A Study of Manifold Learning Methods for Multiclass Motor Imagery Classification

Mishra, Pradeep Kumar and Rajalakshmi, P (2019) A Study of Manifold Learning Methods for Multiclass Motor Imagery Classification. Masters thesis, Indian institute of technology Hyderabad.

Text
Mtech_Thesis_TD1472_2019.pdf
Restricted to Repository staff only until 8 July 2024.
Download (2MB) | Request a copy

Abstract

Recent advances in the Brain-Computer Interface(BCI) systems state that the accurate Motor Imagery (MI) classification using Electroencephalogram (EEG) plays a vital role. we propose two novel methods for four class Motor Imagery (MI) classification using Electroencephalography (EEG). Also, we developed a real-time Health 4.0 (H4.0) architecture for Brain Controlled Internet of Things (IoT) enabled Environments (BCE), which uses the classified MI task to assist the disabled persons in controlling IoT enabled environments such as lighting, Heating, Ventilation, and Air Conditioning (HVAC), etc. The first method for classification involves a simple and low-complex classification framework using a combination of Regularized Riemannian Mean (RRM) and Linear SVM. Although this method performs better compared to state-of-the-art techniques, it still suffers from a non-negligible misclassification rate. Hence, to overcome this, the second method offers a persistent decision engine (PDE) for the MI classification, which improves the classification accuracy (CA) significantly. The proposed two methods are validated using: 1) in-house recorded four class MI dataset (Dataset-I collected over 14 subjects) and 2) four class MI dataset 2a of BCI Competition IV (Dataset-II collected over 9 subjects). The proposed RRM architecture obtained an average CAs of 74.30% and 67.60% when validated using Dataset-I and Dataset-II, respectively. When analyzed along with the proposed PDE classification framework, an average CA of 92.25% on 12 subjects of Dataset-I and 82.54% on 7 subjects of Dataset-II is obtained. The results show that the PDE algorithm is more reliable for the classification of four class MI and is also feasible for BCE applications. The proposed low-complex BCE architecture is implemented in real-time using Raspberry Pi 3 Model B+ along with the Virgo EEG data acquisition system. The hardware implementation results show that the proposed system architecture is well suited for body wearable devices in the scenario of Health 4.0. We strongly feel that this study can aid in driving the future scope of BCE research.

[error in script]

IITH Creators: