Juan José Pazmiño Gordillo
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Juan José Pazmiño Gordillo has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Alex Rolando Moyota Paguay
Escuela Superior Politecnica de Chimborazo
1 shared publication David Moreno Avilés
Escuela Superior Politecnica de Chimborazo
1 shared publicationGisela Alexandra Pilco Bonilla
Escuela Superior Politecnica de Chimborazo
1 shared publication- Iván Marcelo Ortiz Parra
Investigador independiente, Riobamba, Ecuador
1 shared publication - José Luis Cortés Llanganate
Escuela Superior Politecnica de Chimborazo
1 shared publication - Julio Cesar López Ayala
Mining Engineering Program, Escuela Superior Politécnica de Chimborazo (ESPOCH), Macas, Ecuador
1 shared publication
Latest Publications
- Open Access
- 1 September 2026
- Published by MDPI AG in Preprints.org
Multiscale Mining Pressure and Machine Learning-Based Susceptibility of Protected Areas in Ecuador
This study evaluates the spatial relationship between Ecuador’s mining cadastre and protected areas and investigates whether multiscale mining pressure can explain and predict direct mining-cadastre overlap. The objective was to move beyond conventional binary overlay analysis by identifying protected areas whose surrounding mining configurations indicate elevated overlap susceptibility. A CRISP-DM-based geospatial machine-learning framework was applied to 6,275 mining entities and 97 protected areas. Direct geometric intersections were quantified, followed by multiscale proximity analysis using 1, 5, 10, and 20 km distance thresholds and exclusive rings. Spatial autocorrelation was assessed, and multiscale frequency, area, and density indicators were used as predictors. Logistic Regression, Random Forest, and XGBoost were evaluated using spatial block cross-validation to reduce geographic information leakage. Model performance was assessed using ROC-AUC, PR-AUC, Brier score, and complementary classification metrics. Direct cadastral overlap affected 14 protected areas (14.43%), comprising 31 intersection pairs and approximately 90.91 km2 of cumulative overlap. Mining presence increased substantially with distance, occurring around 52.58%, 86.60%, 93.81%, and 97.94% of protected areas within 1, 5, 10, and 20 km, respectively. XGBoost achieved the best pooled spatially out-of-fold performance (ROC-AUC = 0.901; PR-AUC = 0.688; Brier score = 0.093). The most informative predictors were concentrated within the immediate 0–1 km surroundings. Direct overlap alone underrepresents the broader spatial context of mining pressure around Ecuador’s protected areas. Integrating multiscale geospatial analysis with spatially validated machine learning provides a reproducible framework for identifying and ranking protected areas according to mining-cadastre overlap susceptibility, while avoiding interpretation of these probabilities as evidence of active mining or environmental degradation.
- 1 September 2026
- Published by MDPI AG in Preprints.org
Open AccessMultiscale Mining Pressure and Machine Learning-Based Susceptibility of Protected Areas in Ecuador
This study evaluates the spatial relationship between Ecuador’s mining cadastre and protected areas and investigates whether multiscale mining pressure can explain and predict direct mining-cadastre overlap. The objective was to move beyond conventional binary overlay analysis by identifying protected areas whose surrounding mining configurations indicate elevated overlap susceptibility. A CRISP-DM-based geospatial machine-learning framework was applied to 6,275 mining entities and 97 protected areas. Direct geometric intersections were quantified, followed by multiscale proximity analysis using 1, 5, 10, and 20 km distance thresholds and exclusive rings. Spatial autocorrelation was assessed, and multiscale frequency, area, and density indicators were used as predictors. Logistic Regression, Random Forest, and XGBoost were evaluated using spatial block cross-validation to reduce geographic information leakage. Model performance was assessed using ROC-AUC, PR-AUC, Brier score, and complementary classification metrics. Direct cadastral overlap affected 14 protected areas (14.43%), comprising 31 intersection pairs and approximately 90.91 km2 of cumulative overlap. Mining presence increased substantially with distance, occurring around 52.58%, 86.60%, 93.81%, and 97.94% of protected areas within 1, 5, 10, and 20 km, respectively. XGBoost achieved the best pooled spatially out-of-fold performance (ROC-AUC = 0.901; PR-AUC = 0.688; Brier score = 0.093). The most informative predictors were concentrated within the immediate 0–1 km surroundings. Direct overlap alone underrepresents the broader spatial context of mining pressure around Ecuador’s protected areas. Integrating multiscale geospatial analysis with spatially validated machine learning provides a reproducible framework for identifying and ranking protected areas according to mining-cadastre overlap susceptibility, while avoiding interpretation of these probabilities as evidence of active mining or environmental degradation.
