Santiago González
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Santiago González has a total of 39 co-authors. Here are the top co-authors by number of shared publications:
- Juan Carlos Guerri
Institute of Telecommunications and Multimedia Applications (iTEAM), Universitat Politècnica de Valencia, Valencia, Spain
3 shared publications Pau Arce
Universität Politècnica de València-Spain
3 shared publications- Alonso Cartuche
Centro de Investigaciones Tropicales del Ambiente y Biodiversidad (CITIAB), Grupo de Investigación de Medio Ambiente y Recursos Naturales-GIMARN, Carrera de Ingeniería Ambiental, Universidad Nacional de Loja, Guillermo Falconí University Campus, Loja 110150, Ecuador
2 shared publications - Andrés Gonzales
Department of Electric, Electronic and Telecommunication Engineering, Universidad de Cuenca, Cuenca, Ecuador
2 shared publications - Iván Santiago Palacios Serrano
Universidad de Cuenca
2 shared publications - Luis González
Department of Electric, Electronic and Telecommunication Engineering, Universidad de Cuenca, Cuenca, Ecuador
2 shared publications
Latest Publications
- Open Access
- 15 October 2025
- Published by Escuela Superior Politecnica del Litoral in Revista Tecnológica - ESPOL
- Vol. 37 (E1) , 88-111
Sistema de Detección y Alerta de Incendios Forestales Basado en Procesamiento de Imágenes e IA
The objective of this work focuses on the design and implementation of a low-cost intelligent system for the early detection of forest fires, using IoT (Internet of Things) and AI (Artificial Intelligence) technologies. The designed methodology involved the development and comparative evaluation of multiple algorithms, divided into two approaches: techniques based on the analysis of color spaces (RGB, YCbCr, HSI, HSV, and PJF) and AI models (CNN, YOLOv8, and Haar Cascade). From this analysis, a hybrid architecture was selected that integrates the two highest-performing methods: an object detector based on YOLOv8 (Method 9) and a chromatic algorithm that fuses the PJF, RGB, and YCbCr spaces (Method 12). This visual system is complemented by a PM2.5 particle sensor to validate the presence of smoke and GPS/4G modules to issue georeferenced alerts. As a key result, the final prototype validated under controlled conditions achieved outstanding metrics such as 99.82% accuracy, 99.64% sensitivity, and 100.00% specificity under high illumination conditions. It also demonstrated energy efficiency and thermal stability through continuous monitoring of CPU, RAM, and current consumption. The main contribution of this work consists of a validated field solution, whose hybrid architecture proves to be accurate, efficient, and adaptable, confirming its feasibility for implementation in emergency contexts.
- 15 October 2025
- Published by Escuela Superior Politecnica del Litoral in Revista Tecnológica - ESPOL
- Vol. 37 (E1) , 88-111
Open AccessSistema de Detección y Alerta de Incendios Forestales Basado en Procesamiento de Imágenes e IA
The objective of this work focuses on the design and implementation of a low-cost intelligent system for the early detection of forest fires, using IoT (Internet of Things) and AI (Artificial Intelligence) technologies. The designed methodology involved the development and comparative evaluation of multiple algorithms, divided into two approaches: techniques based on the analysis of color spaces (RGB, YCbCr, HSI, HSV, and PJF) and AI models (CNN, YOLOv8, and Haar Cascade). From this analysis, a hybrid architecture was selected that integrates the two highest-performing methods: an object detector based on YOLOv8 (Method 9) and a chromatic algorithm that fuses the PJF, RGB, and YCbCr spaces (Method 12). This visual system is complemented by a PM2.5 particle sensor to validate the presence of smoke and GPS/4G modules to issue georeferenced alerts. As a key result, the final prototype validated under controlled conditions achieved outstanding metrics such as 99.82% accuracy, 99.64% sensitivity, and 100.00% specificity under high illumination conditions. It also demonstrated energy efficiency and thermal stability through continuous monitoring of CPU, RAM, and current consumption. The main contribution of this work consists of a validated field solution, whose hybrid architecture proves to be accurate, efficient, and adaptable, confirming its feasibility for implementation in emergency contexts.
- Open Access
- 15 October 2025
- Published by Escuela Superior Politecnica del Litoral in Revista Tecnológica - ESPOL
- Vol. 37 (E1) , 56-76
Evaluación y Comparación de Métricas Objetivas PSNR, SSIM y LPIPS para el Análisis de Calidad de Video
This paper presents a tool for video quality assessment that allows the selection of quality (QP), temporal (FPS), and spatial (bitrate) scalability parameters. The proposal integrates traditional metrics such as Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM), together with the perceptual metric Perceptual Image Patch Similarity (LPIPS), which is based on deep neural networks. To validate its effectiveness, a two-phase subjective evaluation methodology was applied. In the first phase, participants assessed videos encoded with the same scalability parameter, showing a strong correspondence between visual perception and objective metrics. In the second phase, different configurations were compared, revealing a preference for high quality and intermediate spatial scalability. Additionally, in experiments with common distortions such as blurring and noise, LPIPS achieved a sensitivity of 73.64%, outperforming PSNR and SSIM in its alignment with human perception. The main contribution of this work is a tool that combines objective and subjective evaluations, enabling a more comprehensive analysis that closely reflects human visual perception.
