Jaime Sayago-Heredia
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Jaime Sayago-Heredia has a total of 41 co-authors. Here are the top co-authors by number of shared publications:
- Wilson Chango
Department of Systems and Computation, Pontifical Catholic University of Ecuador, Esmeraldas Campus PUCESE, Esmeraldas 080101, Ecuador
7 shared publications - Juan Diego Erazo Rodríguez
Escuela Superior Politecnica de Chimborazo
3 shared publications - Ricardo Pérez-Castillo
Universidad de Castilla-La Mancha
3 shared publications - Xavier Quiñonez-Ku
Pontificia Universidad Católica del Ecuador
3 shared publications - Guido Mazón-Fierro
Escuela Superior Politecnica de Chimborazo
2 shared publications Gustavo Chango Sailema
Pontificia Universidad Católica del Ecuador, Sede Esmeraldas Esmeraldas Ecuador
2 shared publications
Latest Publications
- Open Access
- 26 March 2026
- Published by MDPI AG in Computation
- Vol. 14 (4) , 78
Multiregional Forecasting of Traffic Accidents Using Prophet Models with Statistical Residual Validation
This study develops a multiregional forecasting framework for road traffic accidents in Ecuador, addressing a critical limitation in existing predictive approaches that rely predominantly on point error metrics without validating the statistical assumptions underlying forecast uncertainty. Although the analysis is conducted at the provincial level, the spatial dimension is used primarily for cross-regional comparison and risk classification rather than for explicit spatial interaction modeling. Using a dataset of 27,648 monthly observations covering all 24 provinces from 2014 to 2025, the study applies the Prophet model within a Design Science Research paradigm and a CRISP-DM implementation cycle. Separate provincial models are estimated with a 24-month forecasting horizon, and methodological rigor is ensured through systematic residual diagnostics using the Shapiro–Wilk test for normality and the Ljung–Box test for temporal independence. Empirical results indicate that the Prophet-based artifact outperforms a naïve seasonal benchmark in 70.8% of the provinces, demonstrating excellent predictive accuracy in structurally stable regions such as Tungurahua (MAPE = 10.9%). At the same time, the framework enables the identification of critical emerging risks in provinces such as Santo Domingo and Cotopaxi, where projected increases exceed 49% despite acceptable point forecasts. The findings confirm that point accuracy alone does not guarantee the validity of confidence intervals and that residual validation is essential for trustworthy uncertainty quantification. Overall, the proposed approach provides a robust foundation for a predictive surveillance system capable of supporting differentiated, evidence-based road safety policies in territorially heterogeneous contexts.
- 26 March 2026
- Published by MDPI AG in Computation
- Vol. 14 (4) , 78
Open AccessMultiregional Forecasting of Traffic Accidents Using Prophet Models with Statistical Residual Validation
This study develops a multiregional forecasting framework for road traffic accidents in Ecuador, addressing a critical limitation in existing predictive approaches that rely predominantly on point error metrics without validating the statistical assumptions underlying forecast uncertainty. Although the analysis is conducted at the provincial level, the spatial dimension is used primarily for cross-regional comparison and risk classification rather than for explicit spatial interaction modeling. Using a dataset of 27,648 monthly observations covering all 24 provinces from 2014 to 2025, the study applies the Prophet model within a Design Science Research paradigm and a CRISP-DM implementation cycle. Separate provincial models are estimated with a 24-month forecasting horizon, and methodological rigor is ensured through systematic residual diagnostics using the Shapiro–Wilk test for normality and the Ljung–Box test for temporal independence. Empirical results indicate that the Prophet-based artifact outperforms a naïve seasonal benchmark in 70.8% of the provinces, demonstrating excellent predictive accuracy in structurally stable regions such as Tungurahua (MAPE = 10.9%). At the same time, the framework enables the identification of critical emerging risks in provinces such as Santo Domingo and Cotopaxi, where projected increases exceed 49% despite acceptable point forecasts. The findings confirm that point accuracy alone does not guarantee the validity of confidence intervals and that residual validation is essential for trustworthy uncertainty quantification. Overall, the proposed approach provides a robust foundation for a predictive surveillance system capable of supporting differentiated, evidence-based road safety policies in territorially heterogeneous contexts.
