A comparative evaluation of 3d and spatio-temporal deep learning techniques for crime classification and prediction
| dc.contributor.advisor | Ghaziasgar, Mehrdad | |
| dc.contributor.author | Matereke, Tawanda Lloyd | |
| dc.date.accessioned | 2022-03-09T09:22:10Z | |
| dc.date.accessioned | 2024-10-30T14:00:40Z | |
| dc.date.available | 2022-03-09T09:22:10Z | |
| dc.date.available | 2024-10-30T14:00:40Z | |
| dc.date.issued | 2021 | |
| dc.description | >Magister Scientiae - MSc | en_US |
| dc.description.abstract | This research is on a comparative evaluation of 3D and spatio-temporal deep learning methods for crime classification and prediction using the Chicago crime dataset, which has 7.29 million records, collected from 2001 to 2020. In this study, crime classification experiments are carried out using two 3D deep learning algorithms, i.e., 3D Convolutional Neural Network and the 3D Residual Network. The crime classification models are evaluated using accuracy, F1 score, Area Under Receiver Operator Curve (AUROC), and Area Under Curve - Precision-Recall (AUCPR). The effectiveness of spatial grid resolutions on the performance of the classification models is also evaluated during training, validation and testing. | en_US |
| dc.identifier.uri | https://hdl.handle.net/10566/16926 | |
| dc.language.iso | en | en_US |
| dc.publisher | University of Western Cape | en_US |
| dc.rights.holder | University of Western Cape | en_US |
| dc.subject | Crime classification | en_US |
| dc.subject | Chicago crime dataset | en_US |
| dc.subject | 3D deep learning algorithms | en_US |
| dc.subject | 3D residual network | en_US |
| dc.subject | Crime | en_US |
| dc.title | A comparative evaluation of 3d and spatio-temporal deep learning techniques for crime classification and prediction | en_US |