基于PCANet的脉搏信号亚健康检测
|
摘要
目前亚健康状态识别中脉搏信号特征提取困难,且多依赖于手工提取特征而影响识别率。针对这一问题,本文提出了一种基于主成分分析网络(Principal Component Analysis Network,PCANet)的脉搏信号亚健康检测新方法。首先对预处理的脉搏信号进行特征提取;其次将这些特征进行哈希编码,直方图分块,作为特征描述;然后使用分类器将健康和亚健康的两类脉搏信号进行分类识别,并与传统特征提取方法的分类效果进行比较。实验结果表明本文方法对亚健康状态识别达到了较高的准确率,相比传统的特征提取方法,PCANet方法在识别率上提高了10%以上,因此,本文所提出的方法能够有效地区分健康与亚健康状态,为亚健康状态的检测提供了一种新的参考依据。
Now pulse signal feature is difficult to be extracted in the sub-health detection,and it is easy to affect recognition accuracy due to the relying on mainly hand-crafted feature extraction.To solve these problems,this paper proposes a pulse signal sub-health detection method based on principal component analysis network(PCANet).Firstly,PCANet is used to extract features from preprocessing pulse signal in the experiment.Then,we deal these features with Hash code,histogram block as the description features.Finally,the feature vectors are fed into two classifiers to classify the healthy and sub-healthy subjects.The test results is compared with the results from other methods of traditional features extraction.The experimental analysis show that our method obtains the highest accuracy rate in sub-health recognition field.The recognition rate of PCANet method is improveed by 10% compared with those of traditional feature extraction methods.So our approach can effectively distinguish health and sub-health subjects,and provides a new reference for human detection of sub-health state.
Now pulse signal feature is difficult to be extracted in the sub-health detection,and it is easy to affect recognition accuracy due to the relying on mainly hand-crafted feature extraction.To solve these problems,this paper proposes a pulse signal sub-health detection method based on principal component analysis network(PCANet).Firstly,PCANet is used to extract features from preprocessing pulse signal in the experiment.Then,we deal these features with Hash code,histogram block as the description features.Finally,the feature vectors are fed into two classifiers to classify the healthy and sub-healthy subjects.The test results is compared with the results from other methods of traditional features extraction.The experimental analysis show that our method obtains the highest accuracy rate in sub-health recognition field.The recognition rate of PCANet method is improveed by 10% compared with those of traditional feature extraction methods.So our approach can effectively distinguish health and sub-health subjects,and provides a new reference for human detection of sub-health state.
引文
[1] Ayinuer Muhemaitibake, Xiao-Ling H U. Treatment and regulation of sub-health insomnia by Chinese medicine[J].Chinese Journal of Experimental Traditional Medical Formulae,2011,(22):280-282.
[2] Zhang A,Yang F.Study on recognition of sub-health from pulse signal[C].International Conference on Neural Networks and Brain,2005.Icnn&b.IEEE,2006,1516-1518.
[3] WANG Yue-yun,YI Ping.Epidemic situation and research progress of sub-health[J].Chinese Journal of Social Medicine,2007,24(2):140-142.王月云,尹平.亚健康的流行现状与研究进展[J].中国社会医学杂志,2007,24(2):140-142.
[4] Lipp I,Murphy K,Wise R G,et al.Understanding the contribution of neural and physiological signal variation to the low repeatability of emotion-induced BOLD responses[J].Neuroimage,2014,86(100):335-342.
[5] Kim H,Kim J Y,Park Y J,et al.Development of pulse diagnostic devices in Korea[J].Integrative Medicine Research,2013,2(1):7-17.
[6] Zhang S,Sun Q.Human pulse recognition based on wavelet transform and BP network[C].IEEE International Conference on Signal Processing,Communications and Computing.IEEE,2015,1-4.
[7] Lecun Y,Bengio Y,Hinton G.Deep learning[J].Nature,2015,521(7553):436-444.
[8] Deng L,Yu D.Deep learning:methods and applications[J].Foundations & Trends in Signal Processing,2014,7(3):197-387.
[9] Chen Y,Lin Z,Zhao X,et al.Deep learning-based classification of hyperspectral data[J].IEEE Journal of Selected Topics in Applied Earth Observations & Remote Sensing,2017,7(6):2094-2107.
[10] Denil M,Shakibi B,Dinh L,et al.Predicting Parameters in Deep Learning[J].University of British Columbia,2013,2148-2156.
[11] Young S R,Rose D C,Karnowski T P,et al.Optimizing deep learning hyper-parameters through an evolutionary algorithm[J].2015,1-5.
[12] Chan T H,Jia K,Gao S,et al.PCANet:A simple deep learning baseline for image classification[J].IEEE Transactions on Image Processing,2015,24(12):5017-5032.
[13] GU Ling-yun,LU Wen-zhi,YANG Yong,et al.Deception detection study based on PCANet and support vector machine[J].Acta Electroica Sinica,2016,44(8):1969-1973.顾凌云,吕文志,杨勇,等.基于PCANet和SVM的谎言测试研究[J].电子学报,2016,44(8):1969-1973.
[14] HU Zheng-ping,HE Wei,WANG Meng,et al.Face feature extraction algorithm based on deep subspace with Gabor filter modulation[J].Journal of Signal Processing,2017,33(3):338-345.胡正平,何薇,王蒙,等.Gabor调制的深度多层子空间人脸特征提取算法[J].信号处理,2017,33(3):338-345.
