Resumen La corrosión es un problema recurrente en la industria del gas natural, debido a la presencia de gases corrosivos como el CO2 y el H2S que en presencia de agua pueden atacar el acero y producir daños y fugas que generen accidentes y contaminación, es por ello que la predicción de la tendencia del gas natural hacia la corrosión es fundamental para desarrollar estrategias de inhibición y mitigación de este proceso. El objetivo del estudio fue desarrollar una Red Neuronal Artificial (RNA) entrenada con datos de composición de muestras de gas natural para predecir la tendencia corrosiva, como método alternativo que pueda ser utilizado como una herramienta predictiva eficiente. La RNA se entrenó con una muestra de 46 gases naturales y 11 componentes por cada una, además de la presión y la temperatura como condiciones operacionales, lo que representa un total de 598 datos de entrenamiento de la RNA, además se utilizaron 8 muestras adicionales para la validación externa del modelo. La RNA que desarrolló fue dentro de los principios de la estadística Bayesiana, con una arquitectura de Perceptrón Multicapa. Se obtuvo que la RNA es capaz de clasificar correctamente el 95,65% de la tendencia corrosiva de las muestras, siendo aquellas con tendencia no corrosiva las que presentaron el menor porcentaje de predicción (75%). La predicción de las muestras externas siguió la tendencia esperada, con menor capacidad para clasificar a las no corrosivas, y las muestras con posible corrosión y corrosivas fueron predichas en 80%. Se concluye que la RNA es una herramienta eficiente para la predicción de la tendencia corrosiva del gas natural en presencia de CO2 y su efectividad depende de que se utilicen muestras con todos los componentes necesarios para entrenar la misma, además puede ser mejorada al introducir otros parámetros como la cantidad de agua presente.

Abstract Corrosion is a recurrent problem in the natural gas industry, due to the presence of corrosive gases such as CO2 and H2S that in the presence of water can attack steel and produce damages and leaks that generate accidents and contamination, that is why the prediction of the tendency of natural gas towards corrosion is essential to develop strategies to inhibit and mitigate this process. The objective of the study was to develop an Artificial Neural Network (ANN) trained with composition data of natural gas samples to predict the corrosive tendency, as an alternative method that can be used as an efficient predictive tool. The ANN was trained with a sample of 46 natural gases and 11 components for each one, in addition to pressure and temperature as operational conditions, representing a total of 598 training data of the ANN, also 8 additional samples were used for external validation of the model. The ANN that developed was within the principles of Bayesian statistics, with a Multilayer Perceptron architecture. It was obtained that the ANN is able to correctly classify 95.65% of the corrosive tendency of the samples, being those with non-corrosive tendency the ones that presented the lowest prediction percentage (75%). The prediction of the external samples followed the expected trend, with lower capacity to classify the non-corrosive ones, and the samples with possible corrosion and corrosive were predicted in 80%. It is concluded that ANN is an efficient tool for predicting the corrosive tendency of natural gas in the presence of CO2 and its effectiveness depends on using samples with all the necessary components to train it, and it can be improved by introducing other parameters such as the amount of water present.

ABSTRACT The purpose of this research is to propose a model for the design of work environments in the SMEs Bogotá Metropolitan Area, taking as a guide the methodology of Kansei Engineering, with the support of instruments such as the survey and the semantic differential test, the neural networks (multilayer perceptron) for its validation. A questionnaire is elaborated with the support of experts, and a pilot test is carried out to improve and evaluate the relevance of the questions. Using the SPSS Software, the statistical analysis was performed, applying the normality tests, performing Spearman correlations, principal component analysis, and linear regression to the resulting equations to understand the relationships between the studied perceptions and the work environment in general. Subsequently the multilayer perceptron was used as a neural network model to validate the relationships between the proposed variables and perceptions, allowing at the same time to determine the importance of the emotional dimensions in the design of work environments, from which it was possible to conclude that the application of Kansei Engineering for the design of work environments is possible.

