期刊文献+

基于加权软投票融合模型的脉象信号识别研究 被引量:1

Research on Pulse Signal Recognition Based on Weighted Soft Voting Fusion Model
在线阅读 下载PDF
导出
摘要 目的脉象识别是中医客观化、智能化的重要组成部分,这种无创、快速的诊断方法具有巨大的临床价值,然而数据不平衡和特征提取繁杂仍是具有挑战性的问题。方法利用tsfresh库对巴特沃兹带通滤波器后的一维脉象信号提取特征向量,并加入探索性数据分析所选出的9列医学辅助特征,共同进行特征筛选得出21列特征向量作为加权软投票融合模型的输入。通过边界合成少数类样本过采样技术,解决数据不平衡问题,构建基于XGBoost、随机森林、LightGBM、梯度提升决策树4种机器学习的加权软投票融合模型,最终模型将输出具体脉象类别,通过评价指标准确率、精确率、召回率和F1分数进行性能展示。结果实验结果表明,所筛选出的21项特征向量共六类脉象信号测试集,在五折交叉验证中取得准确率90.04%,且仅耗时65.9466 s。结论本论文能为脉象信号识别提供更精准、更智能的辅助参考,与常用脉象识别方法相比有更低的操作复杂性和更高的准确率,较短的训练时间也使其在多种类脉象信号识别中更具临床实用价值。 Pulse recognition is an important part of the objectification and intelligence of TCM.This non-invasive and fast diagnostic method has great clinical value,however,data imbalance and cumbersome feature extraction are still challenging problems.The feature vectors were extracted from the one-dimensional pulse signal obtained after the Butterworth bandpass filter using the tsfresh library.And 9 columns of medical auxiliary features selected by exploratory data analysis were added.The feature filtering is performed jointly to derive 21 columns of feature vectors,which are used as input to the weighted soft voting fusion model.The data imbalance problem is solved by Borderline SMOTE algorithm.Construct a weighted soft-voting fusion model based on four types of machine learning:XGBoost,RF,LGBM,and GBDT.Eventually,the models will output specific pulse categories and demonstrate the performance by evaluating the metrics accuracy,precision,recall and F1 score.The experimental results show that the screened 21 feature vectors for a total of six types of pulse signal test sets achieve an accuracy of 90.04%in the five-fold cross-validation and take only 65.9466 seconds.It can provide a more accurate and intelligent auxiliary reference for pulse signal recognition,with lower operational complexity and higher accuracy compared to commonly used pulse recognition methods.The shorter training time also makes it more clinically useful in the recognition of multiple pulse signals.
作者 刘启超 徐红 林卓胜 朱嘉健 刘慧琳 吴欣 冯跃 Liu Qichao;Xu Hong;Lin Zhuosheng;Zhu Jiajian;Liu Huilin;Wu Xin;Feng Yue(Intelligent Manufacturing Department,Wuyi University,Jiangmen 529020,China;Institute for Sustainable Industry and Liveable Cities,Victoria University,Melbourne 8001,Australia;Teaching Experiment Center,Shanghai University of Traditional Chinese Medicine,Shanghai 201203,China)
出处 《世界科学技术-中医药现代化》 CSCD 北大核心 2023年第8期2883-2891,共9页 Modernization of Traditional Chinese Medicine and Materia Medica-World Science and Technology
基金 广东省普通高校重点领域专项项目(2021ZDZX1032):元学习在中医诊断五脏状态的应用,负责人:冯跃 广东省国际及港澳台高端人才交流专项(2020A1313030021):智能中医诊断应用研究,负责人:冯跃 五邑大学科研项目(2018TP023):人工智能中医望诊研究,负责人:徐红。
关键词 脉象识别 数据不平衡 加权软投票融合模型 特征提取 机器学习 Pulse recognition Data imbalance Weighted soft voting fusion model Feature extraction Machine learning
作者简介 通讯作者:冯跃,博士,教授,研究生导师,主要研究方向:计算机视觉与生物特征识别。
  • 相关文献

参考文献9

二级参考文献82

共引文献121

同被引文献15

引证文献1

二级引证文献1

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部