification Method of Thyroid Disease Based on Rotation Forest

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

本文评价

[1]	张亚文, 林文忠, 韩晓东. 基于组合特征点和主成分分析的点云配准算法[J]. 计算机与现代化, 2023, 0(09): 59-63.
[2]	申志, 李元 . 基于KPCA和SSA优化SVM的非线性过程故障检测#br#[J]. 计算机与现代化, 2023, 0(06): 15-20.
[3]	朱卓樾, 黄欢, 宋清玲, 侯居攀. 基于心血管核磁共振图像的房室平面位移检测与重建[J]. 计算机与现代化, 2023, 0(04): 78-82.
[4]	王扬, 陈梅, 李晖. FOCoR:一种基于特征选择优化的课程推荐技术[J]. 计算机与现代化, 2022, 0(10): 1-7.
[5]	赵迎利, 朱旭. 基于组稀疏联合学习的影像遗传学数据关联分析[J]. 计算机与现代化, 2022, 0(08): 43-49.
[6]	莫云. 基于混合特征选择的脑电解码方法[J]. 计算机与现代化, 2022, 0(04): 92-96.
[7]	赵延平, 王芳, 夏杨. 基于支持向量机的短文本分类方法[J]. 计算机与现代化, 2022, 0(02): 92-96.
[8]	张东方, 陈海燕, 袁立罡. S2R2:基于相关性与冗余性分析的半监督特征选择[J]. 计算机与现代化, 2021, 0(09): 113-120.
[9]	代继鹏, 邵峰晶, 孙仁诚. 基于改进CHI和TF-IDF的短文本分类的研究[J]. 计算机与现代化, 2021, 0(06): 6-11.
[10]	陈丝雨, 庄毅, 李静. 基于LSTM网络的移动云计算多元负载预测模型[J]. 计算机与现代化, 2021, 0(06): 74-85.
[11]	黄旭彬, 梁树杰. 基于PCA融合PSO-SVM的运动想象脑电信号分类方法[J]. 计算机与现代化, 2021, 0(03): 70-76.
[12]	杨秋良, 王钰, 杨杏丽, 李济洪. 基于互信息F统计量特征选择技术的地基气象云图分类[J]. 计算机与现代化, 2021, 0(02): 18-23.
[13]	黄欣辰, 皋军, 黄豪杰. 基于PCA降维的成对约束半监督聚类集成[J]. 计算机与现代化, 2021, 0(01): 94-99.
[14]	蒋万明1,2，郭春1,2，蒋朝惠1,2. 一种基于BiLSTM的低速率DDoS攻击检测方法[J]. 计算机与现代化, 2020, 0(05): 120-.
[15]	刘树艺，李静，胡春，王伟. 基于卷积神经网络与集成学习的交通标志识别[J]. 计算机与现代化, 2019, 0(12): 67-.