Predicting the Poaceae pollen season: six month-ahead forecasting and identification of relevant features.

In this paper, we approach the problem of predicting the concentrations of Poaceae pollen which define the main pollination season in the city of Madrid. A classification-based approach, based on a computational intelligence model (random forests), is applied to forecast the dates in which risk concentration levels are to be observed. Unlike previous works, the proposal extends the range of forecasting horizons up to 6 months ahead. Furthermore, the proposed model allows to determine the most influential factors for each horizon, making no assumptions about the significance of the weather features. The performace of the proposed model proves it as a successful tool for allergy patients in preventing and minimizing the exposure to risky pollen concentrations and for researchers to gain a deeper insight on the factors driving the pollination season.

[Predictions of three mathematical models related with the COVID-19 Vaccination Strategy in Spain. June 2021.] / Predicciones de tres modelos matemáticos en relación a la estrategia de vacunación frente a la COVID-19 en España. Junio de 2021.

The Ministry of Health has coordinated three studies that have estimated the impact of the COVID-19 Vaccination Strategy in Spain. The models aim to help how to establish priority population groups for vaccination, in an initial context of dose limitation. With the same epidemiological and vaccine information, the results of this three different mathematical models point in the same direction: combined with physical distancing, staggered vaccination, starting with the high risk groups, would prevent 60% of infections, 42% of hospitalizations and 60% of mortality in the population. These models, which can be adapted to the new available scientific evidence, are dynamic and powerful tools for the evaluation and adjustment of immunization programs, promoting research on this field, and helping to achieve more efficient results in health.

El Ministerio de Sanidad ha coordinado tres estudios que han estimado el impacto de la Estrategia de Vacunación frente a COVID-19 en España. El objetivo era que los modelos ayudaran a establecer los grupos de población prioritarios para la vacunación, en un contexto inicial de limitación de dosis. A partir de la misma información epidemiológica y de vacunas se han elaborado tres modelos matemáticos distintos cuyos resultados apuntan en la misma dirección: combinada con el distanciamiento físico, la vacunación escalonada, empezando por los grupos de mayor riesgo de complicaciones, evitaría el 60% de las infecciones, el 42% de las hospitalizaciones y el 60% de la mortalidad en la población. Estos modelos, que pueden adaptarse a la nueva evidencia científica disponible, son herramientas dinámicas y potentes para la evaluación y el ajuste de los programas de vacunación, impulsando el desarrollo de este campo de investigación, y ayudando a lograr resultados más eficientes en salud.

SatDNA Analyzer: a computing tool for satellite-DNA evolutionary analysis.

UNLABELLED: satDNA Analyzer is a program, implemented in C++, for the analysis of the patterns of variation at each nucleotide position considered independently amongst all units of a given satellite-DNA family when comparing it between a pair of species. The program classifies each site accordingly as monomorphic or polymorphic, discriminates shared from non-shared polymorphisms and classifies each non-shared polymorphism according to the model proposed by Strachan et al. in six different stages of transition during the spread of a variant repeat unit toward its fixation. Furthermore, this program implements several other utilities for satellite-DNA analysis evolution such as the design of the average consensus sequences, the average base pair contents, the distribution of variant sites, the transition to transversion ratio and different estimates of intra-specific variation and inter-specific variation. Aprioristic hypotheses on factors influencing the molecular drive process and the rates and biases of concerted evolution can be tested with this program. Additionally, satDNA Analyzer generates an output file containing a sequence alignment without shared polymorphisms to be used for further evolutionary analysis by using different phylogenetic softwares. AVAILABILITY: satDNA Analyzer is freely available at http://satdna.sourceforge.net/. SatDNA Analyzer has been designed to operate on Windows, Linux and Mac OS X.

What are the most important variables for Poaceae airborne pollen forecasting?

