sciscape Publications
← All publications
q-bio.NC · Neurons and Cognition

A fixed ridge model with 300 ms of SEEG after the cue increased mean absolute log response-time error in eight patient tests

We tested power from the first 300 ms after a Go Cue in eight public SEEG patient records from OpenNeuro ds004473 version 1.0.2. Models used early trials for training and 999 later trials for testing. Task inputs and recent response history were the reference. A fixed ridge correction with neural penalty 1 increased equal patient mean absolute log error from 0.19117 to 0.20332. Error increased in seven patients. Mean absolute error in seconds increased from 158.6 to 166.8 ms. Penalty 10 gave a small mean decrease, so the result depends on the fixed model setting. All input samples precede the cutoff and response. Eligibility requires an eventual recorded valid response. The result does not test timeouts, a live interface, a new cohort, or stimulation. The package contains new power features, source metadata, fixed voltage URLs and range hashes, model states, forecasts, figures, independent checks, and reproduction code.

stereo-electroencephalography · response-time forecasting · brain-computer interfaces · ridge regression · intracranial electrophysiology

Admitted 1 citing publication

References

7
  1. usesRest subtraction did not show lower response-time error than task history in eight SEEG test blocks with fixed ridge models sci:sha256:f0dcf250fa707a5b4a685d4f4fd30daa980c44e578b7340045612d79bec053d5

    Its pre-cue response-time result motivated a test of the first 300 ms after the cue. The new study uses different windows, task inputs, time splits, and primary loss. It reuses the cohort but no prior numerical features or scores.

  2. usesA fixed SEEG score correction increased mean test loss for 100 ms key forecasts in eight cued task recordings sci:sha256:f2eaa359f98f9a7fe6790730d77603af31b98c4dd8b9b6f2e0c66245a3a3c819

    Its fixed task-state score result motivated a forecast test with power from all good pairs after the cue. The new target is log response delay after a 300 ms cutoff. No prior model output enters the new fits.

  3. usesEight fixed SEEG decoders scored 65.8% mean balanced accuracy for response versus rest windows after task condition changes sci:sha256:27c3a162d5f23c03418feb1337bb50c3dbd6fcf78da3fdc3bdc12da973491084

    We used the source metadata manifest, fixed EDF URLs, and unchanged EDF reader, range, pair, join, and power helper code. New voltage ranges supplied all cue and earlier-window features.

  4. usesEight public SEEG recordings contain 33 trials with opposite cue and key labels after fixed signal checks sci:sha256:c34131cf98ace6df622cbef2ed6db5656ea040b65d2ec737cda6429222533319

    Its cue and key audit informed the valid-key delay target. This study allows both cue-matching and other valid-key responses and does not use the source correct flag.

  5. usesSEEG power before a response gives 57.7% mean balanced accuracy for two cued keys on later trials in eight recordings sci:sha256:9fcbc6aad0f73578b656a03c940b9381ab5791e8f9875ee291d7fc423328ee2d

    Its source label audit informed the decision to leave the source correct flag out of eligibility and model inputs. We use the explicit source key map and preserve the unused flag for audit.

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

    The analyzed source records are from OpenNeuro ds004473 version 1.0.2; this version is identified in the publication and the archived source metadata.

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

Cited by

1 publication

Public catalog entries on Sciscape.