Motorcycle crash severity is under-researched in Ghana. Thus, the probable risk factors and association between these factors and motorcycle crash severity outcomes is not known. Traditional statistical models have intrinsic assumptions and pre-defined correlations that, if flouted, can generate inaccurate results. In this study, machine learning based algorithms were employed to predict and classify motorcycle crash severity. Machine learning based techniques are non-parametric models without the presumption of relationships between endogenous and exogenous variables. The main aim of this research is to evaluate and compare different approaches to modeling motorcycle crash severity as well as investigating the effect of risk factors on the injury outcomes of motorcycle crashes. Motorcycle crash dataset between 2011 and 2015 was extracted from the National Road Traffic Crash Database at the Building and Road Research Institute (BRRI) in Ghana. The dataset was classified into four injury severity categories: fatal, hospitalized, injured, and damage-only. Three machine learning based models were developed: J48 Decision Tree Classifier, Random Forest (RF) and Instance-Based learning with parameter k (IBk) were employed to model the severity of injury in a motorcycle crash. These machine learning algorithms were validated using 10-fold cross-validation technique. The three machine learning based algorithms were compared with one another and the statistical model: multinomial logit model (MNLM). Also, the relative importance analysis of the attribute was conducted to determine the impact of these attributes on injury severity outcomes. The results of the study reveal that the predictions of machine learning algorithms are superior to the MNLM in accuracy and effectiveness, and the RF-based algorithms show the overall best agreement with the experimental data out of the three machine learning algorithms, for its global optimization and extrapolation ability. Location type, time of the crash, settlement type, collision partner, collision type, road separation, road surface type, the day of the week, and road shoulder condition were found as the critical determinants of motorcycle crash injury severity.

This study uses classification algorithms to establish models to predict the severity of crash injuries when motorcycle crashes occur. In this study, the power of multi-layer perceptron (MLP), rule induction (PART) and classification and regression trees (SimpleCart) models for predicting the severity of motorcycle crash was evaluated by comparing their results. To accomplish this objective, motorcycle crash data set extracted from the National Road Traffic Crash Database at the Building and Road Research Institute in Ghana. The data set was classified into four injury severity categories: fatal, hospitalised, injured and damage. The data collected from this database will provide means to directly compare and rank the data mining models, while also allowing for the identification of variables that are significantly influencing the severity of motorcycle crash. The results showed that among the tested classification algorithms, the SimpleCart model with an average accuracy of 73.81% outperformed the PART model (73.45%) and the MLP (72.16%) model based on a 10-fold cross-validation approach. The results revealed that the most significant factors associated with motorcycle crash injury severity were location type, settlement type, time of the crash, collision type and collision partner.

Objective: The objective of this study was to explore the factors affecting motorcycle crash severity in Ghana. Methods: A retrospective analysis of motorcycle crash data between 2011 and 2015 was conducted using a motorcycle crash data set extracted from the National Road Traffic Crash Database at the Building and Road Research Institute (BRRI) in Ghana. Injury severity was classified into 4 categories: Fatal, hospitalized, injured, and damage only. A multinomial logit modeling framework was used to identify the possible determinants of motorcycle crash severity. Results: During the study period, a total of 8,516 motorcycle crashes were recorded, of which 22.9% were classified as fatal, 42.1% were classified as hospitalized injuries, 29.4% were classified as slight injuries, and 5.6% were classified as damage-only crashes. The estimation results indicate that the following factors increase the probability of fatal injuries: At a junction; weekend; signage; poor road shoulder; village settlement; tarred and good road surface; and collision between motorcycle and heavy goods vehicle (HGV). Motorcycle crashes occurring during the daytime and on the weekend increases the probability of hospitalized injury. The results also suggest that motorcycle crashes occurring during the daytime, in curves or inclined portions of roads, or in unclear weather conditions decrease the probability of fatal injury. Conclusions: This study provides further empirical evidence to support motorcycle crash modeling research, which is lacking in developing countries. The ability to understand the various factors that influence motorcycle crash severity is a step forward in providing an appropriate basis upon which informed motorcycle crash policies can be developed. Particular attention should be given to the provision of road signage at junctions and speed humps and controlling traffic during the weekend. In addition, road maintenance should be carried out periodically to address motorcycle safety in Ghana.