一种改进的字典学习方法在医疗疾病分析中的应用

doi:10.16180/j.cnki.issn1007-7820.2019.02.010

电子科技 ›› 2019, Vol. 32 ›› Issue (2): 47-50.doi: 10.16180/j.cnki.issn1007-7820.2019.02.010

一种改进的字典学习方法在医疗疾病分析中的应用

骆冲,邬春学

上海理工大学光电信息与计算机工程学院, 上海 200093

收稿日期:2018-01-18 出版日期:2019-02-15 发布日期:2019-01-02
作者简介:骆冲(1991-),男,硕士研究生。研究方向:大数据,机器学习,无线传感网等。|邬春学(1964-),男,教授。研究方向:无线传感网,分布式和嵌入式系统,物联网等。
基金资助:
上海市科学计划项目(16111107502);上海市科学计划项目(17511107203)

An Improved Dictionary Learning Method for Medical Disease Analysis

LUO Chong,WU Chunxue

School of Optical Electrical & Computer Engineering,University of Shanghai for Science & Technology,Shanghai 200093,China

Received:2018-01-18 Online:2019-02-15 Published:2019-01-02
Supported by:
Shanghai Science and Technology Innovation Action Plan Project(16111107502);Shanghai Science and Technology Innovation Action Plan Project(17511107203)

摘要/Abstract

摘要：

针对传统字典学习算法忽略样本与字典原子之间关联信息及有限的训练集容易出现过拟合的现象,文中提出了通过加权机制及二范数约束的方法,建立样本与字典原子之间的权重关系,并对编码系数用二范数进行约束。采用留一交叉验证法在抑郁症数据集上比较了算法的精确度、灵敏度和错误率等指标。实验结果表明,改进的算法在医疗疾病分类中有良好的效果,分类精确度平均提高了21.87%,灵敏度和错误率等方面也有良好的表现。

关键词: 医疗大数据, 字典学习, 稀疏表示, 疾病分类, 加权机制, 范式约束

Abstract:

This paper proposed the weighted mechanism to combine the sample with the dictionary atom based on the traditional dictionary learning algorithm, which ignored the relationship between the sample and the dictionary atom. At the same time, the l₂ norm regularization constraint was adopted to avoid over fitting on coding coefficients. The paper used the leave one out cross validation to compare the accuracy, sensitivity and mean error rate of the algorithm in the depression data sets. The results showed that the improved method had a good effect on the medical disease classification. The average classification accuracy was improved by 21.87%, and the sensitivity and mean error rate also displayed good performance.

Key words: medical big data, dictionary learning, sparse representation, disease classification, weighted mechanism, paradigm constraint

中图分类号:

TP301.6

骆冲,邬春学. 一种改进的字典学习方法在医疗疾病分析中的应用[J]. 电子科技, 2019, 32(2): 47-50.

LUO Chong,WU Chunxue. An Improved Dictionary Learning Method for Medical Disease Analysis[J]. Electronic Science and Technology, 2019, 32(2): 47-50.

