A facile and flexible motor imagery classification using electroencephalogram signals

Mind machine interface (MMI) enables communication with milieu by measuring brain activities. The reliability of MMI systems is highly dependent on the identification of various motor imagery (MI) tasks. Perfect discrimination of brain activities is required to avoid miscommunication. Electroencephalogram (EEG) signals provide a scrupulous solution for the development of MMI. Analysis of multi-channel EEG signals increases the burden of computation drastically. The extraction of hidden information from raw EEG signals is difficult due to its complex nature. A signal is needed to be decomposed and classified for the extraction of hidden information from it. But selecting the uniform decomposition and hyperparameters for decomposition and classification of the signal can lead to information loss and misclassification.

This paper presents a novel method for identifying right-hand and right-foot MI tasks. The method employs a single-channel adaptive decomposition and EEG signal classification. The multi-cluster unsupervised learning method is employed for the selection of significant channel. Further, flexible variational mode decomposition (F-VMD) is used for the adaptive decomposition of signals. The values of decomposition parameters are selected adaptively following the nature of EEG signals. The value of decomposition parameters is used to decompose the signals into narrow-band modes. Hjorth, entropy and quartile based features are elicited from the modes of F-VMD. These features are classified by using a flexible extreme learning machine (F-ELM). F-ELM selects the hyperparameters and kernel adaptively by reducing the classification error.

The performance of the proposed method is evaluated by measuring five performance parameters namely accuracy (ACC), sensitivity (SEN), specificity (SPE), Mathew's correlation coefficient (MCC), and F-1 score. An ACC, SEN, SPE, MCC and F-1 score is obtained as 100%, 100%, 100%, 100%, and 1. The performance parameters obtained by the proposed method prove the superiority over other methodologies using the same data-set.

The proposed method proved to be promising and efficient with a single channel and two features. This framework can be utilized for the development of a real-time mind-machine interface like robotic arm, wheel chairs, etc.