Marco Antonio Aguirre Lam

Polysaccharide-based films represent a sustainable alternative for the development of intelligent packaging systems capable of monitoring food quality through colorimetric changes. In this study, films formulated with chitosan, starch, glycerol, and Hibiscus sabdariffa extract were evaluated as potential freshness indicators for pork meat. The films were prepared using different extract concentrations and stored at 6 and 25 °C before and after contact with pork samples for 36 h. Their colorimetric response was quantified through digital image analysis using the RGB color model combined with the K-means clustering algorithm. The relationships among the experimental variables were investigated using descriptive statistics, Spearman correlation analysis, and feature relevance metrics, including Information Gain, Gain Ratio, and Analysis of Variance (ANOVA). The results demonstrated that polymer blend concentration was the most influential factor in differentiating film performance, whereas storage time and extract concentration significantly affected both the colorimetric response and pH values. Multivariable analysis revealed distinct patterns associated with film stability and the physicochemical changes induced by contact with pork meat during storage. These findings highlight the potential of integrating polysaccharide-based materials with data science approaches to support the design, optimization, and performance evaluation of intelligent packaging systems for real-time freshness monitoring of meat products. Beyond the specific application evaluated, the proposed methodology demonstrates how data science tools can support the objective assessment of intelligent biodegradable films, facilitating their future implementation in real-time food quality monitoring systems.

Introduction The integration of artificial intelligence (AI) in teledermatology presents significant diagnostic potential, yet the vulnerability of these models to real-world image degradation remains a major patient safety concern. This study investigates the accuracy discrepancy, where global metrics obscure severe sensitivity drops in melanoma detection under visual stress. Methods We evaluated two deep learning architectures, ResNet-50 and MobileNetV2, using the HAM10000 dataset. An experimental pipeline was developed using the Python programming language to simulate three clinical photographic artifacts: Gaussian noise, focal blur, and low luminance. The models were subjected to stress tests to observe shifts in diagnostic classification and evaluate their structural stability. Results While baseline global accuracy remained deceptively stable, targeted degradation exposed catastrophic failures. Under moderate degradation, ResNet-50 sensitivity collapsed to near-zero levels, erroneously classifying malignant lesions as benign nevi. MobileNetV2 exhibited similar structural vulnerabilities, proving that standard evaluation metrics fail to capture critical diagnostic risks. Conclusions Deep learning models in dermatology exhibit significant vulnerability to common image degradation, posing a direct threat to patient safety. The implementation of automated image quality gates is essential before deploying these algorithms in clinical settings to prevent AI-induced diagnostic errors.

The University Course Timetabling Problem is regarded as one of the most significant administrative activities in academic institutions. It is framed as a combinatorial optimisation problem involving the scheduling of courses, students, lecturers, and classrooms, making it extremely complex. This work presents an analytical study of the Timetabling Problem, including its classifications, techniques, advantages, disadvantages, and a case study based on the model implemented at the Instituto Tecnológico de Ciudad Madero.

La plantación de árboles en entornos urbanos es esencial para combatir los efectos del cambio climático y fomentar un desarrollo sostenible; sin embargo, la escasa supervivencia de los árboles plantados, debido a la falta de seguimiento y cuidado, constituye un desafío significativo. Para resolver esta problemática es necesario establecer mecanismos que permitan aumentar la tasa de supervivencia de los árboles plantados. En este artículo se propone un sistema de inventario forestal el cual utiliza tecnologías de la información para su funcionamiento, permitiendo la gestión y supervisión de árboles en proyectos de plantación urbana. El sistema implementa una clasificación ABCD que es adaptada al contexto forestal, la cual representa una extensión del método ABC tradicional al incorporar categorías para árboles en riesgo de supervivencia. Al integrar tecnologías móviles con técnicas de clasificación adaptadas al contexto forestal, el sistema propuesto representa una alternativa para la gestión de inventarios en reforestación urbana, esta tecnología está diseñada principalmente para jóvenes y comunidades educativas y promueve valores universales relacionados al cuidado del medio ambiente. El análisis y desarrollo realizados en este trabajo representan una herramienta potencial para el apoyo de políticas públicas, proyectos comunitarios y programas de reforestación urbana.

Ethyl 4-((11-(hexylamino)-11-oxoundecyl)oxy)benzoate was synthesized using 11-bromoundecanoic acid hexylamide and commercially available ethyl 4-hydroxybenzoate through a Williamson etherification synthesis. The structural characterization was performed using UV-Vis, FT-IR, ¹H-NMR, ¹³C-NMR, and HRMS.

In recent years, the amount of texts in natural language, in digital format, has had an impressive increase. To obtain useful information from a large volume of data, new specialized techniques and efficient algorithms are required. Text mining consists of extracting meaningful patterns from texts; one of the basic approaches is clustering. The most used clustering algorithm is k-means. This chapter proposes an improvement of the k-means algorithm in the convergence step; the process stops whenever the number of objects that change their assigned cluster in the current iteration is bigger than the ones that changed in the previous iteration. Experimental results showed a reduction in execution time up to 93%. It is remarkable that, in general, better results are obtained when the volume of the text increase, particularly in those texts within big data environments.