Bibliographic citations
Tapia, B., (2021). Generación de rutas óptimas en sistemas de transporte público masivo usando ciencia de datos con Big Data y Machine Learning [Tesis, Universidad Nacional de Ingeniería]. http://hdl.handle.net/20.500.14076/22099
Tapia, B., Generación de rutas óptimas en sistemas de transporte público masivo usando ciencia de datos con Big Data y Machine Learning [Tesis]. PE: Universidad Nacional de Ingeniería; 2021. http://hdl.handle.net/20.500.14076/22099
@misc{renati/711637,
title = "Generación de rutas óptimas en sistemas de transporte público masivo usando ciencia de datos con Big Data y Machine Learning",
author = "Tapia Quispitupa, Betzy Suey",
publisher = "Universidad Nacional de Ingeniería",
year = "2021"
}
The objective is to improve the Mass Public Transportation System by means of route optimization. The proposal of a model of “Generation of optimal routes“ for a transportation system where the data of the users and some operation parameters are available is elaborated, from the model optimal routes are obtained according to the demand of the users. In order to test the effectiveness of the model, a case study of a Mass Public Transportation System in the city of Lima is taken as a specific case “Metropolitano“ (Lima's public, urban and mass transportation system), since this system has a route that connects ends of the city (direct distance) and with an exclusive route (optimal time without obstacles) and with the users' data, resulting in transporting the largest number of users in the shortest possible time. The proposed model is based on generating optimal routes through user demand; for this purpose, Transportation Engineering and Computer Science tools such as Data Science, Big Data and Machine Learning will be used, with the purpose of using urban transportation criteria to process the data, codify the algorithm and simulate the generation of optimal routes. In addition, it should be noted that the proposal will serve for any transportation system that makes use of electronic cards or has the origin-destination of users. When generating the routes, in the “Metropolitano“, with the algorithm of the “Generation of optimal routes“ model, in the peak hour from 7 to 8am, 347 trips were obtained as a result, which implies an improvement of 51 trips compared to the 398 trips used by the “Metropolitano” system. By optimizing the routes, the waiting time was reduced by 66.6%, the transfer time by 83.44% and the number of transfers by 69.06%.
This item is licensed under a Creative Commons License