基于模型过滤的多任务回归在帕金森症预测中的应用

doi:10.11772/j.issn.1001-9081.2018041329

计算机应用 ›› 2018, Vol. 38 ›› Issue (11): 3221-3224.DOI: 10.11772/j.issn.1001-9081.2018041329

• 第七届中国数据挖掘会议(CCDM 2018) • 上一篇下一篇

基于模型过滤的多任务回归在帕金森症预测中的应用

刘峰¹, 季薇¹, 李云²

1. 南京邮电大学通信与信息工程学院, 南京 210003;
2. 南京邮电大学计算机学院, 南京 210023

收稿日期:2018-04-30 修回日期:2018-06-21 出版日期:2018-11-10 发布日期:2018-11-10
通讯作者: 刘峰
作者简介:刘峰(1990-),男,江苏泰州人,硕士研究生,主要研究方向:机器学习、数据挖掘;季薇(1979-),女,江苏淮安人,副教授,博士,主要研究方向:信号处理、机器学习;李云(1974-),安徽芜湖人,教授,博士,CCF会员,主要研究方向:机器学习、数据挖掘、模式识别。
基金资助:
国家自然科学基金资助项目（61603197，61772284，41571389）；南京邮电大学科研基金资助项目（NY215104）。

Prediction of Parkinson’s disease based on multi-task regression of model filtering

LIU Feng¹, JI Wei¹, LI Yun²

1. College of Telecommunications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing Jiangsu 210003, China;
2. College of Computer Science and Technology, Nanjing University of Posts and Telecommunications, Nanjing Jiangsu 210023, China

Received:2018-04-30 Revised:2018-06-21 Online:2018-11-10 Published:2018-11-10
Supported by:
This work is partially supported by the National Natural Science Foundation of China (61603197,61772284,41571389), the Nangjing University of Posts and Telecommunications Fund (NY215104).

摘要/Abstract

摘要： 传统基于语音的帕金森症（PD）病情预测方法则是分别预测运动症状评分（motor-UPDRS）和总体症状评分（total-UPDRS）。为解决在单任务预测过程中，传统方法无法利用任务之间的共享信息和预测性能不佳的问题，提出了一种基于模型过滤的多任务回归方法来预测帕金森症患者的motor-UPDRS和total-UPDRS。首先，考虑到子任务语音特征对预测motor-UPDRS和total-UPDRS不同的影响，添加L1正则化项进行特征选择；其次，在构建模型的同时，根据不同帕金森患者对象分布在不同的域，添加了过滤机制，来提高预测精度。在远程帕金森数据集仿真实验中，基于模型过滤的多任务回归方法在预测UPDRS时，较单任务条件下最小二乘法（LS）模型预测motor值准确度提高了67.2%，预测total值则提高了83.3%；相比单任务条件下决策回归树（CART）模型预测motor值提高了64%，预测total值则提高了78.4%。实验结果表明，基于模型过滤的多任务回归算法对UPDRS预测要优于单任务回归算法。

关键词: 帕金森症, 语音, 多任务回归, 模型过滤, 特征选择, 统一帕金森评定量表

Abstract: The traditional speech-based Parkinson's Disease (PD) prediction method is to predict the motor Unified Parkinson's Disease Rating Scale (motor-UPDRS) and the total Unified Parkinson's Disease Rating Scale (total-UPDRS) respectively. In order to solve the problem that the traditional method could not use the shared information between tasks and the poor prediction performance in the process of single task prediction, a multi-task regression method based on model filtering was proposed to predict the motor-UPDRS and total-UPDRS of Parkinson's disease patients. Firstly, considering the different effects of the subtask speech features on the predicted motor-UPDRS and total-UPDRS, an L1 regularization term was added for feature selection. Secondly, according to different Parkinson's patient objects distributed in different domains, a filtering mechanism was added to improve the prediction accuracy. In the simulation experiments of remote Parkinson data set, the Mean Absolute Error (MAE) of motor-UPDRS is 67.2% higher than that of the Least Squares (LS) method. Compared with the Classification And Regression Tree (CART) in the single task, the motor value increased by 64% and the total value increased by 78.4%. The results of experiment show that multi-task regression based on model filtering is superior to the single task regression algorithm for UPDRS prediction.

