Litcius/Paper detail

A hybrid CNN model for classification of motor tasks obtained from hybrid BCI system

R. Shelishiyah, Deepa Beeta Thiyam, M. Jehosheba Margaret, N. M. Masoodhu Banu

2025Scientific Reports12 citationsDOIOpen Access PDF

Abstract

The Hybrid-Brain Computer Interface (BCI) has shown improved performance, especially in classifying multi-class data. Two non-invasive BCI modules are combined to achieve an improved classification which are Electroencephalogram (EEG) and functional Near Infra-red Spectroscopy (fNIRS). Classifying contralateral and ipsilateral motor movements is found challenging among the other mental activity signals. The current work focuses on the performance of deep learning methods like - Convolutional Neural Networks (CNN) and Bidirectional Long-Short term memory (Bi-LSTM) in classifying a four-class motor execution of Right Hand, Left Hand, Right Arm and Left Arm taken from the CORE dataset. The model performance was evaluated using metrics such as Accuracy, F1 - score, Precision, Recall, AUC and ROC curve. The CNN and Hybrid CNN models have resulted in 98.3% and 99% accuracy respectively.

Topics & Concepts

Brain–computer interfaceComputer scienceConvolutional neural networkMotor imageryArtificial intelligenceRecallElectroencephalographyInterface (matter)F1 scorePattern recognition (psychology)Machine learningSpeech recognitionNeurosciencePsychologyBubbleCognitive psychologyMaximum bubble pressure methodParallel computingEEG and Brain-Computer InterfacesNeuroscience and Neural EngineeringFunctional Brain Connectivity Studies
A hybrid CNN model for classification of motor tasks obtained from hybrid BCI system | Litcius