RESUMEN

This paper focuses on the emissions of the three most sold categories of light vehicles: sedans, SUVs, and pickups. The research is carried out through an innovative methodology based on GPS and machine learning in real driving conditions. For this purpose, driving data from the three best-selling vehicles in Ecuador are acquired using a data logger with GPS included, and emissions are measured using a PEMS in six RDE tests with two standardized routes for each vehicle. The data obtained on Route 1 are used to estimate the gears used during driving using the K-means algorithm and classification trees. Then, the relative importance of driving variables is estimated using random forest techniques, followed by the training of ANNs to estimate CO2, CO, NOX, and HC. The data generated on Route 2 are used to validate the obtained ANNs. These models are fed with a dataset generated from 324, 300, and 316 km of random driving for each type of vehicle. The results of the model were compared with the IVE model and an OBD-based model, showing similar results without the need to mount the PEMS on the vehicles for long test drives. The generated model is robust to different traffic conditions as a result of its training and validation using a large amount of data obtained under completely random driving conditions.

RESUMEN

Road traffic accidents result in injury or even death of passengers. One potential cause of these accidents is mechanical failures due to a lack of vehicle maintenance. In the quest to identify these mechanical failures, this paper aims to set up the procedure to identify the mechanical failures that contribute to traffic accidents in cities located in developing countries, including the city of Cuenca-Ecuador. For present research, a database provided by the entity responsible for the Vehicle Technical Inspection, the Empresa Pública Municipal de Movilidad, Tránsito y Transporte and for the ones responsible of managing traffic accident data, Oficina de Investigación de Accidentes de Tránsito and Sección de Investigación de Accidentes de Tránsito was used. The vehicle subcategories M1 and M3 (bus type) and N1, so named according to Ecuadorian technical standards, were considered the most relevant regarding accident rates. The database was analysed with descriptive statistics, a Pareto chart and time series with the quadratic trend. From this analysis, the most significant failures found in the VTI in all three subcategories were the alignment of the driver headlight, both horizontal and vertical, braking imbalance on the 2nd axle, insufficient tire tread and parking brake effectiveness. All these failures showed a decreasing trend over time and in the forecast at a maximum of two to three years. The most relevant causes of road accidents recorded during the period 2009-2018 related to mechanical failures were the braking system (65.5%) and the steering system (17.2%) for subcategory M1.

Asunto(s)

RESUMEN

This article proposes a methodology for the estimation of emissions in real driving conditions, based on board diagnostics data and machine learning, since it has been detected that there are no models for estimating pollutants without large measurement campaigns. For this purpose, driving data are obtained by means of a data logger and emissions through a portable emissions measurement system in a real driving emissions test. The data obtained are used to train artificial neural networks that estimate emissions, having previously estimated the relative importance of variables through random forest techniques. Then, by the application of the K-means algorithm, labels are obtained to implement a classification tree and thereby determine the selected gear by the driver. These models were loaded with a data set generated covering 1218.19 km of driving. The results generated were compared to the ones obtained by applying the international vehicle emissions model and with the results of the real driving emissions test, showing evidence of similar results. The main contribution of this article is that the generated model is stronger in different traffic conditions and presents good results at the speed interval with small differences at low average driving speeds because more than half of the vehicle's trip occurs in urban areas, in completely random driving conditions. These results can be useful for the estimation of emission factors with potential application in vehicular homologation processes and the estimation of vehicular emission inventories.

Asunto(s)

RESUMEN

Knowledge of the kilometers traveled by vehicles is essential in transport and road safety studies as an indicator of exposure and mobility. Its application in the determination of user risk indices in a disaggregated manner is of great interest to the scientific community and the authorities in charge of ensuring road safety on highways. This study used a sample of the data recorded during passenger vehicle inspections at Vehicle Technical Inspection stations and housed in a data warehouse managed by the General Directorate for Traffic of Spain. This study has three notable characteristics: (1) a novel data source is explored, (2) the methodology developed applies to other types of vehicles, with the level of disaggregation the data allows, and (3) pattern extraction and the estimate of mobility contribute to the continuous and necessary improvement of road safety indicators and are aligned with goal 3 (Good Health and Well-Being: Target 3.6) of The United Nations Sustainable Development Goals of the 2030 Agenda. An Operational Data Warehouse was created from the sample received, which helped in obtaining inference values for the kilometers traveled by Spanish fleet vehicles with a level of disaggregation that, to the knowledge of the authors, was unreachable with advanced statistical models. Three machine learning methods, CART, random forest, and gradient boosting, were optimized and compared based on the performance metrics of the models. The three methods identified the age, engine size, and tare weight of passenger vehicles as the factors with greatest influence on their travel patterns.

