Browsing by Keyword "Plant Science"
Now showing 1 - 3 of 3
Results Per Page
Sort Options
Item Analysis of Few-Shot Techniques for Fungal Plant Disease Classification and Evaluation of Clustering Capabilities Over Real Datasets(2022-03-07) Egusquiza, Itziar; Picon, Artzai; Irusta, Unai; Bereciartua-Perez, Arantza; Eggers, Till; Klukas, Christian; Aramendi, Elisabete; Navarra-Mestre, Ramon; COMPUTER_VISIONPlant fungal diseases are one of the most important causes of crop yield losses. Therefore, plant disease identification algorithms have been seen as a useful tool to detect them at early stages to mitigate their effects. Although deep-learning based algorithms can achieve high detection accuracies, they require large and manually annotated image datasets that is not always accessible, specially for rare and new diseases. This study focuses on the development of a plant disease detection algorithm and strategy requiring few plant images (Few-shot learning algorithm). We extend previous work by using a novel challenging dataset containing more than 100,000 images. This dataset includes images of leaves, panicles and stems of five different crops (barley, corn, rape seed, rice, and wheat) for a total of 17 different diseases, where each disease is shown at different disease stages. In this study, we propose a deep metric learning based method to extract latent space representations from plant diseases with just few images by means of a Siamese network and triplet loss function. This enhances previous methods that require a support dataset containing a high number of annotated images to perform metric learning and few-shot classification. The proposed method was compared over a traditional network that was trained with the cross-entropy loss function. Exhaustive experiments have been performed for validating and measuring the benefits of metric learning techniques over classical methods. Results show that the features extracted by the metric learning based approach present better discriminative and clustering properties. Davis-Bouldin index and Silhouette score values have shown that triplet loss network improves the clustering properties with respect to the categorical-cross entropy loss. Overall, triplet loss approach improves the DB index value by 22.7% and Silhouette score value by 166.7% compared to the categorical cross-entropy loss model. Moreover, the F-score parameter obtained from the Siamese network with the triplet loss performs better than classical approaches when there are few images for training, obtaining a 6% improvement in the F-score mean value. Siamese networks with triplet loss have improved the ability to learn different plant diseases using few images of each class. These networks based on metric learning techniques improve clustering and classification results over traditional categorical cross-entropy loss networks for plant disease identification.Item Candida albicans/Macrophage Biointerface on Human and Porcine Decellularized Adipose Matrices(2021-05-17) Cicuéndez, Mónica; Casarrubios, Laura; Feito, María José; Madarieta, Iratxe; Garcia-Urkia, Nerea; Murua, Olatz; Olalde, Beatriz; Briz, Nerea; Diez-Orejas, Rosalía; Portolés, María Teresa; Biomateriales; SGMacrophages, cells effective in sensing, internalizing and killing Candida albicans, are intertwined with the extracellular matrix (ECM) through different signals, which include the release of specific cytokines. Due to the importance of these interactions, the employment of in vitro models mimicking a fungal infection scenario is essential to evaluate the ECM effects on the macrophage response. In this work, we have analyzed the effects of human and porcine decellularized adipose matrices (DAMs), obtained by either enzymatic or organic solvent treatment, on the macrophage/Candida albicans interface. The present study has allowed us to detect differences on the activation of macrophages cultured on either human- or porcine-derived DAMs, evidencing changes in the macrophage actin cytoskeleton, such as distinct F-actin-rich membrane structures to surround the pathogen. The macrophage morphological changes observed on these four DAMs are key to understand the defense capability of these cells against this fungal pathogen. This work has contributed to the knowledge of the influence that the extracellular matrix and its components can exert on macrophage metabolism, immunocompetence and capacity to respond to the microenvironment in a possible infection scenario.Item Utilization of Volatile Fatty Acids from Microalgae for the Production of High Added Value Compounds(2017-10-15) Chalima, Angelina; Oliver, Laura; Fernández de Castro, Laura; Karnaouri, Anthi; Dietrich, Thomas; Topakas, Evangelos; Tecnalia Research & Innovation; Alimentación SostenibleVolatile Fatty Acids (VFA) are small organic compounds that have attracted much attention lately, due to their use as a carbon source for microorganisms involved in the production of bioactive compounds, biodegradable materials and energy. Low cost production of VFA from different types of waste streams can occur via dark fermentation, offering a promising approach for the production of biofuels and biochemicals with simultaneous reduction of waste volume. VFA can be subsequently utilized in fermentation processes and efficiently transformed into bioactive compounds that can be used in the food and nutraceutical industry for the development of functional foods with scientifically sustained claims. Microalgae are oleaginous microorganisms that are able to grow in heterotrophic cultures supported by VFA as a carbon source and accumulate high amounts of valuable products, such as omega-3 fatty acids and exopolysaccharides. This article reviews the different types of waste streams in concert with their potential to produce VFA, the possible factors that affect the VFA production process and the utilization of the resulting VFA in microalgae fermentation processes. The biology of VFA utilization, the potential products and the downstream processes are discussed in detail.