Conference Agenda

Summary - The migration of Hondurans to the United States is a complex phenomenon driven by economic, social, and security factors. This study analyzes the determinants of migratory intent using a sample of data from 7,616 households from the 2023 Permanent Survey of Multipurpose Households (EPHPM), integrated with the complementary migration and remittances module, selected from more than 42,000 valid records after applying inclusion criteria, such as the elimination of incomplete observations and the selection of households with migration projection to the United States. A logistic regression model was trained to evaluate the influence of sociodemographic variables, income levels, perception of insecurity, and family ties abroad. The SMOTE technique was applied to address the imbalance of the dependent variable. The results show that having relatives abroad is the strongest predictor (Odds Ratio ≈ 2.08), even surpassing perceived insecurity. Economic precariousness also increases the intention to migrate, but transnational links structure and facilitate mobility, reducing associated risks and costs. The study shows that the decision to migrate is multicausal, the result of the interaction between economic, social and family conditions, and provides relevant empirical inputs for the design of public policies aimed at addressing its structural causes and generating local opportunities.

This work presents a computational framework for generating swept surfaces (ruled, cylindrical, and sweep) based exclusively on curves NURBS, eliminating the reliance on explicit analytical parametric formulas. The proposal enables the construction of surfaces through direct transformations between generative curves and trajectories, introducing a 'scaled cylindrical' model to control cross-sectional expansion. This approach ensures precise local geometric control and a unified computational structure for computer-aided design.

Data-driven battery prognostics models are increasingly expected to be accurate, efficient, robust, and interpretable, yet existing benchmarks often report accuracy alone using random train/test splits that permit temporal leakage. This study presents a comprehensive multi-metric evaluation of liquid neural networks (LNNs) and neural circuit policies (NCPs) for capacity-based state-of-health prediction on the four-unit NASA Prognostics Center of Excellence (PCoE) lithium-ion battery dataset under a chronological splitting protocol designed to prevent future-cycle information leakage. On the shared raw-capacity benchmark, compact continuous-time architectures (under 10K parameters) obtain accuracy comparable to selected larger baselines with approximately 5-550x more parameters in the evaluated same-protocol and contextual comparisons; the main LNN-TS configuration trains 4-20x faster than conventional raw time-series baselines. An accuracy-robustness trade-off emerges across model families, with the most accurate models exhibiting 4.6-5.5% noise degradation and NCP sparsity providing a controllable trade-off between prediction quality and noise insensitivity. However, intrinsic uncertainty estimation through tau variability and hidden-state stability yields poorly calibrated confidence signals, identifying reliable self-assessment of prediction quality as an open challenge. Complementary interpretability experiments (confidence estimation, hidden-state trajectory analysis, phase-wise position importance, and counterfactual perturbation) suggest that LNNs learn representations correlated with physically plausible degradation behavior, while fixed-sparsity NCP experiments characterize accuracy-interpretability trade-offs without claiming learned causal pathways. Together, these results support compact continuous-time architectures as efficient and interpretable candidates for battery prognostics benchmarks that jointly evaluate accuracy, robustness, and model transparency.

Ammonia (NH3) refrigeration systems are critical infrastructures in the brewing industry, yet they pose significant safety risks due to the toxic nature of the refrigerant. Traditional monitoring systems, reliant on fixed-threshold alarms (typically set at 25 ppm), often fail to detect precursor anomalies in dynamic operational environments, leading to delayed responses and increased safety risk. This study proposes an early warning predictive framework leveraging Internet of Things (IoT) sensor fusion and Machine Learning (ML) algorithms. By integrating chemical concentration data with operational variables—such as discharge pressure, temperature, vibration, and compressor state—two models were developed and evaluated: Random Forest (RF) and Long Short-Term Memory (LSTM) networks. Results demonstrate that the LSTM model, optimized for temporal sequence analysis, achieved a Recall of 0.74 (vs 0.97 for RF) and an AUC of 0.999 (LSTM)vs 0.93 (RF), providing an average early warning lead time of 42 minutesbefore the safety threshold (25 ppm) is breached. Furthermore, explainability analysis using SHAP (SHapley Additive exPlanations) confirmed that pressure drops and thermal variability are key predictors of leakage events. This research bridges the gap between theoretical ML applications and real-world industrial safety.