A Complete Scheme for Multi-Character Classification Using EEG Signals From Speech Imagery
Top Cited Papers
- 12 March 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Biomedical Engineering
- Vol. 71 (8) , 2454-2462
Abstract
Some classification studies of brain–computer interface (BCI) based on speech imagery show potential for improving communication skills in patients with amyotrophic lateral sclerosis (ALS). However, current research on speech imagery is limited in scope and primarily focuses on vowels or a few selected words. In this paper, we propose a complete research scheme for multi-character classification based on EEG signals derived from speech imagery. Firstly, we record 31 speech imagery contents, including 26 alphabets and 5 commonly used punctuation marks, from seven subjects using a 32-channel electroencephalogram (EEG) device. Secondly, we introduce the wavelet scattering transform (WST), which shares a structural resemblance to Convolutional Neural Networks (CNNs), for feature extraction. The WST is a knowledge-driven technique that preserves high-frequency information and maintains the deformation stability of EEG signals. To reduce the dimensionality of wavelet scattering coefficient features, we employ Kernel Principal Component Analysis (KPCA). Finally, the reduced features are fed into an Extreme Gradient Boosting (XGBoost) classifier within a multi-classification framework. The XGBoost classifier is optimized through hyperparameter tuning using grid search and 10-fold cross-validation, resulting in an average accuracy of 78.73% for the multi-character classification task. We utilize t-Distributed Stochastic Neighbor Embedding (t-SNE) technology to visualize the low-dimensional representation of multi-character speech imagery. This visualization effectively enables us to observe the clustering of similar characters. The experimental results demonstrate the effectiveness of our proposed multi-character classification scheme. Furthermore, our classification categories and accuracy exceed those reported in existing research.Keywords
This publication has 30 references indexed in Scilit:
- The decoder design and performance comparative analysis for closed-loop brain–machine interface systemCognitive Neurodynamics, 2022
- A hybrid autoencoder framework of dimensionality reduction for brain-computer interface decodingComputers in Biology and Medicine, 2022
- The LightGBM-based classification algorithm for Chinese characters speech imagery BCI systemCognitive Neurodynamics, 2022
- An efficient P300 detection algorithm based on Kernel Principal Component Analysis-Support Vector MachineComputers and Electrical Engineering, 2022
- Classification of alcoholic EEG signals using wavelet scattering transform-based featuresComputers in Biology and Medicine, 2021
- Scattering transform-based features for the automatic seizure detectionBiocybernetics and Biomedical Engineering, 2020
- Implementing a fuzzy inference system in a multi-objective EEG channel selection model for imagined speech classificationExpert Systems with Applications, 2016
- Classification of silent speech using support vector machine and relevance vector machineApplied Soft Computing, 2014
- An improved method to calculate phase locking value based on Hilbert–Huang transform and its applicationNeural Computing and Applications, 2013
- Spatiotemporal dynamics of electrocorticographic high gamma activity during overt and covert word repetitionNeuroImage, 2011