- Open Access
- 15 January 2026
- Published by MDPI AG in Preprints.org
Spatio-Temporal Forecasting of Traffic Accidents Using Prophet Models with Statistical Residual Validation
This study develops a spatio-temporal forecasting artifact for road traffic accidents in Ecuador, addressing a critical limitation in existing predictive approaches that rely predominantly on point error metrics without validating the statistical assumptions underlying forecast uncertainty. Motivated by pronounced territorial heterogeneity in accident incidence and the need for reliable decision-support tools, the research proposes a multiregional modeling framework that integrates statistical residual validation to enhance the robustness of road safety planning. Using a dataset of 27{,}648 monthly observations covering all 24 provinces from 2014 to 2025, the study applies the Prophet model within a Design Science Research paradigm and a CRISP-DM implementation cycle. Separate provincial models are estimated with a 24-month forecasting horizon, and methodological rigor is ensured through systematic residual diagnostics using the Shapiro--Wilk test for normality and the Ljung--Box test for temporal independence. Empirical results indicate that the Prophet-based artifact outperforms a naïve seasonal benchmark in 70.8\% of the provinces, demonstrating excellent predictive accuracy in structurally stable regions such as Tungurahua (MAPE = 10.9\%). At the same time, the framework enables the identification of critical emerging risks in provinces such as Santo Domingo and Cotopaxi, where projected increases exceed 49\% despite acceptable point forecasts. The findings confirm that point accuracy alone does not guarantee the validity of confidence intervals and that residual validation is essential for trustworthy uncertainty quantification. Overall, the proposed approach provides a robust foundation for a predictive surveillance system capable of supporting differentiated, evidence-based road safety policies in territorially heterogeneous contexts.
- 15 January 2026
- Published by MDPI AG in Preprints.org
Open AccessSpatio-Temporal Forecasting of Traffic Accidents Using Prophet Models with Statistical Residual Validation
This study develops a spatio-temporal forecasting artifact for road traffic accidents in Ecuador, addressing a critical limitation in existing predictive approaches that rely predominantly on point error metrics without validating the statistical assumptions underlying forecast uncertainty. Motivated by pronounced territorial heterogeneity in accident incidence and the need for reliable decision-support tools, the research proposes a multiregional modeling framework that integrates statistical residual validation to enhance the robustness of road safety planning. Using a dataset of 27{,}648 monthly observations covering all 24 provinces from 2014 to 2025, the study applies the Prophet model within a Design Science Research paradigm and a CRISP-DM implementation cycle. Separate provincial models are estimated with a 24-month forecasting horizon, and methodological rigor is ensured through systematic residual diagnostics using the Shapiro--Wilk test for normality and the Ljung--Box test for temporal independence. Empirical results indicate that the Prophet-based artifact outperforms a naïve seasonal benchmark in 70.8\% of the provinces, demonstrating excellent predictive accuracy in structurally stable regions such as Tungurahua (MAPE = 10.9\%). At the same time, the framework enables the identification of critical emerging risks in provinces such as Santo Domingo and Cotopaxi, where projected increases exceed 49\% despite acceptable point forecasts. The findings confirm that point accuracy alone does not guarantee the validity of confidence intervals and that residual validation is essential for trustworthy uncertainty quantification. Overall, the proposed approach provides a robust foundation for a predictive surveillance system capable of supporting differentiated, evidence-based road safety policies in territorially heterogeneous contexts.
- Open Access
- 23 November 2025
- Published by Red Latinoamericana de Investigación Contemporánea S.A.S.
