Learning Patterns in Imaginary Vowels for an Intelligent Brain Computer Interface (BCI) Design
This work addresses the challenge of data-poor environments in healthcare applications like emotion detection, offering a specific solution for vowel recognition in BCI systems, but it is incremental as it builds on existing EEG processing methods.
The paper tackles the problem of recognizing English vowels from raw EEG signals for brain-computer interfaces, proposing a modular framework that includes signal segmentation, filtering, feature extraction, dimensionality reduction, and classification using a decision-tree-based SVM, with performance evaluated via test-set and resubstitution error rates.
Technology advancements made it easy to measure non-invasive and high-quality electroencephalograph (EEG) signals from human's brain. Hence, development of robust and high-performance AI algorithms becomes crucial to properly process the EEG signals and recognize the patterns, which lead to an appropriate control signal. Despite the advancements in processing the motor imagery EEG signals, the healthcare applications, such as emotion detection, are still in the early stages of AI design. In this paper, we propose a modular framework for the recognition of vowels as the AI part of a brain computer interface system. We carefully designed the modules to discriminate the English vowels given the raw EEG signals, and meanwhile avoid the typical issued with the data-poor environments like most of the healthcare applications. The proposed framework consists of appropriate signal segmentation, filtering, extraction of spectral features, reducing the dimensions by means of principle component analysis, and finally a multi-class classification by decision-tree-based support vector machine (DT-SVM). The performance of our framework was evaluated by a combination of test-set and resubstitution (also known as apparent) error rates. We provide the algorithms of the proposed framework to make it easy for future researchers and developers who want to follow the same workflow.