Population projection of the Indian subcontinent using TP-aided WASD neuronet

Abstract

The population projection of the Indian subcontinent, which is closely related to the future development of this region and even the whole world, has catched great attention among sociologists as well as scientists. However, most of the former researches are just based on fertility, mortality or other individual quantifiable factors by using some traditional statistical models and thus may lack all-sidedness in their results. The historical population data are the comprehensive reflection of population development under the influence of all factors. Based on the historical population data over 2000 years, a feedforward neuronet equipped with the weights-and-structure-determination (WASD) algorithm aided by twice-pruning (TP) technique is constructed. Besides, by introducing the cubic spline and error evaluation methods, the neuronet shows great performance in the population projection. Due to the marvelous learning and generalization abilities of the presented TP-aided WASD neuronet, we successfully draw up the population projection for the Indian subcontinent.