Deep CNN model based on serial-parallel structure optimization for four-class motor imagery EEG classification

نویسندگان

چکیده

Motor imagery electroencephalogram (MI-EEG) is one of the most important brain-computer interface (BCI) signal. It vital to analyze MI-EEG for manipulation external BCI actuator. However, traditional methods usually undertake EEG feature extraction and classification separately, which may lose efficient information. behaves beyond our satisfaction multi-class MI activity evoked by space-close cannot eliminate influence individual differences. To solve these problems, we propose a convolutional neural network (CNN) with an end-to-end serial-parallel (SP) structure followed tranfer learning. In detail, use serial module extract rough features in time–frequency-space domain, parallel fine learning different scales. Meanwhile, freeze-and-retrain fune tuning transfer strategy proposed improve cross-subject accuracy. When model compared other three typical networks, results show that performs best average testing accuracy 72.13% loss 0.47, among subject only takes 0.7 s reach 89.17% as highest one. Through learning, reduce training parameters 53%. The increases approximate 15%, reaches 76.98%. conclusion, integrity separability SPCNN determine require no additional signal analysis, conducive realization online BCI. can also get rid dependence on time data rapidly advance future.

برای دانلود باید عضویت طلایی داشته باشید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Classification of EEG-based motor imagery BCI by using ECOC

AbstractAccuracy in identifying the subjects’ intentions for moving their different limbs from EEG signals is regarded as an important factor in the studies related to BCI. In fact, the complexity of motor-imagination and low amount of signal-to-noise ratio for EEG signal makes this identification as a difficult task. In order to overcome these complexities, many techniques such as variou...

متن کامل

A Detective Method for Multi-class EEG-based Motor Imagery Classification Based on OCSVM

The aim of BCI is to translate the activity of brain into command to control external device completing the task of communication. To achieve this goal, we need to recognize the various patterns of the brain. So improving classification accuracy is essential in BCI. In this paper, a detective method: one class support vector machine (OCSVM) is applied to three (EEG) motor imagery (MI) tasks cla...

متن کامل

A Deep Learning Method for Classification of EEG Data Based on Motor Imagery

Effectively extracting EEG data features is the key point in Brain Computer Interface technology. In this paper, aiming at classifying EEG data based on Motor Imagery task, Deep Learning (DL) algorithm was applied. For the classification of left and right hand motor imagery, firstly, based on certain single channel, a weak classifier was trained by deep belief net (DBN); then borrow the idea of...

متن کامل

Classification of Four-Class Motor Imagery Employing Single-Channel Electroencephalography

With advances in brain-computer interface (BCI) research, a portable few- or single-channel BCI system has become necessary. Most recent BCI studies have demonstrated that the common spatial pattern (CSP) algorithm is a powerful tool in extracting features for multiple-class motor imagery. However, since the CSP algorithm requires multi-channel information, it is not suitable for a few- or sing...

متن کامل

Classification of Right/Left Hand Motor Imagery by Effective Connectivity Based on Transfer Entropy in EEG Signal

The right and left hand Motor Imagery (MI) analysis based on the electroencephalogram (EEG) signal can directly link the central nervous system to a computer or a device. This study aims to identify a set of robust and nonlinear effective brain connectivity features quantified by transfer entropy (TE) to characterize the relationship between brain regions from EEG signals and create a hierarchi...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: Biomedical Signal Processing and Control

سال: 2022

ISSN: ['1746-8094', '1746-8108']

DOI: https://doi.org/10.1016/j.bspc.2021.103338