Innovación y Tecnología en Educación
Prólogo La sabiduría popular está llena de intuiciones que en su mayoría resisten a su tiempo y a su contexto, pues nos sugieren comprensiones de la realidad más allá de sus circunstancias. En el contexto actual resulta pertinente una reflexión científica sobre educación, innovación y tecnología. Se alude al conocido dicho “nada nuevo hay bajo el sol”, expresión bastante conocida y muy usada entre nosotros para expresar que de alguna manera todo ya está dicho o hecho. No obstante, cuando la usamos también parece cierto que no estamos renunciando a la novedad o a la creatividad que siempre nos enseñan formas nuevas de abordar la realidad y sus distintos aspectos. Un elemento común en el uso de esta expresión es que recurrimos a ella cuando estamos en situaciones en las que aquello que parecería totalmente nuevo, no es más que una forma un poco distinta de mostrarse o hacer algo que ya todos conocemos. Es, por un lado, una expresión que clama por reconocer y no olvidar que hay unas cosas, unos valores, unas comprensiones sobre la realidad, que siempre son y serán las mismas, aunque parecería que todo puede cambiar. Por otro lado, también es el reconocimiento de que lo novedoso de nuestro tiempo, lo extraño, lo que se nos aparece como totalmente diferente y nuevo, no es sino el resultado de todo lo que hasta ahora se ha investigado. Lo nuevo entraña lo viejo; lo nuevo lo es en cuanto tal en la medida en que conserva lo que ya fue y puede seguir siendo aun en un contexto diferente. En medio de los desafíos que hoy tenemos que enfrentar como sociedad, sobre todo desde la academia y desde nuestros espacios y grupos de investigación, la sentencia de “nada nuevo hay bajo el sol” puede servirnos como un mantra capaz de devolvernos a lo verdaderamente fundamental. Muchos avances tecnológicos y todos los recursos que la innovación nos ofrece tienen el potencial de hacernos creer que estamos frente a la muerte de todo lo que hasta ahora ha sido, y a partir de hoy todo será distinto. Es lo que ocurre en los contextos educativos, donde algunos han llegado a sugerir que los profesores pronto ya no serán necesarios. Sin duda la nuestra es una época movediza, donde resulta muy difícil no perder de vista lo esencial. Allí es donde precisamente la academia y la investigación científica tienen que generar conocimientos orientadores, entre cuyos principales aportes está el de darnos las herramientas para proteger y cuidar lo fundamental de lo accesorio. ¿Qué es lo fundamental? En la publicación que ahora el lector tiene en sus manos, lo fundamental está a la base de las preocupaciones de las investigaciones cuyos resultados aquí se comparten. Sin pretender agotar los resultados de investigación aquí socializados, el principal aporte de esta obra en su conjunto es la capacidad que tiene de sumergirnos en las tensiones del mundo actual y sus avances tecnológicos en el marco de la preocupación por la humanización, lo que nos constituye profundamente. Bella y fecunda contradicción a la que somos llevados por esta publicación: somos invitados a pensar un mundo cambiante y novedoso desde la certeza de que todo esto tiene que estar en sintonía con nuestro anhelo más profundo: humanizarnos. Así y sin más, los trabajos aquí publicados nos ponen de cara a la tarea más urgente, actual y acuciante que tiene la Universidad: humanizarnos. Mgtr. Diego A. Jiménez Bosquez
- 23 November 2025
- Published by Red Latinoamericana de Investigación Contemporánea S.A.S.