RESUMEN El propósito de esta investigación es proponer un modelo para el diseño de ambientes laborales en las Pymes Bogotá Área - Metropolitana tomando como guía la metodología de la Ingeniera Kansei, con el apoyo de instrumentos como la encuesta y la prueba de diferencial semántico, las redes neuronales (perceptrón multicapa) para su validación. Se elabora un cuestionario con cuestionario con el apoyo de expertos, al que se le realiza una prueba piloto para mejorar y evaluar la pertinencia de las preguntas. Haciendo uso del Software SPSS se realizó el análisis estadístico, aplicando las pruebas de normalidad, realizando correlaciones de Spearman, análisis de componentes principales, regresión lineal a las ecuaciones resultantes para entender las relaciones entre las percepciones estudiadas y el ambiente laboral en general. Posteriormente, hizo uso del perceptrón multicapa como modelo de redes neuronales para validar las relaciones entre las variables y percepciones propuestas permitiendo a su vez determinar la importancia de las dimensiones emocionales en el diseño de ambientes laborales, a partir de lo cual se pudo concluir que es posible la aplicación de la Ingeniería Kansei para el diseño de ambientes laborales.

RESUMO O objetivo desta pesquisa é propor um modelo para o projeto de ambientes de trabalho em PMEs da Região Metropolitana de Bogotá, usando a metodologia da Engenharia Kansei como guia, com o apoio de instrumentos como a pesquisa e o teste de diferencial semântico, e redes neurais (perceptron multicamadas) para validação. É elaborado um questionário com o apoio de especialistas, que é testado como piloto para melhorar e avaliar a relevância das perguntas. A análise estatística foi realizada com o software SPSS, aplicando testes de normalidade, correlações de Spearman, análise de componentes principais e regressão linear às equações resultantes para entender as relações entre as percepções estudadas e o ambiente de trabalho em geral. Posteriormente, utilizou-se o perceptron de múltiplas camadas como modelo de rede neural para validar as relações entre as variáveis e as percepções propostas, permitindo, por sua vez, determinar a importância das dimensões emocionais no projeto de ambientes de trabalho, a partir do qual foi possível concluir que é possível aplicar a Engenharia Kansei ao projeto de ambientes de trabalho.

SUMMARY: The determination of sex differences in anatomical structures is critical in establishing gold standard morphometric data in basic medical sciences, and in surgical and internal sciences in selecting the right area during invasive intervention and applying the correct intervention methodology appropriate to the area. The aim of this study is to determine the sex difference using Machine learning (ML) algorithms and Artificial neural networks (ANN) with parameters obtained from basilar artery. The study was performed on computed tomography angiography images of 63 women and 94 men. The following parameters were measured on the images: initial width of the right vertebral artery, initial width of the left vertebral artery, termination width of the right vertebral artery, termination width of the left vertebral artery, basilar artery width, and basilar artery length. The measurements were used in ML algorithms and ANN input to determine sex differences. As a result of the study, a sex difference rate of 0.84 was determined with the ML algorithms Random Forest (RF), Quadratic Discriminant Analysis (QDA), Extra Tree Classifier (ETC) and 0.84 with the Multilayer Perceptron Classifier (MLCP) algorithm of ANN. As a result of the study, sex difference was found with an accuracy rate of 0.84 using ML algorithms and ANN with parameters obtained from basilar artery. In this context, we think that this study will shed light on basic and clinical medical sciences.

