Examinando por Autor "Galleguillos Silva, Renato Bruno"

Mostrando 1 - 2 de 2
  • Miniatura
    Ítem
    Feasibility of using ultrasound for drug delivery through micellar systems
    (Institute of Electrical and Electronics Engineers (IEEE), 2025-04-02) Marambio, E.; Velásquez, P.; Cepeda-Plaza, M.; Galleguillos Silva, Renato Bruno
    A study of micellar structures subjected to continuous high-intensity ultrasonic perturbation was carried out. The micelles were characterized by high-speed absorption spectrophotometry and the use of fluorophores, such as Rhodamine 123, as a spectroscopic indicator of the micellar kinetic process. It was found that above the critical micellar concentration, the absorbance peak of the fluorophore experiences a 14 nm red shift. Preliminary experiments indicate a reversal of this shift under certain ultrasonic conditions. In subsequent experiments, no effect of high intensity ultrasonic radiation on the micellar systems studied was observed. A dependence of the spectroscopic response of Rh123 on temperature is found, which can be confused with the effect of micelle breaking in solutions. The study presented considers the use of Quillaja Saponaria Molina and Triton X-100 as a surfactant, but it is extensible to other micellar systems.
  • Miniatura
    Ítem
    Limitations of transfer learning for chilean cherry tree health monitoring: when lab results do not translate to the orchard
    (MDPI, 2025-08-13) Hidalgo, Mauricio; Yanine, Fernando; Galleguillos Silva, Renato Bruno; Lagos, Miguel; Kumar Sahoo, Sarat; Paredes, Rodrigo
    Chile, which accounts for 27% of global cherry exports (USD 2.26 billion annually), faces a critical industry challenge in crop health monitoring. While automated sensors monitor environmental variables, phytosanitary diagnosis still relies on manual visual inspection, leading to detection errors and delays. Given this reality and the growing use of AI models in agriculture, our study quantifies the theory–practice gap through comparative evaluation of three transfer learning architectures (namely, VGG16, ResNet50, and EfficientNetB0) for automated disease identification in cherry leaves under both controlled and real-world orchard conditions. Our analysis reveals that excellent laboratory performance does not guarantee operational effectiveness: while two of the three models exceeded 97% controlled validation accuracy, their field performance degraded significantly, reaching only 52% in the best-case scenario (ResNet50). These findings identify a major risk in agricultural transfer learning applications: strong laboratory performance does not ensure real-world effectiveness, creating unwarranted confidence in model performance under real conditions that may compromise crop health management.