EEG Seizure Detection (PWDR) L1-531

Medical ImagingCortical electrical signal feature recovery from EEG with seizure / non-seizure categorical readoutδ=5 · advancedL_DAG = 6📋 Stub — not mineable

📋

Unclaimed Principle — open for contribution

This Principle is declared in the catalog but has no reference solver, no pinned dataset, and is not registered on-chain. There is no reward pool. Submitting a cert against this Principle today will record the cert for reproducibility but pay zero PWM.

To claim it as a Bounty #7 contribution: open a PR adding (1) a reference solver, (2) ≥1 dataset pinned to IPFS, (3) updates to the L3 manifest with dataset CIDs. After verifier-agent triple-review, the founders' 3-of-5 multisig signs PWMRegistry.register() and the Principle becomes mineable.

Read the contribution guide →Open a claim issue →

Forward model E

S t a g e 1 (L 1 - 068) : m u l t i - c hann e l E E G \to s p ec t r a l_{p} o w er (c hann e l, f r e q u e n cy, t im e), s p a t ia l_{c} o h er e n ce, e v o l u t i o n_{f} e a t u r es, a r t i f a c t_{m} a s k . S t a g e 2 : se i z u r e_{c} l a ss = s t e p (f e a t u r es p er I L A E 2017 + T r ink a 2015 t h r es h o l d s) .

EEG Seizure Detection (PWDR): wraps L1-068 EEG with ILAE 2017 + Trinka 2015 + AAN clinical neurophysiology rules. Stage 1 (analytical, from L1-068): from multi-channel scalp EEG (typically 19-256 channels per international 10-20 / 10-10 systems), recover per-channel spectral content (delta 0.5-4 Hz, theta 4-8 Hz, alpha 8-13 Hz, beta 13-30 Hz, gamma 30-80 Hz), spatial coherence patterns, evolution of dominant frequency/amplitude/morphology, artifact rejection (eye blinks, muscle, cardiac). Stage 2 (deterministic threshold): apply rhythmic-pattern + evolution + duration + spatial-distribution rules. Difficulty tier delta = 5.

L-DAG

L.eeg_acquisition -> L.bandpass_filter -> L.artifact_rejection -> L.spectral_decomposition -> L.evolution_detection -> L.seizure_threshold_classifier -> int.temporal_spatial

L.eeg_acquisitionL.bandpass_filterL.artifact_rejectionL.spectral_decompositionL.evolution_detectionL.seizure_threshold_classifierint.temporal_spatial

Well-posedness W

Existence:: true
Uniqueness:: conditional
Stability:: conditional
κ:: 100

Existence inherited from L1-068. Uniqueness conditional on adequate channel coverage + electrode impedance < 10 kohm. Stability dominated by muscle_artifact and drowsy_state_confounder (subclinical seizures). Joint Hadamard well-posedness established by Fisher 2017 (ILAE 2017 Operational Classification), Trinka 2015 (status epilepticus definition), Hirsch 2013 (ACNS critical-care EEG terminology), Roy 2019 (deep learning EEG seizure benchmark), Acharya 2018 (EEG seizure deep learning review).

Solvability C

Solver class:: linear-operator + signal-processing [bandpass + ICA artifact rejection + STFT/wavelet] + categorical-readout [ILAE classifier] | end-to-end deep neural [SeizNet, SeizureNet, EEGNet]
Convergence rate q:: 1
Complexity:: O(N_channels * N_samples * log(N_samples)) for stage 1 STFT + O(N_segments * N_features) for stage 2

Specs (0)

No L2 specs registered yet for this principle.