SOURCE RECORD / S0200

Subject-Independent Wearable P300 Brain-Computer Interface Based on Convolutional Neural Network and Metric Learning

Evidence B

Subject-Independent Wearable P300 Brain-Computer Interface Based on Convolutional Neural Network and Metric Learning

Authors or organization
Hu L, Gao W, Lu Z, Shan C, Ma H, Zhang W, Li Y
Published date
2024-09-25
Source type
peer_reviewed_human_dataset_study
Technology route
non-invasive wearable EEG P300
Function or setting
assistive spelling and low-calibration BCI
Rights status
manual_review / CC BY-NC-ND 4.0 (association not snapshotted)

Evidence summary

Evidence: Subject-independent and fine-tuned wearable P300 feasibility. Key figures: 73.23+/-7.62% without calibration; 78.75+/-6.37% with fine-tuning. Limitations: Accuracy is not characters per minute or errors per hour; patient, cross-day, home-use, product availability and China TCO evidence not reported.

Key figures

73.23+/-7.62% without calibration; 78.75+/-6.37% with fine-tuning

Limitations

Accuracy is not characters per minute or errors per hour; patient, cross-day, home-use, product availability and China TCO evidence not reported

SOURCE RECORD

Source record

Open complete source detail