RESUMEN: La determinación de las diferencias de sexo en las estructuras anatómicas es fundamental para establecer datos morfométricos de gold estándar, en las ciencias médicas básicas y en las ciencias quirúrgicas e internas para seleccionar el área correcta durante la intervención invasiva y aplicar la metodología de intervención correcta y apropiada. El objetivo de este estudio fue determinar la diferencia de sexo utilizando algoritmos de aprendizaje automático (ML) y redes neuronales artificiales (ANN) con parámetros obtenidos de la arteria basilar. El estudio se realizó sobre imágenes de angiografía por tomografía computarizada de 63 mujeres y 94 hombres. Se midieron en las imágenes los siguientes parámetros: ancho inicial de la arteria vertebral derecha, ancho inicial de la arteria vertebral izquierda, ancho de terminación de la arteria vertebral derecha, ancho de terminación de la arteria vertebral izquierda, ancho de la arteria basilar y longitud de la arteria basilar. Las mediciones se utilizaron en algoritmos de ML y entradas de ANN para determinar las diferencias de sexo. Como resultado del estudio, se determinó una tasa de diferencia de sexo de 0,84 con los algoritmos ML Random Forest (RF), Análisis Discriminante Cuadrático (QDA), Extra Tree Classifier (ETC) y 0,84 con el algoritmo Multilayer Perceptron Classifier (MLCP) de ANA. Como resultado del estudio, se encontró una diferencia de sexo con una tasa de precisión de 0,84 utilizando algoritmos ML y ANN con parámetros obtenidos de la arteria basilar. En este contexto, pensamos que este estudio será de utilidad en las ciencias médicas básicas y clínicas.

ABSTRACT Rainfall forecasts are of great importance to prevent disasters, economic losses in crops and several important aspects for the country's hydroeconomy, hence the need to develop rainfall prediction models. At the Villa Clara Provincial Meteorological Center (CMPVC), mathematical models with a high level of accuracy are used, but they require a lot of processing time. Hence, the need to look for more current and accurate, ways to make accurate rainfall forecasts but in a faster way. The progress of artificial intelligence and especially artificial neural networks have allowed the development of models to solve the problem of rainfall prediction; using the metrics provided by the World Meteorological Organization (WMO) from 1975 to 2016. In this work, an analysis of the different regression models with multiple outputs to predict rainfall is carry out in the months of May, June, July and August. The regression models that best fit this problem were linear regression, regression tree, k-nearest neighbors, direct regression, chained regression and multilayer perceptron. After running the models, the multilayer perceptron was the regression model with the best results, with a high degree of efficiency for rainfall forecasting.

RESUMEN Los pronósticos de las precipitaciones tienen gran importancia para prevenir desastres, pérdidas económicas en cultivos y varios aspectos importantes para la hidroeconomía del país, de ahí la necesidad de desarrollar modelos de predicción de precipitaciones. En el Centro Meteorológico Provincial de Villa Clara (CMPVC) se emplean modelos matemáticos con un nivel de precisión alto, pero requieren mucho tiempo de procesamiento. De ahí la necesidad de buscar maneras más actuales y precisas para realizar pronósticos de lluvia acertados, pero de manera más rápida. El progreso de la inteligencia artificial y en especial, las redes neuronales artificiales han permitido desarrollar modelos para dar solución al problema de predicción de precipitaciones; mediante las métricas proporcionadas por la Organización Meteorológica Mundial (OMM) comprendidas entre los años 1975 hasta el 2016. En este trabajo se realiza un análisis de los diferentes modelos de regresión con múltiples salidas para predecir las precipitaciones en los meses mayo, junio, julio y agosto. Los modelos de regresión que más se ajustaron a esta problemática fueron la regresión lineal, el árbol de regresión, el k-vecinos más cercanos, la regresión directa, la regresión encadenada y el perceptrón multicapa. Luego de realizar las corridas de los modelos resultó el perceptrón multicapa, el modelo de regresión con mejores resultados, con un alto grado de eficacia para el pronóstico de las precipitaciones.

Resumen En la exploración geofísica, el análisis del terreno es fundamental para planificar la adquisición de datos de gravimetría y magnetometría. No obstante, en la actualidad dichos análisis requieren el uso supervisado de información secundaria extensa. Por este motivo, en este estudio se propone una metodología que utiliza el aprendizaje profundo para evaluar el impacto de la cobertura vegetal y la topografía en la adquisición geofísica. Se usó una red neuronal artificial perceptrón multicapa para considerar cinco variables terrestres, y una red neural convolucional para la clasificación automatizada de coberturas vegetales sobre imágenes satelitales. A partir de esto, se obtuvieron puntos para la localización de estaciones de levantamiento geofísico que cumplen con un criterio de favorabilidad por accesibilidad, distancias, restricciones por cuerpos de agua y coberturas boscosas. La geometría obtenida se evaluó en la exploración del Granito de Durania en Colombia, y los resultados se analizaron utilizando transectas de adquisición y modelado computacional de anomalías magnéticas y de gravedad. Finalmente, se aplicaron técnicas de interpolación donde el método Ponderación de Distancia Inversa (IDW) mostró la mejor imagen para interpretar la delimitación del cuerpo intrusivo.

