Politecnica Salesiana University

CONTEXT Digital technologies are promoted for export horticulture, but their value in rose systems depends on how they connect crop management, postharvest quality, traceability and market coordination, and adoption capacity differs across producers. OBJECTIVE This article develops a systems framework for prioritizing inclusive digital interventions in export rose production, using Ecuadorian floriculture as a strategic case: which interventions matter most, how adoption varies across farm sizes, and under which conditions they reach heterogeneous producers. METHODS A mixed-methods design combined a structured synthesis of 40 scientific sources in three evidence tiers (17 direct floriculture, 6 transferable protected-horticulture, 17 systems and inclusion) plus 11 sectoral documents, with a survey of greenhouse rose producers (n = 79), interviews with chain actors (n = 9) and an expert panel (n = 4). RESULTS AND CONCLUSIONS Four domains emerged: crop-health early warning, irrigation and fertigation, postharvest quality and traceability, and digital commercialization. Digital adoption increased with farm size (index 1.1 to 4.1; Spearman ρ = 0.59, p < 0.001), but unevenly: differences were steep for postharvest quality records (15 to 72%) and digital sales platforms (15 to 84%), absent for smart greenhouses and crop-health AI, and confined to the largest farms for irrigation AI. Implementation cost (57.6%) and limited technical knowledge (55.6%) outranked connectivity (29.3%), and 81% were unaware of any public policy supporting digitalization. SIGNIFICANCE Digital inequality is both producer-specific and domain-specific. Inclusive digitalization requires differentiated pathways, service-scale rather than farm-scale provision, local model validation and transparent data governance.

This study evaluated the activity concentrations of 226Ra in cassava pulp, peel, and derived starch cultivated in three production sectors of Chone, Ecuador, and assessed soil-to-plant transfer and associated dietary exposure. Results show pronounced sector-dependent variability in radionuclide distribution, with consistently lower 226Ra levels in starch relative to raw plant fractions. Estimated ingestion doses for both children and adults were negligible and well below international reference values. These findings provide the first multi-matrix baseline for 226Ra transfer in cassava under tropical Ecuadorian conditions and support site-specific radiological risk assessments.

Neural network quantization has become established as a key strategy for transitioning medical imaging models from research environments to clinical devices and resource-constrained edge platforms; however, the available evidence remains fragmented and focused on highly heterogeneous use cases. This study presents a systematic review of 72 studies on quantization applied to medical images, following PRISMA guidelines, with the aim of characterizing the relationship among quantization technique, network architecture, imaging modality, and execution environment, as well as their impact on latency, memory footprint, and clinical deployment. Based on a structured variable matrix, we analyze—through tailored visualizations—usage patterns of Post-Training Quantization (PTQ), Quantization-Aware Training (QAT), mixed precision, and binary/low-bit schemes across frameworks such as PyTorch V 2.6.0, TensorFlow 2.19.0, and TensorFlow Lite, executed on server-class GPUs, edge/embedded devices, and specialized hardware. The results reveal a strong concentration of evidence in PyTorch/TensorFlow pipelines using INT8 or mixed precision on GPUs and edge platforms, contrasted with limited attention to PACS/RIS interoperability, model lifecycle management, energy consumption, cost, and regulatory traceability. We conclude that, although quantization can approximate real-time performance and reduce memory footprint, its clinical adoption remains constrained by integration challenges, model governance requirements, and the maturity of the hardware–software ecosystem.

This study presents a measurement–modeling pathway for diagnosing corrosion-driven contact degradation in power equipment using infrared thermography and color-channel analysis. Thermal data were acquired with a Fluke Ti450 (LWIR, 7.5–14 μm) under typical high-altitude, temperate conditions in Quito, Ecuador. Radiometric parameters (emissivity, distance, ambient/reflected temperature, and humidity) are reported explicitly, and images are processed with a reproducible pipeline that combines adaptive thresholding, morphology, and region-of-interest statistics, including ΔT relative to a reference region. A worked example links an observed hotspot to emissivity-corrected temperature and discusses qualitative implications for the effective contact resistance Reff. Uncertainty is summarized through a per-case template that propagates uΔT to u(Reff) and Weibull characteristic life η. Environmental influences (solar load, wind, and emissivity variability) are acknowledged and mitigated. Two field cases illustrate the approach to substation assets. Because the dataset comprises single-visit inspections, formal parameter estimation (e.g., EIS-validated Reff and full Weibull/Arrhenius fits) is reserved for longitudinal follow-up. By making radiometry, processing steps, and limitations explicit, the study reduces ambiguity in the transition from temperature contrast to physics-based interpretation and supports auditable maintenance decisions.

Facial recognition systems have experienced rapid progress with the integration of deep learning architectures, especially convolutional neural networks (CNNs). Among the most prominent approaches, ArcFace and FaceNet are recognized for their high accuracy and robustness in identity verification tasks. However, their comparative performance under real-world, uncontrolled conditions where factors such as illumination, resolution, and occlusion vary remains insufficiently studied. This research presents a systematic comparison between ArcFace and FaceNet using the Analytic Hierarchy Process (AHP) as a decision-support framework. The study employs three publicly available datasets—Labeled Faces in the Wild (LFW), CASIA-WebFace, and Celeb-DF—to evaluate performance in terms of accuracy, precision, recall, F1-score, and equal error rate (EER). Controlled experiments simulate degraded conditions, including low resolution, poor lighting, and partial occlusion. Results reveal that ArcFace consistently outperforms FaceNet in accuracy and F1-score across challenging scenarios, while FaceNet achieves faster inference and a lower false positive rate in some instances. These insights offer practical guidance for selecting optimal models for security, forensic, and identity verification applications.