Asunto(s)

RESUMEN

Background: Although public bodies need to know drivers' perception of road safety, in Latin America there are no valid and reliable instruments that propose an integral dimensionality. The objective of this study was to design and validate a Road Safety Perception Questionnaire (RSPQ). Methodology: The design included a review of the available evidence and expert knowledge to select the dimensional items for the instrument. A pilot test was carried out to determine possible corrections and adjustments to the questionnaire, after which a Confirmatory Factor Analysis was performed on a stratified sample of 736 Ecuadorian drivers to determine its reliability and construct validity. Results: The results suggest that the RSPQ has a clear factorial structure with high factorial weight items and good internal consistency. The results of the 41-item model grouped into six dimensions (human, vehicle, road infrastructure, regulatory framework and intervention measures, socioeconomic and driving precautions) obtained the best adjustment indexes at the absolute, incremental and parsimonious levels. Conclusions: The preliminary RSPQ evidence can be considered a valid and reliable instrument to assess drivers' perception of road safety.

Asunto(s)

RESUMEN

An accurate estimation of exposure is essential for road collision rate estimation, which is key when evaluating the impact of road safety measures. The quasi-induced exposure method was developed to estimate relative exposure for different driver groups based on its main hypothesis: the not-at-fault drivers involved in two-vehicle collisions are taken as a random sample of driver populations. Liability assignment is thus crucial in this method to identify not-at-fault drivers, but often no liability labels are given in collision records, so unsupervised analysis tools are required. To date, most researchers consider only driver and speed offences in liability assignment, but an open question is if more information could be added. To this end, in this paper, the visual clustering technique of self-organizing maps (SOM) has been applied to better understand the multivariate structure in the data, to find out the most important variables for driver liability, analyzing their influence, and to identify relevant liability patterns. The results show that alcohol/drug use could be influential on liability and further analysis is required for disability and sudden illness. More information has been used, given that a larger proportion of the data was considered. SOM thus appears as a promising tool for liability assessment.

Asunto(s)

RESUMEN

Identification of the most relevant factors for explaining road accident occurrence is an important issue in road safety research, particularly for future decision-making processes in transport policy. However model selection for this particular purpose is still an ongoing research. In this paper we propose a methodological development for model selection which addresses both explanatory variable and adequate model selection issues. A variable selection procedure, TIM (two-input model) method is carried out by combining neural network design and statistical approaches. The error structure of the fitted model is assumed to follow an autoregressive process. All models are estimated using Markov Chain Monte Carlo method where the model parameters are assigned non-informative prior distributions. The final model is built using the results of the variable selection. For the application of the proposed methodology the number of fatal accidents in Spain during 2000-2011 was used. This indicator has experienced the maximum reduction internationally during the indicated years thus making it an interesting time series from a road safety policy perspective. Hence the identification of the variables that have affected this reduction is of particular interest for future decision making. The results of the variable selection process show that the selected variables are main subjects of road safety policy measures.

Asunto(s)

RESUMEN

This paper investigates the relationship between a passenger car's year of registration and its crashworthiness and aggressivity in real-world crashes. Crashworthiness is defined as the ability of a car to protect its own occupants, and has been evaluated in single and two-car crashes. Aggressivity is defined as the ability to protect users travelling in other vehicles, and has been evaluated only in two-car crashes. The dependent variable is defined as the proportion of injured drivers who are killed or seriously injured; following previous research, we refer to this magnitude as injury severity. A decrease in the injury severity of a driver is interpreted as an improvement in the crashworthiness of their car; similarly, a decrease in the injury severity of the opponent driver is regarded as an improvement in aggressivity. Data have been extracted from the Spanish Road Accident Database, which contains information on every accident registered by the police in which at least one person was injured. Two types of regression models have been used: logistic regression models in single-car crashes, and generalised estimating equations (GEE) models in two-car crashes. GEE allow to take account of the correlation between the injury severities of drivers involved in the same crash. The independent variables considered have been: year of registration of the subject car (crashworthiness component), year of registration of the opponent car (aggressivity component), and several factors related to road, driver and environment. Our models confirm that crashworthiness has largely improved in two-car crashes: when crashing into the average opponent car, drivers of cars registered before 1985 have a significantly higher probability of being killed or seriously injured than drivers of cars registered in 2000-2005 (odds ratio: 1.80; 95% confidence interval: 1.61; 2.01). In single-car crashes, the improvement in crashworthiness is very slight (odds ratio: 1.04; 95% confidence interval: 0.93; 1.16). On the other hand, we have also found a significant worsening in aggressivity in two-car crashes: the driver of the average car has a significantly lower probability of being killed or seriously injured when crashing into a car registered before 1985, than when crashing into a car registered in 2000-2005 (odds ratio: 0.52; 95% confidence interval: 0.45; 0.60). Our results are consistent with a large amount of previous research that has reported significant improvements in the protection of car occupants. They also add to some recent studies that have found a worsening in the aggressivity of modern cars. This trend may be reflecting the impact of differences in masses and travel speeds, as well as the influence of consumer choices. The precise reasons have to be investigated. Also, the causes have to be found for so large a discrepancy between crashworthiness in single and two-car crashes.

Asunto(s)