Search

Some of the effects of climate change may be related to a change in patterns of rainfall intensity or scarcity. Therefore, humanity is facing environmental challenges due to an increase in the occurrence and intensity of droughts. The forecast of droughts can be of great help when trying to reduce the adverse effects that the scarcity of water brings, particularly in agriculture. When evaluating the conditions of water scarcity, as well as in the identification and characterization of droughts, the use of predictive models of drought indices could be a very useful tool. In this research, the utility of Artificial Neural Networks with exogenous inputs was tested, with the aim of predicting the monthly Standardized Precipitation Index in 4 regions (Semi-desert, Highlands, Canyons and Mountains) of north-central México using predictor data from 1979 to 2014. The best model was found using the scaled conjugate gradient backpropagation algorithm as the optimization method and was set to the following architecture: 6-25-1 network. The correlation coefficient of predicted and observed Standardized Precipitation Index values for the test dataset was between 0.84 and 0.95. As a result, the Artificial Neural Network models performed successfully in predicting Standardized Precipitation Index at the four analyzed regions. The developed and tested Artificial Neural Network models in this research suggest remarkable prediction abilities of the monthly Standardized Precipitation Index in the study region. [ABSTRACT FROM AUTHOR]

Se analizaron mediante regresión lineal series de largo plazo de evaporación en 35 estaciones localizadas en el estado de Zacatecas, México, con el objetivo de identificar sus tendencias y calcular sus anomalías. Adicionalmente, se analizaron mediante análisis fractal los espectros de potencia de las anomalías de evaporación con el fin de identificar sus frecuencias importantes y su posible conexión con fenómenos periódicos. Los resultados sugieren que las tendencias negativas en las series de tiempo de evaporación prevalecen sobre las tendencias positivas. Se encontró tendencia lineal negativa en 21 de 35 series; 18 de las 21 series fueron significativas a p <0.05. Por otra parte, 14 series tuvieron tendencias lineales positivas, pero solo 8 fueron significativas a p<0.05. El ruido en todas las series de tiempo de evaporación mensual tiene un comportamiento persistente. Adicionalmente, se encontró que las frecuencias importantes detectadas pueden estar relacionadas con el ciclo anual, el ciclo cuasi-bianual, el fenómeno "El Niño Oscilación del Sur" y el ciclo de manchas solares. [ABSTRACT FROM AUTHOR]

The development of medical diagnostic models to support healthcare professionals has witnessed remarkable growth in recent years. Among the prevalent health conditions affecting the global population, diabetes stands out as a significant concern. In the domain of diabetes diagnosis, machine learning algorithms have been widely explored for generating disease detection models, leveraging diverse datasets primarily derived from clinical studies. The performance of these models heavily relies on the selection of the classifier algorithm and the quality of the dataset. Therefore, optimizing the input data by selecting relevant features becomes essential for accurate classification. This research presents a comprehensive investigation into diabetes detection models by integrating two feature selection techniques: the Akaike information criterion and genetic algorithms. These techniques are combined with six prominent classifier algorithms, including support vector machine, random forest, k-nearest neighbor, gradient boosting, extra trees, and naive Bayes. By leveraging clinical and paraclinical features, the generated models are evaluated and compared to existing approaches. The results demonstrate superior performance, surpassing accuracies of 94%. Furthermore, the use of feature selection techniques allows for working with a reduced dataset. The significance of feature selection is underscored in this study, showcasing its pivotal role in enhancing the performance of diabetes detection models. By judiciously selecting relevant features, this approach contributes to the advancement of medical diagnostic capabilities and empowers healthcare professionals in making informed decisions regarding diabetes diagnosis and treatment. [ABSTRACT FROM AUTHOR]

In crop science, tools of non-linear dynamics, fractals, chaos, intermittency and self-organized criticality may be employed and applied to the analysis of spatial variability and temporal behavior of agro-meteorological variables, soil properties, plant attributes, commercial yields, and prices of the agricultural products in order to gain knowledge about underlying complex processes. A search on the occurrence of particular scaling laws in Mexico's normalized yearly mean grain yield anomaly series of maize (Zea mays L.), beans (Phaseolus vulgaris L.), wheat (Triticum aestivum L.) and rice (Oriza sativa L.), using a variography approach is reported in this work. Additionally, power spectrum determination, time-frequency analysis, and estimation of Lyapunov exponent were performed for each profile in order to obtain useful information on the frequency contents and signs at which important frequencies occur as well as to determine their sensitivity to initial conditions. Fractal analysis gives us the order maize < wheat < rice < beans of sensitivity to external forcings, which was the same as that obtained through the Lyapunov exponent values. Results confirm that the final outputs (crop yields) in agricultural systems are affected by the magnetic and sunspot cycles of the Sun, the El Niño Southern Oscillation (ENSO), and the quasi-biannual oscillation, and possibly by the so-called heliospheric mid-term-quasi-periodicities, which act on different time (or spatial and spatial-time) scales. In particular, the maize normalized year anomaly series is clearly correlated with March, April, May and June series of the ENSO index. [ABSTRACT FROM AUTHOR]

