<abstract xmlns="http://www.w3.org/1999/xhtml"><p>Research scientists have been developing mathematical tools to detect objects, recognize objects and actions, and discover behaviours and events to human abilities. In all these efforts, the understanding of human actions is of a special interest for both application and research purposes. In this study, crowd flow parameters are analysed by considering linear and non linear relationships between stream flow parameters using conventional and soft computing approach. Deterministics models like Greenshield and Underwood were applied in the study to describe flow characteristics. A non-linear model based on Artificial Neural Network (ANN) approach is also used to build a relationship between different crowd flow parameters and compared with the other deterministic models. ANN model gave good results based on accuracy measurement to deterministic models because of their self-processing and intelligent behaviour. Mean absolute error (MAE) and root mean square error (RMSE) values for the best fitted ANN model are less than those for the other models. ANN model gives better performance in fitness of model and future prediction of flow parameters.</p></abstract>

Research scientists have been developing mathematical tools to detect objects, recognize objects and actions, and discover behaviours and events to human abilities. In all these efforts, the understanding of human actions is of a special interest for both application and research purposes. In this study, crowd flow parameters are analysed by considering linear and non linear relationships between stream flow parameters using conventional and soft computing approach. Deterministics models like Greenshield and Underwood were applied in the study to describe flow characteristics. A non-linear model based on Artificial Neural Network (ANN) approach is also used to build a relationship between different crowd flow parameters and compared with the other deterministic models. ANN model gave good results based on accuracy measurement to deterministic models because of their self-processing and intelligent behaviour. Mean absolute error (MAE) and root mean square error (RMSE) values for the best fitted ANN model are less than those for the other models. ANN model gives better performance in fitness of model and future prediction of flow parameters.

Analysis of Crowd Flow Parameters Using Artificial Neural Network

Transportation Division, Department of Civil Engineering, National Institute of Technology

Transport and Telecommunication Journal

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

{"article-title":"Analysis of Crowd Flow Parameters Using Artificial Neural Network"}

Research scientists have been developing mathematical tools to detect objects, recognize objects and actions, and discover behaviours and events to human...

Analysis of Crowd Flow Parameters Using Artificial Neural Network

Pubblicato online: 30 nov 2018

Pagine: 335 - 345

DOI: https://doi.org/10.2478/ttj-2018-0028

Parole chiave
ANN, deterministic models, Greenshield, Macroscopic flow diagram, MAE, RMSE

© 2018 Transport and Telecommunication Institute, published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Analysis of Crowd Flow Parameters Using Artificial Neural Network

Pubblicato online: 30 nov 2018

Pagine: 335 - 345

DOI: https://doi.org/10.2478/ttj-2018-0028

Parole chiaveANN, deterministic models, Greenshield, Macroscopic flow diagram, MAE, RMSE

© 2018 Transport and Telecommunication Institute, published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Parole chiave
ANN, deterministic models, Greenshield, Macroscopic flow diagram, MAE, RMSE