Measuring vital signs can reveal the state of body functioning and help to detect a health problem. In the state-of-the-art, numerous methods and devices are available for measuring vital signs. However, with the advent of artificial intelligence, new methods have been proposed that employ this technology. This paper aims to highlight the recent methods and devices based on artificial intelligence and novel techniques for measuring vital signs and processing algorithms. We analyzed 122 papers and classified them into six categories: (i) body temperature, (ii) blood oxygen saturation, (iii) heart rate monitoring, (iv) respiratory rate, (v) blood pressure, and (vi) simultaneous vital sign measurements. The Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA) methodology was used for the search and selection of scientific papers. The criteria to guide the scope of the review were defined with the Population, Intervention, Comparison, Outcomes, and Context (PICOC) methodology. The review highlighted significant efforts to develop and implement contactless, non-invasive devices for continuous monitoring outside clinical environments. It also revealed clear pathways for integrating AI at different stages of measurement and signal processing methods.

Because of the increased prevalence of chronic diseases, older adults frequently take many medications. However, adhering to a medication treatment tends to be difficult. The lack of medication adherence can cause health problems or even patient death. This paper describes the methodology used in developing a mobile augmented reality (MAR) pill box. The proposal supports patients in adhering to their medication treatment. First, we explain the design and construction of the automatic pill box, which includes alarms and uses QR codes recognized by the MAR system to provide medication information. Then, we explain the development of the MAR system. We conducted a preliminary survey with 30 participants to assess the feasibility of the MAR app. One hundred older adults participated in the survey. After one week of using the proposal, each patient answered a survey regarding the proposal functionality. The results revealed that 88% of the participants strongly agree and 11% agree that the app is a support in adhering to medical treatment. Finally, we conducted a study to compare the time elapsed between the scheduled time for taking the medication and the time it was actually consumed. The results from 189 records showed that using the proposal, 63.5% of the patients take medication with a maximum delay of 4.5 min. The results also showed that the alarm always sounded at the scheduled time and that the QR code displayed always corresponded to the medication that had to be consumed.

Este trabajo presenta un sistema capaz de realizar una clasificación binaria (buena y podrida) de manzanas red delicious, lo cual se logra mediante el uso del Índice de Vegetación de Diferencia Normalizada (NDVI) y una Red Neural Xception. Para ello, se utiliza una cámara multiespectral para observar detalles fuera del alcance del ojo humano, reduciendo la presencia de errores durante su clasificación. La selección del NDVI es resultado de su comparación con los índices de vegetación GNDVI, GVI, NDRE, NDVIR, NG, NGRDI y RVI, aplicados a un banco de imágenes obtenido mediante la cámara multiespectral. Además, se muestran los resultados de la clasificación al utilizar redes neuronales Xception, ResNet y MobileNet, lo que justifica el uso de la red Xception. Finalmente se describe la instrumentación e iluminación empleada en un prototipo que emula el proceso de clasificación real utilizando una banda transportadora, lo que permite validar de forma experimental el sistema de clasificación propuesto, obteniéndose un 73 % de éxito en la clasificación en línea. El desarrollo de este trabajo se basa en la siguiente metodología: Se utiliza una cámara multiespectral para la creación de una base de datos, las imágenes obtenidas pasan a una etapa de procesamiento conformada por la alineación y reconstrucción RGB. Posteriormente, se utilizan dos o más bandas para el cálculo, comparación y análisis de diferentes índices de vegetación. Una vez determinado el índice de vegetación a utilizar, se procede al entrenamiento y comparativa entre distintas arquitecturas de redes neuronales. Respecto a la etapa de entrenamiento, se emplea transferencia de aprendizaje para reducir la necesidad de una gran base de datos. Por último, se realizan pruebas experimentales para validar el comportamiento