[15] Wang S,Chen L,Zhou Z,et al.Human fall detection in surveillance video based on PCANet[J].Multimedia Tools & Applications,2016,75(19):11603-11613.
[16] Huang Z,Xue W,Mao Q,et al.Unsupervised domain adaptation for speech emotion recognition using PCANet[J].Multimedia Tools & Applications,2017,76(5):6785-6799.
[17] Gao F,Dong J,Li B,et al.Automatic change detection in synthetic aperture radar images based on PCANet[J].IEEE Geoscience & Remote Sensing Letters,2017,13(12):1792-1796.
[18] Sun S,Zhao X,An N,et al.RGB-D object recognition based on RGBD-PCANet learning[C].IEEE International Conference on Mechatronics and Automation.IEEE,2017,1075-1080.
[19] Zeng R,Wu J,Senhadji L,et al.Tensor object classification via multilinear discriminant analysis network[C].IEEE International Conference on Acoustics,Speech and Signal Processing.IEEE,2015,1971-1975.
[20] Keerthi S S,Shevade S K,Bhattacharyya C,et al.Improvements to platt's SMO algorithm for SVM classifier design[J].Neural Computation,2014,13(3):637-649.
[21] Loosli G,Canu S,Cheng S O.Learning SVM in kreYn spaces[J].IEEE Trans Pattern Anal Mach Intell,2016,38(6):1204-1216.
[2] Zhang A,Yang F.Study on recognition of sub-health from pulse signal[C].International Conference on Neural Networks and Brain,2005.Icnn&b.IEEE,2006,1516-1518.
[3] WANG Yue-yun,YI Ping.Epidemic situation and research progress of sub-health[J].Chinese Journal of Social Medicine,2007,24(2):140-142.王月云,尹平.亚健康的流行现状与研究进展[J].中国社会医学杂志,2007,24(2):140-142.
[4] Lipp I,Murphy K,Wise R G,et al.Understanding the contribution of neural and physiological signal variation to the low repeatability of emotion-induced BOLD responses[J].Neuroimage,2014,86(100):335-342.
[5] Kim H,Kim J Y,Park Y J,et al.Development of pulse diagnostic devices in Korea[J].Integrative Medicine Research,2013,2(1):7-17.
[6] Zhang S,Sun Q.Human pulse recognition based on wavelet transform and BP network[C].IEEE International Conference on Signal Processing,Communications and Computing.IEEE,2015,1-4.
[7] Lecun Y,Bengio Y,Hinton G.Deep learning[J].Nature,2015,521(7553):436-444.
[8] Deng L,Yu D.Deep learning:methods and applications[J].Foundations & Trends in Signal Processing,2014,7(3):197-387.
[9] Chen Y,Lin Z,Zhao X,et al.Deep learning-based classification of hyperspectral data[J].IEEE Journal of Selected Topics in Applied Earth Observations & Remote Sensing,2017,7(6):2094-2107.
[10] Denil M,Shakibi B,Dinh L,et al.Predicting Parameters in Deep Learning[J].University of British Columbia,2013,2148-2156.
[11] Young S R,Rose D C,Karnowski T P,et al.Optimizing deep learning hyper-parameters through an evolutionary algorithm[J].2015,1-5.
[12] Chan T H,Jia K,Gao S,et al.PCANet:A simple deep learning baseline for image classification[J].IEEE Transactions on Image Processing,2015,24(12):5017-5032.
[13] GU Ling-yun,LU Wen-zhi,YANG Yong,et al.Deception detection study based on PCANet and support vector machine[J].Acta Electroica Sinica,2016,44(8):1969-1973.顾凌云,吕文志,杨勇,等.基于PCANet和SVM的谎言测试研究[J].电子学报,2016,44(8):1969-1973.
[14] HU Zheng-ping,HE Wei,WANG Meng,et al.Face feature extraction algorithm based on deep subspace with Gabor filter modulation[J].Journal of Signal Processing,2017,33(3):338-345.胡正平,何薇,王蒙,等.Gabor调制的深度多层子空间人脸特征提取算法[J].信号处理,2017,33(3):338-345.
[15] Wang S,Chen L,Zhou Z,et al.Human fall detection in surveillance video based on PCANet[J].Multimedia Tools & Applications,2016,75(19):11603-11613.
[16] Huang Z,Xue W,Mao Q,et al.Unsupervised domain adaptation for speech emotion recognition using PCANet[J].Multimedia Tools & Applications,2017,76(5):6785-6799.
[17] Gao F,Dong J,Li B,et al.Automatic change detection in synthetic aperture radar images based on PCANet[J].IEEE Geoscience & Remote Sensing Letters,2017,13(12):1792-1796.
[18] Sun S,Zhao X,An N,et al.RGB-D object recognition based on RGBD-PCANet learning[C].IEEE International Conference on Mechatronics and Automation.IEEE,2017,1075-1080.
[19] Zeng R,Wu J,Senhadji L,et al.Tensor object classification via multilinear discriminant analysis network[C].IEEE International Conference on Acoustics,Speech and Signal Processing.IEEE,2015,1971-1975.
[20] Keerthi S S,Shevade S K,Bhattacharyya C,et al.Improvements to platt's SMO algorithm for SVM classifier design[J].Neural Computation,2014,13(3):637-649.
[21] Loosli G,Canu S,Cheng S O.Learning SVM in kreYn spaces[J].IEEE Trans Pattern Anal Mach Intell,2016,38(6):1204-1216.