Editorial: Methods in Brain-Computer Interfaces: 2023

Davide Borra^1*Ming Ma^2*Ester Martinez-Martin^3*Likun Xia⁴

• ¹Universita degli Studi di Bologna, Bologna, Italy
• ²Yeshiva University, New York, United States
• ³University of Alicante, Alicante, Spain
• ⁴Capital Normal University, Beijing, China

Brain-computer interfaces (BCIs) represent a rapidly evolving field within human neuroscience, 14 enabling direct link between the brain and external devices. BCI research is aiming at transitioning 15 from experimental constructs to accurate and generalized tools with transformative implications in 16 clinical, commercial, and assistive domains. Despite significant advancements in the field, such as the 17 design and application of artificial intelligence methods (e.g., convolutional neural networks) [1] for 18 improving neural decoding, several challenges persist. A primary concern involves neural decoding, 19 which is affected by intra-and inter-subject variability as well as the limited availability of labeled data 20 [2]. In addition, improving user experience and ensuring system robustness in follow-up care. While the integration of these technologies is in its infancy, this approach theorizes an 55 interesting future direction of BCIs, towards LLM-enhanced BCI frameworks. However, an important 56 challenge of such theorized framework lies in orchestrating its components to operate synchronously, 57 ethically, and securely. 58Collectively, these contributions underscore the need for standardized methodologies and 59 comprehensive evaluations of existing techniques to bridge the gap between experimental success and 60 practical implementation. We hope this collection of articles inspires ongoing methodological 61 exploration and interdisciplinary collaboration, fostering the development of more efficient and 62 effective BCI solutions. 63The methodological advances of BCI research in 2023 reflect a field that is aiming to bridge the gap 65 between theoretical innovations and practical utility. From BCI frameworks employing reinforcement 66 learning, heterogeneous transfer learning and LLMs to speech decoding, the year has been marked by 67 a diverse array of breakthroughs. Future research should prioritize a robust benchmarking of the 68 algorithms -also consolidating their validation on larger datasets -and testing online the approaches, 69 to promote the integration of BCIs into real-world applications. 70We extend our deepest gratitude to the contributing authors for their excellent work, and to the 72 reviewers for their thoughtful and constructive feedback. Special thanks to the editorial team for 73 supporting this research topic and ensuring a smooth publication process. We believe this research 74 topic offers valuable insights for researchers, practitioners, and technologists who are committed to 75 advancing the science and application of BCIs. 76