Estimation of Time Voting in Elections Using Artificial Neural Network

Abstract

Since the first election policy was enacted simultaneously, it does not mean that it does not have potential problems, instead it causes other problems, which require extra time and energy in doing recapitulation. Simultaneous elections consist of presidential elections, DPR elections, Provincial DPRDs, City / Regency DPRDs, DPD, the more they are elected, the more influential is the time of voting and the time of vote recapitulation. The longer the voting time is done by the voters, the longer the recapitulation time. The longer time of recapitulation results in the fatigue of KPPS members which triggers inaccurate work and prone to manipulation and fraud so that it can damage the quality of elections. This study aims to determine the estimated time needed for voting for ballots in elections using the Multilayer Perceptron Artificial Neural Network (ANN) approach. The resulting time estimate is based on the time of the voter in the voting booth. The results of this study indicate that ANN with the Multilayer Perceptron Algorithm can calculate the estimated time required for ballot balloting by producing the best combination of learning parameters with 4 hidden neurons, learning rate 0.001, and 2000 epoch iterations resulting in an RMSE value of 108,015 seconds.