search query: @keyword sequential Monte Carlo method / total: 1
reference: 1 / 1
« previous | next »
Author: | Abbas, Mudassar |
Title: | Statistical Estimation of Wild Animal Population in Finland: A Multiple Target Tracking Approach |
Publication type: | Master's thesis |
Publication year: | 2011 |
Pages: | 68 Language: eng |
Department/School: | Perustieteiden korkeakoulu |
Main subject: | Laskennallinen tekniikka (S-114) |
Supervisor: | Lampinen, Jouko |
Instructor: | Särkkä, Simo ; Vehtari, Aki |
Electronic version URL: | http://urn.fi/URN:NBN:fi:aalto-201207022760 |
OEVS: | Electronic archive copy is available via Aalto Thesis Database.
Instructions Reading digital theses in the closed network of the Aalto University Harald Herlin Learning CentreIn the closed network of Learning Centre you can read digital and digitized theses not available in the open network. The Learning Centre contact details and opening hours: https://learningcentre.aalto.fi/en/harald-herlin-learning-centre/ You can read theses on the Learning Centre customer computers, which are available on all floors.
Logging on to the customer computers
Opening a thesis
Reading the thesis
Printing the thesis
|
Location: | P1 Ark Aalto | Archive |
Keywords: | Bayesian inference sequential Monte Carlo method Kalman filter multiple target tracking data association |
Abstract (eng): | Control and management of wild animals, especially large carnivores, is an important task for game and wildlife management authorities all over the world. Central to the scheme of wild animal conservation is the population size estimation methodology which depends on the used data sampling technique. The index based data sampling method has been found suitable in the case of large carnivores. On the other hand, telemetry data has been used to learn the individual movement of animals. Subsequently, mathematical modeling is utilized in order to learn both animal population dynamics and animal movement behavior. In that context, stochastic state-space models have proved to be appropriate for handling uncertainty that occurs in the process and observation models. This thesis provides a novel approach for the estimation of wild animal population. We utilize the state-space modeling framework as well as animal movement models on an unconventional observation and index based dataset. We formulate the problem as a conditionally linear Gaussian state-space model and recursively estimate the state of the animals. More specifically, we reformulate the problem as a special case of multiple target tracking, which can be solved by using Bayesian optimal filtering methodology. The solution to the problem of tracking an unknown number of targets is exactly applicable to our animal observation datasets. |
ED: | 2012-02-24 |
INSSI record number: 43955
+ add basket
« previous | next »
INSSI