Theft Prediction Model Based on Spatial Clustering to Reflect Spatial Characteristics of Adjacent Lands
| Autor: | Yongwook Jeong, Dong-Young Kim, Sungwon Jung |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
Geographic information system
Geography Planning and Development TJ807-830 02 engineering and technology Management Monitoring Policy and Law TD194-195 Renewable energy sources mental disorders 0202 electrical engineering electronic engineering information engineering GE1-350 Set (psychology) health care economics and organizations Event (probability theory) crime prediction Environmental effects of industries and plants Renewable Energy Sustainability and the Environment business.industry 020207 software engineering social sciences Grid GIS Random forest Environmental sciences spatial clustering Tree (data structure) Geography machine learning smart city Spatial clustering population characteristics 020201 artificial intelligence & image processing F1 score business Cartography human activities |
| Zdroj: | Sustainability Volume 13 Issue 14 Sustainability, Vol 13, Iss 7715, p 7715 (2021) |
| ISSN: | 2071-1050 |
| DOI: | 10.3390/su13147715 |
| Popis: | Previous studies have shown that when a crime occurs, the risk of crime in adjacent areas increases. To reflect this, previous grid-based crime prediction studies combined all the cells surrounding the event location to be predicted for use in model training. However, the actual land is continuous rather than a set of independent cells as in a geographic information system. Because the patterns that occur according to the detailed method of crime vary, it is necessary to reflect the spatial characteristics of the adjacent land in crime prediction. In this study, cells with similar spatial characteristics were classified using the Max-p region model (a spatial clustering technique), and the performance was compared to the existing method using random forest (a tree-based machine learning model). According to the results, the F1 score of the model using spatial clustering increased by approximately 2%. Accordingly, there are differences in the physical environmental factors influenced by the detailed method of crime. The findings reveal that crime involving the same offender is likely to occur around the area of the original crime, indicating that a repeated crime is likely in areas with similar spatial features to the area where the crime occurred. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|