Abstract In geophysical exploration, terrain analysis is fundamental for planning the gravity and magnetic surveys. However, current analyses necessitate supervised use of extensive secondary information. Consequently, this study proposes a methodology that leverages deep learning to assess the impact of vegetation coverage and topography in geophysical acquisition. An artificial neural network multilayer perceptron was used to consider five terrain-related variables, while a convolutional neural network is used for automated classification of vegetation cover on satellite imagery. From this, geophysical acquisition points are obtained, adhering to criteria involving accessibility favourability, distances, restrictions imposed by bodies of water, and forested cover. The obtained geometry was tested in the exploration of the Granito de Durania in Colombia, and the results were analysed using acquisition transects and computational modelling of gravity and magnetic anomalies. Interpolation techniques were applied, with the Inverse Distance Weighting (IDW) method yielding the most informative map for interpreting the delineation of the intrusive body.

Abstract: The focus of this work is to analyze the implications of pre-training tasks in the development of language models for learning linguistic representations. In particular, we study three pre-trained BERT models and their corresponding unsupervised training tasks (e.g., MLM, Distillation, etc.). To consider similarities and differences, we fine-tune these language representation models on the classification task of four different categories of short answer responses. This fine-tuning process is implemented with two different neural architectures: with just one additional output layer and with a multilayer perceptron. In this way, we enrich the comparison of the pre-trained BERT models from three perspectives: the pre-training tasks in the development of language models, the fine-tuning process with different neural architectures, and the computational cost demanded on the classification of short answer responses.

Resumen La inteligencia artificial ha permitido desarrollar herramientas para el reconocimiento automático de frutos y hortalizas con mayor precisión y rapidez. El desarrollo de nuevos genotipos de árboles frutales requiere del uso de herramientas tecnológicas para la identificación de variedades con mayor robustez que los métodos convencionales. En esta investigación se aplicaron algoritmos de aprendizaje automático para identificar seis variedades de durazno (Prunus persica L.) CP-03-06, Oro Azteca, Oro San Juan, Cardenal, Colegio y Robin a partir de imágenes digitales de hojas. Los modelos máquina de soporte vectorial (SVM), bosque aleatorio (RF) y perceptrón multicapa (MLP) se entrenaron y evaluaron con base en tres descriptores cromáticos y 14 morfológicos extraídos de imágenes digitales. La evaluación del desempeño en predicción de los modelos se realizó con base en métricas globales y específicas para cada clase objetivo (variedad de durazno). Los cinco descriptores más importantes para identificar las variedades de durazno fueron los tres canales de color HSV (hue, saturation, value), la redondez y la excentricidad de las hojas. SVM obtuvo la mayor precisión global de clasificación con Acc de 98.7 % y F1macro de 98 %. SVM obtuvo el mayor puntaje F1 (99.2 %) para identificar la variedad de durazno CP-03-06 y el menor puntaje F1 (96.1 %) para identificar la variedad Cardenal. La utilización conjunta de descriptores cromáticos y morfológicos mejoró el desempeño de los algoritmos de aprendizaje para identificar las seis variedades de durazno. Los modelos SVM, RF y MLP obtuvieron un Acc de 98.7, 98.6 y 97 %, respectivamente. Este estudio muestra el potencial de las técnicas de aprendizaje automático para su aplicación en el reconocimiento de descriptores de interés en cultivos agrícolas y su aplicación a procesos automatizados en la agricultura.