Open AccessInnovación y Tecnología en Educación
Prólogo La sabiduría popular está llena de intuiciones que en su mayoría resisten a su tiempo y a su contexto, pues nos sugieren comprensiones de la realidad más allá de sus circunstancias. En el contexto actual resulta pertinente una reflexión científica sobre educación, innovación y tecnología. Se alude al conocido dicho “nada nuevo hay bajo el sol”, expresión bastante conocida y muy usada entre nosotros para expresar que de alguna manera todo ya está dicho o hecho. No obstante, cuando la usamos también parece cierto que no estamos renunciando a la novedad o a la creatividad que siempre nos enseñan formas nuevas de abordar la realidad y sus distintos aspectos. Un elemento común en el uso de esta expresión es que recurrimos a ella cuando estamos en situaciones en las que aquello que parecería totalmente nuevo, no es más que una forma un poco distinta de mostrarse o hacer algo que ya todos conocemos. Es, por un lado, una expresión que clama por reconocer y no olvidar que hay unas cosas, unos valores, unas comprensiones sobre la realidad, que siempre son y serán las mismas, aunque parecería que todo puede cambiar. Por otro lado, también es el reconocimiento de que lo novedoso de nuestro tiempo, lo extraño, lo que se nos aparece como totalmente diferente y nuevo, no es sino el resultado de todo lo que hasta ahora se ha investigado. Lo nuevo entraña lo viejo; lo nuevo lo es en cuanto tal en la medida en que conserva lo que ya fue y puede seguir siendo aun en un contexto diferente. En medio de los desafíos que hoy tenemos que enfrentar como sociedad, sobre todo desde la academia y desde nuestros espacios y grupos de investigación, la sentencia de “nada nuevo hay bajo el sol” puede servirnos como un mantra capaz de devolvernos a lo verdaderamente fundamental. Muchos avances tecnológicos y todos los recursos que la innovación nos ofrece tienen el potencial de hacernos creer que estamos frente a la muerte de todo lo que hasta ahora ha sido, y a partir de hoy todo será distinto. Es lo que ocurre en los contextos educativos, donde algunos han llegado a sugerir que los profesores pronto ya no serán necesarios. Sin duda la nuestra es una época movediza, donde resulta muy difícil no perder de vista lo esencial. Allí es donde precisamente la academia y la investigación científica tienen que generar conocimientos orientadores, entre cuyos principales aportes está el de darnos las herramientas para proteger y cuidar lo fundamental de lo accesorio. ¿Qué es lo fundamental? En la publicación que ahora el lector tiene en sus manos, lo fundamental está a la base de las preocupaciones de las investigaciones cuyos resultados aquí se comparten. Sin pretender agotar los resultados de investigación aquí socializados, el principal aporte de esta obra en su conjunto es la capacidad que tiene de sumergirnos en las tensiones del mundo actual y sus avances tecnológicos en el marco de la preocupación por la humanización, lo que nos constituye profundamente. Bella y fecunda contradicción a la que somos llevados por esta publicación: somos invitados a pensar un mundo cambiante y novedoso desde la certeza de que todo esto tiene que estar en sintonía con nuestro anhelo más profundo: humanizarnos. Así y sin más, los trabajos aquí publicados nos ponen de cara a la tarea más urgente, actual y acuciante que tiene la Universidad: humanizarnos. Mgtr. Diego A. Jiménez Bosquez
- Open Access
- 3 June 2025
- Published by MDPI AG in Computation
- Vol. 13 (6) , 137
Data Fusion and Dimensionality Reduction for Pest Management in Pitahaya Cultivation
This study addresses the critical need for effective data fusion strategies in pest prediction for pitahaya (dragon fruit) cultivation in the Ecuadorian Amazon, where heterogeneous data sources—such as environmental sensors and chlorophyll measurements—offer complementary but fragmented insights. Current agricultural monitoring systems often fail to integrate these data streams, limiting early pest detection accuracy. To overcome this, we compared early and late fusion approaches using comprehensive experiments. Multidimensionality is a central challenge: the datasets span temporal (hourly sensor readings), spatial (plot-level chlorophyll samples), and spectral (chlorophyll reflectance) dimensions. We applied dimensionality reduction techniques—PCA, KPCA (linear, polynomial, RBF), t-SNE, and UMAP—to preserve relevant structure and enhance interpretability. Evaluation metrics included the proportion of information retained (score) and cluster separability (silhouette score). Our results demonstrate that early fusion yields superior integrated representations, with PCA and KPCA-linear achieving the highest scores (0.96 vs. 0.94), and KPCA-poly achieving the best cluster definition (silhouette: 0.32 vs. 0.31). Statistical validation using the Friedman test ( = 12.00, p = 0.02) and Nemenyi post hoc comparisons (p < 0.05) confirmed significant performance differences. KPCA-RBF performed poorly (score: 0.83; silhouette: 0.05), and although t-SNE and UMAP offered visual insights, they underperformed in clustering (silhouette < 0.12). These findings make three key contributions. First, early fusion better captures cross-domain interactions before dimensionality reduction, improving prediction robustness. Second, KPCA-poly offers an effective non-linear mapping suitable for tropical agroecosystem complexity. Third, our framework, when deployed in Joya de los Sachas, improved pest prediction accuracy by 12.60% over manual inspection, leading to more targeted pesticide use. This contributes to precision agriculture by providing low-cost, scalable strategies for smallholder farmers. Future work will explore hybrid fusion pipelines and sensor-agnostic models to extend generalizability.- 3 June 2025
