Skip to content

Deep Learning for Meditation’s Impact on Brain-Computer Interface Performance

B. Liu

2022 International Communication Engineering and Cloud Computing Conference October 28, 2022 DOI: 10.1109/ceccc56460.2022.10069731 (opens in new tab)

Study at a glance

AI-extracted from the abstract
Characteristics Theoretical or methodological paper Peer reviewed
Population Meditators and a control group
Intervention Mindfulness meditation
Topics Meditation
Key points Feed-forward neural network and convolutional neural network models classified BCI control for meditators with slightly better accuracy than traditional predictive methods when applied to raw data with minimal noise filtering. The authors also invented an optimal preprocessing method and a novel BCI experiment design to fix feedback control period length.

Abstract

Recent studies uncovered the mindfulness meditation’s impact on the Brain-Computer Interface (BCI) performance. The traditional predictive method for BCI control requires domain expertise in electroencephalogram (EEG) and complicated and time-consuming processing of EEG data. In this paper, for the first time, deep learning models feed-forward neural network (FFNN) and convolutional neural network (CNN) were developed to classify BCI controls for meditators, using a meditation group and a control group. Both models, when applied to raw data with minimal noise filtering, demonstrated slightly better accuracy rates than the traditional predictive methods. The optimal pre-preprocessing method to obtain fixed-length BCI feedback control data was invented. A novel BCI experiment design was created to fix the length of the BCI feedback control period to better utilize the trial time and EEG data. This research also provides the foundation for further application of deep learning models to meditation’s impact on BCI in more complicated investigations that the traditional methods are incapable of handling due to the large dimensions of both temporal and spatial data.

Comparable studies

Other theoretical and historical papers on meditation, most cited first.

Citations in the library

Explore topics