Akima Connelly

Papers

Total Citations

H-Index

About

Akima Connelly is a leading researcher at the intersection of neuroscience and artificial intelligence, specializing in brain-computer interfaces (BCIs) and deep learning for neural signal processing. Her most cited work, "An end-to-end CNN with attentional mechanism applied to raw EEG in a BCI classification task" (2021, 48 citations), introduces a novel convolutional neural network architecture that directly processes raw electroencephalography (EEG) data for motor-imagery classification. This contribution is significant because it eliminates the need for manual feature engineering, while incorporating an attentional mechanism that dynamically focuses on the most informative temporal and spatial patterns in brain signals. Connelly’s approach has advanced the practicality of BCIs for healthcare applications, including mobile assistive robots and neurorehabilitation, by improving classification accuracy and robustness. Her work demonstrates a clear impact on the field, with her top-cited paper serving as a foundational reference for researchers developing end-to-end deep learning solutions for neural decoding. Connelly’s research continues to bridge the gap between raw neural data and real-world assistive technologies, making her a notable figure in the ongoing evolution of intelligent, non-invasive BCIs.