The invention discloses an electroencephalogram signal classification method based on a hybrid neural network, and belongs to the technical field of man-machine interaction intelligence. According to the electroencephalogram signal classification method based on the hybrid neural network, after accurate classification, electroencephalogram signals are converted into digital signals, control instructions used for controlling a vehicle are formed, and the electroencephalogram signals are used for automobile control aided driving. The method comprises the steps of collecting electroencephalogram signals, preprocessing electroencephalogram data, constructing a fusion entropy matrix, training a hybrid neural network model, classifying data of a test set, connecting an upper computer with a simulation cockpit, wearing an electroencephalogram cap on the head of a driver, and testing the control effect of the driver on a vehicle. According to the method, the classification accuracy is greatly improved, and the model of the hybrid neural network is optimized to obtain a better classification effect. Meanwhile, the classification result of the neural network is converted into a control instruction for the automobile, electroencephalogram control over the automobile can be achieved under the emergency condition, and five control states of parking, left turning, right turning, acceleration and normal driving are achieved. And a guarantee is provided for the safety of the driver and the travelers.

    一种基于混合神经网络的脑电信号分类方法,属于人机交互智能技术领域。本发明的目的是在准确的分类后,将脑电信号转换为数字信号并形成用来控制车辆的控制指令,实现脑电信号对于汽车控制辅助驾驶的基于混合神经网络的脑电信号分类方法。本发明步骤是:采集脑电信号,脑电数据预处理,构建融合熵矩阵,训练混合神经网络模型,测试集的数据分类,将上位机与模拟驾驶舱相连,驾驶员头戴脑电帽,测试驾驶员对于车辆的控制效果。本发明大大提高了分类的准确率,并且将混合神经网络的模型进行优化得到了更好的分类效果。同时将神经网络的分类结果转化为对汽车的控制指令,可以实现在紧急状况下对于车辆进行脑电控制,实现停车、左转、右转、加速以及常态驾驶五种控制状态。为驾驶员及同行人员的安全提供了保障。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Electroencephalogram signal classification method based on hybrid neural network


    Weitere Titelangaben:

    基于混合神经网络的脑电信号分类方法


    Beteiligte:
    CHEN WANZHONG (Autor:in) / WANG ZHENG (Autor:in)

    Erscheinungsdatum :

    2023-07-18


    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 / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen



    Automated classification system for drowsiness detection using convolutional neural network and electroencephalogram

    Venkata Phanikrishna Balam / Venkata Udaya Sameer / Suchismitha Chinara | DOAJ | 2021

    Freier Zugriff

    Automated classification system for drowsiness detection using convolutional neural network and electroencephalogram

    Balam, Venkata Phanikrishna / Sameer, Venkata Udaya / Chinara, Suchismitha | Wiley | 2021

    Freier Zugriff



    Classification of Driver Steering Intention Based on Brain-Computer Interface Using Electroencephalogram

    Ikenishi, T. / Kamada, T. / Nagai, M. et al. | British Library Conference Proceedings | 2007