Publications

Interpretable Function Approximation with Gaussian Processes in Value-Based Model-Free Reinforcement Learning

Published in Proceedings of the 6th Northern Lights Deep Learning Conference (NLDL), 2025

This paper explores using Gaussian process models in RL for action-value estimation, finding they outperform linear models but lag behind deep neural networks in speed and performance, while offering better uncertainty estimates and interpretability. Read more

Recommended citation: Lende, M.v.d., Sabatelli, M. &; Cardenas-Cartagena, J. (2025). Interpretable Function Approximation with Gaussian Processes in Value-Based Model-Free Reinforcement Learning. Proceedings of the 6th Northern Lights Deep Learning Conference (NLDL), in Proceedings of Machine Learning Research 265:141-154 Available from https://proceedings.mlr.press/v265/lende25a.html. https://proceedings.mlr.press/v265/lende25a.html

Forecasting Smog Clouds With Deep Learning: A Proof-Of-Concept

Published in ICML 2024, AI4Science, 2024

This study investigates deep learning models, particularly LSTMs and GRUs, for multi-location air pollution forecasting of NO2, O3, PM10 & PM2.5, with a hierarchical GRU emerging as the most effective method. Read more

Recommended citation: Oldenburg, V., Cardenas-Cartagena, J., & Valdenegro-Toro, M. (2024). Forecasting Smog Clouds With Deep Learning. arXiv preprint arXiv:2410.02759. https://openreview.net/forum?id=UQa2PEVHMF&nesting=2&sort=date-desc

Risk-Aware Particle Filtering For State Estimation In Recirculating Aquaculture Systems

Published in The 56th Asilomar Conference on Signals, Systems, and Computers, 2022

We design a sequential non-linear risk-aware estimator based on particle filtering to compute estimates and approximate the system state posterior distribution. For this purpose, we consider the risk given by the expected variance of the squared error between the system state and the estimate conditioned on the observations. Read more

Recommended citation: J. Cardenas-Cartagena, M. Elnourani, B. Beferull-Lozano, and D. Romero, “Risk- Aware Particle Filtering For State Estimation In Recirculating Aquaculture Systems ,” in the 56th Asilomar Conference on Signals, Systems, and Computers, USA, 2022. TBA

Forecasting Aquaponic Systems Behaviour With Recurrent Neural Networks Models

Published in Northern Lights Deep Learning Workshop, 2022

Aquaponic systems provide a reliable solution to grow vegetables while cultivating fish (or other aquatic organisms) in a controlled environment. The main advantage of these systems compared with traditional soil-based agriculture and aquaculture installations is the ability to produce fish and vegetables with low water consumption. Aquaponics requires a robust control system capable of optimizing fish and plant growth while ensuring a safe operation. Read more

Recommended citation: J. Cardenas-Cartagena, M. Elnourani, and B. Beferull-Lozano, “Forecasting Aquaponic Systems Behaviour With Recurrent Neural Networks Models,” in Pro- ceedings of the Northern Lights Deep Learning Workshop, Tromso, Norway, 2022, doi: 10.7557/18.6236 https://septentrio.uit.no/index.php/nldl/article/view/6236

Cocreation laboratory in health: Materialization tool for innovation process in Colombian public hospitals

Published in 2017 Congreso Internacional de Innovacion y Tendencias en Ingenieria (CONIITI), 2017

Although there is a considerable investment in research for overall health, only the 1% of Colombian hospitals and clinical institutions, known as IPS, can afford innovation processes, this phenomenon implies a short generation of intellectual assets in health-care system in Colombia is shown. Read more

Recommended citation: S. Torres-Montoya, J. Cardenas-Cartagena, A. Arenas-Lopez, A. Quintero-Posada, and R. Torres-Villa, “Cocreation laboratory in health: Materialization tool for innovation process in Colombian public hospitals,” in 2017 Congreso Internacional de Innovacion y Tendencias en Ingenieria (CONIITI), Bogota, Oct. 2017, pp. 1–6, doi: 10.1109/CONIITI.2017.8273330. https://ieeexplore.ieee.org/document/8273330/

Glycemic Monitoring in Critical Care using Nonlinear State Estimators

Published in IFAC-PapersOnLine, 2017

As it is already known, patients under physiological stress, i.e., during a stay at an intensive care unit (ICU), often experience stress-induced hyperglycemia and insulin resistance even if they are not diagnosed with diabetes. In order to perform tight glycemic control (TGC) either by human intervention or by means of an automatic insulin infusion system, a proper monitoring system of the critical variables needs to be available. Read more

Recommended citation: E. Aguirre-Zapata, J. Cardenas-Cartagena, and J. Garcia-Tirado, “Glycemic Monitoring in Critical Care using Nonlinear State Estimators,” IFAC-PapersOnLine, vol. 50, no. 1, pp. 4430–4435, Jul. 2017, doi: 10.1016/j.ifacol.2017.08.369. https://linkinghub.elsevier.com/retrieve/pii/S2405896317307127

Juan Diego Cárdenas-Cartagena