Backpropagation Neural Network-Sensitivity Analysis for Smart City Development Implementation Project for Public Infrastructures in an Urbanized City in the Philippines

The world is rapidly changing and experiencing a rapid increase in population, especially in cities and urban areas. The growth in population in these urban areas results in a need for a more competitive and sustainable system. In the onset of the fourth industrial revolution, the trend in equipping these cities with advanced mechanisms in improving the quality of life and service in these cities is needed. In this study, a neural network - based approach for factor prioritization was implemented to determine the most influential factor in the smart city (SC) development implementation in the Philippines. Using the neural network internal characteristics including the Levenberg-Marquardt (LM) as the training algorithm (TA) and the hyperbolic tangent sigmoid (HTS) as the transfer function (TF). The study utilized the 18-37-1 network structure for the neural network model with an R value of 0.95003 and MSE of 0.032609. The connection weights (CW) from this network were utilized to calculate the relative importance (RI) of the factors affecting the smart city implementation through Garson's Algorithm (GA). The results of the study revealed that the most influential parameter (MIP) to the smart city implementation is the SCPD2 - analyzing solutions fit with strategic objectives. Moreover, the results and findings of the study could assist the city planners and SC strategy development authorities in the integration of different systems in the SC implementation.