Key words: Parkinson's Disease (PD), speech, multi-task regression, model filtering, feature selection, unified Parkinson's disease rating scale

中图分类号:

TP391

刘峰, 季薇, 李云. 基于模型过滤的多任务回归在帕金森症预测中的应用[J]. 计算机应用, 2018, 38(11): 3221-3224.

LIU Feng, JI Wei, LI Yun. Prediction of Parkinson’s disease based on multi-task regression of model filtering[J]. Journal of Computer Applications, 2018, 38(11): 3221-3224.

参考文献

[1] de RIJK M C, LAUNER L J, BERGER K, et al. Prevalence of Parkinson's disease in Europe:a collaborative study of population-based cohorts[J]. Neurology, 2000, 54(5):21-23.
[2] HO A K, IANSEK R, MARIGLIANI C, et al. Speech impairment in a large sample of patients with Parkinson's disease[J]. Behavioural Neurology, 1998, 11(3):131-137.
[3] ABDULLAH R, BASAK I, PATIL K, et al. Parkinson's disease and age:the obvious but largely unexplored link[J]. Experimental Gerontology, 2015, 68:33-38.
[4] AICH S, YOUNGA K, HUI K L, et al. A nonlinear decision tree based classification approach to predict the Parkinson's disease using different feature sets of voice data[C]//Proceedings of the 201820th International Conference on Advanced Communication Technology. Piscataway, NJ:IEEE, 2018:638-642.
[5] OUNG Q W, HARIHARAN M, LEE H L. Objective assessment of Parkinson's disease symptoms severity:a review[C]//Proceedings of the 20152nd International Conference on Biomedical Engineering. Piscataway, NJ:IEEE, 2015:1-6.
[6] TSANAS A, LITTLE M A, McSHARRY P E, et al. Nonlinear speech analysis algorithms mapped to a standard metric achieve clinically useful quantification of average Parkinson's disease symptom severity[J]. Journal of the Royal Society Interface, 2011, 8(59):842-855.
[7] HO A K, IANSEK R, MARIGLIANI C, et al. Speech impairment in a large sample of patients with Parkinson's disease[J]. Behavioural Neurology, 1998, 11(3):131-137.
[8] GOETZ C G, STEBBINS G T, WOLFF D, et al. Testing objective measures of motor impairment in early Parkinson's disease:Feasibility study of an at-home testing device[J]. Movement Disorders Official Journal of the Movement Disorder Society, 2009, 24(4):551-556.
[9] TSANAS A. Accurate telemonitoring of Parkinson’s disease symptom severity using nonlinear speech signal processing and statistical machine learning[D]. Oxford: University of Oxford, 2012.
[10] LITTLE M A, MCSHARRY P E, HUNTER E J, et al. Suitability of dysphonia measurements for telemonitoring of Parkinson’s disease[J]. IEEE Transactions on Biomedical Engineering, 2009, 56(4): 1015-1022.
[11] 汪学明, 季薇. 基于语音的帕金森病诊断和判决方案设计[D]. 南京: 南京邮电大学,2017.(WANG X M, JI W. Parkinson’s disease diagnosis and judgment based on speech[D]. Nanjing: Nanjing University of Posts and Telecommunications, 2017.)
[12] ATHANASIOS T, LITTLE M A, MCSHARRY P E, et al. Accurate telemonitoring of Parkinson’s disease progression by noninvasive speech tests.[J]. IEEE Transactions on Bio-Medical Engineering, 2010, 57(4):884-893.
[13] 史荧中,汪菊琴,许敏,等.正则化多任务学习的快速算法[J].计算机科学与探索,2017,11(6):988-997.(SHI Y Z, WANG J Q, XU M, et al. Fast algorithm for regularized multi-task learning[J]. Journal of Frontiers of Computer Science and Technology, 2017, 11(6):988-997.)
[14] ZHUANG F, LUO P, XIONG H, et al. Cross-domain learning from multiple sources: a consensus regularization perspective[J]. IEEE Transactions on Knowledge and Data Engineering, 2010, 22(12): 1664-1678.
[15] EVGENIOU T, PONTIL M. Regularized multi-task learning[C]// Proceedings of the 10th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 2004: 109-117.
[16] LI Y, LI T, LIU H. Recent advances in feature selection and its applications[J]. Knowledge and Information Systems, 2017, 53(3): 551-577.
[17] COMBETTES P L, WAJS V R. Signal recovery by proximal forward-backward splitting[J]. Multiscale Modeling & Simulation, 2005, 4(4): 1168-1200.
[18] BRUCKSTEIN A M, DONOHO D L, ELAD M. From sparse solutions of systems of equations to sparse modeling of signals and images[J]. SIAM Review, 2009, 51(1): 34-81.

