Pixi Kang

About

Pixi Kang is at the forefront of advancing wearable Brain-Computer Interfaces (BCIs), with a primary focus on making EEG-based neural decoding both practical and personalized. Her most-cited work, “On-device Learning of EEGNet-based Network For Wearable Motor Imagery Brain-Computer Interface” (2024, 11 citations), tackles a critical bottleneck in BCI technology: the performance degradation of deep learning models when applied to new users. By pioneering on-device learning strategies for EEGNet, Kang enables real-time, user-specific adaptation directly on wearable hardware—eliminating the need for cloud computing or extensive retraining. This contribution is pivotal for real-world applications in rehabilitation and robotics, where robust, individualized performance is essential. Her research elegantly bridges the gap between high-accuracy neural network decoding and the practical constraints of low-power, portable devices. With a growing citation footprint, Kang is establishing herself as a key innovator in making BCIs more accessible and reliable. Her work not only advances the field of motor imagery decoding but also sets a new standard for adaptive, user-centric wearable neurotechnology.

Research Focus

Key Achievements

Top Papers

1. 1
   On-device Learning of EEGNet-based Network For Wearable Motor Imagery Brain-Computer Interface

   11 citations · 2024

Key Collaborators

Contact & Links