Mining big spatial data
The clustering of geospatial trajectories finds utility in multiple industries. In this report, two trajectory clustering models are presented, and a web-based front-end application is developed for visualization. The first trajectory clustering model contains two parts: i) trajectory reduction; ii)...
Saved in:
Main Author: | |
---|---|
Other Authors: | |
Format: | Final Year Project |
Language: | English |
Published: |
Nanyang Technological University
2023
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/166018 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-166018 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1660182023-04-21T15:38:48Z Mining big spatial data Ye, Ziyuan Gao Cong School of Computer Science and Engineering gaocong@ntu.edu.sg Engineering::Computer science and engineering The clustering of geospatial trajectories finds utility in multiple industries. In this report, two trajectory clustering models are presented, and a web-based front-end application is developed for visualization. The first trajectory clustering model contains two parts: i) trajectory reduction; ii) trajectory clustering. Trajectories are reduced using the Ramer–Douglas–Peucker algorithm and then clustered using Hierarchical Density-Based Spatial Clustering of Applications with Noise (HDBSCAN). The second trajectory clustering model adopts a recurrent neural network (RNN) model to learn spatial and temporal invariant representations of trajectories. It consists of three parts: (i) behavior feature extraction, (ii) trajectory representation learning, and (iii) trajectory clustering. For the behavior feature extraction, a sliding window technique is applied. For trajectory representation learning, a sequence-to-sequence autoencoder and decoder RNN network is trained to learn a fixed-length vector for each input trajectory. The vectors learned are then fed into the K-means clustering algorithm. Comparing the two models, we can conclude that trajectory pattern mining with sequence-to-sequence autoencoder and decoder RNN network yields more suitable results. Bachelor of Engineering (Computer Science) 2023-04-18T13:15:23Z 2023-04-18T13:15:23Z 2023 Final Year Project (FYP) Ye, Z. (2023). Mining big spatial data. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/166018 https://hdl.handle.net/10356/166018 en SCSE22-0161 application/pdf Nanyang Technological University |
institution |
Nanyang Technological University |
building |
NTU Library |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
NTU Library |
collection |
DR-NTU |
language |
English |
topic |
Engineering::Computer science and engineering |
spellingShingle |
Engineering::Computer science and engineering Ye, Ziyuan Mining big spatial data |
description |
The clustering of geospatial trajectories finds utility in multiple industries. In this report, two trajectory clustering models are presented, and a web-based front-end application is developed for visualization. The first trajectory clustering model contains two parts: i) trajectory reduction; ii) trajectory clustering. Trajectories are reduced using the Ramer–Douglas–Peucker algorithm and then clustered using Hierarchical Density-Based Spatial Clustering of Applications with Noise (HDBSCAN). The second trajectory clustering model adopts a recurrent neural network (RNN) model to learn spatial and temporal invariant representations of trajectories. It consists of three parts: (i) behavior feature extraction, (ii) trajectory representation learning, and (iii) trajectory clustering. For the behavior feature extraction, a sliding window technique is applied. For trajectory representation learning, a sequence-to-sequence autoencoder and decoder RNN network is trained to learn a fixed-length vector for each input trajectory. The vectors learned are then fed into the K-means clustering algorithm. Comparing the two models, we can conclude that trajectory pattern mining with sequence-to-sequence autoencoder and decoder RNN network yields more suitable results. |
author2 |
Gao Cong |
author_facet |
Gao Cong Ye, Ziyuan |
format |
Final Year Project |
author |
Ye, Ziyuan |
author_sort |
Ye, Ziyuan |
title |
Mining big spatial data |
title_short |
Mining big spatial data |
title_full |
Mining big spatial data |
title_fullStr |
Mining big spatial data |
title_full_unstemmed |
Mining big spatial data |
title_sort |
mining big spatial data |
publisher |
Nanyang Technological University |
publishDate |
2023 |
url |
https://hdl.handle.net/10356/166018 |
_version_ |
1764208172825837568 |