Summary Artificial intelligence has allowed the development of tools for automatic recognition of fruits and vegetables with greater precision and speed. The development of new genotypes of fruit trees requires the use of technological tools to identify varieties with greater robustness than conventional methods. In this research, machine learning algorithms were applied to identify six peach varieties (Prunus persica L.) CP-03-06, Oro Azteca, Oro San Juan, Cardenal, Colegio and Robin from digital leaf images. The support vector machine (SVM), random forest (RF) and multilayer perceptron (MLP) models were trained and evaluated based on three chromatic and 14 morphological descriptors extracted from digital images. The evaluation of the prediction performance of the models was based on global metrics and specific for each target class (peach variety). The five most important descriptors to identify peach varieties were three HSV color channels (hue, saturation, value), roundness and eccentricity of the leaves. SVM achieved the highest overall classification accuracy with Acc of 98.7 % and F1macro of 98 %. SVM obtained the highest F1 score (99.2 %) to identify the peach variety CP-03-06 and the lowest F1 score (96.1 %) to identify the Cardenal variety. The joint use of chromatic and morphological descriptors improved the performance of learning algorithms to identify the six peach varieties. The SVM, RF and MLP models obtained an Acc of 98.7, 98.6 and 97 %, respectively. This study shows the potential of machine learning methods for their application in recognizing descriptors of interest in agricultural crops and their application to automated processes in agriculture.

ABSTRACT. Variable height is commonly used as an input attribute to estimate other variables. Thus, to ensure less susceptibility to errors, it is necessary to obtain the variable height correctly. In addition to DBH, hypsometric relationships are influenced by several factors, such as site, age, genetic variation, and silvicultural practices. The inclusion of these factors in hypsometric models can lead to a gain in the quality of the estimates and in the biological realism. The objective of this study was to propose and evaluate the performance of a model extracted from artificial neural network training and of new models to estimate the total height of eucalyptus trees. The data used in this study originated from temporary forest inventories conducted in eucalyptus stands in Minas Gerais, Brazil. A multilayer perceptron artificial neural network was trained, and a nonlinear equation was extracted from the best-performing network to predict the total heights of trees. New linear and nonlinear hypsometric models were constructed and fit considering variables related to individual trees (DBH) and stands (plot basal area, age and site index). The new hypsometric models proposed in this study showed satisfactory performance and are effective for estimating the total heights of eucalyptus trees, particularly the model extracted from the artificial neural network and the nonlinear model. ABSTRACT Thus errors correctly DBH variation practices realism Gerais Brazil trained bestperforming best performing (DBH plot area index. index . index)

ABSTRACT Careful implementation of a filtration system is essential for maintaining the operation of an irrigation system. Failure to maintain a filtration system can have a negative eff ect on irrigation pressure and uniformity. To avoid this problem, it is important to clean the filters, which can be done either manually or automatically. Predicting the correct time to clean the filters helps maintain the pressure and efficiency of the system. The aim of this study was to model backwash pressure as a function of water quality and the filter inlet pressure load using artificial neural networks. The characteristics of the water were determined using sensors to measure the pH (hydrogen potential), turbidity, total dissolved solids (TDS), and temperature. A pressure transducer was used to quantify the drop in pressure and the need to clean the filters. To predict the need for cleaning the irrigation filters, a hydraulic structure was constructed that included a screen filtration system with a mesh size of 120, cleaned by backwashing. The need for cleaning estimated by the multilayer perceptron feedforward artificial neural networks with 2-4-1 architecture performed well in modelling the temporal evolution of the pressure load in the screen filtration system (120 mesh), whereas adjusting the pressure load based on the water quality characteristics (pH, turbidity, total dissolved solids and temperature) performed poorly. uniformity problem automatically hydrogen potential, potential , potential) turbidity TDS, TDS (TDS) temperature 120 backwashing 241 2 4 1 2-4- (12 mesh, mesh) pH, (pH poorly (TDS 12 24 2-4 (1 2- (

