基于FSWT和GBDT的癫痫脑电信号分类研究
|
摘要
为解决癫痫脑电信号分类类别以及分类精度不足的问题,使用频率切片小波变换对脑电数据进行信号重构,得到5个频段的节律信号,再利用非线性指标近似熵和线性指标波动指数共同作为癫痫信号的特征值,充分提取信号的特征信息。随后使用梯度提升树算法对得到的特征数据集进行多分类。实验表明,该算法对癫痫脑电信号的三分类识别率为98.4%。较传统Adaboost算法,该方法采取了GBDT(Gradient Boosting Decision Tree)作为分类算法,成功利用更多的数据集,并且使得分类精度更高。
In order to solve the problem of classification and accuracy of epilepsy EEG( Electroencephalogram)signals,frequency slice wavelet transform was used to reconstruct EEG data and get five frequency bands of rhythmic signals. We use approximate entropy of non-linear index and fluctuation index of linear index as the eigenvalues of epileptic signals to fully extract the characteristic information of signals. Gradient lifting tree algorithm was used to classify the feature data set. The classification recognition rate of epileptic EEG signals is 98. 4%. Compared to the traditional Adaboost algorithm,we adopt GBDT( Gradient Boosting Decision Tree) as a classification algorithm. This method can use more data sets successfully and has higher classification accuracy.
In order to solve the problem of classification and accuracy of epilepsy EEG( Electroencephalogram)signals,frequency slice wavelet transform was used to reconstruct EEG data and get five frequency bands of rhythmic signals. We use approximate entropy of non-linear index and fluctuation index of linear index as the eigenvalues of epileptic signals to fully extract the characteristic information of signals. Gradient lifting tree algorithm was used to classify the feature data set. The classification recognition rate of epileptic EEG signals is 98. 4%. Compared to the traditional Adaboost algorithm,we adopt GBDT( Gradient Boosting Decision Tree) as a classification algorithm. This method can use more data sets successfully and has higher classification accuracy.
引文
[1]HUSSEIN A F.Focal and Non-Focal Epilepsy Localization:A Review[J].IEEE Access,2018,6:49306-49324.
[2]SELVATHI D,MEERA V K.Realization of Epileptic Seizure Detection in EEG Signal Using Wavelet Transform and SVM Classifier[C]∥2017 International Conference on Signal Processing and Communication(ICSPC).Coimbsatore,India:IEEE,2017:18-22.
[3]CURAK,ATLI S K,SADIGHZADEH R,et al.Classification of Epileptic EEG Data by Using Ensemble Empirical Mode Decomposition[C]∥2018 26th Signal Processing and Communications Applications Conference(SIU).Izmir,Turkey:IEEE,2018:1-4.
[4]RASHID MD MAMUN OR,MOHIUDDIN AHMAD.Epileptic Seizure Classification Using Statistical Features of EEG Signal[C]∥2017 International Conference on Electrical,Computer and Communication Engineering(ECCE).Cox's Bazar,Bangladesh:IEEE,2017:308-312.
[5]YAN Z H,MIYAMOTO A,JIANG Z W.Frequency Slice Algorithm for Modal Signal Separation and Damping Identification[J].Computers&Structures,2011,89(1/2):14-26.
[6]YAN Z H,MIYAMOTO A,JIANG Z W.Frequency Slice Wavelet Transform for Transient Vibration Response Analysis[J].Mechanical Systems and Signal Processing,2009,23(5):1474-1489.
[7]蔡剑华,黄国玉,黎小琴.基于频率切片小波变换时频分析的齿轮故障诊断[J].机械强度,2017,39(5):1026-1030.CAI Jianhua,HUANG Guoyu,LI Xiaoqin.Gear Fault Diagnosis Based on Time-Frequency Analysis of Frequency Slice Wavelet Transform[J].Journal of Mechanical Strength,2017,39(5):1026-1030.
[8]丁正敏.基于脑电信号检测的麻醉深度监测算法研究[D].广州:华南理工大学材料科学与工程学院,2018.DING Zhengmin.Research on Anesthesia Depth Monitoring Algorithms Based on EEG Signal Detection[D].Guangzhou:College of Materials Science and Engineering,South China University of Technology,2018.