- Published by MDPI AG in Computation
- Vol. 13 (6) , 137
Open AccessData Fusion and Dimensionality Reduction for Pest Management in Pitahaya Cultivation
This study addresses the critical need for effective data fusion strategies in pest prediction for pitahaya (dragon fruit) cultivation in the Ecuadorian Amazon, where heterogeneous data sources—such as environmental sensors and chlorophyll measurements—offer complementary but fragmented insights. Current agricultural monitoring systems often fail to integrate these data streams, limiting early pest detection accuracy. To overcome this, we compared early and late fusion approaches using comprehensive experiments. Multidimensionality is a central challenge: the datasets span temporal (hourly sensor readings), spatial (plot-level chlorophyll samples), and spectral (chlorophyll reflectance) dimensions. We applied dimensionality reduction techniques—PCA, KPCA (linear, polynomial, RBF), t-SNE, and UMAP—to preserve relevant structure and enhance interpretability. Evaluation metrics included the proportion of information retained (score) and cluster separability (silhouette score). Our results demonstrate that early fusion yields superior integrated representations, with PCA and KPCA-linear achieving the highest scores (0.96 vs. 0.94), and KPCA-poly achieving the best cluster definition (silhouette: 0.32 vs. 0.31). Statistical validation using the Friedman test ( = 12.00, p = 0.02) and Nemenyi post hoc comparisons (p < 0.05) confirmed significant performance differences. KPCA-RBF performed poorly (score: 0.83; silhouette: 0.05), and although t-SNE and UMAP offered visual insights, they underperformed in clustering (silhouette < 0.12). These findings make three key contributions. First, early fusion better captures cross-domain interactions before dimensionality reduction, improving prediction robustness. Second, KPCA-poly offers an effective non-linear mapping suitable for tropical agroecosystem complexity. Third, our framework, when deployed in Joya de los Sachas, improved pest prediction accuracy by 12.60% over manual inspection, leading to more targeted pesticide use. This contributes to precision agriculture by providing low-cost, scalable strategies for smallholder farmers. Future work will explore hybrid fusion pipelines and sensor-agnostic models to extend generalizability. - 14 May 2025
- Published by Springer Nature
- p. 3-16
Systematic Mapping of Support Tools for Microservices
- Open Access
- 7 April 2025
- Published by MDPI AG in Computation
- Vol. 13 (4) , 92
Predicting Urban Traffic Congestion with VANET Data
The purpose of this study lies in developing a comparison of neural network-based models for vehicular congestion prediction, with the aim of improving urban mobility and mitigating the negative effects associated with traffic, such as accidents and congestion. This research focuses on evaluating the effectiveness of different neural network architectures, specifically Transformer and LSTM, in order to achieve accurate and reliable predictions of vehicular congestion. To carry out this research, a rigorous methodology was employed that included a systematic literature review based on the PRISMA methodology, which allowed for the identification and synthesis of the most relevant advances in the field. Likewise, the Design Science Research (DSR) methodology was applied to guide the development and validation of the models, and the CRISP-DM (Cross-Industry Standard Process for Data Mining) methodology was used to structure the process, from understanding the problem to implementing the solutions. The dataset used in this study included key variables related to traffic, such as vehicle speed, vehicular flow, and weather conditions. These variables were processed and normalized to train and evaluate various neural network architectures, highlighting LSTM and Transformer networks. The results obtained demonstrated that the LSTM-based model outperformed the Transformer model in the task of congestion prediction. Specifically, the LSTM model achieved an accuracy of 0.9463, with additional metrics such as a loss of 0.21, an accuracy of 0.93, a precision of 0.29, a recall of 0.71, an F1-score of 0.42, an MSE of 0.07, and an RMSE of 0.26. In conclusion, this study demonstrates that the LSTM-based model is highly effective for predicting vehicular congestion, surpassing other architectures such as Transformer. The integration of this model into a simulation environment showed that real-time traffic information can significantly improve urban mobility management. These findings support the utility of neural network architectures in sustainable urban planning and intelligent traffic management, opening new perspectives for future research in this field.
