Brain-machine interface (BMI) has been introduced as a potential bi-directional medium between humans/animals and machines in robotics and medicine. Different neural recording modalities such as single-unit, multi-unit, LFP, ECoG, and EEG can provide different local or global information with differences in spatial-temporal-spectral resolution, long-term stability, noise/artifact contamination, and invasiveness. There are still many key challenges toward making reliable BMIs for both neural restorative technologies and understanding the neural mechanism of the movement/speech/cognitive functions. Topics include, but are not limited to:
• Motor/sensory and speech/language recovery in different neurological disorders
• BCI for human-AI alignment
• Dimensionality reduction for neural population data analysis
• Latent dynamic analysis of neural populations
• Machine learning strategies to improve BMI decoding performance
• Novel experimental design for BMI applications
• Sensory/Neurofeedback to improve BMI efficiency
• Artifact issues in real-world BMI applications with diverse environments and conditions.
• Nonstationary neural signals across sessions/days/subjects
• Speech decoding for natural language processing
• Understanding speech generation and language processing in human subjects
We accept original studies addressing the above challenges. We are also happy to consider theory and review papers.
Brain-machine interface (BMI) has been introduced as a potential bi-directional medium between humans/animals and machines in robotics and medicine. Different neural recording modalities such as single-unit, multi-unit, LFP, ECoG, and EEG can provide different local or global information with differences in spatial-temporal-spectral resolution, long-term stability, noise/artifact contamination, and invasiveness. There are still many key challenges toward making reliable BMIs for both neural restorative technologies and understanding the neural mechanism of the movement/speech/cognitive functions. Topics include, but are not limited to:
• Motor/sensory and speech/language recovery in different neurological disorders
• BCI for human-AI alignment
• Dimensionality reduction for neural population data analysis
• Latent dynamic analysis of neural populations
• Machine learning strategies to improve BMI decoding performance
• Novel experimental design for BMI applications
• Sensory/Neurofeedback to improve BMI efficiency
• Artifact issues in real-world BMI applications with diverse environments and conditions.
• Nonstationary neural signals across sessions/days/subjects
• Speech decoding for natural language processing
• Understanding speech generation and language processing in human subjects
We accept original studies addressing the above challenges. We are also happy to consider theory and review papers.