[9]RAHMAN L,OYAMA K.Long-Term Monitoring of NIRS and EEG Signals for Assessment of Daily Changes in Emotional Valence[C]∥2018 IEEE International Conference on Cognitive Computing(ICCC).San Francisco,CA,USA:IEEE,2018:118-121.
[10]张健钊.基于小波包能量与熵特征和Real Ada Boost算法的癫痫脑电识别[D].济南:山东大学信息科学与工程学院,2018.ZHANG Jianzhao.Epileptic EEG Recognition Based on Wavelet Packet Energy and Entropy Using Real Ada Boost Algorithm[D].Jinan:College of Information Science and Engineering,Shandong University,2018.
[11]DE MELO V V,USHIZIMA D M,BARACHO S F.Gradient Boosting Decision Trees for Echocardiogram Images[C]∥2018International Joint Conference on Neural Networks(IJCNN).Rio de Janeiro:IEEE,2018:1-8.
[12]王守相,刘天宇.计及用电模式的居民负荷梯度提升树分类识别方法[J].电力系统及其自动化学报,2017,29(9):27-33.WANG Shouxiang,LIU Tianyu.Gradient Boosting Decision Tree Method for Residential Load Classification Considering Typical Power Consumption Modes[J].Proceedings of the CSU-EPSA,2017,29(9):27-33.
[13]ANDRZEJAK R G,LEHNERTZ K,RIEKE C,et al.Indications of Nonlinear Deterministic and Finite Dimensional Structures in Time Series of Brain Electrical Activity:Dependence on Recording Region and Brain State[J].Phys Rev E,2001,64(6):1-8.
[14]张涛,陈万忠,李明阳.基于频率切片小波变换和支持向量机的癫痫脑电信号自动检测[J].物理学报,2016,65(3):411-417.ZHANG Tao,CHEN Wanzhong,LI Mingyang.Automatic Detection of Epileptic EEG Signals Based on Frequency Slice Wavelet Transform and Support Vector Machine[J].Journal of Physics,2016,65(3):411-417.
[15]LI Shufang,ZHOU Weidong,YUAN Qi,et al.Feature Extraction and Recognition of Ictal EEG Using EMD and SVM[J].Computers in Biology and Medicine,2013,43(7):807-816.
[16]YATINDRA KUMAR,DEWAL M L,ANAND R S.Epileptic Seizures Detection in EEG Using DWT-Based Ap En and Artificial Neural Network[J].Signal,Image and Video Processing,2014,8(7):1323-1334.
[17]YATINDRA KUMAR,DEWAL M L,ANAND R S.Epileptic Seizure Detection Using DWT Based Fuzzy Approximate Entropy and Support Vector Machine[J].Neurocomputing,2014,133:271-279.
[18]ACHARYA U R,YANTI R,ZHENG J W,et al.Automatic Diagnosis of Epilepsy Using CWT,HOS and Texture Parameters[J].International Journal of Neural Systems,2013,23(3):1-5.
[19]YUAN Q,ZHOU W D,YUAN S S,et al.Epileptic EEG Classification Based on Kernel Sparse Representation[J].International Journal of Neural Systems,2014,24(4):1-13.
[2]SELVATHI D,MEERA V K.Realization of Epileptic Seizure Detection in EEG Signal Using Wavelet Transform and SVM Classifier[C]∥2017 International Conference on Signal Processing and Communication(ICSPC).Coimbsatore,India:IEEE,2017:18-22.
[3]CURAK,ATLI S K,SADIGHZADEH R,et al.Classification of Epileptic EEG Data by Using Ensemble Empirical Mode Decomposition[C]∥2018 26th Signal Processing and Communications Applications Conference(SIU).Izmir,Turkey:IEEE,2018:1-4.
[4]RASHID MD MAMUN OR,MOHIUDDIN AHMAD.Epileptic Seizure Classification Using Statistical Features of EEG Signal[C]∥2017 International Conference on Electrical,Computer and Communication Engineering(ECCE).Cox's Bazar,Bangladesh:IEEE,2017:308-312.
[5]YAN Z H,MIYAMOTO A,JIANG Z W.Frequency Slice Algorithm for Modal Signal Separation and Damping Identification[J].Computers&Structures,2011,89(1/2):14-26.
