Learning inverse kinematics in 3 degrees of freedom (3-DOF) robots usually requires manual intervention, which limits their autonomy. This research proposes to optimize this process using Machine Learning techniques, evaluating the performance of models trained with tabular (organized in tables) and visual (videos and images) data. A robotic arm that could trace a given letter in space was simulated. Cartesian coordinates and angular positions of the robot's joints were extracted to structure a dataset organized in tables (tabular data) and the videos corresponding to each writing task. With these datasets, the performance was compared on the one hand using tabular data with traditional Machine Learning algorithms such as Support Vector Machines (SVMs), Artificial Neural Networks (ANNs), Decision Tree (DTs), and Random Forest (RFs); on the other hand, with the videos with contemporary Machine Learning algorithms with convolutional neural networks of short and long temporal memory CNN-LSTM. The results show good predictability for most of the algorithms under study, with coefficients of determination that are very close to one. However, the CNN-LSTM trained with videos has less error than traditional Machine Learning algorithms and performs automatic feature extraction.

In the Latin American Pacific region, rivers are the primary transportation routes for isolated and non-interconnected areas; however, river transport relies heavily on fossil fuels, resulting in high operating costs, CO₂ emissions, and energy dependence. To address this challenge, this study proposes a methodology for the optimal sizing of renewable-based charging stations specifically adapted to the environmental and operational conditions of the Colombian Pacific coast. This research fills a critical gap in the literature by moving beyond urban-centric charging models and simplified theoretical assumptions, instead integrating real river navigation data with technical modeling of electric boat energy consumption. The methodology evaluates the technical, economic, and operational performance of photovoltaic and hybrid photovoltaic–hydrokinetic microgrids designed to ensure reliability under the region’s extreme resource seasonality and bimodal pluvial regime. Results indicate that while purely photovoltaic systems offer lower initial investment costs, hybrid configurations significantly enhance energy resilience by leveraging complementary renewable sources during periods of low solar irradiation. Crucially, the transition to electric propulsion reduces annual CO₂ emissions by more than 98%, mitigating approximately 3421 kg per vessel compared to conventional 20 HP gasoline engines. A comparative analysis shows that the 1.1 kW electric boat is a cost-effective solution, with a 1.76-year return on investment. In contrast, the 4 kW model offers operational performance comparable to conventional gasoline boats, with a 4.95-year payback. This study provides a foundational framework for sustainable mobility in high-vulnerability territories by adapting technological solutions to site-specific environmental realities.

Due to the growing energy demand and the eminent global warming, there is special interest in the prediction of irradiance based on the reflectance obtained from satellites such as NASA Landsat, since it allows to know where it is more efficient to place photovoltaic receivers. Although there are studies for obtaining regression models with alternative Kernel functions, their performance for classification models is unknown and it is here where this research focuses. The study couples alternative Kernel functions to the support vector machines (SVM) algorithm for classification problems, where the best configuration for these algorithms is explored to finally obtain a set of irradiance maps zoned by class.

This article presents a comparative analysis of automatic error classification in Python programming tasks involving loops, with a focus on machine learning approaches for identifying error types. Three experiments were conducted: the first evaluated traditional machine learning algorithms; the second explored alternative kernel functions in SVM and MLP algorithms; and the third involved two multi-input deep learning models. Following the CRISP-DM methodology, we compiled a dataset of 3000 looped programming tasks, each including a problem description in English, a Python solution, and a classification based on state errors formulated by Gries theory (initial S, final E, state transformation T, and their combinations, totaling seven labels). In preprocessing, the code was partitioned using its AST to align it with Gries states, and both the problem descriptions and code snippets were embedded with Bert, Code-bert, and Graph-code-bert. Ablations were performed to approximate the optimal solutions for each algorithm as closely as possible. The results showed that traditional machine learning algorithms achieved up to 90% accuracy and an MCC of 83%, while alternative kernels marginally improved performance but did not surpass that of traditional algorithms. Deep learning models (ANN-GCB) achieved the best balance, with 94% accuracy and 91% MCC, respectively, demonstrating their superiority for this classification task. The model was validated with external sources from different repositories, yielding an 85% success rate, and with a group of 138 students, achieving a 96.7% correct or partially correct classification rate.

This study presents a comparative evaluation of three Deep Learning (DL) models for the automatic classification of seismo-volcanic events from spectrographic representations. The models considered include an optimized Lightweight Convolutional Neural Network (LCNN) (TFK) and two Transfer Learning (TL) based architectures: RegNetX002 and EfficientNetB0. The evaluation is performed on an unbalanced multiclass dataset including Volcano-Tectonic (VT), Long Period (LP) and Very Long Period (VLP) event signals, using stratified partitions for training, validation and testing. Different Batch Sizes (BS) are analyzed, observing that EfficientNetB0 achieves superior results in metrics such as Accuracy, Recall, F1-Score and Accuracy, while TFK stands out for its high competitiveness with less complexity in its architecture. The learning curves show stable convergence in all three models; EfficientNetB0 and RegNetX002 show minimal validation loss and no overfitting. Although TFK exhibits higher variance, it exceeds 98% accuracy in the validation phase. An adversarial test based on label perturbation is incorporated in order to assess the generalizability of the models. Results indicate that all approaches maintain robust performance even under moderate noise and unbalance conditions, supporting their applicability as efficient solutions for real-time volcano monitoring systems.