A Multi-Stream Approach for Seizure Classification with Knowledge Distillation - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

A Multi-Stream Approach for Seizure Classification with Knowledge Distillation

Jen-Cheng Hou
  • Fonction : Auteur
  • PersonId : 1117053
Aileen Mcgonigal
  • Fonction : Auteur
  • PersonId : 1117054
Fabrice Bartolomei

Résumé

In this work, we propose a multi-stream approach with knowledge distillation to classify epileptic seizures and psychogenic non-epileptic seizures. The proposed framework utilizes multi-stream information from keypoints and appearance from both body and face. We take the detected keypoints through time as spatio-temporal graph and train it with an adaptive graph convolutional networks to model the spatio-temporal dynamics throughout the seizure event. Besides, we regularize the keypoint features with complementary information from the appearance stream by imposing a knowledge distillation mechanism. We demonstrate the effectiveness of our approach by conducting experiments on real-world seizure videos. The experiments are conducted by both seizure-wise cross validation and leaveone-subject-out validation, and with the proposed model, the performances of the F1-score/accuracy are 0.89/0.87 for seizure-wise cross validation, and 0.75/0.72 for leaveone-subject-out validation.
Fichier principal
Vignette du fichier
avss2021.pdf (1.08 Mo) Télécharger le fichier

Dates et versions

hal-03433317 , version 1 (17-11-2021)

Identifiants

Citer

Jen-Cheng Hou, Aileen Mcgonigal, Fabrice Bartolomei, Monique Thonnat. A Multi-Stream Approach for Seizure Classification with Knowledge Distillation. AVSS 2021 - 17th IEEE International Conference on Advanced Video and Signal-based Surveillance, Nov 2021, Virtual, United States. ⟨10.1109/AVSS52988.2021.9663770⟩. ⟨hal-03433317⟩
121 Consultations
138 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More