Brain Machine
Brain-machine interfaces (BMIs) aim to establish direct communication pathways between the brain and external devices, primarily focusing on restoring lost function or enhancing human capabilities. Current research emphasizes improving the accuracy and robustness of decoding brain signals using advanced machine learning techniques, such as large language models (LLMs) and graph neural networks, often incorporating adaptive control strategies to address the inherent limitations of brain signals. This field holds significant promise for revolutionizing healthcare, particularly in neurorehabilitation and assistive technologies, and is also driving innovation in human-computer interaction and augmented reality applications.
Papers
MindSpeech: Continuous Imagined Speech Decoding using High-Density fNIRS and Prompt Tuning for Advanced Human-AI Interaction
Suyi Zhang, Ekram Alam, Jack Baber, Francesca Bianco, Edward Turner, Maysam Chamanzar, Hamid Dehghani
Goal Estimation-based Adaptive Shared Control for Brain-Machine Interfaces Remote Robot Navigation
Tomoka Muraoka, Tatsuya Aoki, Masayuki Hirata, Tadahiro Taniguchi, Takato Horii, Takayuki Nagai