Abstract
To explore whether the brain contains pattern differences in the rock–paper–scissors (RPS) imagery task, this paper attempts to classify this task using fNIRS and deep learning. In this study, we designed an RPS task with a total duration of 25 min and 40 s, and recruited 22 volunteers for the experiment. We used the fNIRS acquisition device (FOIRE-3000) to record the cerebral neural activities of these participants in the RPS task. The time series classification (TSC) algorithm was introduced into the time-domain fNIRS signal classification. Experiments show that CNN-based TSC methods can achieve 97% accuracy in RPS classification. CNN-based TSC method is suitable for the classification of fNIRS signals in RPS motor imagery tasks, and may find new application directions for the development of brain–computer interfaces (BCI).
Highlights
The brain–computer interface (BCI) is a hardware and software communication system that enables people to interact with the surrounding environment by using control signals generated by the brain without the involvement of peripheral nerves and muscles [1]
Red lines represent the motor imagery task of Paper, green lines represent the task of Rock, and blue lines represent the task of Scissors
Exercise-related BCI usually focuses on the primary motor cortex, the channels with the best classification result are located in the somatosensory motor cortex (SMC), which may indicate that SMC is an active area in sports imaging tasks
Summary
The brain–computer interface (BCI) is a hardware and software communication system that enables people to interact with the surrounding environment by using control signals generated by the brain without the involvement of peripheral nerves and muscles [1]. Introducing the PFC area into BCI research helps to solve the control command extraction of patients with impaired brain motor function. Trakoolwilaiwan et al, used SVM, ANN, and Convolutional Neural Network (CNN) to classify right-hand and left-hand motor execution tasks on eight healthy subjects, and the classification accuracy of SVM, ANN, and CNN were 86.19%, 89.35%, and 92.68%, respectively. One-dimensional CNN is suitable for application in time series classification (TSC) tasks and will significantly improve the accuracy of the classification on fNIRS signals. We performed an RPS motor imagery task and combined a near-infrared brain recording with various deep learning classification programs.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
