Powered-Two-Wheeler safety critical events recognition using a mixture model with quadratic logistic proportions - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2015

Powered-Two-Wheeler safety critical events recognition using a mixture model with quadratic logistic proportions

Résumé

This paper presents a statistical methodology that uses both acceleration and angular velocity signals to detect critical safety events for Powered Two Wheelers (PTW). The problem of recognition of critical events has been performed towards two steps: (1) the feature extraction step, where the multidimensional time trajectories of accelerometer/gyroscope data were modeled and segmented by using a specific mixture model with quadratic logistic proportions; (2) the classification step, which consists in using the k-nearest neighbor (k-NN) algorithm in order to assign each trajectory characterized by its extracted features to one of the three classes namely Fall, near Fall and Naturalistic riding. The results show the ability of the proposed methodology to detect critical safety events for Powered Two Wheelers.
Fichier non déposé

Dates et versions

hal-01215028 , version 1 (13-10-2015)

Identifiants

  • HAL Id : hal-01215028 , version 1

Citer

Ferhat Attal, Abderrahmane Boubezoul, Allou Same, Latifa Oukhellou. Powered-Two-Wheeler safety critical events recognition using a mixture model with quadratic logistic proportions. ESANN 2015 - 23rd European Symposium on Artificial Neural Networks, Apr 2015, BRUGES, Belgium. pp 421-426. ⟨hal-01215028⟩
58 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More