A forecasting model based on ARIMA and artificial neural networks for end-OF-life vehicles.

The accelerated growth of the automotive supply network has had an immeasurable impact on the environment, especially relating to reusing and disposal of materials. The appropriate management of End-of-Life Vehicles (ELV) has become an imperative item for achieving sustainable development in the field of interest and it is, therefore, a target of special attention from global economies in recent years. Therefore, the present study aims to estimate the future generation of ELVs to assist decision making and mitigate the global impact of this type of waste on the environment. For this, a hybrid forecasting model was used, based on Autoregressive Integrated Moving Average (ARIMA) methodology and on Artificial Neural Networks (ANN), with a set of temporal data extracted from Brazilian sectoral platforms. The results achieved point to a good convergence of the model, indicating better performance than a naive or trivial prediction. The efficiency obtained by the Nash-Sutcliffe coefficient was 98% and the expectation is that for the year 2030, approximately 5.2 million ELVs will be produced in Brazil, of which only 78 thousand units would be effectively recycled, considering the current vehicle recycling rate in the country. Considering the scarcity of information that supports decision-making in waste management in Brazil, this study may also contribute to the proposition of alternatives that favor the proper management of automotive waste, providing a reference for the formulation and implementation of policies related to ELVs in the country.

Association between National Treatment Guidelines for Upper Respiratory Tract Infections and Outpatient Pediatric Antibiotic Use in France: An Interrupted Time-Series Analysis.

OBJECTIVE: To test whether updated clinical practice guidelines for managing upper respiratory tract infections released in France in November 2011 were associated with changes in national outpatient pediatric antibiotic use. STUDY DESIGN: We performed an interrupted time-series analysis using national antibiotic dispensation data in French children from January 2009 to December 2017 (IQVIA Suivi de la Dispensation Médicale database). We described the overall evolution of antibiotic prescription rates and modeled the changes in the proportion of amoxicillin and the proportion of broad-spectrum antibiotics following the guidelines in 2 age groups (0-5 and 6-14 years old). RESULTS: We analyzed 123 million pediatric antibiotic prescriptions. The most commonly prescribed individual antibiotic agent was amoxicillin (37.7%). Over the study period, the annual antibiotic prescription rate decreased by 33.1% (from 1387 to 928 per 1000 pediatric inhabitants per year), consistently across age groups and major antibiotic agents except for amoxicillin (+14.4%). After the release of the guidelines, we observed a gradual increase in the proportion of amoxicillin (relative change 5 years postintervention of +64.3% [95% CI 51.6-80.1] and +28.4% [21.1-36.2] for children 0-5 and 6-14 years, respectively) concomitantly with a gradual decrease in the proportion of broad-spectrum antibiotics (relative change 5 years postintervention of -26.1% [-29.3, -23.7] and -19.8% [-22.1, -16.0] for children 0-5 and 6-14 years old, respectively). CONCLUSIONS: The 2011 guidelines for upper respiratory tract infections preceded changes in outpatient pediatric antibiotic use at the national level, with a replacement of broad-spectrum antibiotics by amoxicillin.

Ronda clínica y epidemiológica. Series de tiempo / Clinical and epidemiological rounds. Time series / Ronda clínica e epidemiológica. Séries de tempo

El análisis de series de tiempo es una técnica que involucra el estudio de individuos o grupos observados en momentos sucesivos en el tiempo. Este tipo de análisis permite estudiar la relación potencialmente causal entre diferentes variables que cambian en el tiempo y que se relacionan entre sí. Es la técnica más importante para hacer inferencias acerca del futuro, predicción, con base en lo que ha ocurrido en el pasado y se aplica en diferentes disciplinas del conocimiento. Se exponen los diferentes componentes, la técnica de análisis y algunos ejemplos específicos en el área de la salud.

Analysis of time series is a technique that implicates the study of individuals or groups observed in successive moments in time. This type of analysis allows the study of potential causal relationships between different variables that change over time and relate to each other. It is the most important technique to make inferences about the future, predicting, on the basis or what has happened in the past and it is applied in different disciplines of knowledge. Here we discuss different components of time series, theanalysis technique and specific examples in health research.

A análise de séries de tempo é uma técnica que envolve o estudo de indivíduos ou grupos observados em momentos sucessivos no tempo. Este tipo de análise permite estudar a relação potencialmente causal entre diferentes variáveis que mudam no tempo que se relacionam entre si. É a técnica mais importante para fazer inferências sobre o futuro, predição, com base no que há acontecido no passado e se aplica em diferentes disciplinas do conhecimento. Se expõe os diferentes componentes, a técnica de análise e alguns exemplos específicos na área da saúde.

Clima e incidencia de infecciones respiratorias agudas en Ancash, Perú (2005-2013) / Climate and the incidence of acute respiratory infection in Ancash, Peru (2005-2013)

Introducción: algunas variables meteorológicas pudieran influir en el estado de salud de las personas y se admite un cambio climático antrópico y global en marcha. Objetivo: identificar el comportamiento de las temperaturas secas extremas del aire y su posible relación con las infecciones respiratorias agudas. Métodos: se efectúa un análisis de series cronológicas en Ancash, Perú. El análisis se dirige a las temperaturas secas extremas del aire y la incidencia de las infecciones respiratorias agudas, en un período reciente sobre una base mensual. Se utilizó el método no paramétrico de espectro de potencia bivariado, se consideraron densidades espectrales, coherencias y fases para identificar regularidades en las estructuras de frecuencias de las series temporales. La variable dependiente en la fortaleza de enlace y relación de fase fue la incidencia de las infecciones respiratorias agudas. También su empleó el método paramétrico univariado ARIMA (p,d,q) para modelación univariada. Resultados: se identificaron periodicidades anuales de la temperatura diaria mínima mensual promedio en contrafase con análoga periodicidad de la incidencia local de las infecciones respiratorias agudas; y de la temperatura diaria máxima mensual promedio cuasi en fase con las infecciones respiratorias agudas. Conclusiones: el calentamiento no fue confirmado. Las infecciones respiratorias agudas mostraron tendencia oscilante en el periodo analizado(AU)

Introduction: some meteorological variables could influence the health of individuals and anthropogenic global climate change and launch is supported. Objectives: this study attempts to identify regularities of behavior of extreme dry air temperatures and their possible relation to acute respiratory infections (SARI). Method: a time series analysis in Ancash, Peru is made. The analysis addresses the extreme dry air temperatures and the incidence of HCAI, in a recent period on a monthly basis. Nonparametric method of bivariate power spectrum, considering spectral densities, coherences and phases to identify regularities in the structure of the time series frequencies, bond strength and phase relationship, where the dependent variable was the incidence of HCAI was used ; Also the parametric method univariate ARIMA (p, d, q) for univariate modeling. Result: annual periodicity of the average monthly daily minimum temperature in antiphase with periodicity comparable to the local incidence of HCAI and the monthly average daily maximum temperature in quasi-phase with the IRAS identified. To this persistence process first order is added. Conclusions: the heating was not confirmed. The IRAS showed oscillating trend in the period analyzed(AU)