Creation of meta-model for agent-based simulation using machine learning approach
The ability to predict and model crowd behavior is an overwhelming and challenging task. This paper investigates the viability of neural networks in their ability to learn crowd patterns from video data. We tackle the problem of simulating crowd behavior by using neural networks to tackle the proble...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project (FYP) |
| Language: | English |
| Published: |
Nanyang Technological University
2024
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/174965 |
| _version_ | 1811685275261206528 |
|---|---|
| author | Agarwal, Samarth |
| author2 | Cai Wentong |
| author_facet | Cai Wentong Agarwal, Samarth |
| author_sort | Agarwal, Samarth |
| collection | NTU |
| description | The ability to predict and model crowd behavior is an overwhelming and challenging task. This paper investigates the viability of neural networks in their ability to learn crowd patterns from video data. We tackle the problem of simulating crowd behavior by using neural networks to tackle the problem and automatically understand the physics and patterns behind the data. Neural network’s ability to generalize through training data is one that we also aim to leverage in our simulation. We design a simple fully-connected neural network with one hidden layer and tanh activation function. To evaluate its performance, first the neural network learns appropriate weights and biases from a video dataset in Switzerland following which its performance is validated against video data from the United States. The neural network is able to outperform Social Force Model and the Shortest-Path model, achieving a lower score for mean density errors. However, the difference between the Social Force Model and the Neural Network is shown to not be statistically significant. Furthermore, it performs slightly worse with regards to velocity field errors when compared to the Social Force Model. Despite the mixed results, the results obtained demonstrate that a neural network could model crowd dynamics of another scenario in a different context if the crowd behavior patterns are similar. Further investigation, with larger and more varied datasets and different neural network architectures are needed to showcase their capabilities in the field. |
| first_indexed | 2024-10-01T04:41:56Z |
| format | Final Year Project (FYP) |
| id | ntu-10356/174965 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T04:41:56Z |
| publishDate | 2024 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1749652024-04-19T15:46:10Z Creation of meta-model for agent-based simulation using machine learning approach Agarwal, Samarth Cai Wentong School of Computer Science and Engineering ASWTCAI@ntu.edu.sg Computer and Information Science Agent based modelling The ability to predict and model crowd behavior is an overwhelming and challenging task. This paper investigates the viability of neural networks in their ability to learn crowd patterns from video data. We tackle the problem of simulating crowd behavior by using neural networks to tackle the problem and automatically understand the physics and patterns behind the data. Neural network’s ability to generalize through training data is one that we also aim to leverage in our simulation. We design a simple fully-connected neural network with one hidden layer and tanh activation function. To evaluate its performance, first the neural network learns appropriate weights and biases from a video dataset in Switzerland following which its performance is validated against video data from the United States. The neural network is able to outperform Social Force Model and the Shortest-Path model, achieving a lower score for mean density errors. However, the difference between the Social Force Model and the Neural Network is shown to not be statistically significant. Furthermore, it performs slightly worse with regards to velocity field errors when compared to the Social Force Model. Despite the mixed results, the results obtained demonstrate that a neural network could model crowd dynamics of another scenario in a different context if the crowd behavior patterns are similar. Further investigation, with larger and more varied datasets and different neural network architectures are needed to showcase their capabilities in the field. Bachelor's degree 2024-04-17T07:48:03Z 2024-04-17T07:48:03Z 2024 Final Year Project (FYP) Agarwal, S. (2024). Creation of meta-model for agent-based simulation using machine learning approach. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/174965 https://hdl.handle.net/10356/174965 en application/pdf Nanyang Technological University |
| spellingShingle | Computer and Information Science Agent based modelling Agarwal, Samarth Creation of meta-model for agent-based simulation using machine learning approach |
| title | Creation of meta-model for agent-based simulation using machine learning approach |
| title_full | Creation of meta-model for agent-based simulation using machine learning approach |
| title_fullStr | Creation of meta-model for agent-based simulation using machine learning approach |
| title_full_unstemmed | Creation of meta-model for agent-based simulation using machine learning approach |
| title_short | Creation of meta-model for agent-based simulation using machine learning approach |
| title_sort | creation of meta model for agent based simulation using machine learning approach |
| topic | Computer and Information Science Agent based modelling |
| url | https://hdl.handle.net/10356/174965 |
| work_keys_str_mv | AT agarwalsamarth creationofmetamodelforagentbasedsimulationusingmachinelearningapproach |