RESUMO
This research project explored into the intricacies of road traffic accidents severity in the UK, employing a potent combination of machine learning algorithms, econometric techniques, and traditional statistical methods to analyse longitudinal historical data. Our robust analysis framework includes descriptive, inferential, bivariate, multivariate methodologies, correlation analysis: Pearson's and Spearman's Rank Correlation Coefficient, multiple logistic regression models, Multicollinearity Assessment, and Model Validation. In addressing heteroscedasticity or autocorrelation in error terms, we've advanced the precision and reliability of our regression analyses using the Generalized Method of Moments (GMM). Additionally, our application of the Vector Autoregressive (VAR) model and the Autoregressive Integrated Moving Average (ARIMA) models have enabled accurate time series forecasting. With this approach, we've achieved superior predictive accuracy and marked by a Mean Absolute Scaled Error (MASE) of 0.800 and a Mean Error (ME) of -73.80 compared to a naive forecast. The project further extends its machine learning application by creating a random forest classifier model with a precision of 73%, a recall of 78%, and an F1-score of 73%. Building on this, we employed the H2O AutoML process to optimize our model selection, resulting in an XGBoost model that exhibits exceptional predictive power as evidenced by an RMSE of 0.1761205782994506 and MAE of 0.0874235576229789. Factor Analysis was leveraged to identify underlying variables or factors that explain the pattern of correlations within a set of observed variables. Scoring history, a tool to observe the model's performance throughout the training process was incorporated to ensure the highest possible performance of our machine learning models. We also incorporated Explainable AI (XAI) techniques, utilizing the SHAP (Shapley Additive Explanations) model to comprehend the contributing factors to accident severity. Features such as Driver_Home_Area_Type, Longitude, Driver_IMD_Decile, Road_Type, Casualty_Home_Area_Type, and Casualty_IMD_Decile were identified as significant influencers. Our research contributes to the nuanced understanding of traffic accident severity and demonstrates the potential of advanced statistical, econometric, machine learning techniques in informing evidence based interventions and policies for enhancing road safety.
RESUMO
Analysis of environmental samples obtained from the Live Poultry Markets (LPMs) of Dhaka City, Bangladesh, has revealed that the highest degree of prevalence of highly pathogenic avian influenza A (HPAI, H5N1), besides other subtypes of the LPAI virus, poses the plausible risk of transmission of these viruses between human and poultry species. The present study was conducted using the OIE risk analysis framework to assess the risk level of each pathway successively. The estimated risk parameters were integrated towards to obtain the overall risk level for each specific HPAI transmission pathway using the matrix adapted by Cristobel Zepeda accompanying other expert consultations. The relevant data obtained from published and unpublished sources, together with survey data of field observations, were used to formulate and confirm the risk pathways and their associated risks. The results revealed that the risk of the release of the HPAI virus was medium when exposure was high. Additionally, the consequence would be considered very high with a medium degree of uncertainty for all parameters. Ultimately, the overall risk for transmission was estimated as medium with a medium degree of uncertainty. The findings of this study reveal that there is a significant threat that HPAI virus transmission could occur among poultry and humans and effectively sustain within the environment of the LPMs. Our findings are primarily focused on public health considerations, the hygienic slaughter of poultry and the relevant cleaning and sanitation practices conducted in the LPMs to support evidence-based decision-making processes. The findings of the study have the potential to be used to formulate effective risk reduction measures and can be further adapted in low-resource settings without major infrastructural changes required of the LPMs. All of which would reduce the risk of HPAI virus release and further lessen the degree of exposure and transmission in established LPMs.
