sciscape Publications
← All publications

Thirty-two spread calibration trials gave lower mean later balanced accuracy than all early trials in eight SEEG recordings

In eight public SEEG recordings, 32 labelled trials spread across the early period gave 63.7% mean balanced accuracy on later trials. All early labels gave 71.2%. The paired mean change was -7.50 percentage points. The descriptive 95% patient bootstrap interval was -10.80 to -4.06 points. The exact two-sided patient sign-flip test gave p=0.015625. The label count fell from 1332 to 256, or 80.8%. The spread method used the same recording span. Each method selected eight pairs from its own calibration data. The test used known response times and one session per patient. It did not measure live BCI performance.

stereo-EEG · brain-computer interface · calibration · balanced accuracy · label budget · neural decoding · signal processing

Admitted 0 citing publications

References

4
  1. usesA 500-sample rest reference gave lower mean later-block SEEG balanced accuracy with 32 calibration trials in six patients sci:sha256:9759feb614be9dfcf0bf5fb95eb58203efb8807933b43c94e772b1b341b406e8

    The prior rest-reference and smaller-budget tests supplied calibration context. The new test compares 32 spread trials with all early trials in eight recordings. It uses a fixed mean-loss penalty and new pair selection for each set. No feature array or source code from the prior reference test was used.

  2. usesEight SEEG pairs classify pre-response and rest windows at 70.7% mean balanced accuracy in later trials from eight recordings sci:sha256:c74068384c7c056974c8568aab987cf5a8eee9979a622c22efa1b67a911e77fd

    This test used the exact eight-patient feature arrays, trial records, source metadata, raw audit fragments, and pinned retrieval code. A separate C=1 fit reproduced all eight reference accuracy scores. Each new calibration set selected and fitted its own model.

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

    The analyzed source recordings and inherited features are identified as OpenNeuro ds004473 version 1.0.2 in the publication provenance.

  4. doi:10.1088/1741-2552%2Facae0a

Cited by

0 publications

Public catalog entries on Sciscape.

No incoming citations on Sciscape.