- 7 April 2025
- Published by MDPI AG in Computation
- Vol. 13 (4) , 92
Open AccessPredicting Urban Traffic Congestion with VANET Data
The purpose of this study lies in developing a comparison of neural network-based models for vehicular congestion prediction, with the aim of improving urban mobility and mitigating the negative effects associated with traffic, such as accidents and congestion. This research focuses on evaluating the effectiveness of different neural network architectures, specifically Transformer and LSTM, in order to achieve accurate and reliable predictions of vehicular congestion. To carry out this research, a rigorous methodology was employed that included a systematic literature review based on the PRISMA methodology, which allowed for the identification and synthesis of the most relevant advances in the field. Likewise, the Design Science Research (DSR) methodology was applied to guide the development and validation of the models, and the CRISP-DM (Cross-Industry Standard Process for Data Mining) methodology was used to structure the process, from understanding the problem to implementing the solutions. The dataset used in this study included key variables related to traffic, such as vehicle speed, vehicular flow, and weather conditions. These variables were processed and normalized to train and evaluate various neural network architectures, highlighting LSTM and Transformer networks. The results obtained demonstrated that the LSTM-based model outperformed the Transformer model in the task of congestion prediction. Specifically, the LSTM model achieved an accuracy of 0.9463, with additional metrics such as a loss of 0.21, an accuracy of 0.93, a precision of 0.29, a recall of 0.71, an F1-score of 0.42, an MSE of 0.07, and an RMSE of 0.26. In conclusion, this study demonstrates that the LSTM-based model is highly effective for predicting vehicular congestion, surpassing other architectures such as Transformer. The integration of this model into a simulation environment showed that real-time traffic information can significantly improve urban mobility management. These findings support the utility of neural network architectures in sustainable urban planning and intelligent traffic management, opening new perspectives for future research in this field.
- Open Access
- 3 April 2025
- Published by MDPI AG in Future Internet
- Vol. 17 (4) , 159
Internet of Things and Deep Learning for Citizen Security: A Systematic Literature Review on Violence and Crime
This study conducts a systematic literature review following the PRISMA framework and the guidelines of Kitchenham and Charters to analyze the application of Internet of Things (IoT) technologies and deep learning models in monitoring violent actions and criminal activities in smart cities. A total of 45 studies published between 2010 and 2024 were selected, revealing that most research, primarily from India and China, focuses on cybersecurity in IoT networks (76%), while fewer studies address the surveillance of physical violence and crime-related events (17%). Advanced neural network models, such as Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTM) networks, and hybrid approaches, have demonstrated high accuracy rates, averaging over 97.44%, in detecting suspicious behaviors. These models perform well in identifying anomalies in IoT security; however, they have primarily been tested in simulation environments (91% of analyzed studies), most of which incorporate real-world data. From a legal perspective, existing proposals mainly emphasize security and privacy. This study contributes to the development of smart cities by promoting IoT-based security methodologies that enhance surveillance and crime prevention in cities in developing countries.
- 3 April 2025
- Published by MDPI AG in Future Internet
- Vol. 17 (4) , 159
Open AccessInternet of Things and Deep Learning for Citizen Security: A Systematic Literature Review on Violence and Crime
This study conducts a systematic literature review following the PRISMA framework and the guidelines of Kitchenham and Charters to analyze the application of Internet of Things (IoT) technologies and deep learning models in monitoring violent actions and criminal activities in smart cities. A total of 45 studies published between 2010 and 2024 were selected, revealing that most research, primarily from India and China, focuses on cybersecurity in IoT networks (76%), while fewer studies address the surveillance of physical violence and crime-related events (17%). Advanced neural network models, such as Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTM) networks, and hybrid approaches, have demonstrated high accuracy rates, averaging over 97.44%, in detecting suspicious behaviors. These models perform well in identifying anomalies in IoT security; however, they have primarily been tested in simulation environments (91% of analyzed studies), most of which incorporate real-world data. From a legal perspective, existing proposals mainly emphasize security and privacy. This study contributes to the development of smart cities by promoting IoT-based security methodologies that enhance surveillance and crime prevention in cities in developing countries.