Abstract In this paper, the application of AI and machine learning (ML) to the study of wireless propagation channels is investigated in two parts: first, an artificial neural network model is used to improve path loss prediction, and then, a pattern recognition model using multilayer perceptron (MLP) networks is used to identify and remove impulsive noise in power delay profiles (PDP). These studies were conducted based on field measurements in the 2400 MHz band in a public square with vegetation. The results are analyzed and compared with ordinary least squares (OLS) nonlinear regression results and results from similar studies. The Root Mean Square Error (RMSE) values between the experimental results of mean path loss and those provided by each propagation model are presented. The adjustment performed by OLS nonlinear regression and ANN significantly reduced the RMSE. The best results are those presented by artificial neural networks, with RMSE of 0.39 when using four neurons in the hidden layer of the ANN. The ANN used to identify and remove impulsive noise in power delay profiles (PDP) through pattern recognition proved to be more efficient than the CFAR technique. ANN technique found a larger number of valid multipaths compared to the CFAR technique. paper ML (ML parts first prediction then MLP (MLP PDP. PDP . 240 vegetation (OLS (RMSE 039 0 39 0.3 (PDP 24 03 3 0. 2

RESUMEN Objetivos: evaluar el rendimiento predictivo de diferentes algoritmos de inteligencia artificial para estimar el tiempo de ejecución del baño en cama en pacientes críticos. Métodos: estudio metodológico, que utilizó algoritmos de inteligencia artificial para predecir el tiempo de baño en cama en pacientes críticos. Se analizaron los resultados de modelos de regresión múltiple, redes neuronales perceptrón multicapa y función de base radial, árbol de decisión y random forest. Resultados: entre los modelos evaluados, el modelo de red neuronal con función de base radial, que contiene 13 neuronas en la capa oculta, presentó el mejor desempeño predictivo para estimar el tiempo de ejecución del baño en cama. En la validación de datos, la correlación al cuadrado entre los valores predichos y los valores originales fue del 62,3%. Conclusiones: el modelo de red neuronal con función de base radial mostró mejor rendimiento predictivo para estimar el tiempo de ejecución del baño en cama en pacientes críticos. Objetivos críticos Métodos metodológico múltiple forest Resultados evaluados 1 oculta datos 623 62 3 62,3% Conclusiones 6 62,3 62,

ABSTRACT Objectives: to assess the predictive performance of different artificial intelligence algorithms to estimate bed bath execution time in critically ill patients. Methods: a methodological study, which used artificial intelligence algorithms to predict bed bath time in critically ill patients. The results of multiple regression models, multilayer perceptron neural networks and radial basis function, decision tree and random forest were analyzed. Results: among the models assessed, the neural network model with a radial basis function, containing 13 neurons in the hidden layer, presented the best predictive performance to estimate the bed bath execution time. In data validation, the squared correlation between the predicted values and the original values was 62.3%. Conclusions: the neural network model with radial basis function showed better predictive performance to estimate bed bath execution time in critically ill patients. Objectives patients Methods study analyzed Results assessed 1 layer validation 623 62 3 62.3% Conclusions 6 62.3 62.

RESUMO Objetivos: avaliar a performance preditiva de diferentes algoritmos de inteligência artificial para estimar o tempo de execução do banho no leito em pacientes críticos. Métodos: estudo metodológico, que utilizou algoritmos de inteligência artificial para predizer o tempo de banho no leito em pacientes críticos. Foram analisados os resultados dos modelos de regressão múltipla, redes neurais perceptron multicamadas e função de base radial, árvore de decisão e random forest. Resultados: entre os modelos avaliados, o modelo de rede neural com função de base radial, contendo 13 neurônios na camada oculta, apresentou melhor performance preditiva para estimar o tempo de execução do banho no leito. Na validação dos dados, o quadrado da correlação entre os valores preditos e os valores originais foi de 62,3%. Conclusões: o modelo de rede neural com função de base radial apresentou melhor performance preditiva para estimar o tempo de execução do banho no leito em pacientes críticos. Objetivos críticos Métodos metodológico múltipla forest Resultados avaliados 1 oculta dados 623 62 3 62,3% Conclusões 6 62,3 62,

