A Machine-Learning Approach to Distinguish Passengers and Drivers Reading While Driving.

Driver distraction is one of the major causes of traffic accidents. In recent years, given the advance in connectivity and social networks, the use of smartphones while driving has become more frequent and a serious problem for safety. Texting, calling, and reading while driving are types of distractions caused by the use of smartphones. In this paper, we propose a non-intrusive technique that uses only data from smartphone sensors and machine learning to automatically distinguish between drivers and passengers while reading a message in a vehicle. We model and evaluate seven cutting-edge machine-learning techniques in different scenarios. The Convolutional Neural Network and Gradient Boosting were the models with the best results in our experiments. Results show accuracy, precision, recall, F1-score, and kappa metrics superior to 0.95.

Ergonomic work analysis: A case study of bus drivers in the private collective transportation sector.

BACKGROUND: The collective transportation system is essential to reduce the number of automobiles in the roads. Concerns exist related to quality, comfort and safety of bus driver's workstations. OBJECTIVE: The objective of this study was to improve the driver's workstation in the private collective transportation sector by analyzing ergonomic practices using the Ergonomic Work Analysis (EWA). The EWA was chosen because it seeks to evaluate the labor condition as it relates to the psychophysiological conditions of workers, it complies with regulatory standard 17 (NR17). METHODS: To identify driver concerns, interviews and questionnaires were administered. The workstation and worker routines were observed. RESULTS: The analysis revealed that the largest number of complaints related to noise, display light and location of the passenger identifier device. Drivers reported discomfort in the knees and lower back. CONCLUSION: Recommendations were made to improve the workstation and change the routine to minimize the discomfort and ergonomic risk factors.

A safe speed guidance model for highways.

This paper presents a fuzzy logic model to support decisions for the suggested speed limit for sections of highways as they become affected by adverse road conditions, environmental factors and differing traffic levels. The definition of the main factors, and their weight, that reduce safety on highways was conducted by the Delphi method, consulting traffic engineering experts. The survey served as a basis for structuring indicators and indexes in a soft decision tree, structured by a fuzzy logic system. The system can be used to support the decisions of those that manage the roads, indicating to drivers' speeds, by visual, audible or combined systems.

Non-frail elderly people and their license to drive motor vehicles / Ancianos no frágiles y la habilitación para conducir vehículos automotores / Idosos não frágeis e a habilitação para dirigir veículos automotores

ABSTRACT Objective: to analyse the link between the non-frailty condition and the results of driving license for elderly people to drive motor vehicles. Method: cross-sectional study with data collection in the sample period from August 2015 to March 2016. Study performed with 347 elderlies (≥60 years). Results: 180 (51.9%) of the participants were classified as non-frail. 48 (26.7%) of them were considered capable to drive, 121 (67.2%) capable to drive with restrictions and 11 (6.1%) temporarily uncapable. No significant relation was found between the non-frailty conditions and the results of the motor vehicles driving license study (p=0.557). Conclusion: The absence of physical frailty does not necessarily points out that the elderly are able to drive motor vehicles. Tracking the frailty subsidizes preventive interventions, which seek to interfere positively in the act of driving. This is an unprecedented study in nursing and it highlights an essential field for the performance of gerontological nursing.

RESUMEN Objetivo: analizar la asociación entre la condición de no fragilidad física y los resultados de la habilitación de ancianos para conducir vehículos automotores. Método: estudio transversal con recolección de datos en el período de muestreo de agosto de 2015 a marzo de 2016 y realizado con 347 ancianos (≥60 años). Resultados: De los participantes, 180 (51,9%) fueron clasificados como no frágiles. De estos, 48 (26,7%) fueron considerados aptos para conducir, 121 (67,2%) aptos con restricción y 11 (6,1%) inaptos temporalmente. No hubo asociación significativa entre la condición de no fragilidad física y los resultados de la habilitación para conducir vehículos automotores (p=0,557). Conclusión: La ausencia de fragilidad física no indica necesariamente que el anciano está apto para conducir vehículos automotores. El rastreo de la fragilidad subsidia intervenciones preventivas, que apuntan a interferir de manera positiva en el acto de conducir. El estudio es inédito en la enfermería y apunta un local indispensable para la actuación de la enfermería gerontológica.

