Karina Gutiérrez-Fragoso

Objective: To develop a communication system for people with speech difficulties that allows them to express their needs by issuing instructions to the computer with minimal eye blinks, using a model created with MediaPipe and Deep Learning techniques. Theoretical Framework: The research is based on concepts of eye position tracking, convolutional networks and media pipe technology, with a focus on applying it to the communication needs of people with speech difficulties. Method: Qualitative and exploratory study, convolutional networks and media pipe techniques were used. To create the dataset, web scraping techniques were combined with manual image collection, the model was trained by comparing the performance of two CNN architectures. Results and Discussion: The incorporation of AI in the eye blink detection process is relatively recent, with more publications since 2020. It was found that the system is capable of processing facial gestures in real time with an average delay of 0.5 seconds, users reported improvements in their ability to communicate independently and reducing the effort their relatives had to make to interpret their needs, an accuracy of 94.5% was achieved in standard lighting conditions and 92% in variable conditions. Research Implications: The research reveals how AI with the incorporation of continuously emerging methods can improve the task of detecting images for eye tracking, obtaining increasingly better results in precision. Originality/Value: The application of emerging AI techniques in eye tracking to apply it in the development of a system that helps people with speech problems communicate.

The link between bipolar disorder (BP) and immune dysfunction remains controversial. While epidemiological studies have long suggested an association, recent research has found only limited evidence of such a relationship. To clarify this, we performed an exploratory study of the contributions of immune-relevant genetic factors to the response to lithium (Li) treatment and the clinical presentation of BP. First, we assessed the association of a large collection of immune-related genes (4925) with Li response, defined by the Retrospective Assessment of the Lithium Response Phenotype Scale (Alda scale), and clinical characteristics in patients with BP from the International Consortium on Lithium Genetics (ConLi⁺Gen, N = 2374). Second, we calculated here previously published polygenic scores (PGSs) for immune-related traits and evaluated their associations with Li response and clinical features. Overall, we observed relatively weak associations (p < 1 × 10⁻⁴) with BP phenotypes within immune-related genes. Network and functional enrichment analyses of the top findings from the association analyses of Li response variables showed an overrepresentation of pathways participating in cell adhesion and intercellular communication. These appeared to converge on the well-known Li-induced inhibition of GSK-3β. Association analyses of age-at-onset, number of mood episodes, and presence of psychosis, substance abuse and/or suicidal ideation suggested modest contributions of genes such as RTN4, XKR4, NRXN1, NRG1/3 and GRK5 to disease characteristics. PGS analyses returned weak associations (p < 0.05) between inflammation markers and the studied BP phenotypes. Our results suggest a modest relationship between immunity and clinical features in BP. More research is needed to assess the potential therapeutic relevance.

Background: The introduction of foods or fluids other than breast milk in the first few days after birth interferes with the establishment of breastfeeding. This study aimed to investigate the association of formula introduction during the first 3 days of life with maternal sociodemographic characteristics, hospital practices, and breastfeeding duration. Materials and Methods: Information from the National Survey of Demographic Dynamics, 2018, which includes 17,686 mother–baby pairs was analyzed. Mother–baby pairs were classified into categories according to breastfeeding duration: Results: In general, 3,720 (21%) mothers reported introducing formula during the first 3 days of life. A lower education level, lower sociodemographic stratum, living in a rural area, and considering oneself indigenous were factors associated with not introducing formula during the first 3 days of life. A total of 5,168 (29.2%) mother–baby pairs practiced breastfeeding for Discussion: Introducing formula during the first 3 days of life was associated with a shorter breastfeeding duration. BN analysis showed a probabilistic dependency between the type of delivery and variables associated with the establishment of breastfeeding.

La modernización del proceso educativo implica la automatización de las actividades académicas y administrativas que fomenten un entorno inteligente. Incorporar tecnologías emergentes en las instituciones educativas de nivel superior permitirá transitar hacia la conversión de procesos rutinarios para mejorar la calidad del servicio educativo. El presente trabajo consiste en automatizar la detección de alumnos que copian durante la aplicación de sus exámenes en las aulas utilizando técnicas de Deep Learning con redes neuronales convolucionales. Se obtuvo una precisión de un 95.75% en el modelo de clasificación después de experimentar con diferentes parámetros y arquitecturas de una red neuronal convolucional.

La Industria 4.0 está cambiando la producción global, y esto demanda que los futuros profesionistas conozcan y dominen las tecnologías habilitadoras de ésta. Es por ello que las universidades necesitan generar los mecanismos de enseñanza-aprendizaje para que los estudiantes adquieran habilidades que demandarán los nuevos puestos de trabajo y que les permitan ser competitivos. Los sistemas ciber-físicos son los grandes protagonistas de la Industria 4.0, éstos conjuntan muchas tecnologías, y cuentan con una infraestructura física que funciona al combinarse con una parte digital. En este trabajo se muestra el desarrollo de un sistema ciber-físico como medio de enseñanza-aprendizaje para propiciar que los estudiantes generen las capacidades requeridas por la Industria 4.0. La maqueta I4.0, mejora el proceso de ubicación e identificación de lugares en una institución, pero, por otra parte, permite al estudiante experimentar con tecnologías como computación en la nube, internet de las cosas y recorridos virtuales, de una manera práctica, modificando o agregando nueva funcionalidad a la maqueta. Finalmente, se describen un conjunto de prácticas, como una propuesta a utilizarse en el proceso de enseñanza por parte de los docentes, las cuales pueden permitir a los estudiantes asimilar los conceptos y tecnologías de Industria 4.0, a través del desarrollo de las mismas.

Efforts have been being made to improve the diagnostic performance of colposcopy, trying to help better diagnose cervical cancer, particularly in developing countries. However, improvements in a number of areas are still necessary, such as the time it takes to process the full digital image of the cervix, the performance of the computing systems used to identify different kinds of tissues, and biopsy sampling. In this paper, we explore three different, well-known automatic classification methods (k-Nearest Neighbors, Naïve Bayes, and C4.5), in addition to different data models that take full advantage of this information and improve the diagnostic performance of colposcopy based on acetowhite temporal patterns. Based on the ROC and PRC area scores, thek-Nearest Neighbors and discrete PLA representation performed better than other methods. The values of sensitivity, specificity, and accuracy reached using this method were 60% (95% CI 50–70), 79% (95% CI 71–86), and 70% (95% CI 60–80), respectively. The acetowhitening phenomenon is not exclusive to high-grade lesions, and we have found acetowhite temporal patterns of epithelial changes that are not precancerous lesions but that are similar to positive ones. These findings need to be considered when developing more robust computing systems in the future.