1. Extracting temporal dependencies from geospatial time series data
- Author
-
Chisholm, S. and Hailes, S.
- Subjects
004 - Abstract
In recent years, there have been significant advances in the technology used to collect data on the movement and activity patterns of humans and animals. GPS units, which form the primary source of location data, have become cheaper, more accurate, lighter and less power-hungry, and their accuracy has been further improved with the addition of inertial measurement units. The consequence is a glut of geospatial time series data, recorded at rates that range from one position fix every several hours (to maximise system lifetime) to ten fixes per second (in high dynamic situations). Since data of this quality and volume has only recently become available, the analytical methods to extract behavioural information from raw position data are at an early stage of development. An instance of this lies in the analysis of animal movement patterns. There are, broadly speaking, two types of animals: solitary animals and social animals. In the former case, the timing and location of instances of avoidance and association are important behavioural markers. In the latter case, the identification of periods and strengths of social interaction is a necessary precursor to social network analysis. In this dissertation, we present two novel analytical methods for extracting behavioural information from geospatial time series, one for each case. For solitary animals, a new method to detect avoidance and association between individuals is proposed; unlike existing methods, assumptions about the shape of the territories or the nature of individual movement are not needed. For social individuals, we have made significant progress in developing a method to test for cointegration; this measures the extent to which two non-stationary time series have a stationary linear relationship between them and can be used to assess whether a pair of animals move together. This method has more general application in time series analysis; for example, in financial time series analysis.
- Published
- 2016