Analysis on the Bus Arrival Time Prediction Model for Human-Centric Services Using Data Mining Techniques

Autor: N. Shanthi, Sathishkumar V E, K. Upendra Babu, P. Karthikeyan, Sukumar Rajendran, Shaikh Muhammad Allayear
Jazyk: angličtina
Rok vydání: 2022
Předmět:
Zdroj: Computational Intelligence and Neuroscience.
ISSN: 1687-5265
DOI: 10.1155/2022/7094654
Popis: The human-computer interaction has become inevitable in digital world. HCI helps humans to incorporate technology to resolve even their day-to-day problems. The main objective of the paper is to utilize HCI in Intelligent Transportation Systems. In India, the most common and convenient mode of transportation is the buses. Every state government provides the bus transportation facility to all routes at an affordable cost. The main difficulty faced by the passengers (humans) is lack of information about bus numbers available for the particular route and Estimated Time of Arrival (ETA) of the buses. There may be different reasons for the bus delay. These include heavy traffic, breakdowns, and bad weather conditions. The passengers waiting in the bus stops are neither aware of the delay nor the bus arrival time. These issues can be resolved by providing an HCI-based web/mobile application for the passengers to track their bus locations in real time. They can also check the Estimated Time of Arrival (ETA) of a particular bus, calculated using machine learning techniques by considering the impacts of environmental dynamics, and other factors like traffic density and weather conditions and track their bus locations in real time. This can be achieved by developing a real-time bus management system for the benefit of passengers, bus drivers, and bus managers. This system can effectively address the problems related to bus timing transparency and arrival time forecasting. The buses are equipped with real-time vehicle tracking module containing Raspberry Pi, GPS, and GSM. The traffic density in the current location of the bus and weather data are some of the factors used for the ETA prediction using the Support Vector Regression algorithm. The model showed RMSE of 27 seconds when tested. The model is performing well when compared with other models.
Databáze: OpenAIRE
Externí odkaz:
Nepřihlášeným uživatelům se plný text nezobrazuje