Personalized Posture and Fall Classification with Shallow Gated Recurrent Units

Abstract

Activities of Daily Living (ADL) classification is a key part of assisted living systems as it can be used to assess a person autonomy. We present in this paper an activity classification pipeline using Gated Recurrent Units (GRU) and inertial sequences. We aim to take advantage of the feature extraction properties of neural networks to free ourselves from defining rules or manually choosing features. We also investigate the advantages of resampling input sequences and personalizing GRU models to improve the performances. We evaluate our models on two datasets: a dataset containing five common postures: sitting, lying, standing, walking and transfer and a dataset named MobiAct V2 providing ADL and falls. Results show that the proposed approach could benefit eHealth services and particularly activity monitoring.

Learning personalized ADL recognition models from few raw data

“…Finally, we propose to analyze the results as a binary classification of falls vs. non falls similarly as in [5] where 0.808 of F-measure and 0.878 of Accuracy could be achieved on personalized fall detection. The results are presented in Table 7.…”

“…We tackle both of these issues in this extended version of our paper [5] by proposing a model able to perform personalized ADL classification from few raw data. Contrary to a common practice [6], we advocate for personalized models instead of general models: better performances can be achieved with personalized models since each user has his/her own way of doing his/her activities.…”

“…The selected users are the following : 1, 2,3,5,6,12,20,45, 53, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67 6. Actually, there remain some "standing" or "lying" parts in some sequences, for example in fall sequences.…”