Accelerometer based Activity Classification with Variational Inference on Sticky HDP-SLDS
This work addresses activity monitoring for daily human use via smartphones, presenting an incremental improvement in inference speed for an existing model.
The paper tackled activity classification using smartphone accelerometer data by proposing a fast variational inference method for a sticky HDP-SLDS model, achieving differentiation of activities like sitting and walking with variational inference being an order of magnitude faster than Gibbs sampling.
As part of daily monitoring of human activities, wearable sensors and devices are becoming increasingly popular sources of data. With the advent of smartphones equipped with acceloremeter, gyroscope and camera; it is now possible to develop activity classification platforms everyone can use conveniently. In this paper, we propose a fast inference method for an unsupervised non-parametric time series model namely variational inference for sticky HDP-SLDS(Hierarchical Dirichlet Process Switching Linear Dynamical System). We show that the proposed algorithm can differentiate various indoor activities such as sitting, walking, turning, going up/down the stairs and taking the elevator using only the acceloremeter of an Android smartphone Samsung Galaxy S4. We used the front camera of the smartphone to annotate activity types precisely. We compared the proposed method with Hidden Markov Models with Gaussian emission probabilities on a dataset of 10 subjects. We showed that the efficacy of the stickiness property. We further compared the variational inference to the Gibbs sampler on the same model and show that variational inference is faster in one order of magnitude.