Ginna Viviana Leytón Yela

The Population-based Cancer Registry of the Municipality of Pasto (RPCMP) faces significant challenges in spatial data integrity due to the high variability, inconsistency, and ambiguity of manually collected addresses. Such limitations restrict the analytical capacity of the YACHAY-GIS platform to generate precise geospatial intelligence across multiscalar levels. To address these issues, this paper proposes a novel hybrid address normalization framework structured in two sequential stages. First, a specialized deterministic geocoding engine, optimized for local urban morphology, is utilized. Second, for highly non-standard records—characterized by “block and lot” (manzana y lote) nomenclatures—a workflow based on Large Language Models (LLMs) is integrated. To ensure computational efficiency in resource-constrained environments, a Supervised Fine-Tuning (SFT) process was implemented using the Low-Rank Adaptation (LoRA) technique across various open-source LLMs. Experimental results demonstrate that the workflow integrated with the Llama-3.2-3B-Instruct model achieved the highest performance, with a normalization accuracy of 99.40%. The end-to-end evaluation shows an increase in spatial recovery from a 33.02% baseline to 55.13%, effectively isolating the semantic gap from the underlying cartographic limitations of the region. This architecture provides a scalable data engineering model for oncological registries, with future work focused on integrating external spatial providers such as OpenStreetMap and Colombia’s Agustín Codazzi Geographic Institute (IGAC) to further enhance geographic coverage.

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.

Objetivo: Identificar los trabajos de investigación centrados en los MOOC K-12 o STEAM, enfocados en el potencial de los entornos de educación, remodelando el marco educativo actual en la educación secundaria. Metodología: Se definieron ecuaciones para realizar las búsquedas de articulos publicados en conferencias y revistas mediante bases de datos bibliográficas, que permitieron sustraer los articulos para construir el corpus de referencias. Posteriormente, se analizan y sintetizan las investigaciones más significativas para el desarrollo de la revisión sistemática. Resultados: Esta revisión permitió identificar las tendencias, desafíos y oportunidades sobre MOOC K-12 o STEAM, identificando las implementaciones de cursos de ciencias de computación o pensamiento computacional en educación secundaria. Este tipo de iniciativas han obtenido resultados positivos, puesto que se han incrementado el número de estudiantes que seleccionan la programación informática como eje fundamental en el examen nacional para educación superior. Conclusiones: Las investigaciones se han centrado en su mayoría en la incorporación de la programación con cursos complementarios ofertados de forma opcional en educación secundaria, con un enfoque combinado, es decir, se llevan a cabo clases tradicionales con el apoyo de los MOOC. La gran mayoría de los MOOC para educación secundaria se han implementado específicamente para satisfacer las necesidades de los docentes y estudiantes de educación secundaria, con el fin de mejorar y apoyar el plan de estudios, y motivar a los estudiantes como futuros miembros activos en la creación de tecnología.

At the time of establishing communications, the configuration of network resources, storage and computer systems worked independently. With the innovation and the new communication alternatives, the management was initiated so that all the parts mentioned above work together. This is how the idea of virtualization emerged, a process by which virtual versions of computers, operating systems and applications are created. For all network devices and servers to communicate with each other and function correctly there must be a centrally functioning controller, this is when a promising SDN paradigm emerges; networks defined by software considered as a promising method to rebuild the Internet architecture and improve the implementation and distribution of applications in communication networks. In addition, we will discuss how SDN networks perform their inclusion in optical networks, study these advanced architectures, in order to facilitate flexibility and resource optimization in optical transport.