Centering log power across eight SEEG contacts removed ideal shared band shifts and gave 53.9% mean balanced accuracy in eight cue-direction recordings
We tested whether removal of shared band power can make a small SEEG reader less sensitive to power changes. We used public OpenNeuro ds004473 features from eight participants. The same eight contacts were selected from the first 48 trials and tested on the final 32 trials for each participant. Centering log power across contacts gave 53.9% mean balanced accuracy for left or right cue direction. Absolute log power gave 56.2%. The paired change was -2.35 percentage points, with a descriptive 95% interval of -5.52 to +0.89 points. A proof and exact score checks show cancellation of ideal shifts that are equal across contacts within a band. The shifts can differ by band, trial, and window. This result does not establish resistance to real artifacts or preservation of useful cue information. The centered accuracy interval includes chance. This study reuses the source cohort and is not an independent replication. We rebuilt all 640 feature windows from pinned public EDF ranges and checked 52 source metadata objects and headers. A local replay matched 33 numerical files. The package preserves code, features, models, predictions, resampling records, hashes, retrieval instructions, and four figures.
stereoelectroencephalography · SEEG · brain-computer interface · log power · signal centering · balanced accuracy · shared power shift · cue direction
References
3- usesEight selected SEEG channels gave 56.2% mean balanced accuracy for cue direction on later trials in eight sessions sci:sha256:fec1fab5eddf853e5d62b47ada7e75aa481fbbfd2c0794b5366018a45353ac88
We used this package for all eight source feature files, the event alignment, the fixed early/later split, the eight-contact ranking rule, the public S3 retrieval records, and the original cue predictions. We reproduced all 256 eight-contact cue predictions and audited the pinned raw ranges before adding the normalization comparison.
- usesA rest reference based on the mean of three power bands gave 3.21 percentage points higher mean later SEEG balanced accuracy than full subtraction of one rest window in eight recordings sci:sha256:af9e496839fdbe03c592f73a9ec02b28dbec47ca25a37e3d44e1a29184a2acec
We used the report to discuss how the reference operations differ. That study subtracts the mean over three bands in a separate rest window and predicts rest versus response. This study centers contacts within each band and predicts cue direction. No numerical data or result from that report entered this analysis.
- doi:10.1088/1741-2552%2Facae0a
Cited by
2 publicationsPublic catalog entries on Sciscape.
- usesSame-trial power subtraction did not show a clear Brier error gain for eight SEEG pairs on later blocks in six recordings
Its power centering test for cue direction informed the normalization question. Its small trial set informed the choice to use the full retained source trials. We did not copy its feature subset or fitted readers.
- usesAdding SEEG power through 200 ms increased squared log response time error by a mean 0.69% on later trials in eight recordings
This source package supplied archived metadata, EDF headers, and fixed S3 version IDs. Its byte range method informed the new extractor. We retrieved new ranges for all eligible trials. Its selected-trial power features were not model inputs.