Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Raul Ramirez-Velarde has a total of 73 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Modelling Extreme Uncertainty: Estimating Maximum Queue Size of Systems with Pareto Inter-arrival Times and Pareto Service Times

    by Raul Ramirez-Velarde, Cristobal Pareja-Flores, Neil Hernandez-Gress, Laura Hervert-Escobar

  • AI-Driven Psychoeducational Analytics for Early Detection of Academic Risk in Colombian Schools

    by Ruth Y. Zuleta Torres, Dixon Salcedo Morillo, Raúl Ramírez Velarde, Pedro López Pérez

    This article presents the development of an academic management model integrating artificial intelligence, aimed at the early prediction of school failure risk. The study employed scientifically validated psychometric instruments, from which multi-stage databases were constructed, incorporating variables related to reading comprehension, mental health, spelling, and mathematical performance. Regression and clustering algorithms were compared with traditional linear approaches, showing a substantial enhancement in predictive performance. The proposed model is designed to support institutional data-driven decision-making and to guide timely pedagogical interventions. The findings confirm the high potential of artificial intelligence as a tool to strengthen educational inclusion, optimize academic management processes, and improve school performance in public education contexts marked by socioeconomic vulnerability. These findings lay the groundwork for scalable, ethical AI systems supporting inclusive education.

  • Sickle Cell Disease Patient Care System Using Artificial Intelligence

    by Jorge Gómez Gómez, Jorge Gómez, Daniel Salas Álvarez, Raúl Valente Ramírez, Raúl Valente

  • Modelling Extreme Uncertainty: Queues with Pareto Inter-arrival Times and Pareto Service Times

    by Raul Ramirez-Velarde, Cristobal Pareja-Flores, Neil Hernandez-Gress, Laura Hervert-Escobar

  • Open Access

    Forecasting Air Pollution Contingencies Using Predictive Analytic Techniques

    by Raul Ramirez-Velarde, Oscar Esquivel-Flores, Gerardo Mejía-Velázquez

    The proliferation of pollutants affects the world’s population, mainly those who live in large cities. Neurological and cardiovascular dysfunctions have a correlation with air particulate matter concentration, among other chronic diseases. Therefore, it is important to utilize different methods of analysis to build predictive models that can identify possible concentrations of contaminants in metropolitan areas. This work presents a methodology that will enable the forecasting of severe pollution contingencies using weather measurements as input variables. This predictive analytical technique combines several mathematical and statistical tools, which we refer to as predictive factor association (PFA). We perform principal component analysis on the samples to determine possible causal relationships and reduce dimensionality, resulting in orthogonal linear combinations of the variables called sample scores. For categorical variables, each linear combination probability is estimated using a window-based estimation technique or a machine learning algorithm to determine the class of a particular sample. For continuous variables, regression over the scores is carried out. The technique is used to predict environmental contingencies in Monterrey’s metropolitan area based on meteorological data with R2 between 0.7 and 0.8 and classification accuracies between 0.74 and 0.98.

  • Open Access

    LSTM Networks for Home Energy Efficiency

    by Zurisaddai Severiche-Maury, Wilson Arrubla-Hoyos, Raul Ramirez-Velarde, Dora Cama-Pinto, Juan Antonio Holgado-Terriza, Miguel Damas-Hermoso, Alejandro Cama-Pinto

    This study aims to develop and evaluate an LSTM neural network for predicting household energy consumption. To conduct the experiment, a testbed was created consisting of five common appliances, namely, a TV, air conditioner, fan, computer, and lamp, each connected to individual smart meters within a Home Energy Management System (HEMS). Additionally, a meter was installed on the distribution board to measure total consumption. Real-time data were collected at 15-min intervals for 30 days in a residence that represented urban energy consumption in Sincelejo, Sucre, inhabited by four people. This setup enabled the capture of detailed and specific energy consumption data, facilitating data analysis and validating the system before large-scale implementation. Using the detailed power consumption information of these devices, an LSTM model was trained to identify temporal connections in power usage. Proper data preparation, including normalisation and feature selection, was essential for the success of the model. The results showed that the LSTM model was effective in predicting energy consumption, achieving a mean squared error (MSE) of 0.0169. This study emphasises the importance of continued research on preferred predictive models and identifies areas for future research, such as the integration of additional contextual data and the development of practical applications for residential energy management. Additionally, it demonstrates the potential of LSTM models in smart-home energy management and serves as a solid foundation for future research in this field.


  • Analyzing Grade Inflation in Engineering Education

    by Raul Ramirez-Velarde, Laura Hervert-Escobar, Neil Hernandez-Gress

  • Evaluating Teacher’s Classroom Performance

    by Raul Ramirez-Velarde, Laura Hervert-Escobar, Neil Hernandez-Gress


  • Open Access

    Modeling of Path Loss for Radio Wave Propagation in Wireless Sensor Networks in Cassava Crops Using Machine Learning

    by Alexis Barrios-Ulloa, Alejandro Cama-Pinto, Emiro De-La-Hoz-Franco, Raúl Ramírez-Velarde, Dora Cama-Pinto

    Modeling radio signal propagation remains one of the most critical tasks in the planning of wireless communication systems, including wireless sensor networks (WSN). Despite the existence of a considerable number of propagation models, the studies aimed at characterizing the attenuation in the wireless channel are still numerous and relevant. These studies are used in the design and planning of wireless networks deployed in various environments, including those with abundant vegetation. This paper analyzes the performance of three vegetation propagation models, ITU-R, FITU-R, and COST-235, and compares them with path loss measurements conducted in a cassava field in Sincelejo, Colombia. Additionally, we applied four machine learning techniques: linear regression (LR), k-nearest neighbors (K-NN), support vector machine (SVM), and random forest (RF), aiming to enhance prediction accuracy levels. The results show that vegetation models based on traditional approaches are not able to adequately characterize attenuation, while models obtained by machine learning using RF, K-NN, and SVM can predict path loss in cassava with RMSE and MAE values below 5 dB.


  • Open Access

    An Ontological Model for the Representation of Vallenato as Cultural Heritage in a Context-Aware System

    by María Antonia Diaz-Mendoza, Emiro De-La-Hoz-Franco, Jorge Eliecer Gómez Gómez, Raúl Ramírez-Velarde

    The traditional Colombian vallenato was declared Intangible Cultural Heritage of Humanity by UNESCO on 1 December 2015 with urgency for it to be safeguarded, which led the government of Colombia in the head of the Ministry of Culture and the vallenato music cluster to develop a safeguarding plan that contains different activities, among which stands out a platform for the management of vallenato through educational processes. In this sense, this document proposes an ontological model for the representation of vallenato as cultural heritage in a context-aware system called Vallenatic. The ontology was developed using the NeOn methodology, designed in the Protégé software, and has 15 concepts (Vallenata Songs, Artist, Devices, Persons, Environment, Cultural Managers, Interface, Location, MOOC, Learning Object, Profile, Preference, Net, Time Cultural, Event, Cultural_Sites). The model was evaluated by means of nine (9) situations described in natural language and SWRL; this language was used since it allows expressing OWL concepts in combination with RuleML. The proposed model can be used for other musical genres that have the recognition of cultural and intangible heritage, such as the Spanish flamenco, Argentine Tango, Mexican Mariachi music, Peruvian scissors dance, Brazilian capoeira, Dominican bachata, Jamaican reggae, among others.