کنفرانس مهندسی برق ایران

صفحه اصلی / سی و سومین کنفرانس بین المللی مهندسی برق

A Combined Channel Approach for Decoding Intracranial EEG Signals: Enhancing Accuracy through Spatial Information Integration

نویسندگان :

Maryam Ostadsharif Memar¹ Navid Ziaei² Behzad Nazari³

1- دانشگاه صنعتی اصفهان 2- دانشگاه صنعتی اصفهان 3- دانشگاه صنعتی اصفهان

کلمات کلیدی :

Intracranial Electroencephalography (iEEG)،Neural decoding،iEEG decoder،Machine learning،Brain-computer interface (BCI)

چکیده :

Intracranial EEG (iEEG) recording, characterized by its high spatial and temporal resolution and superior signal-to-noise ratio (SNR), enables the development of precise brain-computer interface (BCI) systems for neural decoding. However, the invasive nature of the procedure significantly limits the availability of iEEG datasets, both in terms of the number of participants and the duration of recorded sessions. To overcome this, we propose a single-participant machine learning model optimized for decoding iEEG signals. The model employs 18 key features and operates in two modes: best channel and combined channel. The combined channel mode integrates spatial information from multiple brain regions, resulting in superior classification performance. Evaluations across three datasets—Music Reconstruction, Audio Visual, and AJILE12—demonstrate that the model in combined channel mode consistently outperforms the best channel mode across all classifiers. In the best-performing cases, Random Forest reached an F1 score of 0.81 ± 0.05 in the Music Reconstruction dataset, 0.82 ± 0.10 in the Audio Visual dataset, and XGBoost achieved an F1 score of 0.84 ± 0.08 in the AJILE12 dataset. Additionally, the analysis of brain region contributions in combined channel mode revealed that the model can identify relevant brain regions, aligned with physiological expectations, for each task and effectively combine the data from electrodes in these regions to achieve high performance. These findings underscore the resulting of integrating spatial information across brain regions to improve task decoding, offering new avenues for advancing BCI systems and neurotechnological applications.