基于模型过滤的多任务回归在帕金森症预测中的应用

Prediction of Parkinson’s disease based on multi-task regression of model filtering

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

[1]	湛航, 何朗, 黄樟灿, 李华峰, 张蔷, 谈庆. 改进的基于层次距离的基因表达式编程特征选择分类算法[J]. 计算机应用, 2021, 41(9): 2658-2667.
[2]	徐丽云, 闫涛, 钱宇华. 基于级联混沌系统的分数域语音加密算法[J]. 计算机应用, 2021, 41(9): 2623-2630.
[3]	祝承, 赵晓琦, 赵丽萍, 焦玉宏, 朱亚飞, 陈建英, 周伟, 谭颖. 基于谱聚类半监督特征选择的功能磁共振成像数据分类[J]. 计算机应用, 2021, 41(8): 2288-2293.
[4]	李蒙蒙, 秦伟, 刘艺, 刁兴春. 结合头脑风暴优化的混合蚁群优化算法[J]. 计算机应用, 2021, 41(8): 2412-2417.
[5]	林筠超, 万源. 基于图结构优化的自适应多度量非监督特征选择方法[J]. 计算机应用, 2021, 41(5): 1282-1289.
[6]	贾鹤鸣, 姜子超, 李瑶, 孙康健. 基于改进斑点鬣狗优化算法的同步优化特征选择[J]. 计算机应用, 2021, 41(5): 1290-1298.
[7]	任奕茗, 王让定, 严迪群, 林昱臻. 基于深度残差网络的语音隐写分析方法[J]. 计算机应用, 2021, 41(3): 774-779.
[8]	张志浩, 林耀进, 卢舜, 郭晨, 王晨曦. 缺失标记下基于类属属性的多标记特征选择[J]. 计算机应用, 2021, 41(10): 2849-2857.
[9]	顾桐, 许国良, 李万林, 李家浩, 王志愿, 雒江涛. 基于集成LightGBM和贝叶斯优化策略的房价智能评估模型[J]. 计算机应用, 2020, 40(9): 2762-2767.
[10]	黄学雨, 徐浩特, 陶剑文. 具有特征选择的多源自适应分类框架[J]. 计算机应用, 2020, 40(9): 2499-2506.
[11]	龙超, 曾庆宁, 罗瀛. 基于噪声抵消与波束形成的小阵语音增强[J]. 计算机应用, 2020, 40(8): 2386-2391.
[12]	刘丹, 姚立霜, 王云锋, 裴作飞. 面向类不平衡流量数据的分类模型[J]. 计算机应用, 2020, 40(8): 2327-2333.
[13]	肖跃雷, 张云娇. 基于特征选择和超参数优化的恐怖袭击组织预测方法[J]. 计算机应用, 2020, 40(8): 2262-2267.
[14]	陈修凯, 陆志华, 周宇. 基于卷积编解码器和门控循环单元的语音分离算法[J]. 计算机应用, 2020, 40(7): 2137-2141.
[15]	汪志远, 降爱莲, 奥斯曼·穆罕默德. 基于正则互表示的无监督特征选择方法[J]. 计算机应用, 2020, 40(7): 1896-1900.