本发明公开了一种结合PCA和PCANet的驾驶疲劳特征提取方法。本发明包含以下步骤:1、使用脑电采集设备采集驾驶脑电信号;2、对采集到的脑电信号进行预处理,包括降频、降噪;3、对预处理后的信号通过结合PCA和PCANet的特征提取方法提取特征;4、对提取的特征使用分类器进行分类学习、识别。本发明使用结合PCA和PCANet的驾驶疲劳特征提取方法,相比单独使用PCANet产生的维度爆炸,一方面可以降低对计算机的运算要求,同时加快了计算速度,减少了运算的时间,有利于后续的实时监测;另一方面PCANet这个图像的处理方法跨领域使用在驾驶疲劳特征的提取,也使分类的准确率有了有效的提升。

    The invention discloses a driving fatigue feature extraction method based on PCA and PCANet. The method comprises the following steps: 1, collecting driving EEG signals by using an EEG acquisition device; 2, preprocessing the collected EEG signal, including frequency reduction and noise reduction; 3, extracting features from the preprocessed signals by combining PCA and PCANet; 4. Classifying andlearning and identifying the extracted features by using classifier. Compared with the dimension explosion generated by using PCANet alone, the driving fatigue feature extraction method combined withPCA and PCANet can reduce the operation requirement of the computer on the one hand, accelerate the calculation speed, reduce the operation time and facilitate the follow-up real-time monitoring on the other hand; On the other hand, PCANet, an image processing method, is used to extract the features of driving fatigue, which improves the accuracy of classification.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    一种结合PCA和PCANet的驾驶疲劳特征提取方法


    Erscheinungsdatum :

    01.02.2022


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

    IPC:    G06F ELECTRIC DIGITAL DATA PROCESSING , Elektrische digitale Datenverarbeitung / A61B DIAGNOSIS , Diagnostik / B60W CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION , Gemeinsame Steuerung oder Regelung von Fahrzeug-Unteraggregaten verschiedenen Typs oder verschiedener Funktion / G06K Erkennen von Daten , RECOGNITION OF DATA



    Gait recognition based on curvelet transform and PCANet

    Chhatrala, R. / Jadhav, D. | British Library Online Contents | 2017


    A PCANet based method for Vehicle Make Recognition

    Baojun Li / Ying Dong / Dedong Zhao et al. | IEEE | 2016


    RGB-D Object Recognition based on RGBD-PCANet Learning

    Sun, Shiying / Zhao, Xiaoguang / An, Ning et al. | British Library Conference Proceedings | 2017


    PCANet-Based Convolutional Neural Network Architecture for a Vehicle Model Recognition System

    Soon, Foo Chong / Khaw, Hui Ying / Chuah, Joon Huang et al. | IEEE | 2019