Darío Amaya Hurtado

Prediction of endocrine system affectation in fisher 344 rats by food intake exposed with malathion, applying naïve bayes classifier and genetic algorithms

Background: Reported cases of uncontrolled use of pesticides and its produced effects by direct or indirect exposition, represent a high risk for human health. Therefore, in this paper, it is shown the results of the development and execution of an algorithm that predicts the possible effects in endocrine system in Fisher 344 (F344) rats, occasioned by ingestion of malathion. Methods: It was referred to ToxRefDB database in which different case studies in F344 rats exposed to malathion were collected. The experimental data were processed using Naïve Bayes (NB) machine learning classifier, which was subsequently optimized using genetic algorithms (GAs). The model was executed in an application with a graphical user interface programmed in C#. Results: There was a tendency to suffer bigger alterations, increasing levels in the parathyroid gland in dosages between 4 and 5 mg/kg/day, in contrast to the thyroid gland for doses between 739 and 868 mg/kg/day. It was showed a greater resistance for females to contract effects on the endocrine system by the ingestion of malathion. Females were more susceptible to suffer alterations in the pituitary gland with exposure times between 3 and 6 months. Conclusions: The prediction model based on NB classifiers allowed to analyze all the possible combinations of the studied variables and improving its accuracy using GAs. Excepting the pituitary gland, females demonstrated better resistance to contract effects by increasing levels on the rest of endocrine system glands.

Prediction of Reproductive System Affectation in Sprague Dawley Rats by food Intake Exposed with Fenthion, using Naïve Bayes Classifier and Genetic Algorithms

Improper application of pesticides in agricultural crops and indirect effects caused by exposure to them through consumption of contaminated crops, nowadays represent a serious risk to public health harmony. It is vital then, to know the degree of toxicity of each of these chemicals in order to properly regulate its application and sensitize the population at risk. Therefore, this paper shows the results of an algorithm with the ability to predict the effects on the reproductive system in Sprague Dawley rats, caused by the intake of food exposed with Fenthion. The original data were processed using the Naïve Bayes classifier, then optimized using genetic algorithms. It is concluded that the prediction algorithm does the job properly, processing qualitative information with relatively low computational cost, which allows its easy portability to different development platforms.

Control architecture to reproducethe knee and ankle movement using a transfemoral prosthesis

The development of dynamical prosthesis can be considered as an effort of the bioengineering to substitute the functions of the member affected by an amputation. The performance of these devices is strictly related with its control system. In this way, this work aims proposinga control architecture for transfemoral prosthesis, based on the complementary limb motion estimation, considering the hypothesis about the symmetry of the human gait and the characteristic potentially predictive of itself. Thus, it is developed an analysis about the rotation of the articulation and its relation with the prosthesis. From of this, it is developed two level of control, that aims to determinate the movement and regulate the behavior of the actuator. This development provides a different perspective about solutions related to the control parameters of this kind of devices. Through of this work, it concludes about the existence of a relation between the behavior of the articulations during a normal gait cycle, and its applicability to solve the prosthesis problem control.

Monitoreo preliminar de incidencia de fisiopatías en cultivos de fresa usando procesamiento digital de imágenes