RESUMO Objetivo: analisar a associação entre a condição de não fragilidade física e os resultados da habilitação dos idosos para dirigir veículos automotores. Método: estudo transversal com coleta de dados no período amostral de agosto de 2015 a março de 2016 e realizado com 347 idosos (≥60 anos). Resultados: dos participantes, 180 (51,9%) foram classificados como não frágeis. Destes, 48 (26,7%) foram considerados aptos para dirigir, 121 (67,2%) aptos com restrição e 11 (6,1%) inaptos temporariamente. Não houve associação significativa entre a condição de não fragilidade física e os resultados da habilitação para dirigir veículos automotores (p=0,557). Conclusão: a ausência de fragilidade física não indica, necessariamente, que o idoso está apto para dirigir veículos automotores. O rastreamento da fragilidade subsidia intervenções preventivas, que visam interferir de maneira positiva no ato de dirigir. O estudo é inédito na enfermagem e aponta um local indispensável para atuação da enfermagem gerontológica.

Non-frail elderly people and their license to drive motor vehicles.

OBJECTIVE: to analyse the link between the non-frailty condition and the results of driving license for elderly people to drive motor vehicles. METHOD: cross-sectional study with data collection in the sample period from August 2015 to March 2016. Study performed with 347 elderlies (≥60 years). RESULTS: 180 (51.9%) of the participants were classified as non-frail. 48 (26.7%) of them were considered capable to drive, 121 (67.2%) capable to drive with restrictions and 11 (6.1%) temporarily uncapable. No significant relation was found between the non-frailty conditions and the results of the motor vehicles driving license study (p=0.557). CONCLUSION: The absence of physical frailty does not necessarily points out that the elderly are able to drive motor vehicles. Tracking the frailty subsidizes preventive interventions, which seek to interfere positively in the act of driving. This is an unprecedented study in nursing and it highlights an essential field for the performance of gerontological nursing.

Representaciones sociales de normas de tránsito, agresividad, facilidad percibida en la conducción, accidentes y multas en conductores de Bogotá, D. C. / Social representations of traffic rules, aggressiveness, easiness perceivedin driving, accidents, and traffic tickets involving drivers in Bogota, D. C. / Representações sociais de normas de trânsito, agressividade, facilidadepercebida na condução, acidentes e multas nos motoristas de Bogotá, D. C.

El objetivo principal de este trabajo fue conocer las representaciones sociales sobre normas de tránsito, y su relación con la agresividad y con la accidentalidad, y multas de tránsito autoinformadas en conductores de Bogotá. Se aplicó una encuesta basada en casos (Mamontoff, 2010) con elementosgráficos (Abric, 1993), a una muestra no aleatoriade conductores infractores o en proceso de renovación dela licencia de conducción. Como resultados se identificaron cuatro clases de conductores: dos grupos más dispuestos a consumir alcohol y exceder límites de velocidad (1.ª clase)o no respetar semáforos en rojo y otras señalizaciones (2.ªclase), otro grupo menos de acuerdo con consumir alcohol antes de conducir, pero favorable a superar límites de velocidad(3.ª clase) y otro grupo favorable a no violar ninguna norma de conducción (4.ª clase). Una actitud más favorable a consumir alcohol en la conducción se asoció con atribución de los accidentes a factores externos a los conductores, con haber sido multado más veces en el pasado y con más daños en accidentes. Una mayor agresividad se asoció, asimismo,con una intención de conducta más imprudente.

The main objective in this work consisted of getting to know the social representations about traffic rules and their connection with self-reported aggressiveness, accident rates and fines for traffic offenses by drivers in Bogota. A case-based survey (Mamontoff, 2010) with graphic elements (Abric,1993) was applied to a non-random sample of driving offenders or drivers undergoing their driving license renewal process. As results, four classes of drivers were identified: Two groups more likely to: abuse alcohol and exceed speed limits (1st class), pass through red or yellow lights and disregar dother traffic signs (2nd class); another group that was more cautious about drinking alcohol before driving, but not with regard to exceeding speed limits (3rd class), and another group with a willingness to comply with all driving rules (4th class). A more lenient attitude towards drinking alcohol before or while driving was associated to attributing accidents to factors external to the driver, or with a higher record of fines or sanctions in the past, and having suffered more damages in road-traffic. Likewise, a more far-reaching aggressiveness was associated with an intended less prudent or cautious conduct.