- Open Access
- 11 February 2025
- Published by MDPI AG in Preprints.org
Climate Characterization and Prediction in Vulnerable Regions of the Ecuadorian Amazon
According to the Intergovernmental Panel on Climate Change (IPCC), a significant increase in climate change has been identified during the last decade, generating adverse impacts in Ecuador’s most vulnerable regions. Among these areas is the province of Orellana, particularly the cantons of Joya de los Sachas and Loreto, where agriculture constitutes the main economic activity. However, these localities face a lack of a continuous meteorological monitoring system, which hinders both climate prediction and the adequate planning of productive activities. In response to this problem, a comprehensive characterization of climatic variables and soil and water quality was carried out on experimental farms located in the San Carlos and La Paz parishes. To this end, historical and current meteorological data related to temperature, atmospheric pressure, precipitation, relative humidity, solar radiation, wind speed, and wind direction were collected. Additionally, the statistical analysis included multivariate hypothesis tests, such as MANOVA and MANCOVA, with the aim of identifying significant differences between the studied localities. In the water quality analysis, physicochemical and microbiological parameters were evaluated according to the specifications of Tables 1 and 3 of the Unified Text of Secondary Legislation of the Ministry of Environment (TULSMA). Complementarily, the parameters recommended by the National Institute of Agricultural Research (INIAP) were considered to evaluate soil quality. The results included monthly and annual descriptive graphs of the climatic variables, which evidenced significant differences between the analyzed cantons. On the other hand, although the soil data did not show relevant discrepancies, the water analysis revealed a seasonal increase in metal and microorganism concentrations, reflecting the influence of climatic variations on water resources. These temporal and geographical differences were evaluated using machine learning techniques, which allowed for the identification of more complex patterns and trends. The predictions for Loreto and Sacha coincided in several aspects, highlighting a clear trend towards the reduction of climate variability and greater stability in meteorological patterns. This behavior manifests itself in the attenuation of seasonal fluctuations in variables such as temperature, pressure, relative humidity, solar radiation, wind speed, and precipitation. Consequently, these changes could reflect a transition towards a more predictable and constant climate, with direct implications for agriculture, water resource management, and planning for extreme weather events.
- 11 February 2025
- Published by MDPI AG in Preprints.org
Open AccessClimate Characterization and Prediction in Vulnerable Regions of the Ecuadorian Amazon
According to the Intergovernmental Panel on Climate Change (IPCC), a significant increase in climate change has been identified during the last decade, generating adverse impacts in Ecuador’s most vulnerable regions. Among these areas is the province of Orellana, particularly the cantons of Joya de los Sachas and Loreto, where agriculture constitutes the main economic activity. However, these localities face a lack of a continuous meteorological monitoring system, which hinders both climate prediction and the adequate planning of productive activities. In response to this problem, a comprehensive characterization of climatic variables and soil and water quality was carried out on experimental farms located in the San Carlos and La Paz parishes. To this end, historical and current meteorological data related to temperature, atmospheric pressure, precipitation, relative humidity, solar radiation, wind speed, and wind direction were collected. Additionally, the statistical analysis included multivariate hypothesis tests, such as MANOVA and MANCOVA, with the aim of identifying significant differences between the studied localities. In the water quality analysis, physicochemical and microbiological parameters were evaluated according to the specifications of Tables 1 and 3 of the Unified Text of Secondary Legislation of the Ministry of Environment (TULSMA). Complementarily, the parameters recommended by the National Institute of Agricultural Research (INIAP) were considered to evaluate soil quality. The results included monthly and annual descriptive graphs of the climatic variables, which evidenced significant differences between the analyzed cantons. On the other hand, although the soil data did not show relevant discrepancies, the water analysis revealed a seasonal increase in metal and microorganism concentrations, reflecting the influence of climatic variations on water resources. These temporal and geographical differences were evaluated using machine learning techniques, which allowed for the identification of more complex patterns and trends. The predictions for Loreto and Sacha coincided in several aspects, highlighting a clear trend towards the reduction of climate variability and greater stability in meteorological patterns. This behavior manifests itself in the attenuation of seasonal fluctuations in variables such as temperature, pressure, relative humidity, solar radiation, wind speed, and precipitation. Consequently, these changes could reflect a transition towards a more predictable and constant climate, with direct implications for agriculture, water resource management, and planning for extreme weather events.