- Open Access
- 1 July 2026
- Published by Puerto Madero Editorial Académica in Tesla Revista Científica
- Vol. 6 (2) , e706
Implementación y evaluación de un prototipo de servidor de streaming adaptativo bajo condiciones de red simuladas
Educational institutions with limited network infrastructure need local alternatives to distribute audiovisual content without relying entirely on external platforms. This study implemented and evaluated an adaptive streaming server prototype based on MPEG-DASH under simulated and controlled network conditions. A quantitative approach with an experimental and comparative design was applied. The prototype was deployed on Ubuntu 24.04.4 LTS using Nginx, FFmpeg, Shaka Packager, Flask, and dash.js. Four bandwidth scenarios were configured: 2.6, 1.4, 0.8, and 0.5 Mbps, with 400 ms latency and 0.1% packet loss. Each scenario was executed ten times for five minutes. A total of 12,108 telemetry records were collected. The results showed that the average video bitrate decreased from 1,805.64 to 483.00 kbps, while startup delay ranged from 2.77 to 4.43 seconds. No stalling events were recorded, and the O.46 MOS remained between 4.38 and 4.62. It was concluded that the dash.js adaptive bitrate mechanism responded consistently to network restrictions and maintained playback continuity. Therefore, the developed prototype provides a reproducible foundation for future institutional evaluations and for further studies focused on local adaptive streaming services in educational environments with limited connectivity and restricted technological resources. Its implementation also demonstrates the feasibility of conducting controlled performance tests locally.
- 1 July 2026
- Published by Puerto Madero Editorial Académica in Tesla Revista Científica
- Vol. 6 (2) , e706
Open AccessImplementación y evaluación de un prototipo de servidor de streaming adaptativo bajo condiciones de red simuladas
Educational institutions with limited network infrastructure need local alternatives to distribute audiovisual content without relying entirely on external platforms. This study implemented and evaluated an adaptive streaming server prototype based on MPEG-DASH under simulated and controlled network conditions. A quantitative approach with an experimental and comparative design was applied. The prototype was deployed on Ubuntu 24.04.4 LTS using Nginx, FFmpeg, Shaka Packager, Flask, and dash.js. Four bandwidth scenarios were configured: 2.6, 1.4, 0.8, and 0.5 Mbps, with 400 ms latency and 0.1% packet loss. Each scenario was executed ten times for five minutes. A total of 12,108 telemetry records were collected. The results showed that the average video bitrate decreased from 1,805.64 to 483.00 kbps, while startup delay ranged from 2.77 to 4.43 seconds. No stalling events were recorded, and the O.46 MOS remained between 4.38 and 4.62. It was concluded that the dash.js adaptive bitrate mechanism responded consistently to network restrictions and maintained playback continuity. Therefore, the developed prototype provides a reproducible foundation for future institutional evaluations and for further studies focused on local adaptive streaming services in educational environments with limited connectivity and restricted technological resources. Its implementation also demonstrates the feasibility of conducting controlled performance tests locally.
- Open Access
- 1 January 2025
- Published by Puerto Madero Editorial Académica in Tesla Revista Científica
- Vol. 5 (1) , e505
Diagnóstico de eficiencia energética en infraestructura pública del centro andino ecuatoriano utilizando el software RETScreen
La creciente demanda energética en las edificaciones públicas del centro andino ecuatoriano plantea desafíos en términos de sostenibilidad, eficiencia operativa y mitigación de impactos ambientales. Herramientas de simulación energética como RETScreen permiten evaluar el rendimiento energético de infraestructuras existentes y proponer estrategias de optimización. Este estudio tuvo como objetivo diagnosticar el nivel de eficiencia energética de un edificio público en Ambato, utilizando RETScreen. Se evaluaron distintos escenarios de consumo y se cuantificó el impacto de medidas correctivas sobre iluminación, calentamiento de agua y ventilación. A partir de un modelo energético ajustado a las condiciones locales de Ambato, se compararon dos escenarios: uno base (consumo actual) y otro eficiente, que incluyó medidas como la sustitución de luminarias por LED, la reducción de calderas y la optimización de horarios. Los resultados mostraron una reducción del 28,2% en el consumo eléctrico anual, lo que representa un ahorro de 109.310 kWh. La inversión fue de USD 10.200, con un periodo de retorno de 2,8 años, una Tasa Interna de Retorno (TIR) del 17,5% y un Valor Actual Neto positivo. Además, se evitó la emisión de 22 toneladas de CO₂ anuales. El estudio confirma la viabilidad, rentabilidad y beneficios ambientales de las medidas implementadas.
