Towards a Network Expansion Approach for Reliable Brain-Computer Interface

Robotic arms are increasingly being used in collab-orative environments, requiring an accurate understanding of human intentions to ensure both effectiveness and safety. Elec-troencephalogram (EEG) signals, which measure brain activity, provide a direct means of communication between humans and robo...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:The ... International Winter Conference on Brain-Computer Interface s. 1 - 4
Hlavní autoři: Lee, Byeong-Hoo, Yin, Kang
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 24.02.2025
Témata:
Brain
brain-computer interface
Brain-computer interfaces
convolutional neural network
Convolutional neural networks
Data collection
electroencephalogram
Electroencephalography
Feature extraction
Manipulators
network expansion
Neural networks
Reliability
Safety
ISSN:2572-7672
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Robotic arms are increasingly being used in collab-orative environments, requiring an accurate understanding of human intentions to ensure both effectiveness and safety. Elec-troencephalogram (EEG) signals, which measure brain activity, provide a direct means of communication between humans and robotic systems. However, the inherent variability and instability of EEG signals, along with their diverse distribution, pose significant challenges in data collection and ultimately affect the reliability of EEG-based applications. This study presents an extensible network designed to improve its ability to extract essential features from EEG signals. This strategy focuses on improving performance by increasing network capacity through expansion when learning performance is insufficient. Evaluations were conducted in a pseudo-online format. Results showed that the proposed method outperformed control groups over three sessions and yielded competitive performance, confirming the ability of the network to be calibrated and personalized with data from new sessions.
ISSN:2572-7672
DOI:10.1109/BCI65088.2025.10931572