Search

Traffic accidents are of worldwide concern, as they are one of the leading causes of death globally. One policy designed to cope with them is the design and deployment of road safety systems. These aim to predict crashes based on historical records, provided by new Internet of Things (IoT) technologies, to enhance traffic flow management and promote safer roads. Increasing data availability has helped machine learning (ML) to address the prediction of crashes and their severity. The literature reports numerous contributions regarding survey papers, experimental comparisons of various techniques, and the design of new methods at the point where crash severity prediction (CSP) and ML converge. Despite such progress, and as far as we know, there are no comprehensive research articles that theoretically and practically approach the model selection problem (MSP) in CSP. Thus, this paper introduces a bibliometric analysis and experimental benchmark of ML and automated machine learning (AutoML) as a suitable approach to automatically address the MSP in CSP. Firstly, 2318 bibliographic references were consulted to identify relevant authors, trending topics, keywords evolution, and the most common ML methods used in related-case studies, which revealed an opportunity for the use AutoML in the transportation field. Then, we compared AutoML (AutoGluon, Auto-sklearn, TPOT) and ML (CatBoost, Decision Tree, Extra Trees, Gradient Boosting, Gaussian Naive Bayes, Light Gradient Boosting Machine, Random Forest) methods in three case studies using open data portals belonging to the cities of Medellín, Bogotá, and Bucaramanga in Colombia. Our experimentation reveals that AutoGluon and CatBoost are competitive and robust ML approaches to deal with various CSP problems. In addition, we concluded that general-purpose AutoML effectively supports the MSP in CSP without developing domain-focused AutoML methods for this supervised learning problem. Finally, based on the results obtained, we introduce challenges and research opportunities that the community should explore to enhance the contributions that ML and AutoML can bring to CSP and other transportation areas. [ABSTRACT FROM AUTHOR]

Copyright of Boletín de Ciencias de la Tierra is the property of Universidad Nacional de Colombia and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Background: There is scarce information about ischemic stroke in young patients in Colombia. To get insights about this phenomenon, this study describes the etiologies and risk factors of ischemic stroke in young patients in a third level complexity referral hospital in Medellin, Colombia.Methods: A retrospective observational cross-sectional study was carried out reviewing the medical records of patients between 18 to 49 years old admitted for the first time for ischemic stroke, from January 2009 to December 2019. The sociodemographic characteristics, risk factors, and etiological classification of ischemic stroke according to the Trial of Org 10,172 in Acute Stroke Treatment (TOAST) were described.Results: Two hundred thirty-seven cases were found. The most frequent risk factors were arterial hypertension (31.7%), smoking (29.5%) and alcohol intake (23.2%). There was a greater number of traditional cardiovascular risk factors at older ages. The TOAST classification was large-artery atherosclerosis (6.8%), cardioembolism (17.7%), small-vessel disease (7.6%), other determined etiology (25.7%) and undetermined (42.2%). Within cardioembolism, the most common high-risk source was valve replacement, and the most common moderate-risk source was patent foramen ovale. Craniocervical arterial dissection (11.4%) and substance abuse (2.9%) were the two most frequent sources within other determined etiologies. The most common compromised vascular territory was the anterior (55.7%).Conclusions: The high frequency of traditional risk factors in young patients highlights the need to optimize primary and secondary prevention plans. This study provides new insights about the relevance of illicit substance abuse in Colombia as a cause of stroke in young patients, unlike the previous one conducted in Bogotá. Infectious causes were other peculiarities found. It is necessary to investigate the reasons for the high proportion of undetermined causes. [ABSTRACT FROM AUTHOR]

Recent studies have shown that public transport users can be exposed to high levels of pollution emitted from their own vehicles and nearby sources. The purpose of this research is to determine the personal exposure of passengers to PM2.5 inside the vehicles of the massive public transport of two of the main and more populated cities of Colombia, Bogotá and Medellín. TM (TransMilenio powered by diesel) and SITVA (electric and gas natural vehicles) were the systems studied. Were evaluated the integration of new vehicles with technologies Euro V and Euro VI in the TM system, the impact of the weekend effect on personal exposure into public transport (TM and SITVA), and the possible differences between personal exposure regarding the ways of the systems (mixed lane or exclusive lane for TM and SITVA). To measure PM2.5 levels, a DustTrak monitor previously calibrated was used. This measurement campaigns lasted for more than 80 hours and a mean of 17000 data of PM2.5 concentrations were obtained for each route. The personal dose was calculated based on the recorded data. The mean PM2.5 concentrations and personal dose found in the research for TM are 167 µg/m³ and 2.3 µg/min, respectively, while, for SITVA they are 41 µg/m³ and 0.53 µg/min, respectively. Therefore, SITVA users have a 5 times lower personal exposure to PM2.5 than TM users. It was also found that due to the poor proportion of new TM vehicles during the monitoring period, the personal exposure in the old vehicles and in the new ones is similar. In the case of SITVA, it was evidenced that the mixed lane contributes to a high personal exposure to PM2.5 than the exclusive one. [ABSTRACT FROM AUTHOR]

The article presents an exploration into the history of engineering education in Colombia in the late-19th and 20th centuries, focusing on how their educational systems contributed to the social identity of engineers within Colombian society. The histories of the technological schools Escuela Nacional de Minas, the Facultad de Matemáticas e Ingeniería and the Universidad de los Andes are discussed in turn, noting how they stood as centers of technological history and social influence in their host cities of Medellin and Bogotá.

Copyright of Desarrollo y Sociedad is the property of Universidad de los Andes and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)