Oral health represents an essential component in the quality of life of people, being a determinant factor in general health since it may affect the risk of suffering other conditions, such as chronic diseases. Oral diseases have become one of the main public health problems, where dental caries is the condition that most affects oral health worldwide, occurring in about 90% of the global population. This condition has been considered a challenge because of its high prevalence, besides being a chronic but preventable disease which can be caused depending on the consumption of certain nutritional elements interacting simultaneously with different factors, such as socioeconomic factors. Based on this problem, an analysis of a set of 189 dietary and demographic determinants is performed in this work, in order to find the relationship between these factors and the oral situation of a set of subjects. The oral situation refers to the presence and absence/restorations of caries. The methodology is performed constructing a dense artificial neural network (ANN), as a computer-aided diagnosis tool, looking for a generalized model that allows for classifying subjects. As validation, the classification model was evaluated through a statistical analysis based on a cross validation, calculating the accuracy, loss function, receiving operating characteristic (ROC) curve and area under the curve (AUC) parameters. The results obtained were statistically significant, obtaining an accuracy' 0.69 and AUC values of 0.69 and 0.75. Based on these results, it is possible to conclude that the classification model developed through the deep ANN is able to classify subjects with absence of caries from subjects with presence or restorations with high accuracy, according to their demographic and dietary factors. [ABSTRACT FROM AUTHOR]

The indoor location of individuals is a key contextual variable for commercial and assisted location-based services and applications. Commercial centers and medical buildings (e.g., hospitals) require location information of their users/patients to offer the services that are needed at the correct moment. Several approaches have been proposed to tackle this problem. In this paper, we present the development of an indoor location system which relies on the human activity recognition approach, using sound as an information source to infer the indoor location based on the contextual information of the activity that is realized at the moment. In this work, we analyze the sound information to estimate the location using the contextual information of the activity. A feature extraction approach to the sound signal is performed to feed a random forest algorithm in order to generate a model to estimate the location of the user. We evaluate the quality of the resulting model in terms of sensitivity and specificity for each location and we also perform out-of-bag error estimation. Our experiments were carried out in five representative residential homes. Each home had four individual indoor rooms. Eleven activities (brewing coffee, cooking, eggs, taking a shower, etc.) were performed to provide the contextual information. Experimental results show that developing an indoor location system (ILS) that uses contextual information from human activities (identified with data provided from the environmental sound) can achieve an estimation that is 95% correct. [ABSTRACT FROM AUTHOR]

Estimation of indoor location represents an interesting research topic since it is a main contextual variable for location bases services (LBS), eHealth applications and commercial systems, among others. For instance, hospitals require location data of their employees, as well as the location of their patients to offer services based on these locations at the correct moments of their needs. Several approaches have been proposed to tackle this problem using different types of artificial or natural signals (i.e., wifi, bluetooth, rfid, sound, movement, etc.). In this work, it is proposed the development of an indoor location estimator system, relying in the data provided by the magnetic field of the rooms, which has been demonstrated that is unique and quasi-stationary. For this purpose, it is analyzed the spectral evolution of the magnetic field data viewed as a bidimensional heatmap, avoiding temporal dependencies. A Fourier transform is applied to the bidimensional heatmap of the magnetic field data to feed a convolutional neural network (CNN) to generate a model to estimate the user's location in a building. The evaluation of the CNN model to deploy an indoor location system (ILS) is done through measuring the Receiver Operating Characteristic (ROC) curve to observe the behavior in terms of sensitivity and specificity. Our experiments achieve a 0.99 Area Under the Curve (AUC) in the training data-set and a 0.74 in a total blind data set. [ABSTRACT FROM AUTHOR]

Depression is a mental disorder characterized by recurrent sadness and loss of interest in the enjoyment of the positive aspects of life, in addition to fatigue, causing inability to perform daily activities, which leads to a loss of quality of life. To monitor depression (unipolar and bipolar patients), traditional methods rely on reports from patients; nevertheless, bias is commonly present in them. To overcome this problem, Ecological Momentary Assessment (EMA) reports have been widely used, which include data of the behavior, feelings and other types of activities recorded almost in real time through the use of portable devices and smartphones containing motion sensors. In this work a methodology was proposed to detect depressive subjects from control subjects based in the data of their motor activity, recorded by a wearable device, obtained from the "Depresjon" database. From the motor activity signals, the extraction of statistical features was carried out to subsequently feed a random forest classifier. Results show a sensitivity value of 0.867, referring that those subjects with presence of depression have a degree of 86.7% of being correctly classified, while the specificity shows a value of 0.919, referring that those subjects with absence of depression have a degree of 91.9% of being classified with a correct response, using the motor activity signal provided from the wearable device. Based on these results, it is concluded that the motor activity allows distinguishing between the two classes, providing a preliminary and automated tool to specialists for the diagnosis of depression. [ABSTRACT FROM AUTHOR]