O objetivo principal deste trabalho era conhecer as representações sociais sobre as normas de trânsito, e a sua relação com a agressividade e a acidentalidade, e as multas de trânsito autoinformadas nos motoristas de Bogotá. Uma pesquisa baseada em casos (Mamontoff, 2010) com elementos gráficos (Abric, 1993) foi aplicada a uma amostra não aleatória de motoristas infratores ou em processo da renovação da carteira de motorista. Como resultados identificaram-se quatro classes de motoristas: dois grupos mais prontos para consumir o álcool e exceder limites de velocidade (1°classe)ou não respeitar semáforos em vermelho e outra sinalização(2° classe), um outro grupo menos de acordo com o consumo de álcool antes de dirigir, mas favorável para exceder limites de velocidade (3° classe) e um outro grupo favorável para não infringir nenhuma norma da condução (4° classe). Uma atitude mais favorável para consumir o álcool ao dirigir foi associada com a atribuição dos acidentes aos fatores externos aos motoristas, por ser multado mais vezes no passado e com mais danos nos acidentes. Uma maior agressividade foi associada, também, com uma intenção da conduta mais imprudente.

Erros de utilização de assentos de segurança infantil por menores de 4 anos / Child safety seat usage errors in under-4s

OBJETIVO: Analisar erros de utilização de assentos de segurança infantil por crianças matriculadas em creches e fatores relacionados. MÉTODOS: Estudo observacional transversal de coleta de dados prospectiva e eixo analítico retrospectivo. RESULTADOS: Um total de 42,7% das crianças apresentava erros de utilização. O modelo de regressão logística evidenciou maiores chances de erros na presença de duas ou mais crianças no veículo (odds ratio = 5,10, p = 0,007) e menores níveis de escolaridade e renda dos pais (renda e escolaridade médias: odds ratio = 7,00, p = 0,003; renda e escolaridade baixas: odds ratio = 3,40, p = 0,03). CONCLUSÃO: Os dados são coerentes com publicações internacionais.

OBJECTIVE: To analyze child safety seat usage errors among children enrolled at daycare. METHODS: This was a cross-sectional, observational study with prospective data collection and a retrospective analytical axis. RESULTS: Overall, 42.7% of the children studied were in incorrectly used seats. A logistic regression model showed that the likelihood of usage errors was higher if there were two or more children in the vehicle (odds ratio = 5.10, p = 0.007) and was dependent on parents' educational level and income (medium income and educational level: odds ratio = 7.00, p = 0.003; low income and educational level: odds ratio = 3.40, p = 0.03). CONCLUSION: The results of this study are in line with findings reported in international publications.

Child safety seat usage errors in under-4s.

OBJECTIVE: To analyze child safety seat usage errors among children enrolled at daycare. METHODS: This was a cross-sectional, observational study with prospective data collection and a retrospective analytical axis. RESULTS: Overall, 42.7% of the children studied were in incorrectly used seats. A logistic regression model showed that the likelihood of usage errors was higher if there were two or more children in the vehicle (odds ratio = 5.10, p = 0.007) and was dependent on parents' educational level and income (medium income and educational level: odds ratio = 7.00, p = 0.003; low income and educational level: odds ratio = 3.40, p = 0.03). CONCLUSION: The results of this study are in line with findings reported in international publications.

[Actions and strategies for the prevention and control of road traffic injuries: peruvian experience by levels of prevention]. / Medidas y estrategias para la prevención y control de los accidentes de tránsito: experiencia peruana por niveles de prevención.

This article aims to describe the main actions that are being developed in Peru for primary and secondary prevention of road traffic injuries, considering the epidemiological aspects that characterize the Peruvian experience, as reported in other countries. At the primary prevention level, it addresses issues related to the timing restriction of the sales of alcoholic beverages, detection of drivers with positive testing for alcohol in blood and the chosen driver. Regarding secondary prevention, the studies on black spots and the impact containment barrels are presented, also a brief overview of the pre-hospital care systems in the case of road traffic injuries. There is a need for better characterization of the problem, in order to establish healthy public policies regarding traffic accidents, there is a need for evidence-based reviews and studies of economic evaluations.

[Sleep monitoring in bus and truck drivers: relevant factor to consider for the renewal of the driving license]. / Monitoreo del sueño en conductores de ómnibus y camiones: factor relevante a considerar para la renovación de la licencia de conducir.

The available information indicates that up to one third of the road traffic accidents are produced by the driver's sleepiness. Sleep apnea-hypopnea syndrome (SAHS) is an organic disease that causes sleepiness. It can be diagnosed by a sleep register and can be controlled by different therapeutic means, varying their complexity according to its severity, which determines the final cost of the management of SAHS. In patients using the therapy thoroughly, the results are very good and achieve to control the sleepiness, improve the quality of life of the affected subject, protect his health and markedly decrease the risk of accidents due to sleepiness during driving. We put into consideration of the respective authorities the application of these tests in drivers suspected of having SAHS who renew their driving licenses type A-II and A-III.

