Date of Award

5-2025

Document Type

Thesis

Degree Name

Master of Science in Computer Science

Department

School of Computer Science and Engineering

First Reader/Committee Chair

Hou, Yunfei

Abstract

This study examines the disproportionately high traffic fatality rates in California's Inland Empire region through neural network analysis of over 500,000 accidents (2013-2022). We argue that the Inland Empire's unique hybrid urban-rural landscape creates a multiplicative risk environment unlike other California regions. Our analysis reveals that San Bernardino County's fatality rate (1.920 per 100 million VMT) significantly exceeds neighboring regions, with alcohol-impaired driving fatalities (0.586) substantially higher than California's average (0.390). Neural network models (92% validation accuracy) identify pedestrian-involved collisions (correlation value 0.164) and alcohol involvement (0.075) as the strongest predictors of fatality in urban areas, while rural crash patterns such as head-on collisions (0.042) and dark conditions with no street lights (0.059) significantly increase fatality risk in non-metropolitan areas. Using SHAP (SHapley Additive exPlanations) analysis and spatial clustering, we identified 131 fatality hotspots throughout the region, with metropolitan areas showing higher percentages of alcohol involvement (36.6% vs. 32.4%) than non-metropolitan areas, but non-metro areas demonstrating reduced sensitivity to adverse weather and hazardous road surfaces. The COVID-19 pandemic exacerbated these risks, creating a 30.4% increase in fatality rates despite reduced traffic volumes. This research suggests that effective interventions must simultaneously address urban-specific concerns while implementing countermeasures typically deployed in rural environments, recognizing the Inland Empire's distinctive blend of metropolitan and non-metropolitan road characteristics.

Download

  Contact Author

Share

COinS