Processes executed for Identifying anomalies in agricultural crops using image processing have been effective, however these methods involve tear off plant’s leaflets and fruits under study. For this paper it is shown the results of the development and validation of an algorithm that allows the execution of incidence monitoring in strawberry crops (Fragaria x ananassa), able to make a first approximation to distinguish senescence and mechanical damage in their leaflets, implementing an indirect (non-destructive) methodology. Image processing techniques used for this research include smoothing, erosion, dilation, edge detection, pattern matching, thresholding, among others. The results were visualized in an application developed in C # using the Emgu CV library. It is concluded that is possible to offer a preliminary monitoring of incidence using this algorithm, saving time for producers and researchers who require a first approximation of the state of the crop, with the ability to run on desktops, notebooks and aerial robots (drones) that allow to automate this task^les^aLa identificacion de diferentes anomalias en cultivos agricolas usando procesamiento de imagenes, ha demostrado cada vez mas su efectividad, contrario con los metodos de ejecucion tradicionales, los cuales arrancan los foliolos y frutos de la planta, para realizar el estudio. En este trabajo se presentan los resultados del desarrollo e validacion de un algoritmo, que permita realizar monitoreo de incidencia en cultivos de fresa (Fragaria x ananassa), capaz de dar una primera aproximacion para distinguir senescencia y danos mecanicos en sus foliolos, implementando una metodologia indirecta (no destructiva). Las tecnicas de procesamiento de imagenes implementadas incluyen Suavizado, Erosion, Dilatacion, Deteccion de Contornos, Correspondencia de Patrones, Umbralizacion, entre otros. Los resultados obtenidos se visualizaron en una aplicacion desarrollada en C# usando la libreria Emgu CV, mostrando al usuario un diagnostico de la planta de estudio. Se concluye que es posible ofrecer un servicio de monitoreo preliminar de incidencia usando este algoritmo, ahorrando tiempo para productores e investigadores que requieran una primera aproximacion del estado del cultivo, con la posibilidad de ejecutarse tanto en computadores e robots aereos (drones) para hacer mas eficiente esta tarea.^len^aProcesses executed for identifying anomalies in agricultural crops using image processing have been effective, however these methods involve tear off plant’s leaflets and fruits under study. For this paper it is shown the results of the development and validation of an algorithm that allows the execution of incidence monitoring in strawberry crops (Fragaria x ananassa), able to make a first approximation to distinguish senescence and mechanical damage in their leaflets, implementing an indirect (non-destructive) methodology. Image processing techniques used for this research include smoothing, erosion, dilation, edge detection, pattern matching, thresholding, among others. The results were visualized in an application developed in C# using the Emgu CV library. It is concluded that is possible to offer a preliminary monitoring of incidence using this algorithm, saving time for producers and researchers who require a first approximation of the state of the crop, with the ability to run on desktops, notebooks and aerial robots (drons) that allow to automate this task.^lpt^aA identificacao das diferentes anomalias em cultivos agricolas utilizando processamento de imagens ha demonstrado cada vez mais sua efetividade. Contrario com os metodos tradicionais, que tiram as folhas e frutos da arvore para realizar o estudo. Neste trabalho se apresentam os resultados do desenvolvimento e validacao do algoritmo, que permite realizar monitoramentos da incidencia em cultivos de morango (Fragaria x ananassa), capaz de realizar uma primeira aproximacao para identificar senescencia e danos mecânicos em suas folias, desenvolvendo uma metodologia nao destrutiva. As tecnicas de processamento de imagens desenvolvidas, incluem suavizacao, erosao, dilatacao, deteccao de bordas, correspondencia de padroes, umbral (Thresholding), entre outros. Os resultados obtidos se visualizaram em uma aplicacao em C# utilizando a biblioteca Emgu CV, mostraram ao usuario um diagnostico da planta em estudo. Se conclui que e possivel oferecer um servico de monitoramento preliminar de incidencia, utilizando este algoritmo, poupando tempo para produtores e pesquisadores que precisem uma primeira aproximacao do estado de um cultivo, com a possibilidade de utilizar computadores e Drones para fazer mais eficiente esta tarefa.

Technologies and Applications Review of Subvocal Speech

This paper presents a review of the main applicative and methodological approaches that have been developed in recent years for sub-vocal speech or silent language. The sub-vocal speech can be defined as the identification and characterization of bioelectric signals that control the vocal tract, when is not produced sound production by the caller. The first section makes a deep review of methods for detecting silent language. In the second part are evaluated the technologies implemented in recent years, followed by a review of the main applications of this type of speech and finally present a broad comparison between jobs that have been developed in industry and academic applications.

Pruebas de estanqueidad en envases de tereftalato de polietileno basado en máquina de soporte vectorial

In this paper we present the results of implementing an algorithm based on Support Vector Machine (SVM) on the National Instruments platform Compaq Rio, abbreviated cRio for the detection of Polyethylene terephthalate (PET) containers leakage. To accomplish this, the acquisition and processing the differential pressure signal is performed and then using a decision model to determine whether the package leaks or not. There are many tools for digital signal processing, however in the SVM classification applications have proven to be a very good alternative. The SVM requires a training process, performed based on signals which are known class to which they belong. After this training, a classification is performed in a new bottle. The final algorithm is implemented on the cRio National Instruments system for online application.