In this paper, the problem of predicting future concentrations of airborne pollen is solved through a computational intelligence data-driven approach. The proposed method is able to identify the most important variables among those considered by other authors (mainly recent pollen concentrations and weather parameters), without any prior assumptions about the phenological relevance of the variables. Furthermore, an inferential procedure based on non-parametric hypothesis testing is presented to provide statistical evidence of the results, which are coherent to the literature and outperform previous proposals in terms of accuracy. The study is built upon Poaceae airborne pollen concentrations recorded in seven different locations across the Spanish province of Madrid.

Predicciones de tres modelos matemáticos en relación a la estrategia de vacunación frente a la COVID-19 en España. Junio de 2021 / Predictions of three mathematical models related with the COVID-19 Vaccination Strategy in Spain. June 2021

El Ministerio de Sanidad ha coordinado tres estudios que han estimado el impacto de la Estrategia de Vacunación frente a COVID-19 en España. El objetivo era que los modelos ayudaran a establecer los grupos de población prioritarios para la vacunación, en un contexto inicial de limitación de dosis. A partir de la misma información epidemiológica y de vacunas se han elaborado tres modelos matemáticos distintos cuyos resultados apuntan en la misma dirección: combinada con el distanciamiento físico, la vacunación escalonada, empezando por los grupos de mayor riesgo de complicaciones, evitaría el 60% de las infecciones, el 42% de las hospitalizaciones y el60% de la mortalidad en la población. Estos modelos, que pueden adaptarse a la nueva evidencia científica disponible, son herramientasdinámicas y potentes para la evaluación y el ajuste de los programas de vacunación, impulsando el desarrollo de este campo de investigación, y ayudando a lograr resultados más eficientes en salud.(AU)

The Ministry of Health has coordinated three studies that have estimated the impact of the COVID-19 Vaccination Strategy in Spain. The models aim to help how to establish priority population groups for vaccination, in aninitial context of dose limitation. With the same epidemiological and vaccine information, the results of this three different mathematical models point in the same direction: combined with physical distancing, staggered vaccination, starting with the high risk groups, would prevent 60% of infections, 42% of hospitalizations and 60% of mortality in the population. These models, which can be adapted to the new available scientific evidence, are dynamic and powerful tools for the evaluation and adjustment of immunization programs, promoting research on this field, and helping to achieve more efficient results in health.(AU)

Time series modeling and forecasting using memetic algorithms for regime-switching models.

In this brief, we present a novel model fitting procedure for the neuro-coefficient smooth transition autoregressive model (NCSTAR), as presented by Medeiros and Veiga. The model is endowed with a statistically founded iterative building procedure and can be interpreted in terms of fuzzy rule-based systems. The interpretability of the generated models and a mathematically sound building procedure are two very important properties of forecasting models. The model fitting procedure employed by the original NCSTAR is a combination of initial parameter estimation by a grid search procedure with a traditional local search algorithm. We propose a different fitting procedure, using a memetic algorithm, in order to obtain more accurate models. An empirical evaluation of the method is performed, applying it to various real-world time series originating from three forecasting competitions. The results indicate that we can significantly enhance the accuracy of the models, making them competitive to models commonly used in the field.

Equivalences between neural-autoregressive time series models and fuzzy systems.

Soft computing (SC) emerged as an integrating framework for a number of techniques that could complement one another quite well (artificial neural networks, fuzzy systems, evolutionary algorithms, probabilistic reasoning). Since its inception, a distinctive goal has been to dig out the deep relationships among their components. This paper considers two wide families of SC models. On the one hand, the regime-switching autoregressive paradigm is a recent development in statistical time series modeling, and it includes a set of models closely related to artificial neural networks. On the other hand, we consider fuzzy rule-based systems in the framework of time series analysis. This paper discloses original results establishing functional equivalences between models of these two classes, and hence opens the door to a productive line of research where results and techniques from one area can be applied in the other. As a consequence of the equivalences presented in this paper, we prove the asymptotic stationarity of a class of fuzzy rule-based systems. Simulations based on information criteria show the importance of the selection of the proper membership function.