RESUMO
Background: Aedes aegypti is the dominant vector of several arboviruses that threaten urban populations in tropical and subtropical countries. Because of the climate changes and the spread of the disease worldwide, the population at risk of acquiring the disease is increasing. Methods: This study investigated the impact of the larval habitats control (CC), nebulization (NEB), and both methods (CCâ¯+â¯NEB) using the distribution of Ae. aegypti eggs collected in urban area of Santa Bárbara d'Oeste, São Paulo State, Brazil. A total of 142,469 eggs were collected from 2014 to 2017. To verify the effects of control interventions, a spatial trend, and a predictive machine learning modeling analytical approaches were adopted. Results: The spatial analysis revealed sites with the highest probability of Ae. aegypti occurrence and the machine learning generated an asymmetric histogram for predicting the presence of the mosquito. Results of analyses showed that CC, NEB, and CCâ¯+â¯NEB control methods had a negative impact on the number of eggs collected in ovitraps, with effects on the distribution of eggs in the three weeks following the treatments, according to the predictive machine learning modeling. Conclusions: The vector control interventions are essential to decrease both occurrence of the mosquito vectors and urban arboviruses. The inference processes proposed in this study revealed the relative causal impact of distinct mosquito control interventions. The spatio-temporal and the machine learning analysis are relevant and Powered by Editorial Manager® and ProduXion Manager® from Aries Systems Corporation robust analytical approach to be employed in surveillance and monitoring the results of public health programs focused on combating urban arboviruses.
RESUMO
In this paper, we apply an immune-inspired approach to design ensembles of heterogeneous neural networks for classification problems. Our proposal, called Bayesian artificial immune system, is an estimation of distribution algorithm that replaces the traditional mutation and cloning operators with a probabilistic model, more specifically a Bayesian network, representing the joint distribution of promising solutions. Among the additional attributes provided by the Bayesian framework inserted into an immune-inspired search algorithm are the automatic control of the population size along the search and the inherent ability to promote and preserve diversity among the candidate solutions. Both are attributes generally absent from alternative estimation of distribution algorithms, and both were shown to be useful attributes when implementing the generation and selection of components of the ensemble, thus leading to high-performance classifiers. Several aspects of the design are illustrated in practical applications, including a comparative analysis with other attempts to synthesize ensembles.
Assuntos
Algoritmos , Inteligência Artificial , Teorema de Bayes , Simulação por Computador/normas , Fenômenos do Sistema Imunitário/fisiologia , Redes Neurais de Computação , Classificação/métodos , Simulação por Computador/estatística & dados numéricos , Humanos , Reconhecimento Automatizado de Padrão/métodos , Reconhecimento Automatizado de Padrão/estatística & dados numéricosRESUMO
The sensitivity of parameters that govern the stability of population size in Chrysomya albiceps and describe its spatial dynamics was evaluated in this study. The dynamics was modeled using a density-dependent model of population growth. Our simulations show that variation in fecundity and mainly in survival has marked effect on the dynamics and indicates the possibility of transitions from one-point equilibrium to bounded oscillations. C. albiceps exhibits a two-point limit cycle, but the introduction of diffusive dispersal induces an evident qualitative shift from two-point limit cycle to a one fixed-point dynamics. Population dynamics of C. albiceps is here compared to dynamics of Cochliomyia macellaria, C. megacephala and C. putoria