Muse 2 EEG during the MR session — 1 CSV row per second. Band powers use a rolling 5 s feature window.
Frontal = mean of AF7 & AF8. All = mean of TP9, TP10, AF7 & AF8. Each scope has its own metrics and its own 60 s baseline.
Within-person standard scores: (value − baseline mean) ÷ baseline SD, from the first 60 s after the window is full. Fixed at 0 until BaselineReady = 1.
Beta ÷ (Alpha + Theta), then 5 s smoothed and clamped 0–1. Higher values suggest relatively more beta vs relaxed (alpha/theta) rhythms.
Wall-clock time when the row was saved (HH:mm:ss.mmm). Chart time is relative to the first row.
Mean delta (0.5–4 Hz) power over 5 s, averaged across AF7 and AF8. Associated with deep sleep / low arousal.
Mean theta (4–8 Hz) power over 5 s, AF7 & AF8. Often linked to drowsiness, memory, or internal focus.
Mean alpha (8–12 Hz) power over 5 s, AF7 & AF8. Often increases when relaxed with eyes closed.
Mean beta (13–30 Hz) power over 5 s, AF7 & AF8. Often associated with active thinking and alertness.
Beta ÷ (Alpha + Theta) from frontal sensors. Raw engagement-related ratio before smoothing.
Z-score of the ratio vs that participant’s 60 s frontal baseline.
Primary frontal focus metric: ratio above, 5 s smoothed, scaled 0–1. Default line on the chart.
How far current frontal engagement is from the person’s own 60 s baseline (in SD units).
log(alpha AF8) − log(alpha AF7). Positive = relatively more right-frontal alpha (frontal alpha asymmetry, FAA).
FAA expressed as a Z-score vs the 60 s frontal baseline.
Pearson correlation of gamma power between AF7 and AF8 over 5 s (−1 to +1). Higher = more synchronized frontal gamma.
Gamma coherence Z-score vs 60 s frontal baseline.
Frontal delta power as a Z-score vs 60 s baseline.
Frontal theta power as a Z-score vs 60 s baseline.
Frontal alpha power as a Z-score vs 60 s baseline.
Frontal beta power as a Z-score vs 60 s baseline.
Mean delta power over 5 s, averaged across all four Muse electrodes.
Mean theta power over 5 s, all four sensors.
Mean alpha power over 5 s, all four sensors.
Mean beta power over 5 s, all four sensors.
Global Beta ÷ (Alpha + Theta) — same formula as frontal, wider spatial average.
Z-score of global ratio vs separate 60 s all-sensor baseline.
Global engagement: ratio above, 5 s smoothed, 0–1. Default white line on the chart.
Global engagement Z-score vs 60 s all-sensor baseline.
log(right alpha) − log(left alpha), where left = mean(TP9, AF7) and right = mean(TP10, AF8).
Global alpha asymmetry Z-score vs 60 s all-sensor baseline.
Correlation of gamma between left (TP9+AF7) and right (TP10+AF8) over 5 s.
Global gamma coherence Z-score vs 60 s all-sensor baseline.
Global delta Z-score vs 60 s all-sensor baseline.
Global theta Z-score vs 60 s all-sensor baseline.
Global alpha Z-score vs 60 s all-sensor baseline.
Global beta Z-score vs 60 s all-sensor baseline.
1 if a blink was detected in that 1 s interval, else 0. Useful for spotting movement artifacts.
Muse headband fit (HSI) per electrode: 0 = good, 1 = ok, 2 = poor, 4 = no signal. Shown as coloured strips under the chart.
Running count of AI tutor speech segments (logged when the NPC actually speaks, not button presses).
Wall-clock start of the current or last AI answer (blank if none yet).
Wall-clock end of the current or last AI answer (blank if none yet).
1 after both 60 s baselines (Frontal and All) are complete. Trust _Z columns from this point onward.
1 when at least ~5 s of EEG data is available for feature calculation.
Seconds since Muse connection — marks the start of baseline collection.
Click or drop MP4
Load redesigned EEG CSV
Workflow: trim CSV/video ranges first, then mark a clear video cue and align it to the matching CSV time (AI answer bar, engagement change, or lesson start). Use nudge or [ ] keys for fine adjustment.