Rodrigo García

Rodrigo García

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Rodrigo García has a total of 41 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Plantain Yield Dynamics in Colombia Through Unsupervised Learning: Comparing Time-Series Clustering and Yield-State Persistence Using Markov Chains

    by Rodrigo Garcia, Adrian Doria, Jessica Polo

    We analyze annual yield and harvested area of domestic-consumption plantain (Musa AAB; export plantain excluded) in 31 continental Colombian departments from 2007 to 2025 (589 records). Bivariate yield and log-area trajectories are grouped with Partitioning Around Medoids (PAM) under Dynamic Time Warping (DTW) and synchronous Euclidean distance, and discrete-time Markov chains describe transitions among pooled yield quartiles. A three-group production-scale partition, which separates Arauca and Meta as the highest-yielding pair, is stable across 37 year-removal perturbations under both distances (10th-percentile adjusted Rand index = 1.000), but departmental means alone reproduce it and unequal weighting of yield and area changes it; the four-group DTW solution fails the stability criteria. Of 556 annual transitions, 75.54% remain in the same yield state, above a within-department permutation null (55.06%), yet transitions differ across departments, so the pooled first-order chain is descriptive. In rolling-origin comparisons for 2020–2025, adding climate reduces pooled root mean squared error (RMSE) by 37.6–45.9% in tree ensembles without lagged yield, but coordinates alone give larger reductions, and repeating the previous year’s yield gives the lowest RMSE (0.734 t ha−1). The results describe productive heterogeneity and persistence without establishing climatic or causal effects.

  • Open Access

    Continual Learning for Precision Livestock Farming: Mitigating Catastrophic Forgetting in Edge-Deployed Behavioral Recognition

    by Rodrigo Garcia, Horderlin Robles

    Precision Livestock Farming (PLF) increasingly relies on edge-deployed sensors to monitor bovine behaviors, fostering improved welfare and management. However, behavioral data naturally expands over time and presents severe class imbalances due to animals’ predominantly sedentary routines. When continuous sequential updates are required without access to historical datasets, deep learning methods frequently succumb to catastrophic forgetting. This study introduces an ultra-lightweight (∼0.85 MB) Continual Learning (CL) architecture built upon a CNN-BiLSTM feature extractor, tailored to process multivariate Inertial Measurement Unit (IMU) streams. We exhaustively evaluated baseline Naïve Fine-Tuning against Elastic Weight Consolidation (EWC), Learning without Forgetting (LwF), and episodic Replay under three rigorous real-world paradigms: Class Incremental, Subject Incremental (domain shift), and Imbalanced Realistic scenarios. Our empirical findings expose the fragility of static paradigms: in Class Incremental expansions, Naïve Fine-Tuning collapsed to an Average Accuracy of 33.33%. Conversely, Experience Replay emerged as the most robust defense, achieving a statistically significant Average Accuracy of 74.64 ± 6.77% across multiple random seeds. Furthermore, LwF effectively mitigated structural variations across unseen animal domains (Subject Incremental) without requiring raw data buffers. Notably, under severe biological class imbalances (Imbalanced Cumulative), the architecture proved highly resilient, maintaining 98.46% Average Accuracy and retaining perfect minority class recall. This research validates the operational feasibility of deploying adaptive, privacy-preserving CL frameworks directly on low-power wearable devices for lifelong livestock monitoring.

  • Open Access

    Combining Fuzzy Cognitive Maps and Metaheuristic Algorithms to Predict Preeclampsia and Intrauterine Growth Restriction

    by María Paula García, Jesús David Díaz-Meza, Kenia Hoyos, Bethia Pacheco, Rodrigo García, William Hoyos

    Preeclampsia (PE) and intrauterine growth restriction (IUGR) are obstetric complications associated with placental dysfunction, which represent a public health problem due to high maternal and fetal morbidity and mortality. Early detection is crucial for timely interventions. Therefore, this study proposes the development of models based on fuzzy cognitive maps (FCM) optimized with metaheuristic algorithms (particle swarm optimization (PSO) and genetic algorithms (GA)) for the prediction of PE and IUGR. The results showed that FCM-PSO applied to the PE dataset achieved excellent performance (accuracy, precision, recall, and F1-Score = 1.0). The FCM-GA model excelled in predicting IUGR with an accuracy and F1-Score of 0.97. Our proposed models outperformed those reported in the literature to predict PE and IUGR. Analysis of the relationships between nodes allowed for the identification of influential variables such as sFlt-1, sFlt-1/PlGF, and uterine Doppler parameters, in accordance with the pathophysiology of placental disorders. FCM optimized with PSO and GA offer a viable clinical alternative as a medical decision support system due to their ability to explore nonlinear relationships and interpretability of variables. In addition, they are suitable for scenarios where low computational resource consumption is required.

  • Open Access

    PRECISION AGRICULTURE FOR GRAZING AND ANIMAL HEALTH MANAGEMENT: A CASE STUDY IN COLOMBIA

    by Rodrigo Garcia

    In this research, we focus on addressing fattening management and animal health in rotational grazing within the framework of precision farming. Our approach leverages advanced technologies like Industry 4.0 and artificial intelligence to optimize agricultural and livestock processes. Our objective was to develop methodologies, models, and approaches supporting decision-making in productivity management and animal health. We pursued sub-objectives including developing a precision livestock farming architecture, creating knowledge models for animal health and herding management, and crafting meta-intelligent models for autonomous grazing and animal health management. Through a series of research articles, we achieved significant milestones. These include autonomous data analysis cycles for beef production, weight identification models using machine learning systems for monitoring cattle fattening using fuzzy classification, and multi-objective optimization models for maximizing weight gain in rotational grazing. We also introduced autonomous data analysis for self-supervision of animal fattening, management systems for cattle fattening, and the use of meta-learning in cattle weight identification for anomaly detection. Our methodologies and models demonstrated strong decision-making capabilities in managing livestock production processes, particularly in fattening and animal health management in rotational grazing, encompassing monitoring, diagnosis, and process optimization.

