Faculty Publications

Now showing 1 - 2 of 2

Short-term passenger demand modelling using automatic fare collection data: A case study of hubli-dharwad brts
(Aracne Editrice, 2023) Halyal, S.; Mulangi, R.H.; Harsha, H.M.
A well-planned Intelligent Transport System (ITS), is the need of the hour for solving the problem of excessive traffic and unacceptable travel durations in public transit systems. However, for the successful operation of an ITS, the forecasting of passenger demand on a regular basis is essential. Obtaining reliable and accurate passenger data required for forecasting passenger demand is a genuinely tedious task for most of the researchers. The current study focused on short-term forecasting of passenger demand using reliable ITS-based data from Hubli-Dharwad Bus Rapid Transit System (HDBRTS) as a case study. The aggregate pattern of passenger demand data was visualized using one month of Automated Fare Collection System (AFCS) data. Subsequently, Autoregressive Integrated Moving Average (ARIMA) and Seasonal ARIMA models were used on the data of selected stations and tested for their forecasting accuracy. Outcomes of the current case study show that Seasonal ARIMA models are the most suitable for forecasting the passenger data over the conventional ARIMA models. The most suitable and reliant models were evidenced through lower values of Mean Absolute Percentage Error (MAPE), Akaike’s Information Criterion (AIC), and Bayesian Information Criterion (BIC). The current case study helps in having an inclusive view of the passenger flow characteristics for the further advancement of the system. Research work in the Indian context, especially on the usage of AFCS data, is quite limited, this study makes to explore the possibility of using AFCS data efficiently in forecasting passenger demand. © 2023, Aracne Editrice. All rights reserved.
Deep learning-based public transit passenger flow prediction model: integration of weather and temporal attributes
(Springer Science and Business Media Deutschland GmbH, 2025) Shanthappa, N.K.; Mulangi, R.H.; Harsha, H.M.
A reliable prediction model is critical for the public transit system to keep it periodically updated. However, it is a challenging task to develop a model of high precision when there is heterogeneity in the travel demand which is very common in developing countries. The spatial and temporal attributes along with external factors like weather should be incorporated into the prediction models to account for heterogeneity. Numerous studies in the past developed passenger flow prediction models considering spatial and temporal dependencies, whereas the integration of weather components with temporal dependencies while developing a prediction model for public bus transit has not been widely considered. Hence, the present research work employs long short-term memory (LSTM) to develop a route-level bus passenger flow prediction model, called RPTW-LSTM, by integrating temporal dependencies such as recent time intervals (R), daily periodicity (P) and weekly trend (T), and weather variables (W). The model is tested using a real-life dataset of the Udupi city bus service, located on the west coast of Karnataka, India. Additionally, Shapley Additive Explanation (SHAP) analysis is adopted to identify the relative importance of the features used. Results imply that the inclusion of the aforementioned factors enhanced the performance of RPTW-LSTM when compared to basic LSTM and other conventional models. Additionally, weekly trend and weather exhibit higher significance on the model than recent time intervals. This implies that evaluating the features affecting the heterogeneity in passenger flow and incorporating them into the model assists transport planners in achieving high precision. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

Faculty Publications

Browse

Filters

Settings

Sort By

Results per page

Search Results