Home // HEALTHINFO 2023, The Eighth International Conference on Informatics and Assistive Technologies for Health-Care, Medical Support and Wellbeing // View article
Authors:
Sandra Viciano-Tudela
Paula Navarro-Garcia
Lorena Parra
Sandra Sendra
Jaime Lloret
Keywords: RGB sensor; photoreceptors; Discriminant Analysis; Artificial Neural Network; Internet of Things
Abstract:
Dehydration poses health risks, leading to confusion, falls, and even death. Tracking water intake, especially among at-risk groups, is vital. Smart bottles with sensors offer a solution for estimating and monitoring fluid consumption efficiently and widely. The paper aims to enhance the existing liquid intake detection systems by developing an optical sensing element to differentiate various liquids for precise hydration assessment. The study evaluates data processing techniques, including classic statistics, Discriminant Analysis, and Artificial Neural Networks, to classify liquids. The system is based on an ESP32 node integrated into the smart bottle as an Internet of Things device with communication capabilities with other wearable devices. A total of 7 different liquids are included in the conducted experiments. The data-gathering process is repeated several times to generate training and verification datasets. The results indicate that it is possible to differentiate the liquids using a reduced number of light wavelengths, white and purple. All analyzed techniques offered good results. Discriminant Analysis is the most effective classification approach with 100% accuracy. Nevertheless, if distinguishing between different types of teas is not necessary, thresholds based on statistical tools can be employed using fewer computation resources.
Pages: 72 to 77
Copyright: Copyright (c) IARIA, 2023
Publication date: November 13, 2023
Published in: conference
ISSN: 2519-8491
ISBN: 978-1-68558-105-3
Location: Valencia, Spain
Dates: from November 13, 2023 to November 17, 2023