Abstract This study utilizes Fourier transform infrared (FTIR) data from honey samples to cluster and categorize them based on their spectral characteristics. The aim is to group similar samples together, revealing patterns and aiding in classification. The process begins by determining the number of clusters using the elbow method, resulting in five distinct clusters. Principal Component Analysis (PCA) is then applied to reduce the dataset’s dimensionality by capturing its significant variances. Hierarchical Cluster Analysis (HCA) further refines the sample clusters. 20% of the data, representing identified clusters, is randomly selected for testing, while the remainder serves as training data for a deep learning algorithm employing a multilayer perceptron (MLP). Following training, the test data are evaluated, revealing an impressive 96.15% accuracy. Accuracy measures the machine learning model’s ability to predict class labels for new data accurately. This approach offers reliable honey sample clustering without necessitating extensive preprocessing. Moreover, its swiftness and cost-effectiveness enhance its practicality. Ultimately, by leveraging FTIR spectral data, this method successfully identifies similarities among honey samples, enabling efficient categorization and demonstrating promise in the field of spectral analysis in food science. (FTIR characteristics together classification PCA (PCA datasets dataset s variances HCA (HCA 20 testing MLP. MLP . (MLP) evaluated 9615 96 15 96.15 accuracy models model accurately preprocessing Moreover costeffectiveness cost effectiveness practicality Ultimately science 2 (MLP 961 9 1 96.1 96.

Abstract Research around the world has focused on developing ways to predict hydraulic parameters in water distribution systems. The application of these forecasts can contribute to the decision-making of water distribution systems managers, aiming to ensure that the demand is met, and even to reduce water losses. The present work sought, among two data prediction models (ARIMA and Multi-Layer Perceptron Artificial Neural Networks), to assess which one can perform best predictions of pressure and discharge rate data. To reach the stipulated goal, real data were obtained from a water supply network provided by NUMMARH - Nucleus of Modeling and Simulation in Environment and Water Resources and Systems of the Federal University of Itajubá, Brazil. These data initially underwent an adjustment so that it was possible to develop a computer program. The results showed that the best prediction model for the data in question was ARIMA, presenting a mean absolute percentage error (MAPE) of 8.54%. Thus, it is concluded that ARIMA models are easy to build and apply, being an advantageous tool to predict such hydraulic parameters. decisionmaking decision making managers met losses sought MultiLayer Multi Layer Networks, Networks , Networks) goal Itajubá Brazil program MAPE (MAPE 854 8 54 8.54% Thus apply 85 5 8.54 8.5 8.

Resumo Pesquisas ao redor do mundo vem se concentrando em desenvolver maneiras de prever parâmetros hidráulicos em sistemas de distribuição de água. A aplicação destas previsões pode contribuir para a tomada de decisão dos gestores dos sistemas de distribuição de água, visando a garantia do atendimento da demanda, e até mesmo a redução de perdas de água. O presente trabalho buscou, dentre os modelos ARIMA e Redes Neurais Artificiais do tipo “Perceptron” de múltiplas camadas, identificar qual é capaz de realizar a melhor previsão de dados de pressão e vazão. Primeiro foram obtidos dados reais de uma rede de abastecimento de água em região de topografia irregular, que foram coletados pelo grupo de pesquisa NUMMARH - Núcleo de Modelagem e Simulação em Meio Ambiente e Recursos e Sistemas Hídricos, e fornecidos para execução deste trabalho. Os resultados mostraram que o melhor modelo de previsão para os dados em questão foi o ARIMA, apresentando erro médio percentual absoluto (MAPE) de 8,54%. Como conclusão identificou-se que os modelos ARIMA são de fácil construção e aplicação, sendo assim uma vantagem para se prever tais parâmetros hidráulicos. demanda buscou Perceptron “Perceptron camadas vazão irregular Hídricos MAPE (MAPE 854 8 54 8,54% identificouse identificou 85 5 8,54 8,5 8,

