Deep learning and 5G and beyond for child drowning prevention in swimming pools
| Autor: | Mari Carmen Domingo, Juan Carlos Cepeda Pacheco |
|---|---|
| Přispěvatelé: | Universitat Politècnica de Catalunya. Doctorat en Enginyeria Telemàtica, Universitat Politècnica de Catalunya. Departament d'Enginyeria Telemàtica, Universitat Politècnica de Catalunya. BAMPLA - Disseny i Avaluació de Xarxes i Serveis de Banda Ampla |
| Jazyk: | angličtina |
| Rok vydání: | 2022 |
| Předmět: |
Parents
Drowning Enginyeria de la telecomunicació::Telemàtica i xarxes d'ordinadors [Àrees temàtiques de la UPC] Infant 5G and beyond Deep learning Biochemistry Atomic and Molecular Physics and Optics Analytical Chemistry Network slicing architecture Deep Learning Swimming Pools Caregivers Child drowning prevention Child Preschool deep learning child drowning prevention network slicing architecture Humans Electrical and Electronic Engineering Child Instrumentation Swimming Aprenentatge profund |
| Zdroj: | Sensors; Volume 22; Issue 19; Pages: 7684 |
| Popis: | Drowning is a major health issue worldwide. The World Health Organization’s global report on drowning states that the highest rates of drowning deaths occur among children aged 1–4 years, followed by children aged 5–9 years. Young children can drown silently in as little as 25 s, even in the shallow end or in a baby pool. The report also identifies that the main risk factor for children drowning is the lack of or inadequate supervision. Therefore, in this paper, we propose a novel 5G and beyond child drowning prevention system based on deep learning that detects and classifies distractions of inattentive parents or caregivers and alerts them to focus on active child supervision in swimming pools. In this proposal, we have generated our own dataset, which consists of images of parents/caregivers watching the children or being distracted. The proposed model can successfully perform a seven-class classification with very high accuracies (98%, 94%, and 90% for each model, respectively). ResNet-50, compared with the other models, performs better classifications for most classes. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|