[6]YAN Z H,MIYAMOTO A,JIANG Z W.Frequency Slice Wavelet Transform for Transient Vibration Response Analysis[J].Mechanical Systems and Signal Processing,2009,23(5):1474-1489.
[7]蔡剑华,黄国玉,黎小琴.基于频率切片小波变换时频分析的齿轮故障诊断[J].机械强度,2017,39(5):1026-1030.CAI Jianhua,HUANG Guoyu,LI Xiaoqin.Gear Fault Diagnosis Based on Time-Frequency Analysis of Frequency Slice Wavelet Transform[J].Journal of Mechanical Strength,2017,39(5):1026-1030.
[8]丁正敏.基于脑电信号检测的麻醉深度监测算法研究[D].广州:华南理工大学材料科学与工程学院,2018.DING Zhengmin.Research on Anesthesia Depth Monitoring Algorithms Based on EEG Signal Detection[D].Guangzhou:College of Materials Science and Engineering,South China University of Technology,2018.
[9]RAHMAN L,OYAMA K.Long-Term Monitoring of NIRS and EEG Signals for Assessment of Daily Changes in Emotional Valence[C]∥2018 IEEE International Conference on Cognitive Computing(ICCC).San Francisco,CA,USA:IEEE,2018:118-121.
[10]张健钊.基于小波包能量与熵特征和Real Ada Boost算法的癫痫脑电识别[D].济南:山东大学信息科学与工程学院,2018.ZHANG Jianzhao.Epileptic EEG Recognition Based on Wavelet Packet Energy and Entropy Using Real Ada Boost Algorithm[D].Jinan:College of Information Science and Engineering,Shandong University,2018.
[11]DE MELO V V,USHIZIMA D M,BARACHO S F.Gradient Boosting Decision Trees for Echocardiogram Images[C]∥2018International Joint Conference on Neural Networks(IJCNN).Rio de Janeiro:IEEE,2018:1-8.
[12]王守相,刘天宇.计及用电模式的居民负荷梯度提升树分类识别方法[J].电力系统及其自动化学报,2017,29(9):27-33.WANG Shouxiang,LIU Tianyu.Gradient Boosting Decision Tree Method for Residential Load Classification Considering Typical Power Consumption Modes[J].Proceedings of the CSU-EPSA,2017,29(9):27-33.
[13]ANDRZEJAK R G,LEHNERTZ K,RIEKE C,et al.Indications of Nonlinear Deterministic and Finite Dimensional Structures in Time Series of Brain Electrical Activity:Dependence on Recording Region and Brain State[J].Phys Rev E,2001,64(6):1-8.
[14]张涛,陈万忠,李明阳.基于频率切片小波变换和支持向量机的癫痫脑电信号自动检测[J].物理学报,2016,65(3):411-417.ZHANG Tao,CHEN Wanzhong,LI Mingyang.Automatic Detection of Epileptic EEG Signals Based on Frequency Slice Wavelet Transform and Support Vector Machine[J].Journal of Physics,2016,65(3):411-417.
[15]LI Shufang,ZHOU Weidong,YUAN Qi,et al.Feature Extraction and Recognition of Ictal EEG Using EMD and SVM[J].Computers in Biology and Medicine,2013,43(7):807-816.
[16]YATINDRA KUMAR,DEWAL M L,ANAND R S.Epileptic Seizures Detection in EEG Using DWT-Based Ap En and Artificial Neural Network[J].Signal,Image and Video Processing,2014,8(7):1323-1334.
[17]YATINDRA KUMAR,DEWAL M L,ANAND R S.Epileptic Seizure Detection Using DWT Based Fuzzy Approximate Entropy and Support Vector Machine[J].Neurocomputing,2014,133:271-279.
[18]ACHARYA U R,YANTI R,ZHENG J W,et al.Automatic Diagnosis of Epilepsy Using CWT,HOS and Texture Parameters[J].International Journal of Neural Systems,2013,23(3):1-5.
[19]YUAN Q,ZHOU W D,YUAN S S,et al.Epileptic EEG Classification Based on Kernel Sparse Representation[J].International Journal of Neural Systems,2014,24(4):1-13.