Mariana Zuñiga Uribe

Mrs. Mariana Zuñiga Uribe


Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 March 2026 in Smart Cities
Verified
Journal Article
Open access
PDF file
MUMariana Zuñiga Uribe
Mariana Zuñiga Uribe
RGRafael Rojas Galván
Rafael Rojas Galván
José M. Álvarez-AlvaradoJosé M. Álvarez-Alvarado
José M. Álvarez-Alvarado
Marcos AvilesMarcos Aviles
Marcos Aviles
Gerardo I. Perez-SotoGerardo I. Perez-Soto
Gerardo I. Perez-Soto
VPVictor Perez
Victor Perez
Early leak detection in water distribution networks is essential to minimize losses and improve operational efficiency. This systematic review analyzes 53 studies published between 2018 and 2025 that employed machine learning, deep learning, and hybrid approaches. The results show that pressure is the most widely used and most sensitive input variable for identifying hydraulic anomalies. Most datasets originate from EPANET-generated simulations, while experimental and field data are less common due to their high costs and operational complexity. Machine learning models, particularly SVMs, achieve accuracies between 94 and 100%, demonstrating stability with noisy data and low computational cost, while in deep learning, CNNs are most effective for multiclass classification and localization, typically reaching 95–99% accuracy. Hybrid approaches that combine automatic feature extraction (e.g., CNNs or autoencoders) with conventional classifiers (such as SVMs or LSSVMs) yield the best results, surpassing 97% accuracy and achieving localization errors below 0.2 m. Based on these findings, a theoretical model is proposed using a hybrid CNN + SVM approach to enhance accuracy, robustness, and adaptability in real-time monitoring systems.

31 December 2024 in Journal of Scientific and Technical Applications
Verified
Journal Article
Open access
MUMariana Zuñiga Uribe
Mariana Zuñiga Uribe
RGRafael Rojas Galván
Rafael Rojas Galván
ENElías Nápoles
Elías Nápoles
MMMoisés Martínez
Moisés Martínez
Vibration analysis has proven to be effective for detecting failures in rotating elements. The objective of this study is to identify different failure conditions in a gear within an automotive gearbox by inducing failures in the gear and subsequently processing the vibration signals in the frequency domain using the Fast Fourier Transform. Two accelerometers were used to acquire data from the automotive transmission under different operating frequencies, to identify patterns indicative of failure in the damaged gear. The results show that the method can help identify the failure in the gear according to the amplitude value, differentiating between failure due to fracture and eccentricity. The increase in vibration levels is directly related to the severity of the failure present in the gear.

20 December 2024 in Revista Ciencias de la Salud
Verified
Journal Article
Open access
RGRafael Rojas Galván
Rafael Rojas Galván
HSHiram Seseña
Hiram Seseña
MUMariana Zuñiga Uribe
Mariana Zuñiga Uribe
MMMoisés Martínez
Moisés Martínez
Cardiovascular diseases are the leading cause of mortality worldwide, necessitating robust predictive models for early diagnosis. This study evaluates and compares the performance of support vector machine (SVM) models optimized using genetic algorithm (GA) and particle swarm optimization (PSO) techniques. A publicly available dataset with health-related features was used, involving preprocessing steps like handling missing values, encoding categorical variables, and feature scaling. The models were assessed based on cross-validation accuracy, test accuracy, and F1 score. Convergence plots were generated to visualize the optimization process. Results highlight the effectiveness of GA and PSO optimizations in enhancing SVM model performance for predicting cardiovascular health outcomes. The comparison provides insights into the relative strengths of each optimization method, guiding the development of advanced predictive models for heart diseases diagnosis and management.

30 December 2024 in Revista de Tecnología Informática
Verified
Journal Article
Open access
HSHiram Seseña
Hiram Seseña
MUMariana Zuñiga Uribe
Mariana Zuñiga Uribe
ENElías Nápoles
Elías Nápoles
MMMoisés Martínez
Moisés Martínez
A percentage of sudden cardiac arrests that occurred outside the hospital, there were no present people to assist in, so it is necessary that people need to be easily trained with equipment capable to feedback concisely to their performance, due to apply a quality CPR may increase survival to persons who suffers cardiac arrests. This article shows the development of training CPR equipment, based on measuring the force during compressions. For the prototype, two strain gauges were used to measure force, also having an embedded system to recollect data to subsequently send them to a graphic interface to be interpretated by persons who are training. The force variation from each sensor is due to their position, therefore, an average of measurements was made, resulting in a variation range between 220 N and 340 N for the applied force during compressions. This equipment can be useful as base for data acquisition