ABSTRACT Wind energy is an important renewable source that has been considerably developed recently. In order to obtain successful 24-h lead-time wind power forecasts for operational and commercial uses, a combination of physical and statistical models is desirable. In this paper, a hybrid methodology that employs a numerical weather prediction model (Weather Research and Forecasting) and a neural network (NN) algorithm is proposed and assessed. The methodology is applied to a wind farm in northwestern Mexico, a region with high wind potential where complex geography adds large uncertainty to wind energy forecasts. The energy forecasts are then evaluated against actual on-site power generation over one year and compared with two reference models: decision trees (DT) and support vector regression (SVR). The proposed method exhibits a better performance with respect to the reference methods, showing an hourly normalized mean absolute percentage error of 6.97%, which represents 6 and 13 percentage points less error in wind power forecasts than with DT and SVR methods, respectively. Under strong synoptic forcing, the NN wind power forecast is not very accurate, and novel approaches such as hierarchical algorithms should be employed instead. Overall, the proposed model is capable of producing high-quality wind power forecasts for most weather conditions prevailing in this region and demonstrates a good performance with respect to similar models for medium-term wind power forecasts.

RESUMEN La energía eólica es una importante fuente de energía renovable que se ha desarrollado considerablemente en los últimos años. Con el fin de obtener pronósticos de energía eólica de alta precisión con 24 horas de anticipación para usos operativos y comerciales, se necesita una combinación de modelos físicos y estadísticos. En este artículo se propone y evalúa una metodología híbrida que emplea un modelo numérico (Weather Research and Forecasting) y un algoritmo de red neuronal (NN). La metodología se aplica a un parque eólico en el noroeste de México, una región con alto potencial eólico donde la compleja geografía agrega gran incertidumbre a los pronósticos de energía eólica. Los pronósticos de energía se evalúan usando la generación de energía real en el sitio de interés durante un año y se comparan con dos modelos de referencia: árboles de decisión (DT, por su sigla en inglés) y regresión de vectores de soporte (SVR). El método propuesto muestra un mejor desempeño respecto a los métodos de referencia, mostrando un error absoluto medio porcentual horario de 6.97%, lo que representa 6 y 13 puntos porcentuales menos de error en los pronósticos de energía eólica que con los métodos DT y SVR, respectivamente. El pronóstico de energía eólica NN no es muy preciso cuando tiene un fuerte forzamiento sinóptico, por lo que en su lugar deben emplearse enfoques novedosos como los algoritmos jerárquicos. En general, el modelo propuesto tiene la capacidad de producir pronósticos de energía eólica de alta calidad para la mayoría de las condiciones climáticas que prevalecen en esta región, y de- muestra un buen desempeño respecto a modelos similares para pronósticos de energía eólica a mediano plazo.

SUMMARY OBJECTIVE: The study used machine learning models to predict the clinical outcome with various attributes or when the models chose features based on their algorithms. METHODS: Patients who presented to an orthopedic outpatient department with joint swelling or myalgia were included in the study. A proforma collected clinical information on age, gender, uric acid, C-reactive protein, and complete blood count/liver function test/renal function test parameters. Machine learning decision models (Random Forest and Gradient Boosted) were evaluated with the selected features/attributes. To categorize input data into outputs of indications of joint discomfort, multilayer perceptron and radial basis function-neural networks were used. RESULTS: The random forest decision model outperformed with 97% accuracy and minimum errors to anticipate joint pain from input attributes. For predicted classifications, the multilayer perceptron fared better with an accuracy of 98% as compared to the radial basis function. Multilayer perceptron achieved the following normalized relevance: 100% (uric acid), 10.3% (creatinine), 9.8% (AST), 5.4% (lymphocytes), and 5% (C-reactive protein) for having joint pain. Uric acid has the highest normalized relevance for predicting joint pain. CONCLUSION: The earliest artificial intelligence-based detection of joint pain will aid in the prevention of more serious orthopedic complications. OBJECTIVE algorithms METHODS age gender Creactive C reactive protein countliver count liver testrenal renal parameters Random Boosted featuresattributes features/attributes discomfort functionneural neural RESULTS 97 classifications 98 100 , acid) 103 10 3 10.3 creatinine, creatinine (creatinine) 9 8 9.8 AST, AST (AST) 54 5 4 5.4 lymphocytes, lymphocytes (lymphocytes) CONCLUSION intelligencebased intelligence complications 1 10. (creatinine 9. (AST 5. (lymphocytes