Invasive Electroencephalography in Epilepsy

Serletis, Demitre

doi:10.1007/978-3-319-95918-4_9

Cited by 1 publication

(1 citation statement)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Among the various brain imaging techniques employed to measure these neural activities, electroencephalography (EEG) stands out, largely owing to its superior advantages such as non-invasiveness, high-temporal resolution, cost-effectiveness, and portability [6], [7]. Although invasive techniques provide more precise control with the advantage of directly reading high-quality neural signals, they also carry the risk of potential side effects [8]. Consequently, the EEG-based BCI system has drawn attention as a promising tool with the capacity to improve the quality of life.…”

Section: Introductionmentioning

confidence: 99%

Two-Phase Multitask Autoencoder-Based Deep Learning Framework for Subject-Independent EEG Motor Imagery Classification

Jin,

Song,

Kim

2024

IEEE Access

View full text Add to dashboard Cite

Electroencephalography (EEG)-based motor imagery (MI) has potential applications in diverse fields including rehabilitation, drone control, and virtual reality. However, its practical use is hindered by low generalization performance in decoding brain signals, primarily due to the subject-dependency of EEG signals. Although multitask autoencoder (MTAE) techniques have recently been used to mitigate this issue, these approaches encounter an imbalance problem between loss functions with different objectives, particularly between reconstruction loss and cross-entropy. To address this, we propose a novel twophase multitask autoencoder (2PMTAE) framework that not only rectifies the imbalance issue but also ensures stable training of the MTAE. Our framework comprises two phases: first, the generation of a classspecific target signal, and second, the calculation of the reconstruction loss based on the generated target signals, effectively aligning the objectives of the two loss functions. In subject-independent experiments, our proposed method significantly outperformed state-of-the-art techniques, achieving accuracies of 71.68% and 75.78% on the BCI competition IV-2a and OpenBMI datasets, respectively. We also show that 2PMTAE is a generic framework for MI applications that can accept any encoder the practitioner wishes to employ. These results highlight the efficacy of our approach in enhancing the generalization performance of MI-EEG decoding.

show abstract

Section: Introductionmentioning

confidence: 99%