SIMILARITY ASSESSMENT FOR THE POPULATION DENSITY OF SOME CITIES IN NIGERIA USING DYNAMIC TIME WARPING ALGORITHMS

Abstract

Similarity, or proximity, measures are used in diverse fields of inquiry to study the trajectory of random variables. Patterns, or trajectories, of human population density growth (measured with respect to constant area) are well-documented to be closely associated with social, economic and environmental development and vulnerabilities. This study is therefore aimed at investigating the trajectory of the population density of some Nigerian cities having population density ≥ 900 persons.km^-2 with a view of clustering the cities using Dynamic Time Warping (DTW) algorithms as the distance measure. The cities considered were selected on the basis of 2006 National Population Commission Census’ report. A Preliminary investigation for the optimal cluster number using K-means, Partition Around Medoids (pam) and Agglomerative Hierarchical algorithms showed that k = 2 and k = 6 produced optimal clusters. Since a higher optimal cluster value connote production of better grouping, outputs for k = 6 was selected. The result showed a dissimilar population density trajectory for Okene and Zaria while Uyo and Ikorodu cities had similar population density trajectory for the periods considered. Although Kano showed similar population density trajectory with Aba and Enugu, the cities of Enugu and Aba had more similar density trajectory than the city of Kano.