RESUMO
Artificial intelligence techniques are now widely used in various agricultural applications, including the detection of devastating diseases such as late blight (Phytophthora infestans) and early blight (Alternaria solani) affecting potato (Solanum tuberorsum L.) crops. In this paper, we present a mobile application for detecting potato crop diseases based on deep neural networks. The images were taken from the PlantVillage dataset with a batch of 1000 images for each of the three identified classes (healthy, early blight-diseased, late blight-diseased). An exploratory analysis of the architectures used for early and late blight diagnosis in potatoes was performed, achieving an accuracy of 98.7%, with MobileNetv2. Based on the results obtained, an offline mobile application was developed, supported on devices with Android 4.1 or later, also featuring an information section on the 27 diseases affecting potato crops and a gallery of symptoms. For future work, segmentation techniques will be used to highlight the damaged region in the potato leaf by evaluating its extent and possibly identifying different types of diseases affecting the same plant.
RESUMO
The Andean weevil Premnotrypes vorax represents an important cause of damage to Colombian potato crops. Due to the impact of this plague on the economy of the country, we searched for new alternatives for its biological control, based on the entomopathogenic bacteria Bacillus thuringiensis. A total of 300 B. thuringiensis strains obtained from potato plantations infested with P. vorax were analyzed through crystal morphology, SDS-PAGE, PCR and bioassays. We used site- directed mutagenesis to modify the Cry3Aa protein. Most of the B. thuringiensis isolates had a bipyramidal crystal morphology. SDS-PAGE analyses had seven strains groups with σ-endotoxins from 35 to 135 kDa. The genes cry 2 and cry 1 were significantly more frequent in the P. vorax habitat (PCR analyses). Three mutant toxins, 1 (D354E), 2 (R345A, ∆Y350, ∆Y351), and 3 (Q482A, S484A, R485A), were analyzed to assess their activity against P. vorax larvae. Toxicity was low, or absent, against P. vorax for isolates, wild type cry 3Aa and cry 3Aa mutants. The genetic characterization of the collection provides opportunities for the selection of strains to be tested in bioassays against other insect pests of agricultural importance, and for designing Cry proteins with improved insecticidal toxicity. Rev. Biol. Trop. 57 (4): 1235-1243. Epub 2009 December 01.
El gorgojo andino Premnotrypes vorax es una causa importante de daño en los cultivos colombianos de este tubérculo. Debido al impacto que esta plaga tiene sobre la economía del país, nos interesamos en buscar alternativas nuevas para el control biológico de P. vorax, basadas en la bacteria entomopatógena Bacillus thuringiensis. Se recolectaron un total de 300 cepas de B. thuringiensis a partir de plantaciones de papa infestadas con P. vorax, las cuales fueron analizadas por medio de la morfología del cristal, SDS-PAGE, PCR y ensayos biológicos. La mayoría de los aislamientos de B. thuringiensis presentaron cristales bipiramidales. Los análisis de SDS-PAGE indicaron la presencia de siete grupos de cepas con σ- endotoxinas que variaban entre 35 a 135 kDa. Las pruebas con PCR demostraron que los genes cry 2 y cry 1 fueron significativamente más frecuentes en el medioambiente de P. vorax. Además, se utilizó la mutagénesis sitio-dirigida para modificar la proteína Cry3Aa. Se analizaron tres toxinas mutantes, 1 (D354E), 2 (R345A, ∆Y350, ∆Y351), y 3 (Q482A, S484A, R485A), para determinar su actividad contra larvas de P. vorax. Los ensayos de toxicidad señalaron escasa, o nula, actividad hacia P. vorax tanto para las cepas, la toxina Cry3Aa de referencia y las proteínas Cry3Aa mutantes. La caracterización genética de la colección puede proveer oportunidades para la selección de cepas que pueden evaluarse por medio de bioensayos contra otros insectos-plaga de importancia agrícola, y para el diseño de proteínas Cry con actividad toxica mejorada.