Browsing by Keyword "Random forests"
Now showing 1 - 2 of 2
Results Per Page
Sort Options
Item Quantile regression forests-based modeling and environmental indicators for decision support in broiler farming(2019-06) Diez-Olivan, Alberto; Averós, Xavier; Sanz, Ricardo; Sierra, Basilio; Estevez, Inma; Tecnalia Research & InnovationAn efficient and sustainable animal production requires fine-tuning and control of all the parameters involved. But this is not a simple task. Animal farming is a complex biological system in which environmental parameters and management practices interact in a dynamic way. In addition, the typical non-linear response of biological processes implies that relationships across parameters that are critical to assure animal welfare and performance are difficult to determine. In this paper a novel decision support system based on environmental indicators and on weights, leg problems and mortality rates is proposed to address this issue. The data-driven modeling process is performed by a quantile regression forests approach that allows estimating growth, welfare and mortality parameters on the basis of environmental deviations from optimal farm conditions. Resulting models also provide confidence intervals able to deal with uncertainty. They are deployed in farm, offering an accessible tool for farmers, veterinarians and technical personnel. Experimental results involving 20 flocks of broiler meat chickens from different farms show the validity of the system, obtaining robust prediction intervals and high accuracy, namely over 81% for every model. The in-field use of the proposed approach will facilitate an efficient and animal welfare-friendly production management.Item The role of local urban traffic and meteorological conditions in air pollution: A data-based case study in Madrid, Spain: A data-based case study in Madrid, Spain(2016-11-01) Laña, Ibai; Del Ser, Javier; Padró, Ales; Vélez, Manuel; Casanova-Mateo, Carlos; IA; CALIDAD Y CONFORT AMBIENTALUrban air pollution is a matter of growing concern for both public administrations and citizens. Road traffic is one of the main sources of air pollutants, though topography characteristics and meteorological conditions can make pollution levels increase or diminish dramatically. In this context an upsurge of research has been conducted towards functionally linking variables of such domains to measured pollution data, with studies dealing with up to one-hour resolution meteorological data. However, the majority of such reported contributions do not deal with traffic data or, at most, simulate traffic conditions jointly with the consideration of different topographical features. The aim of this study is to further explore this relationship by using high-resolution real traffic data. This paper describes a methodology based on the construction of regression models to predict levels of different pollutants (i.e. CO, NO, NO2, O3 and PM10) based on traffic data and meteorological conditions, from which an estimation of the predictive relevance (importance) of each utilized feature can be estimated by virtue of their particular training procedure. The study was made with one hour resolution meteorological, traffic and pollution historic data in roadside and background locations of the city of Madrid (Spain) captured over 2015. The obtained results reveal that the impact of vehicular emissions on the pollution levels is overshadowed by the effects of stable meteorological conditions of this city.