Yishi Zhao

Cluster Analysis of Injury using Self-­‐Organizing Map – A Case Study of Extended Golden Horseshoe ©2015

Multi-dimensional data analysis has rarely been performed on injury data. In this study, frequency data of 6 injury types in Extended Golden Horseshoe area is collected and self-organizing map (SOM) is used to construct an injury cluster system in the study area. The results indicate that the variables are positively correlated and several outliers are found in the study area. SOM is also proven to be an effective tool for clustering analysis given its low quantization error; yet SOM is very sensitive to outliers in terms of visualizing multi-dimensional data. The results also suggest that the injury prevention strategies should be reinforced in smaller CMAs like St. Catherine's - Niagara and Oshawa. To reveal detailed injury patterns in Toronto CMA, it needs to be analyzed individually. Future research should focus on extending the application of SOM to spatiotemporal analysis of multi-dimensional data.