图/表 4

参考文献 20

[1]	Ali A, Qadir J, Rasool R , et al. Big data for development: applications and techniques[J]. Big Data Analytics, 2016,1(1):2-9. doi: 10.1186/s41044-016-0002-4
[2]	Raham R D, Goldston D, Doctorow C , et al. Big data: science in the petabyte era[J]. Nature, 2008,455(7209):8-9. doi: 10.1038/455008a
[3]	Manyika J, Chui M, Brown B , et al. Big data:the next frontier for innovation, competition, and productivity[J]. Analytics, 2011(9):832-849.
[4]	Siuly S, Zhang Y . Medical big data: neurological diseases diagnosis through medical data analysis[J]. Data Science and Engineering, 2016,1(2):54-64. doi: 10.1007/s41019-016-0011-3
[5]	Suk H I, Lee S W, Shen D . Deep sparse multi-task learning for feature selection in Alzheimer's disease diagnosis[J]. Brain Structure & Function, 2016,221(5):2569-2587. doi: 10.1007/s00429-015-1059-y pmid: 4714963
[6]	Riaz A, Alonso E, Slabaugh G. Phenotypic integrated framework for classification of ADHD using fMRI[M]. Beylin: Springer International Publishing, 2016.
[7]	Shu Z, Xiang L, Lv J , et al. Characterizing and differentiating task-based and resting state fMRI signals via two-stage sparse representations[J]. Brain Imaging & Behavior, 2016,10(1):21-32. doi: 10.1007/s11682-015-9359-7 pmid: 4559495
[8]	Simsek M, Polat E. The effect of dictionary learning algorithms on super-resolution hyperspectral reconstruction [C].Sarajevo:Xxv International Conference on Information,Communication and Automation Technologies,IEEE, 2015.
[9]	曹蒙蒙, 李新叶, 范月坤 . 基于判别低秩矩阵恢复和稀疏表示的车标识别[J]. 电子科技, 2015,28(4):57-60. doi: 10.16180/j.cnki.issn1007-7820.2015.04.016
	Cao Mengmeng, Li Xinye, Fan Yuekun . Vehicle logo recognition based on discriminative low-rank matrix recovery and sparse representation[J]. Electronic Science and Technology, 2015,28(4):57-60. doi: 10.16180/j.cnki.issn1007-7820.2015.04.016
[10]	Wright J, Yang A Y, Ganesh A , et al. Robust face recognition via sparse representation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009,31(2):210-227. doi: 10.1109/TPAMI.2008.79 pmid: 19110489
[11]	Yang M, Zhang L, Yang J, et al. Metaface learning for sparse representation based face recognition [C].Hong Kong:IEEE International Conference on Image Processing,IEEE, 2010.
[12]	Ramirez Ignacio, Pablo Sprechmann, Guillermo Sapiro . Classification and clustering via dictionary learning with structured incoherence and shared features[C].San Francisco:IEEE Conference on Computer Vision and Pattern Recognition ( CVPR), 2010.
[13]	Zhang Q, Li B . Discriminative K-SVD for dictionary learning in face recognition[C].San Francisco: IEEE Conference on Computer Vision and Pattern Recognition ( CVPR), 2010.
[14]	Khamis H, Zurakhov G, Azar V , et al. Automatic apical view classification of echocardiograms using a discriminative learning dictionary[J]. Medical Image Analysis, 2017,36(8):15-21. doi: 10.1016/j.media.2016.10.007 pmid: 27816858
[15]	Yang M, Zhang L, Feng X , et al. Fisher discrimination dictionary learning for sparse representation[J]. Proceedings, 2012,24(4):543-550. doi: 10.1109/ICCV.2011.6126286
[16]	Tiep H Vu, Mousavi H S, Monga V , et al. Histopathological image classification using discriminative feature-oriented dictionary learning[J]. IEEE Transactions on Medical Imaging, 2016,35(3):738-751. doi: 10.1109/TMI.2015.2493530 pmid: 26513781
[17]	Mairal J, Bach F, Ponce J , et al. Online learning for matrix factorization and sparse coding[J]. Journal of Machine Learning Research, 2010,11(1):19-60. doi: 10.1145/1756006.1756008
[18]	Vu T, Mousavi H, Monga V , et al. Histopathological image classification using discriminative feature-oriented dictionary learning[J]. IEEE Transactions on Medical Imaging, 2016,35(3):738-751. doi: 10.1109/TMI.2015.2493530 pmid: 26513781
[19]	Dugas C, Gadoury D . Pointwise exact bootstrap distributions of ROC curves[J]. Machine Learning, 2010,78(1-2):103-136. doi: 10.1007/s10994-009-5134-6
[20]	Ota K, Oishi N, Ito K , et al. Effects of imaging modalities, brain atlases and feature selection on prediction of Alzheimer's disease[J]. Journal of Neuroscience Methods, 2015,256(3):168-183. doi: 10.1016/j.jneumeth.2015.08.020 pmid: 26318777

Algorithm	Accuracy/%	Sensitivity/%	Specificity/%
SVM^[20]	62.73	33.33	87.50
SRC^[10]	72.73	66.67	75.00
FDDL^[15]	76.32	64.87	80.41
Improved	89.73	87.59	92.56

一种改进的字典学习方法在医疗疾病分析中的应用

An Improved Dictionary Learning Method for Medical Disease Analysis

RichHTML

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

图/表 4

参考文献 20

相关文章 7

Metrics

本文评价

推荐阅读 0

[1]	顾正之,王素玉. 基于端元字典稀疏解混的高光谱图像亚像元定位[J]. 电子科技, 2019, 32(4): 33-39.
[2]	陈益, 李文钧. 基于正交匹配追踪算法的语音信号重构研究[J]. , 2018, 31(3): 44-.
[3]	郑昊辰, 姜维. 基于压缩感知的阅卷系统手写汉字识别算法[J]. , 2018, 31(3): 75-.
[4]	沈丽,韩彦芳. 基于稀疏表示的超分辨率图像重建[J]. , 2015, 28(9): 144-.
[5]	田香玲,席志红. 压缩感知观测矩阵的优化算法[J]. , 2015, 28(8): 102-.
[6]	曹蒙蒙,李新叶,范月坤. 基于判别低秩矩阵恢复和稀疏表示的车标识别[J]. , 2015, 28(4): 57-.
[7]	刘甜甜. 基于稀疏和低秩表示的显著性目标检测[J]. , 2015, 28(2): 112-.