Examinando por Autor "Fuentes, P."

Mostrando 1 - 2 de 2
  • Miniatura
    Ítem
    A Novel Low-Cost Sensor Prototype for Nocturia Monitoring in Older People
    (Institute of Electrical and Electronics Engineers Inc., 2018-09) Taramasco, C.; Rodenas, T.; Martinez, F.; Fuentes, P.; Munoz, R.; Olivares, R.; Albuquerque, V.H.C.; Demongeot, J.
    Nocturia is frequently defined as the necessity to get out of bed at least one time during the night to urinate, with each of these episodes being preceded and continued by sleep. Several studies suggest that an increase of nocturia is seen with the onset of age, occurring in around 70% of adults over the age of 70. Its appearance is associated with detrimental quality of life for those who present nocturia, since it leads to daytime sleepiness, cognitive dysfunction, among others. Currently, a voiding diary is necessary for nocturia assessment; these are prone to bias due to their inherent subjectivity. In this paper, we present the design of a low-cost device that automatically detects micturition events. The device obtained 73% in sensibility and 81% in specificity; these results show that systems such as the proposed one can be a valuable tool for the medical team when evaluating nocturia. © 2013 IEEE.
  • Miniatura
    Ítem
    A novel monitoring system for fall detection in older people
    (2169-3536, 2018-07) Taramasco, C.; Rodenas, T.; Martinez, F.; Fuentes, P.; Munoz, R.; Olivares, R.; De Albuquerque, V.H.C.; Demongeot, J.
    Each year, more than 30% of people over 65 years-old suffer some fall. Unfortunately, this can generate physical and psychological damage, especially if they live alone and they are unable to get help. In this field, several studies have been performed aiming to alert potential falls of the older people by using different types of sensors and algorithms. In this paper, we present a novel non-invasive monitoring system for fall detection in older people who live alone. Our proposal is using very-low-resolution thermal sensors for classifying a fall and then alerting to the care staff. Also, we analyze the performance of three recurrent neural networks for fall detections: Long short-term memory (LSTM), gated recurrent unit, and Bi-LSTM. As many learning algorithms, we have performed a training phase using different test subjects. After several tests, we can observe that the Bi-LSTM approach overcome the others techniques reaching a 93% of accuracy in fall detection. We believe that the bidirectional way of the Bi-LSTM algorithm gives excellent results because the use of their data is influenced by prior and new information, which compares to LSTM and GRU. Information obtained using this system did not compromise the user's privacy, which constitutes an additional advantage of this alternative. © 2013 IEEE.