Classification d'événements à partir de capteurs sols - Application au suivi de personnes fragiles.

This thesis addresses the subject of event detection in temporal signals for elderly monitoring by the use of a floor pressure sensor. We first show that most proposed systems do not meet main practical issues and that floor systems constitute promising candidates for monitoring tasks. Since complex signals require sophisticated models, we propose a random-forest-based approach that detects falls with state-of-the-art accuracy and meets hardware constraints with a feature selection procedure. The model performance is improved with data augmentation and time aggregation of the random forest outputs. Then, we address the issue of confronting our model to the real world with transfer learning methods that act on the core model of random forests, i.e. decision trees. These methods are adaptations of seminal work and are designed to tackle the class imbalance problem as falls are rare events. Methods are tested on several data sets, showing interesting potential continuation, and a Python implementation is made available. Finally, motivated by the issue of elderly monitoring while dealing with one-dimensional signals for a large areas, we propose to distinguish elderly persons from younger individuals with a model based on convolutional neural network and convolutional dictionary learning. Since signals are mainly made of walks, the first part of the model is trained to recognize steps, and the last part of the model is trained with all previous layers frozen. This novel approach to gait classification allows to isolate elderly-generated signals with very high accuracy.