- 15 October 2025
- Published by Escuela Superior Politecnica del Litoral in Revista Tecnológica - ESPOL
- Vol. 37 (E1) , 56-76
Open AccessEvaluación y Comparación de Métricas Objetivas PSNR, SSIM y LPIPS para el Análisis de Calidad de Video
This paper presents a tool for video quality assessment that allows the selection of quality (QP), temporal (FPS), and spatial (bitrate) scalability parameters. The proposal integrates traditional metrics such as Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM), together with the perceptual metric Perceptual Image Patch Similarity (LPIPS), which is based on deep neural networks. To validate its effectiveness, a two-phase subjective evaluation methodology was applied. In the first phase, participants assessed videos encoded with the same scalability parameter, showing a strong correspondence between visual perception and objective metrics. In the second phase, different configurations were compared, revealing a preference for high quality and intermediate spatial scalability. Additionally, in experiments with common distortions such as blurring and noise, LPIPS achieved a sensitivity of 73.64%, outperforming PSNR and SSIM in its alignment with human perception. The main contribution of this work is a tool that combines objective and subjective evaluations, enabling a more comprehensive analysis that closely reflects human visual perception.
- Open Access
- 30 June 2025
- Published by Escuela Superior Politecnica del Litoral in Revista Tecnológica - ESPOL
- Vol. 37 (1) , 264-284
Evaluación de un algoritmo de control para video adaptativo empleando enrutamiento tradicional y SDN
Currently, according to the Cisco Annual Internet Report, between 80% and 85% of internet data traffic is generated by video content, making it imperative to develop methods or algorithms that enable the efficient transmission of multimedia content over the network. In this context, this article proposes an optimized algorithm for video traffic control in an SDN environment, allowing for adaptive real-time transmission. The methodology consists of the following stages: first, the video is transmitted at a minimum encoded bitrate; then, the available network bandwidth is measured, based on which the encoding rate and video quality are adjusted; and finally, the video is played on the client side. The results obtained using the control algorithm were compared with those obtained using common routing protocols such as RIP (Routing Information Protocol) and OSPF (Open Shortest Path First). The use of the control algorithm resulted in an 18.1% lower delay compared to RIP and a 94.8% lower delay compared to OSPF. Under background traffic conditions, SDN demonstrated a 27.23% lower delay than RIP and a 54.1% lower delay than OSPF. The main contribution of this work is, through the implementation of a testbed, the analysis of a mechanism that improves quality of service (QoS) and quality of experience (QoE) by optimizing real-time video transmission through the selection of the best route and/or the dynamic adjustment of video bitrate according to network conditions.
- 30 June 2025
- Published by Escuela Superior Politecnica del Litoral in Revista Tecnológica - ESPOL
- Vol. 37 (1) , 264-284
Open AccessEvaluación de un algoritmo de control para video adaptativo empleando enrutamiento tradicional y SDN
Currently, according to the Cisco Annual Internet Report, between 80% and 85% of internet data traffic is generated by video content, making it imperative to develop methods or algorithms that enable the efficient transmission of multimedia content over the network. In this context, this article proposes an optimized algorithm for video traffic control in an SDN environment, allowing for adaptive real-time transmission. The methodology consists of the following stages: first, the video is transmitted at a minimum encoded bitrate; then, the available network bandwidth is measured, based on which the encoding rate and video quality are adjusted; and finally, the video is played on the client side. The results obtained using the control algorithm were compared with those obtained using common routing protocols such as RIP (Routing Information Protocol) and OSPF (Open Shortest Path First). The use of the control algorithm resulted in an 18.1% lower delay compared to RIP and a 94.8% lower delay compared to OSPF. Under background traffic conditions, SDN demonstrated a 27.23% lower delay than RIP and a 54.1% lower delay than OSPF. The main contribution of this work is, through the implementation of a testbed, the analysis of a mechanism that improves quality of service (QoS) and quality of experience (QoE) by optimizing real-time video transmission through the selection of the best route and/or the dynamic adjustment of video bitrate according to network conditions.