Utilização de assentos de segurança por crianças matriculadas em creches / Child safety restraint use among children attending day care centers

OBJETIVO: Estimar a prevalência de utilização de assentos de segurança infantil e fatores associados. MÉTODOS: Estudo transversal observacional, com amostragem estratificada, realizado em 15 creches da cidade de Maringá, PR, entre os meses de março e maio de 2007. Cada creche foi visitada em apenas um dia letivo. O desfecho considerado foi a utilização de assento de segurança infantil por crianças de até quatro anos de idade. Carros (N=301) que transportavam crianças menores de quatro anos de idade foram abordados e as informações foram coletadas por meio de questionários semi-estruturados. Variáveis relacionadas a distribuição de adultos e crianças nos assentos do veículo, situação de restrição dos ocupantes e sexo do condutor foram analisadas. Para análise dos dados aplicou-se o teste exato de Fisher, qui-quadrado de Mantel-Haenszel e regressão logística. RESULTADOS: Entre os motoristas abordados, 51,8 por cento usavam cinto de segurança (60,4 por cento das mulheres, 44,9 por cento dos homens). Entre as crianças, 36,1 por cento usavam assentos de segurança infantil, 45,4 por cento eram transportadas soltas, 16,0 por cento estavam no colo de adultos, 2,7 por cento usavam o cinto de segurança. Segundo a regressão logística, os fatores que mais influenciaram o uso dos assentos de segurança infantil foram: idade da criança inferior a 15 meses (OR= 3,76), uso de cinto de segurança pelo condutor (OR= 2,45) e crianças pertencentes aos estratos sociocupacionais de maior renda e escolaridade (OR= 1,37). CONCLUSÕES: A utilização de assentos de segurança infantil mostrou-se associada à idade da criança, uso de cinto de segurança pelo condutor e estrato sociocupacional da creche. Frente ao baixo índice de utilização, o uso dos assentos de segurança infantil surge como desafio à medicina preventiva no Brasil, exigindo atenção e atuação para sua disseminação na população.

OBJECTIVE: To estimate the prevalence of child safety restraint use and factors associated. METHODS: Observational cross-sectional study using a stratified sampling conducted in the city of Maringá, Southern Brazil, between March and May 2007. Each day care center was visited at one day only. The outcome was use of child safety restraints by children under four. Vehicles (N=301) driving children under four were approached and information was collected using semi-structured questionnaires. Variables regarding child and adult seat distribution, use of safety restraints by occupants and driver's gender were analyzed. Data analyses included Fisher's exact test, Mantel-Haenszel chi-square test, and logistic regression. RESULTS: Of the drivers approached, 51.8 percent were using seat belts (60.4 percent among women, 44.9 percent among men). Among children, 36.1 percent were using child safety seats, 45.4 percent were unrestrained during traveling, 16.0 percent were seated on an adult lap, and 2.7 percent were using seat belts. The logistic regression showed the following factors affecting child safety restraint use: child age under 15 months (OR = 3.76); seat belt use by the driver (OR = 2.45); and children from socio-occupational condition with higher income and education (OR = 1.37). CONCLUSIONS: Child safety restraint use was associated to child age, seat belt use by the driver, and socio-occupational condition of day care centers. The finding of low rates of child safety restraint use poses a challenge to preventive medicine in Brazil, requiring attention and action to promote its widespread use.

Child safety restraint use among children attending day care centers.

OBJECTIVE: To estimate the prevalence of child safety restraint use and factors associated. METHODS: Observational cross-sectional study using a stratified sampling conducted in the city of Maringá, Southern Brazil, between March and May 2007. Each day care center was visited at one day only. The outcome was use of child safety restraints by children under four. Vehicles (N=301) driving children under four were approached and information was collected using semi-structured questionnaires. Variables regarding child and adult seat distribution, use of safety restraints by occupants and driver's gender were analyzed. Data analyses included Fisher's exact test, Mantel-Haenszel chi-square test, and logistic regression. RESULTS: Of the drivers approached, 51.8% were using seat belts (60.4% among women, 44.9% among men). Among children, 36.1% were using child safety seats, 45.4% were unrestrained during traveling, 16.0% were seated on an adult lap, and 2.7% were using seat belts. The logistic regression showed the following factors affecting child safety restraint use: child age under 15 months (OR = 3.76); seat belt use by the driver (OR = 2.45); and children from socio-occupational condition with higher income and education (OR = 1.37). CONCLUSIONS: Child safety restraint use was associated to child age, seat belt use by the driver, and socio-occupational condition of day care centers. The finding of low rates of child safety restraint use poses a challenge to preventive medicine in Brazil, requiring attention and action to promote its widespread use.

