Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Investigators publish new report on ar tificial intelligence. According to news originating from South Carolina State U niversity by NewsRx correspondents, research stated, “Scooters have gained wides pread popularity in recent years due to their accessibility and affordability, b ut safety concerns persist due to the vulnerability of riders. Researchers are a ctively investigating the safety implications associated with scooters, given th eir relatively new status as transportation options.” The news reporters obtained a quote from the research from South Carolina State University: “However, analyzing scooter safety presents a unique challenge due t o the complexity of determining safe riding environments. This study presents a comprehensive analysis of scooter crash risk within various buffer zones, utiliz ing the Extreme Gradient Boosting (XGBoost) machine learning algorithm. The core objective was to unravel the multifaceted factors influencing scooter crashes a nd assess the predictive model’s performance across different buffers or spatial proximity to crash sites. After evaluating the model’s accuracy, sensitivity, a nd specificity across buffer distances ranging from 5 ft to 250 ft with the scoo ter crash as a reference point, a discernible trend emerged: as the buffer dista nce decreases, the model’s sensitivity increases, although at the expense of acc uracy and specificity, which exhibit a gradual decline. Notably, at the widest b uffer of 250 ft, the model achieved a high accuracy of 97% and spe cificity of 99 %, but with a lower sensitivity of 31%. Contrastingly, at the closest buffer of 5 ft, sensitivity peaked at 95 % , albeit with slightly reduced accuracy and specificity. Feature importance anal ysis highlighted the most significant predictor across all buffer distances, emp hasizing the impact of vehicle interactions on scooter crash likelihood. Explain able Artificial Intelligence through SHAP value analysis provided deeper insight s into each feature’s contribution to the predictive model, revealing passenger vehicle types of significantly escalated crash risks. Intriguingly, specific veh icular maneuvers, notably stopping in traffic lanes, alongside the absence of Tr affic Control Devices (TCDs), were identified as the major contributors to incre ased crash occurrences. Road conditions, particularly wet and dry, also emerged as substantial risk factors.”
NETL
NSTL