  • Open Access

    A Self-Configurable IoT-Based Monitoring Approach for Environmental Variables in Rotational Grazing Systems

    by Rodrigo Garcia, Mario Macea, Samir Castaño, Pedro Guevara

    Shaded resting zones in rotational grazing systems are prone to thermal stress due to limited ventilation and the congregation of animals during peak heat periods. Addressing these challenges requires sensing solutions that are not only accurate but also capable of adapting to dynamic environmental conditions and energy constraints. In this context, we present the development and simulation-based validation of a self-configurable IoT protocol for adaptive environmental monitoring. The approach integrates embedded machine learning, specifically a Random Forest classifier, to detect critical conditions using synthetic data of temperature, humidity, and CO2. The model achieved an accuracy of 98%, with a precision of 98%, recall of 85%, and F1-score of 91% in identifying critical states. These results demonstrate the feasibility of embedding adaptive intelligence into IoT-based monitoring solutions. The protocol is conceived as a foundation for integration into physical devices and subsequent evaluation in farm environments such as rotational grazing systems.


  • Open Access

    Desarrollo de un modelo de detección de maleza en potreros de fincas productoras de carne bovina mediante la integración de tecnologías emergentes como drones, visión por computadora e inteligencia artificial

    by Rodrigo García, Yulieth Vanessa Jiménez Bertel

    La presencia de malezas en potreros ganaderos afecta la calidad del forraje y, por ende, la productividad de la carne bovina. En esta investigación se presenta una aplicación basada en tecnologías emergentes como drones, visión por computadora e inteligencia artificial, diseñada para estimar y detectar la presencia de malezas en tiempo real. El modelo, desarrollado con algoritmos de Machine Learning y entrenado con imágenes aéreas etiquetadas, permite identificar zonas afectadas con alta precisión. Esta herramienta busca optimizar el manejo de los potreros y apoyar al sector ganadero mediante un diagnóstico visual automatizado. El documento expone las fases de análisis, diseño, desarrollo y evaluación del sistema.

  • Open Access

    Distributed Adaptive Coding Optimization for IoT Using Fulcrum Code and Model-Agnostic Meta-Learning (MAML) in Ultra-Low Latency Environments

    by Yair Rivera Julio, A. Pinto, R. García, J. Aguilar, Nelson A. Pérez-García

    The exponential growth of the Internet of Things (IoT) has amplified the demand for energy-conscious, low-latency, and efficient data transmission techniques. This study proposes an adaptive distributed coding scheme combining Fulcrum Code and Model-Agnostic Meta-Learning (MAML) to optimize IoT communications in ultralow-latency environments. Fulcrum Code improves packet resilience by adjusting redundancy to channel conditions, while MAML optimizes coding parameters in real-time to improve transmission efficiency. Forward Error Correction (FEC) and Hybrid Automatic Repeat Request (HARQ) further balance error correction and retransmission overhead. Simulations show significant reductions in transmission time and energy consumption, particularly in high-packet-loss scenarios. This approach ensures robust performance in resource-constrained IoT devices, preserving battery life while supporting critical applications such as smart cities, Industry 4.0, and the tactile Internet. By optimizing trade-offs between resilience and efficiency, this scheme advances scalable and energy-efficient communication for next-generation IoT systems.


  • Open Access

    Multistage Training of Fuzzy Cognitive Maps to Predict Preeclampsia and Fetal Growth Restriction

    by William Hoyos, Rodrigo García, Jose Aguilar

    Preeclampsia (PE) and fetal growth restriction (FGR) are pregancy complications related to placental dysfunction that pose significant challenges in terms of morbidity and mortality worldwide. Addressing these challenges involves early identification of the disease, which could reduce both the burden on healthcare systems and associated morbidity rates. In this study, we propose an innovative strategy using multistage training of fuzzy cognitive maps (FCM) to predict specific pregnancy disorders such as PE and FGR. The objective was to develop a predictive approach as a result of multistage training to simulate disease progression in a human individual. The models were rigorously evaluated for their predictive ability using datasets containing characteristics related to the mother, fetus, signs, symptoms, Doppler studies, and laboratory tests. The results conclusively reveal that multistage training better uncovers patterns in the data, leading to significantly improved predictive performance for these disorders. Convergence analysis demonstrated the stability of the FCM generated during the training stages. Also, the comparison with other machine learning models demonstrates that our approach is competitive to predict PE and FGR. The application of these models in healthcare settings holds promise as a valuable tool for the early detection of PE and FGR, contributing to the reduction of morbidity and mortality rates.


  • Open Access

    Emotion-Recognition System for Smart Environments Using Acoustic Information (ERSSE)

    by Gabriela Santiago, Jose Aguilar, Rodrigo García

    Acoustic management is very important for detecting possible events in the context of a smart environment (SE). In previous works, we proposed a reflective middleware for acoustic management (ReM-AM) and its autonomic cycles of data analysis tasks, along with its ontology-driven architecture. In this work, we aim to develop an emotion-recognition system for ReM-AM that uses sound events, rather than speech, as its main focus. The system is based on a sound pattern for emotion recognition and the autonomic cycle of intelligent sound analysis (ISA), defined by three tasks: variable extraction, sound data analysis, and emotion recommendation. We include a case study to test our emotion-recognition system in a simulation of a smart movie theater, with different situations taking place. The implementation and verification of the tasks show a promising performance in the case study, with 80% accuracy in sound recognition, and its general behavior shows that it can contribute to improving the well-being of the people present in the environment.