Binary classification of meditative state from the resting state using EEG

EEG-based investigation of effects of mindfulness meditation training on state and trait by deep learning and traditional machine learning

“…The inter-subject classification accuracy using traditional machine learning technique FBCSP + SVM in our study is 68.50%, which is comparable to 74.0% reported in Panachakel et al (2021b) using also traditional machine learning method, but as discussed above our task is much more difficult. The inter-subject classification accuracy for Raja yoga experts is greatly improved from 74.0% in Panachakel et al (2021b) to 79.1, 86.5, 91.0, and 94.1% in Panachakel et al (2021a) for using alpha, beta, low gamma, high gamma features, respectively, followed by the CSP + LDA + LSTM deep learning framework. However, the meditation state classification accuracy for our MBSR novices using deep and shallow ConvNets does not improve over the traditional FBCSP + SVM method but instead drops to around chance levels of 48.34 and 50.60%, respectively.…”

“…For meditation state/experience classification, the intra-subject classification strategy has been used in Panachakel et al (2021b) , the mix-subject classification strategy has been used in Ahani et al (2014) , Khoury et al (2015) , Shaw and Routray (2016) , Lee et al (2017) , Sharma et al (2019) , and Han et al (2020) , and the inter-subject classification strategy has been used in Panachakel et al (2021a , b) and Pandey and Miyapuram (2021) . The inter-subject classification strategy is most suitable for the general case but it is the most difficult due to inter-subject variation.…”

“…Traditional machine learning techniques have been extensively applied for many different meditation styles using various feature extraction methods. Features used for meditation state recognition are from either frequency domain such as Fourier transform and time-frequency analysis, or spatial-temporal domain such as linear analysis using independent component analysis (ICA), common spatial patterns (CSP), and linear discriminator (LD), as well as non-linear analysis using entropy, correlation dimension (CD), largest Lyapunov exponent (LLE), and hurst exponent (HE) ( Goshvarpour and Goshvarpour, 2012 ; Lin and Li, 2017 ; Han et al, 2020 ; Tee et al, 2020 ; Huang et al, 2021 ; Kora et al, 2021 ; Panachakel et al, 2021b ). Brain connectivity features have also been exploited ( Dissanayaka et al, 2015 ; Pandey et al, 2021 ).…”

“…Brain connectivity features have also been exploited ( Dissanayaka et al, 2015 ; Pandey et al, 2021 ). The classification techniques used for meditation state recognition include linear discriminant analysis (LDA) ( Panachakel et al, 2021b ), support vector machine (SVM) ( Shaw and Routray, 2016 ; Han et al, 2020 ), random forest (RF) ( Huang et al, 2021 ), and artificial neural network (ANN). Recently, deep learning techniques including long short-term memory (LSTM) framework ( Panachakel et al, 2021a ) as well as various deep convolutional neural networks (CNN) such as VGG16, ResNet50, and MobileNet ( Pandey and Miyapuram, 2021 ), have also been exploited for meditation state recognition.…”

“…There are only a small number of publications reporting meditation state classification, mostly on yoga meditation ( Han et al, 2020 ), including Raja yoga ( Panachakel et al, 2021a , b ), Kriya yoga ( Shaw and Routray, 2016 ), and Himalayan yoga ( Pandey and Miyapuram, 2021 ), with only one on non-specified meditation ( Goshvarpour and Goshvarpour, 2012 ).…”