Study Title
Thought on Food: A Systematic Review of Current Approaches and Challenges for Food Intake Detection
Principal Investigator
Paulo Alexandre Neves, João Simões, Ricardo Costa, Luís Pimenta, Norberto Jorge Gonçalves, Carlos Albuquerque, Carlos Cunha, Eftim Zdravevski, Petre Lameski, Nuno M. Garcia, Ivan Miguel Pires
Affiliation
Polytechnic Institute of Castelo Branco, Portugal; University of Trás-os-Montes e Alto Douro, Portugal; Health Sciences Research Unit, Nursing School of Coimbra, Portugal; University Ss Cyril and Methodius, North Macedonia; Instituto de Telecomunicações, Universidade da Beira Interior, Portugal
Start Date
Not specified
End Date
Not specified
Study Objective
To explore and review the various sensors and methods used for detecting food intake episodes, focusing on the challenges, technologies, and methodologies, particularly those involving machine learning techniques.
Short Abstract
This systematic review examines various technologies for food intake detection, such as cameras, microphones, inertial sensors, and electrogastrography. The paper investigates sensor types, their applications, and data processing methodologies, aiming to enhance automated food intake monitoring. The review identifies key challenges and research gaps in integrating food intake detection into daily life.
Study Design
Systematic review of studies using sensors and machine learning approaches for food intake detection
Population
Global studies related to food intake detection using sensors
Sample Size
30 studies included
Inclusion Criteria
- Studies using sensors for food intake detection
- Published between 2010 and 2021
- Studies involving wearable sensors and data processing methods like deep learning and machine learning
Exclusion Criteria
- Studies not focused on food intake detection
- Non-original research articles
Intervention/Exposure
Food intake detection technologies using various sensors and machine learning methods
Outcome Measures
- Effectiveness of sensors in detecting food intake
- Data processing methodologies
- Accuracy of food intake detection
Funding Source
Funded by FCT/MEC (Foundation for Science and Technology, Portugal), co-funded by FEDER-PT2020
Collaborating Institutions
Polytechnic Institute of Castelo Branco, University of Trás-os-Montes e Alto Douro, University Ss Cyril and Methodius, Instituto de Telecomunicações
Ethics Approval
Not applicable
Publication Status
Published in Sensors (2022)
Keywords
Food intake detection, biosensors, neural networks, image processing, nutrition, machine learning
Data Collection Methods
Systematic review and NLP-based search methodology across various databases, including PubMed, Springer, IEEE Xplore, MDPI, Elsevier
Primary Data Availability
Not applicable
Contact Information
Ivan Miguel Pires: