New formulation of the Logistic-Normal process to analyze trajectory tracking data

by   Gianluca Mastrantonio, et al.

Improved communication systems, shrinking battery sizes and the price drop of tracking devices have led to an increasing availability of trajectory tracking data. These data are often analyzed to understand animals behavior using mixture-type model. Due to their straightforward implementation and efficiency, hidden Markov mod- els are generally used but they are based on assumptions that are rarely verified on real data. In this work we propose a new model based on the Logistic-Normal process. Due to a new formalization and the way we specify the coregionalization matrix of the associated multivariate Gaussian process, we show that our model, differently from other proposals, is invariant with respect to the choice of the reference element and the ordering of the probability vectors components. We estimate the model under a Bayesian framework, using an approximation of the Gaussian process needed to avoid impractical computational time. After a simulation study, where we show the ability of the model to retrieve the parameters used to simulate the data, the model is applied to the real data example, that motivated this work, where a wolf is observed before and after the procreation. Results are easy interpretable showing differences in the two time windows.


page 10

page 11

page 14


A Bayesian approach for clustering skewed data using mixtures of multivariate normal-inverse Gaussian distributions

Non-Gaussian mixture models are gaining increasing attention for mixture...

Backflipping with Miniature Quadcopters by Gaussian Process Based Control and Planning

The paper proposes two control methods for performing a backflip maneuve...

Using neural networks to estimate parameters in spatial point process models

In this paper, I show how neural networks can be used to simultaneously ...

Infinite Mixtures of Multivariate Gaussian Processes

This paper presents a new model called infinite mixtures of multivariate...

The modeling of multiple animals that share behavioral features

In this work, we propose a model that can be used to infer the behavior ...

Mixture of hidden Markov models for accelerometer data

This work is motivated by the analysis of accelerometer data. The analys...

Please sign up or login with your details

Forgot password? Click here to reset