- Open Access
- 1 January 2025
- Published by Salesian Polytechnic University of Ecuador in INGENIUS
- No. 33,p. 27-37
Aplicación de MANET como sistema de comunicación en la movilidad sostenible
This paper presents an architecture based on the MANET (Mobile Ad Hoc Network) paradigm as an emergency communication system between users of electric bicycles. The solution consists of 4 mobile nodes representing the users and a main fixed node, which emulates a bicycle docking station. This architecture allows multi-hop communication between the nodes, using the proactive routing protocols OLSR (Optimized Link State Routing) and BATMAN (Better Approach to Mobile Ad Hoc Networking). The study was divided into 3 main stages. First, an analysis of the wireless medium was performed to determine the maximum transmission distance and the maximum bitrate between 2 nodes. Subsequently, the throughput behavior was characterized in a multihop configuration consisting of 4 nodes in order to establish the network capacity in terms of bandwidth. Finally, a web application was implemented for the transmission of audio and text traffic. Regarding the evaluation of the proposal, two scenarios were designed to emulate the integration of a new cyclist to the network and the communication between two users in motion. The results reveal that OLSR provides a better system operation, with a throughput of 2.54 Mbps at 3 hops and a PRR (Packet Reception Rate) higher than 96%. In addition, it guarantees a delay within the ITU-T (International Telecommunication Union-Telecommunication) G.114 recommendation for bidirectional communication.
- 1 January 2025
- Published by Salesian Polytechnic University of Ecuador in INGENIUS
- No. 33,p. 27-37
Open AccessAplicación de MANET como sistema de comunicación en la movilidad sostenible
This paper presents an architecture based on the MANET (Mobile Ad Hoc Network) paradigm as an emergency communication system between users of electric bicycles. The solution consists of 4 mobile nodes representing the users and a main fixed node, which emulates a bicycle docking station. This architecture allows multi-hop communication between the nodes, using the proactive routing protocols OLSR (Optimized Link State Routing) and BATMAN (Better Approach to Mobile Ad Hoc Networking). The study was divided into 3 main stages. First, an analysis of the wireless medium was performed to determine the maximum transmission distance and the maximum bitrate between 2 nodes. Subsequently, the throughput behavior was characterized in a multihop configuration consisting of 4 nodes in order to establish the network capacity in terms of bandwidth. Finally, a web application was implemented for the transmission of audio and text traffic. Regarding the evaluation of the proposal, two scenarios were designed to emulate the integration of a new cyclist to the network and the communication between two users in motion. The results reveal that OLSR provides a better system operation, with a throughput of 2.54 Mbps at 3 hops and a PRR (Packet Reception Rate) higher than 96%. In addition, it guarantees a delay within the ITU-T (International Telecommunication Union-Telecommunication) G.114 recommendation for bidirectional communication.
- Open Access
- 3 May 2024
- Published by Wiley in Evolutionary Applications
- Vol. 17 (5) , e13691
Estimation of contemporary effective population size in plant populations: Limitations of genomic datasets
Effective population size (Ne) is a pivotal evolutionary parameter with crucial implications in conservation practice and policy. Genetic methods to estimate Ne have been preferred over demographic methods because they rely on genetic data rather than time‐consuming ecological monitoring. Methods based on linkage disequilibrium (LD), in particular, have become popular in conservation as they require a single sampling and provide estimates that refer to recent generations. A software program based on the LD method, GONE, looks particularly promising to estimate contemporary and recent‐historical Ne (up to 200 generations in the past). Genomic datasets from non‐model species, especially plants, may present some constraints to the use of GONE, as linkage maps and reference genomes are seldom available, and SNP genotyping is usually based on reduced‐representation methods. In this study, we use empirical datasets from four plant species to explore the limitations of plant genomic datasets when estimating Ne using the algorithm implemented in GONE, in addition to exploring some typical biological limitations that may affect Ne estimation using the LD method, such as the occurrence of population structure. We show how accuracy and precision of Ne estimates potentially change with the following factors: occurrence of missing data, limited number of SNPs/individuals sampled, and lack of information about the location of SNPs on chromosomes, with the latter producing a significant bias, previously unexplored with empirical data. We finally compare the Ne estimates obtained with GONE for the last generations with the contemporary Ne estimates obtained with the programs currentNe and NeEstimator.
