Robust Unsupervised Transient Detection With Invariant Representation based on the Scattering Network
This work addresses the problem of reliable seizure prediction and spike detection for epileptic patients, which is incremental as it builds on existing scattering network methods.
The paper tackles robust unsupervised transient detection in noisy signals, specifically for predicting seizure onset and detecting inter-ictal spikes in epileptic patients from subdural recordings, by developing a sparse and invariant representation based on wavelet transforms and scattering networks with low asymptotic complexity.
We present a sparse and invariant representation with low asymptotic complexity for robust unsupervised transient and onset zone detection in noisy environments. This unsupervised approach is based on wavelet transforms and leverages the scattering network from Mallat et al. by deriving frequency invariance. This frequency invariance is a key concept to enforce robust representations of transients in presence of possible frequency shifts and perturbations occurring in the original signal. Implementation details as well as complexity analysis are provided in addition of the theoretical framework and the invariance properties. In this work, our primary application consists of predicting the onset of seizure in epileptic patients from subdural recordings as well as detecting inter-ictal spikes.