- 1 January 2025
- Published by Puerto Madero Editorial Académica in Tesla Revista Científica
- Vol. 5 (1) , e505
Open AccessDiagnóstico de eficiencia energética en infraestructura pública del centro andino ecuatoriano utilizando el software RETScreen
La creciente demanda energética en las edificaciones públicas del centro andino ecuatoriano plantea desafíos en términos de sostenibilidad, eficiencia operativa y mitigación de impactos ambientales. Herramientas de simulación energética como RETScreen permiten evaluar el rendimiento energético de infraestructuras existentes y proponer estrategias de optimización. Este estudio tuvo como objetivo diagnosticar el nivel de eficiencia energética de un edificio público en Ambato, utilizando RETScreen. Se evaluaron distintos escenarios de consumo y se cuantificó el impacto de medidas correctivas sobre iluminación, calentamiento de agua y ventilación. A partir de un modelo energético ajustado a las condiciones locales de Ambato, se compararon dos escenarios: uno base (consumo actual) y otro eficiente, que incluyó medidas como la sustitución de luminarias por LED, la reducción de calderas y la optimización de horarios. Los resultados mostraron una reducción del 28,2% en el consumo eléctrico anual, lo que representa un ahorro de 109.310 kWh. La inversión fue de USD 10.200, con un periodo de retorno de 2,8 años, una Tasa Interna de Retorno (TIR) del 17,5% y un Valor Actual Neto positivo. Además, se evitó la emisión de 22 toneladas de CO₂ anuales. El estudio confirma la viabilidad, rentabilidad y beneficios ambientales de las medidas implementadas.
- Open Access
- 5 January 2018
- Published by Universidad de las Fuerzas Armadas ESPE in MASKAY
- Vol. 8 (1) , 27
Implementación de sistemas evaluadores de conducta ansiolítica en ratones de laboratorio utilizando procesamiento digital de imágenes
En la actualidad existen varias técnicas para evaluar la conducta ansiolítica en animales de laboratorio, debido a que su comportamiento es muy similar al del ser humano, dichas técnicas incluyen métodos manuales y visuales, donde el evaluador debe observar atentamente todo el experimento y documentar cada uno de los eventos de interés realizados por el ratón, o a su vez adquirir equipos electrónicos que cumplan esta función, sin embargo, esta alternativa podría ser demasiado costosa. El presente artículo plantea el diseño e implementación de dos equipos evaluadores de ansiedad de bajo costo (Laberinto en Cruz Elevada y Cuarto Claro Obscuro) mediante procesamiento digital de imágenes, los mismos que después de la validación del funcionamiento entrega resultados de manera automática a través de una aplicación desarrollada en Matlab. Los resultados brindados por la aplicación coinciden con aquellos que un observador obtendría de forma manual y visual, lo que facilita las labores del evaluador y reduce notablemente los posibles errores humanos y de ambigüedad existentes en las pruebas manuales.
- 5 January 2018
- Published by Universidad de las Fuerzas Armadas ESPE in MASKAY
- Vol. 8 (1) , 27
Open AccessImplementación de sistemas evaluadores de conducta ansiolítica en ratones de laboratorio utilizando procesamiento digital de imágenes
En la actualidad existen varias técnicas para evaluar la conducta ansiolítica en animales de laboratorio, debido a que su comportamiento es muy similar al del ser humano, dichas técnicas incluyen métodos manuales y visuales, donde el evaluador debe observar atentamente todo el experimento y documentar cada uno de los eventos de interés realizados por el ratón, o a su vez adquirir equipos electrónicos que cumplan esta función, sin embargo, esta alternativa podría ser demasiado costosa. El presente artículo plantea el diseño e implementación de dos equipos evaluadores de ansiedad de bajo costo (Laberinto en Cruz Elevada y Cuarto Claro Obscuro) mediante procesamiento digital de imágenes, los mismos que después de la validación del funcionamiento entrega resultados de manera automática a través de una aplicación desarrollada en Matlab. Los resultados brindados por la aplicación coinciden con aquellos que un observador obtendría de forma manual y visual, lo que facilita las labores del evaluador y reduce notablemente los posibles errores humanos y de ambigüedad existentes en las pruebas manuales.