- 3 May 2024
- Published by Wiley in Evolutionary Applications
- Vol. 17 (5) , e13691
Open AccessEstimation of contemporary effective population size in plant populations: Limitations of genomic datasets
Effective population size (Ne) is a pivotal evolutionary parameter with crucial implications in conservation practice and policy. Genetic methods to estimate Ne have been preferred over demographic methods because they rely on genetic data rather than time‐consuming ecological monitoring. Methods based on linkage disequilibrium (LD), in particular, have become popular in conservation as they require a single sampling and provide estimates that refer to recent generations. A software program based on the LD method, GONE, looks particularly promising to estimate contemporary and recent‐historical Ne (up to 200 generations in the past). Genomic datasets from non‐model species, especially plants, may present some constraints to the use of GONE, as linkage maps and reference genomes are seldom available, and SNP genotyping is usually based on reduced‐representation methods. In this study, we use empirical datasets from four plant species to explore the limitations of plant genomic datasets when estimating Ne using the algorithm implemented in GONE, in addition to exploring some typical biological limitations that may affect Ne estimation using the LD method, such as the occurrence of population structure. We show how accuracy and precision of Ne estimates potentially change with the following factors: occurrence of missing data, limited number of SNPs/individuals sampled, and lack of information about the location of SNPs on chromosomes, with the latter producing a significant bias, previously unexplored with empirical data. We finally compare the Ne estimates obtained with GONE for the last generations with the contemporary Ne estimates obtained with the programs currentNe and NeEstimator.
- 4 January 2024
- Published by Springer Nature in SN Computer Science
- Vol. 5 (1) , 1-13
A Low-Cost IoT Architecture Based on LPWAN and MQTT for Monitoring Water Resources in Andean Wetlands
- 4 January 2024
- Published by Springer Nature in SN Computer Science
- Vol. 5 (1) , 1-13
A Low-Cost IoT Architecture Based on LPWAN and MQTT for Monitoring Water Resources in Andean Wetlands
- 26 March 2023
- Published by Springer Nature
- p. 264-278
Application of LPWAN Technologies Based on LoRa in the Monitoring of Water Sources of The Andean Wetlands
- 26 March 2023
- Published by Springer Nature
- p. 264-278
Application of LPWAN Technologies Based on LoRa in the Monitoring of Water Sources of The Andean Wetlands
- Open Access
- 29 November 2022
- Published by Escuela Superior Politecnica del Litoral in Revista Tecnológica - ESPOL
- Vol. 34 (3) , 12-30
Evaluación y comparación de códecs de video para el despliegue de un sistema de comunicación resiliente
En escenarios de emergencia usualmente es difícil contar con una infraestructura de red, especialmente en lugares remotos o geográficamente complicados por el difícil acceso. Sin embargo, es necesario disponer de herramientas para comunicarse o realizar una valoración de la situación. En este sentido, las redes ad hoc surgen como una opción para solucionar esta problemática. En el presente artículo se propone el desarrollo de un sistema de comunicación de emergencia para la transmisión de tráfico multimedia en un escenario real, entre los diferentes pisos de un edificio. Para tal objetivo, se realizaron múltiples experimentos para determinar los valores de métricas fundamentales (v.g. packet loss, delay y throughput) para la transmisión de audio y video en tiempo real. En concreto, se desarrollaron herramientas de código abierto con capacidad de extraer las métricas requeridas y comparar de forma objetiva la calidad del video empleando mecanismos de codificación actuales (v.g. VP8, VP9, H.264, H.265). Los resultados obtenidos muestran que VP8 es el códec más adecuado para el escenario propuesto. Además, se desarrolló una herramienta de videoconferencia con capacidad de adaptar las características del video (v.g. bitrate) acorde a las condiciones de la red.
- 29 November 2022
- Published by Escuela Superior Politecnica del Litoral in Revista Tecnológica - ESPOL
- Vol. 34 (3) , 12-30
Open AccessEvaluación y comparación de códecs de video para el despliegue de un sistema de comunicación resiliente
En escenarios de emergencia usualmente es difícil contar con una infraestructura de red, especialmente en lugares remotos o geográficamente complicados por el difícil acceso. Sin embargo, es necesario disponer de herramientas para comunicarse o realizar una valoración de la situación. En este sentido, las redes ad hoc surgen como una opción para solucionar esta problemática. En el presente artículo se propone el desarrollo de un sistema de comunicación de emergencia para la transmisión de tráfico multimedia en un escenario real, entre los diferentes pisos de un edificio. Para tal objetivo, se realizaron múltiples experimentos para determinar los valores de métricas fundamentales (v.g. packet loss, delay y throughput) para la transmisión de audio y video en tiempo real. En concreto, se desarrollaron herramientas de código abierto con capacidad de extraer las métricas requeridas y comparar de forma objetiva la calidad del video empleando mecanismos de codificación actuales (v.g. VP8, VP9, H.264, H.265). Los resultados obtenidos muestran que VP8 es el códec más adecuado para el escenario propuesto. Además, se desarrolló una herramienta de videoconferencia con capacidad de adaptar las características del video (v.g. bitrate) acorde a las condiciones de la red.
- 3 February 2022
- Published by Springer Nature
- p. 56-70
MQTT Based Event Detection System for Structural Health Monitoring of Buildings
- 3 February 2022
- Published by Springer Nature
- p. 56-70
MQTT Based Event Detection System for Structural Health Monitoring of Buildings