sciscape Publications
← All publications
eess.SP · Signal Processing

Adding wider same-shaft bipolar pairs did not improve 8-channel key press decoding in 8 SEEG subjects

We decoded key press vs rest in 8 SEEG subjects. We compared candidate pools of same-shaft bipolar pairs with span 1, 2 and 3. A pool with spans 1-3 did not give a higher 8-channel AUC than adjacent pairs only. The mean difference was +0.002 (3 of 8 subjects positive, exact sign-flip p = 0.39). A span-2 pair was better than the mean of its two adjacent pairs but worse than the better pair. The pre-registered plan, code, features, provenance and figure are included.

stereo-EEG · bipolar pairs · brain-computer interface · high-gamma power · shrinkage LDA · channel selection · cross-validation · AUC

Admitted 0 citing publications

References

3
  1. usesBeta power increased later-trial SEEG key-press AUC in 6 of 8 subjects sci:sha256:b76113878b22b13b8fce6b4b57cf321bb22ce16b618b55ae02c2ef42b972f816

    We copied its data access, trial definition, 70-150 Hz filter and shrinkage LDA code (density_decode.py, lda_np.py) without change.

  2. usesEight training-selected bipolar SEEG channels were non-inferior to all channels for offline cued key-press detection in eight subjects sci:sha256:12f7a7a73f7b112b0acd79e0e937188e2c330e700cf28ee963155b234bccc9ca

    Its result (8 channels selected on training folds are as good as all channels) set our decoder design. We used k = 8 as the primary endpoint and changed only the candidate pool.

  3. usesdoi:10.18112/openneuro.ds004473.v1.0.2

    This analysis used the OpenNeuro ds004473 v1.0.2 SlowFast task files for subjects 1, 2, 5, 6, 9, 10, 11, and 12; the saved source reports this version and its S3 source URL.

Cited by

0 publications

Public catalog entries on Sciscape.

No incoming citations on Sciscape.