Authors:
Francesco Iacomi
;
Andrea Farabbi
;
Maximiliano Mollura
;
Edoardo Polo
;
Riccardo Barbieri
and
Luca Mainardi
Affiliation:
Department of Electronics, Information and Bioengineering, Politecnico di Milano, Milano, Italy
Keyword(s):
Electroencephalogram (EEG), Machine Learning, Brain Computer Interface (BCI), Imagined Speech, Biomedical Signal Processing.
Abstract:
This study presents an innovative approach for decoding imagined speech using EEG signals. The proposed analysis aims at revealing phonetic and semantic properties of imagined words through brain activity. The experimental protocol involves presenting words to subjects while recording EEG signals via a 64-channels cap. Each word is associated with three specific properties: length, presence of doubles, and category of meaning. The protocol includes fixation, cue presentation, thinking, and rest phases. EEG signals undergo meticulous preprocessing stage to mitigate noise and artifacts. Features are extracted from the processed signal, including statistical, spectral, and fractal domain measures. The dimensionality of features is reduced through statistical means. Several classifiers, (e.g., MLP, KNN, LDA, QDA), are trained and evaluated to predict mentioned properties of imagined words. An ensemble model (LDA) comprising the best 3 models mentioned above is then employed to enhance cl
assification accuracy. Results illustrate the effectiveness of decoding imagined word properties with average accuracies of 35.2% for ”Category”, 57.2% for ”Doubles”, and 55.8% for ”Length”. By aggregating all predictions we are able to decode each single word with a mean accuracy of 11.8% (random accuracy = 8.33%) and an average word distance of 1.54. Post-classification studies on the most relevant variables and on the most discriminating channels further deepen our understanding of the proposed Imagined Speech cognitive process, showing different brain activations for different linguistic aspects.
(More)