Highly reported prevalence of drinking and driving in Brazil: data from the first representative household study.

OBJECTIVE: Brazil lacks information about driving under the influence of alcohol (DUI) originated from representative samples obtained from the general population. METHOD: 333 subjects with a valid driver's license and drinking in the last 12 months were drawn from a multistaged sample of 2,346 adults from the first Brazilian Household Survey of Patterns of Alcohol Use. A multivariate analysis was conducted to understand the associations between risk factors and driving after drinking three or more drinks. RESULTS: the overall DUI prevalence reported in the sample was 34.7% - 42.5% among males and 9.2% among females. Being male (OR = 6.0, 95% CI 2.9-12.6), having a previous DUI accident (OR = 7.9, 95% CI 2.5-24.9), binging in the last year (OR = 2.2, 95% CI 1.03-4.5) and having an unfavorable opinion towards policies (OR = 2.9, 95% CI 1.4-6.2) remained associated with heavy drinking and driving after model adjustments. DISCUSSION: This was the first study evaluating driving under the influence of alcohol in a representative sample of the Brazilian population. The prevalence of DUI found is alarming, and possibly underestimated in the sample. Results demonstrate the need for more studies on this association and show directions towards preventive strategies for the specific high-risk group of male drivers with previous problems with alcohol and unfavorable opinions about prevention policies.

Highly reported prevalence of drinking and driving in Brazil: data from the first representative household study / Alta prevalência relatada de beber e dirigir no Brasil: dados do primeiro estudo representativo realizado em domicílios

OBJECTIVE: Brazil lacks information about driving under the influence of alcohol (DUI) originated from representative samples obtained from the general population. METHOD: 333 subjects with a valid driver's license and drinking in the last 12 months were drawn from a multistaged sample of 2,346 adults from the first Brazilian Household Survey of Patterns of Alcohol Use. A multivariate analysis was conducted to understand the associations between risk factors and driving after drinking three or more drinks. RESULTS: the overall DUI prevalence reported in the sample was 34.7 percent - 42.5 percent among males and 9.2 percent among females. Being male (OR = 6.0, 95 percent CI 2.9-12.6), having a previous DUI accident (OR = 7.9, 95 percent CI 2.5-24.9), binging in the last year (OR = 2.2, 95 percent CI 1.03-4.5) and having an unfavorable opinion towards policies (OR = 2.9, 95 percent CI 1.4-6.2) remained associated with heavy drinking and driving after model adjustments. DISCUSSION: This was the first study evaluating driving under the influence of alcohol in a representative sample of the Brazilian population. The prevalence of DUI found is alarming, and possibly underestimated in the sample. Results demonstrate the need for more studies on this association and show directions towards preventive strategies for the specific high-risk group of male drivers with previous problems with alcohol and unfavorable opinions about prevention policies.

OBJETIVO: O Brasil carece de informação sobre beber e dirigir a partir de amostras representativas da população. MÉTODO: Uma amostra de 2.346 adultos do I Levantamento Nacional Domiciliar sobre Padrões de Consumo de Álcool forneceu 333 indivíduos com carteira de motorista e que haviam bebido álcool nos últimos 12 meses. Utilizou-se análise multivariada para compreender associações entre fatores de risco e dirigir após três ou mais drinques. RESULTADOS: A prevalência de beber e dirigir na amostra foi 34,7 por cento - 42,5 por cento nos homens e 9,2 por cento nas mulheres. Ser homem (OR = 6,0; IC95 por cento 2,9-12,6), ter tido acidente prévio com beber e dirigir (OR = 7,9; IC95 por cento 2,5-24,9), ter tido "consumo excessivo episódico" no ultimo ano (OR = 2,2; IC95 por cento 1,03-4,5) e ter uma opinião desfavorável sobre políticas públicas (OR = 2,9; IC95 por cento 1,4-6,2) mantiveram-se associados com consumo pesado e dirigir após ajustes no modelo. DISCUSSÃO: Este é o primeiro estudo que avalia beber e dirigir em uma amostra representativa da população brasileira. A prevalência de beber e dirigir encontrada é alarmante e possivelmente subestimada nesta amostra. Os achados demonstram a necessidade de outros estudos sobre esta associação, e dão indicações sobre possíveis estratégias preventivas para este grupo específico de motoristas masculinos com problemas prévios com álcool e opiniões desfavoráveis sobre políticas de prevenção.