- Open Access
- 29 January 2025
- Published by MDPI AG in Preprints.org
Predicting Urban Traffic Congestion with VANET Data
Recent research has demonstrated a strong correlation between the exponential growth of the transportation sector and the increase in urban phenomena such as traffic accidents and congestion. In this context, accurate congestion prediction has become a primary objective to improve urban mobility and mitigate the negative effects associated with traffic.The study proposes a machine learning-based classification model to predict vehicular congestion. Using a dataset that includes variables such as speed, traffic flow, and weather conditions, various classification algorithms were trained and evaluated. The results obtained indicate that models based on Random Forest offer superior performance in the task of congestion prediction.To evaluate the impact of these predictions on urban mobility, the model was integrated into a vehicular ad-hoc network (VANET) simulation environment. The simulation results demonstrated that providing real-time traffic information based on model predictions allows drivers to make more informed decisions, consequently reducing travel times and emissions.
- 29 January 2025
- Published by MDPI AG in Preprints.org
Open AccessPredicting Urban Traffic Congestion with VANET Data
Recent research has demonstrated a strong correlation between the exponential growth of the transportation sector and the increase in urban phenomena such as traffic accidents and congestion. In this context, accurate congestion prediction has become a primary objective to improve urban mobility and mitigate the negative effects associated with traffic.The study proposes a machine learning-based classification model to predict vehicular congestion. Using a dataset that includes variables such as speed, traffic flow, and weather conditions, various classification algorithms were trained and evaluated. The results obtained indicate that models based on Random Forest offer superior performance in the task of congestion prediction.To evaluate the impact of these predictions on urban mobility, the model was integrated into a vehicular ad-hoc network (VANET) simulation environment. The simulation results demonstrated that providing real-time traffic information based on model predictions allows drivers to make more informed decisions, consequently reducing travel times and emissions.
- Open Access
- 12 November 2024
- Published by Wiley in Journal of Software: Evolution and Process
- Vol. 37 (2)
Analyzing the Correlation Between Toxic Comments and Code Quality
Software development has a relevant human side, and this could, for example, imply that developers' feelings have an impact on certain aspects of software development such as quality, productivity, or performance. This paper explores the effects of toxic emotions on code quality and presents the SentiQ tool, which gathers and analyzes sentiments from commit messages (obtained from GitHub) and code quality measures (obtained from SonarQube). The SentiQ tool we proposed performs a sentiment analysis (based on natural language processing techniques) and relates the results to the code quality measures. The datasets extracted are then used as the basis on which to conduct a preliminary case study, which demonstrates that there is a relationship between toxic comments and code quality that may affect the quality of the whole software project. This has resulted in the drafting of a predictive model to validate the correlation of the impact of toxic comments on code quality. The main implication of this work is that these results could, in the future, make it possible to estimate code quality as a function of developers' toxic comments.
- 12 November 2024
- Published by Wiley in Journal of Software: Evolution and Process
- Vol. 37 (2)
Open AccessAnalyzing the Correlation Between Toxic Comments and Code Quality
Software development has a relevant human side, and this could, for example, imply that developers' feelings have an impact on certain aspects of software development such as quality, productivity, or performance. This paper explores the effects of toxic emotions on code quality and presents the SentiQ tool, which gathers and analyzes sentiments from commit messages (obtained from GitHub) and code quality measures (obtained from SonarQube). The SentiQ tool we proposed performs a sentiment analysis (based on natural language processing techniques) and relates the results to the code quality measures. The datasets extracted are then used as the basis on which to conduct a preliminary case study, which demonstrates that there is a relationship between toxic comments and code quality that may affect the quality of the whole software project. This has resulted in the drafting of a predictive model to validate the correlation of the impact of toxic comments on code quality. The main implication of this work is that these results could, in the future, make it possible to estimate code quality as a function of developers' toxic comments.