Continuous cursor tracking with a noninvasive BCI, across sessions
Forenzo & He continuous-tracking EEG-BCI dataset: EEG decoding results
The Forenzo & He continuous-tracking dataset (KiltHub 25360300, Carnegie Mellon University) holds EEG from 28 participants who used motor imagery to steer a cursor after a target moving continuously across a screen (continuous pursuit), over several sessions with traditional and deep-learning decoders, in two substudies, the second testing transfer learning; recorded with a 64-channel cap at 1 kHz. Released by Dylan Forenzo and Bin He under CC BY 4.0 and described in PNAS Nexus (2024). Only offline analyses from each record's earliest to its latest complete session are run here; the paper's online results are not reproduced.
Also known asForenzo & He (2024) · KiltHub 25360300 · EEG-BCI Dataset for Continuous Tracking using Deep Learning-based Decoding for Non-invasive Brain-Computer Interface · Forenzo et al. (2024) · continuous pursuit BCI dataset
Historical decoder velocity (historical decoder imitation, not intended motion) · ridge minus comparator, the same records
Paired difference in normalized RMSE
191.0240.026–572.995The ridge had the larger error on 9 of 9 admitted records; 9 of 14 candidate records admitted, the rest held on metadata before scoring, so the result is conditional on that subset.
9 records, not proven unique people
Later sessions · continuous cursor tracking, Main cohort, constructed displacement proxy (a negative result; offline, no online-control claim)
Constructed displacement proxy (constructed proxy) · ridge minus comparator, the same records
Paired difference in normalized RMSE
697.4430.121–2,092The ridge had the larger error on 9 of 9 admitted records; 9 of 14 candidate records admitted, the rest held on metadata before scoring, so the result is conditional on that subset.
9 records, not proven unique people
Later sessions · continuous cursor tracking, Transfer Learning cohort, historical decoder velocity (a negative result; offline, no online-control claim)
Historical decoder velocity (historical decoder imitation, not intended motion) · ridge minus comparator, the same records
Paired difference in normalized RMSE
43.3080.105–129.601The ridge had the larger error on 14 of 14 admitted records; 14 of 14 candidate records admitted. “Transfer Learning” is the publisher’s name for how the data were collected, not a model trained here.
14 records, not proven unique people
Later sessions · continuous cursor tracking, Transfer Learning cohort, constructed displacement proxy (a negative result; offline, no online-control claim)
Constructed displacement proxy (constructed proxy) · ridge minus comparator, the same records
Paired difference in normalized RMSE
68.9280.143–206.410The ridge had the larger error on 14 of 14 admitted records; 14 of 14 candidate records admitted. “Transfer Learning” is the publisher’s name for how the data were collected, not a model trained here.
14 records, not proven unique people
Source and licence
Forenzo & He continuous-tracking EEG-BCI dataset
CreditDylan Forenzo and Bin He · EEG-BCI Dataset for “Continuous Tracking using Deep Learning-based Decoding for Non-invasive Brain-Computer Interface”, KiltHub, Carnegie Mellon University, doi:10.1184/R1/25360300.v1, CC BY 4.0. Citation the record requests: Dylan Forenzo, Hao Zhu, Jenn Shanahan, Jaehyun Lim and Bin He, Continuous tracking using deep learning-based decoding for noninvasive brain–computer interface, PNAS Nexus 3(4), pgae145 (2024), doi:10.1093/pnasnexus/pgae145. Derived analysis by BCI Report; not endorsed by the authors and not a reproduction of the paper's online results.
BCI Report does not redistribute any recording. These are aggregate measurements computed by BCI Report under the licence above; the data belong to the people credited.
BCI Report