Browsing by Subject "Wearable devices"

Now showing 1 - 3 of 3
  • Thumbnail Image
    Publication
    Open Access
    AI and wearable sensors in Higher Education to investigate Public Speaking Skills
    (Universidad de Murcia, Servicio de Publicaciones, 2026-01-01) Gratani, Francesca; Capolla, Lorenza Maria; Dafoulas, Georgios; Tsiakara, Ariadni; Kapetanakis, Stelios; Nalli, Giacomo; Giannandrea, Lorella; Sin departamento asociado
    La capacidad de comunicarse eficazmente con el público se considera una habilidad esencial para el avance profesional. Sin embargo, la literatura científica muestra que los trastornos de ansiedad se encuentran entre los trastornos mentales más comunes que padecen los oradores públicos. El presente estudio involucra a estudiantes universitarios de dos contextos y países diferentes y examina su ansiedad al hablar en público mediante el cruce de datos sobre autopercepciones cognitivas, reacciones fisiológicas (frecuencia cardíaca) y aspectos conductuales (expresiones faciales y movimientos corporales). También explora el potencial de los dispositivos portátiles y la inteligencia artificial en la recopilación y el análisis de datos para identificar diferentes perfiles de estudiantes según sus niveles de estrés y ansiedad al hablar en público. El análisis cruzado mostró una buena consistencia y reveló diferencias interesantes entre las dos muestras, incluyendo grupos relacionados con el estrés y estados emocionales. Los datos obtenidos animan a seguir investigando las variables asociadas con la oratoria y las habilidades oratorias. Los desarrollos futuros podrían explorar la contribución potencial de estas herramientas para ayudar a los profesores a diseñar una formación personalizada eficaz y discutir los resultados con los estudiantes para promover la conciencia de sus debilidades y fortalezas.
  • Thumbnail Image
    Publication
    Open Access
    Feature selection for blood glucose level prediction in type 1 Diabetes Mellitus by using the Sequential Input Selection Algorithm (SISAL)
    (MDPI, 2019-09-14) Rodríguez Rodríguez, Ignacio ; Rodríguez, José Víctor; González Vidal, Aurora; Zamora Izquierdo, Miguel Ángel; Ingeniería de la Información y las Comunicaciones; Facultades de la UMU::Facultad de Informática
    Feature selection is a primary exercise to tackle any forecasting task. Machine learning algorithms used to predict any variable can improve their performance by lessening their computational effort with a proper dataset. Anticipating future glycemia in type 1 diabetes mellitus (DM1) patients provides a baseline in its management, and in this task, we need to carefully select data, especially now, when novel wearable devices offer more and more information. In this paper, a complete characterization of 25 diabetic people has been carried out, registering innovative variables like sleep, schedule, or heart rate in addition to other well-known ones like insulin, meal, and exercise. With this ground-breaking data compilation, we present a study of these features using the Sequential Input Selection Algorithm (SISAL), which is specially prepared for time series data. The results rank features according to their importance, regarding their relevance in blood glucose level prediction as well as indicating the most influential past values to be taken into account and distinguishing features with person-dependent behavior from others with a common performance in any patient. These ideas can be used as strategies to select data for predicting glycemia depending on the availability of computational power, required speed, or required accuracy. In conclusion, this paper tries to analyze if there exists symmetry among the different features that can affect blood glucose levels, that is, if their behavior is symmetric in terms of influence in glycemia.
  • Thumbnail Image
    Publication
    Restricted
    Use of artificial intelligence supported wearable devices forelderly care: a scoping review.
    (Consejo de Enfermería de la Comunidad Valenciana, 2024-12) Pastor Zorita, Andrea; Pastor Seller, Enrique; Bote Díaz, Marcos Alonso; Manzano Nuñez, Ramiro; Enfermería
    Background: Wearable devices such as smart watches already collect and monitor our data on physical activity, sleep time, and even vital signs. One of the groups where this monitoring can be most useful are older people, firstly due to its growing weight in the population and secondly due to its greater fragility and vulnerability. Objective: The purpose of this review is to know the scope in the scientific literature in relation to the use and impact of portable devices with artificial intelligence support in the care of elderly people. Methods: A scoping review was conducted on PubMed, including English articles published between 2017 and 2023, following Joanna Briggs Institute (JBI) guidelines and the Prisma ScR checklist. A narrative synthesis of the included articles was performed. Results: A total of 141 articles addressing the research topic were found, of which 25 met the inclusion criteria. The countries with the most publications are the United States (n=6) followed by Korea and Spain (n=4) each. The most investigated geriatric syndrome was falls (72%). None of the publications considered the ethical implications of using these devices. Only 2 papers were elaborated by nurses. Thirteen clinical trials reported high positive impacts, 10 studies reported minor positive impacts. Conclusions: Most studies demonstrate the effectiveness of this technology for monitoring and its usefulness in elderly care. Falls prevention and detection are the most researched areas, greater ethical analysis of the impact of these devices and nursing involving in research is necessary.