ResumenEn este trabajo se presentan los resultados obtenidos en el reconocimiento de plagas utilizando la visión de máquina por computador como elemento de diagnóstico. La captura de las imágenes se realizó por medio de un agente robótico aéreo (drone) equipado con una cámara, lo que permitió capturar las imágenes del estado de las hojas de un cultivo de la planta conocida como 'flor de azúcar' (Begonia semperflorens). Estas imágenes fueron procesadas utilizando técnicas de visión de máquina con el fin de identificar el posible ataque de plagas en el cultivo. Las técnicas utilizadas corresponden a filtros morfológicos, difuminado gaussiano y filtrado HSL. Como resultado principal de este trabajo se detectaron perforaciones de hojas ocasionadas por el ataque de plagas, específicamente babosas, caracoles, arañas rojas y minadoras.Palabras claves: Procesamiento de imágenes, detección de plagas, monitoreo de cultivos, filtros morfológicos, difuminado gaussiano.
AbstractNowadays, an important element in farming, is the use of technology, based on the analysis of the different factors that affect the succesfull development of the crops. The results are presented in the recognition of pests, in this work a computer machine vision, as a diagnostic was used. The images capturing were doing with a robotic air agent, equipped with a camera, capturing images of the state of a crop of a plant called 'Flor de azúcar' (Begonia semperflorens). These images are processed using machine vision techniques to identify the possible attack of pests on the crop. The techniques used are morphological filters, Gaussian blur filter and HSL. The main result of this work was accomplished, perform the detection of the perforation of the leaves as a result of pest attack, specifically slugs, snails, spider mites and leafminers.
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.
This paper compares the performance of three micro-controlled architectures in the implementation of a fuzzy controller, these correspond to a PIC18F2550, a MSP430G2452 and DSPIC30F4011. In order to establish which of them offers
Este trabajo presenta una revisión de estado de las principales temáticas aplicativas y metodológicas del habla sub-vocal que se han venido desarrollando en los últimos años. La primera sección hace una honda revisión de los métodos de detección del lenguaje silencioso. En la segunda parte se evalúan las tecnologías implementadas en los últimos años, seguido de un análisis en las principales aplicaciones de este tipo de lenguaje y finalmente presentado una amplia comparación entre los trabajos que se han hecho en industria y academia utilizando este tipo de desarrollos.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.