University of Twente Student Theses

Login

Machine learning approach to model internal displacement in Somalia

Kyriazi or Qirjazi, S. (2018) Machine learning approach to model internal displacement in Somalia.

[img] PDF
2MB
Abstract:Predicting migration intents to project flows of population and usually migration is connected to relocation across the border of a country, while internal displacement refers to migration within the borders of a country. The intent of a person to relocate to a new region, is important, for policy development, especially in countries that are in need of aid. The agency of Refugees of the United Nations, provided the data for modeling human displacement in the country of Somalia. There already existing models of human mobility, cannot incorporate all the different aspects affecting movement, when data is of diverse nature. These large datasets can be manipulated and conceptualized with the use of machine learning to model and accurately forecast displacement. We focus on machine learning approaches, such as Neural Networks and Genetic and Evolutionary Algorithms to model multivariate time series forecasting. Lastly, we provide common measures and compare the performance of the models. We also try to detect the most influential variables that can assist to interpret the scenarios that lead to displacement.
Item Type:Essay (Master)
Faculty:EEMCS: Electrical Engineering, Mathematics and Computer Science
Subject:54 computer science, 74 (human) geography, cartography, town and country planning, demography
Programme:Interaction Technology MSc (60030)
Link to this item:http://purl.utwente.nl/essays/75192
Export this item as:BibTeX
EndNote
HTML Citation
Reference Manager

 

Repository Staff Only: item control page