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.

La respuesta al enigma de la moniliasis se encuentra en la ciencia y la tecnología con el proyecto desarrollado en la Provincia de Orellana, en donde la moniliasis es una enfermedad fúngica que causa efectos devastadores incluyen do la pudrición de las flores, vainas y frutos de cacao, lo que conlleva pérdidas significativas a los agricultores. La moniliasis afecta gravemente a los cultivos de cacao y resulta difícil detectar su presencia tempranamente. Para lograr la detección de esta enfermedad, se recopilaron datos obtenidos de sensores y registros manuales para entrenar y validar un modelo predictivo mediante aprendizaje supervisado, en donde se analizó las condiciones ambientales y los síntomas de la enfermedad. Se aplicó la metodología de la ciencia del diseño basada en tres ciclos: el ciclo de relevancia, rigor y diseño. En el ciclo de relevancia se definió el problema y la necesidad del modelo, en el ciclo de rigor se realizó una investigación preliminar para determinar la viabilidad del objetivo y, por último, en el ciclo de diseño se modelaron los datos con algoritmos de aprendizaje automático y se implementó el modelo de predicción, probándolo para verificar su correcto funcionamiento. El modelo se compartió con las familias cacaoteras de Orellana, demostrando su eficacia. Esto permitirá a los agricultores tomar medidas de control adecuadas y oportunas para prevenir la propagación de la enfermedad y, por lo tanto, aumentar la producción y la calidad del cacao.

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.

The primary objective of this research was to enhance cocoa production and quality in tropical countries, such as Latin America and Africa, where cocoa cultivation plays a pivotal role in the economy of rural communities. The primary challenge addressed in this study was moniliasis, a fungal disease that affects cocoa fruits and leads to a significant decline in crop production and quality. A multidisciplinary approach was employed to tackle this issue, combining sensors, MongoDB Compass databases, Progressive Web Applications (PWAs), and predictive models. A research methodology incorporating predictive analysis techniques, particularly the logistic regression method, was utilized to achieve early detection and efficient management of moniliasis. Data collection instruments included sensors monitoring vital environmental factors like humidity and temperature alongside MongoDB Compass databases for storing and managing the gathered data. Furthermore, a PWA was developed for real-time data collection and analysis. The results of implementing this sensor-based tool in cocoa cultivation were highly effective. Early detection of moniliasis allowed for more precise preventive and corrective measures, resulting in a significant improvement in cocoa production and quality. These results were substantiated with concrete data demonstrating the tool's efficacy. Keywords: Data Prediction: Models and Applications; Efficient MongoDB Database Management; HighQuality Cocoa; Moniliasis: Treatment and Prevention; Progressive Web Apps (PWA): User Experience.

The management of municipal solid waste in intermediate cities exhibits high daily variability and source heterogeneity, which hinders operational sizing and material recovery. Reliable predictions are required from heterogeneous and often-scarce data. However, studies that compare multiple machine learning algorithms with temporal validation on short time series in intermediate cities are still limited. This study compares fourteen machine learning algorithms to predict the daily generation of organic and inorganic waste in La Joya de los Sachas, Ecuador, formulating the problem as a multi-output regression problem. An adapted CRISP-DM design was employed, using primary data from a waste characterization campaign, temporal feature engineering, variable encoding, and an expanding-window backtesting protocol against lag-7 persistence and ARIMA. Tree-based ensembles achieved the best performance. AdaBoost provided the best organic forecasts ($R^2$$=0.985$, $\mathrm{RMSE}$ $=0.081$, $\mathrm{MAE}$$=0.061$ in rate space), while Random Forest was best for inorganic ($R^2$$=0.965$, $\mathrm{RMSE}$ $=0.049$, $\mathrm{MAE}$$=0.040$). Linear models were stable but slightly inferior, and other approaches (SVR, KNN, MLP, Lasso, ElasticNet) showed lower generalization capacity. The study provides a multi-output regression protocol with temporal validation for municipal contexts with short time series, comparative evidence across fourteen algorithms, and a conversion from rates to kilograms for operational use.