Classifying Food Items During an Eating Occasion: A Machine Learning Approach with Slope Dynamics for Windowed Kinetic Data
Background: Wearable devices equipped with a range of sensors have emerged as promising tools for monitoring and improving individuals’ health and lifestyle. Objectives: Contribute to the investigation and development of effective and reliable methods for dietary monitoring based on raw kinetic data...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Foods |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2304-8158/14/2/276 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832588464312287232 |
|---|---|
| author | Ileana Baldi Corrado Lanera Mohammad Junayed Bhuyan Paola Berchialla Luca Vedovelli Dario Gregori |
| author_facet | Ileana Baldi Corrado Lanera Mohammad Junayed Bhuyan Paola Berchialla Luca Vedovelli Dario Gregori |
| author_sort | Ileana Baldi |
| collection | DOAJ |
| description | Background: Wearable devices equipped with a range of sensors have emerged as promising tools for monitoring and improving individuals’ health and lifestyle. Objectives: Contribute to the investigation and development of effective and reliable methods for dietary monitoring based on raw kinetic data generated by wearable devices. Methods: This study uses resources from the NOTION study. A total of 20 healthy subjects (9 women and 11 men, aged 20–31 years) were equipped with two commercial smartwatches during four eating occasions under semi-naturalistic conditions. All meals were video-recorded, and acceleration data were extracted and analyzed. Food recognition on these features was performed using random forest (RF) models with 5-fold cross-validation. The performance of the classifiers was expressed in out-of-bag sensitivity and specificity. Results: Acceleration along the x-axis and power show the highest and lowest rates of median variable importance, respectively. Increasing the window size from 1 to 5 s leads to a gain in performance for almost all food items. The RF classifier reaches the highest performance in identifying meatballs (89.4% sensitivity and 81.6% specificity) and the lowest in identifying sandwiches (74.6% sensitivity and 72.5% specificity). Conclusions: Monitoring food items using simple wristband-mounted wearable devices is feasible and accurate for some foods while unsatisfactory for others. Machine learning tools are necessary to deal with the complexity of signals gathered by the devices, and research is ongoing to improve accuracy further and work on large-scale and real-time implementation and testing. |
| format | Article |
| id | doaj-art-157c173af3bd493c93729ba6c518a3bf |
| institution | Kabale University |
| issn | 2304-8158 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Foods |
| spelling | doaj-art-157c173af3bd493c93729ba6c518a3bf2025-01-24T13:33:06ZengMDPI AGFoods2304-81582025-01-0114227610.3390/foods14020276Classifying Food Items During an Eating Occasion: A Machine Learning Approach with Slope Dynamics for Windowed Kinetic DataIleana Baldi0Corrado Lanera1Mohammad Junayed Bhuyan2Paola Berchialla3Luca Vedovelli4Dario Gregori5Unit of Biostatistics, Epidemiology and Public Health, Department of Cardiac, Thoracic, Vascular Sciences and Public Health, University of Padova, 35131 Padova, ItalyUnit of Biostatistics, Epidemiology and Public Health, Department of Cardiac, Thoracic, Vascular Sciences and Public Health, University of Padova, 35131 Padova, ItalyUnit of Biostatistics, Epidemiology and Public Health, Department of Cardiac, Thoracic, Vascular Sciences and Public Health, University of Padova, 35131 Padova, ItalyDepartment of Clinical and Biological Sciences, University of Torino, 10043 Orbassano, ItalyUnit of Biostatistics, Epidemiology and Public Health, Department of Cardiac, Thoracic, Vascular Sciences and Public Health, University of Padova, 35131 Padova, ItalyUnit of Biostatistics, Epidemiology and Public Health, Department of Cardiac, Thoracic, Vascular Sciences and Public Health, University of Padova, 35131 Padova, ItalyBackground: Wearable devices equipped with a range of sensors have emerged as promising tools for monitoring and improving individuals’ health and lifestyle. Objectives: Contribute to the investigation and development of effective and reliable methods for dietary monitoring based on raw kinetic data generated by wearable devices. Methods: This study uses resources from the NOTION study. A total of 20 healthy subjects (9 women and 11 men, aged 20–31 years) were equipped with two commercial smartwatches during four eating occasions under semi-naturalistic conditions. All meals were video-recorded, and acceleration data were extracted and analyzed. Food recognition on these features was performed using random forest (RF) models with 5-fold cross-validation. The performance of the classifiers was expressed in out-of-bag sensitivity and specificity. Results: Acceleration along the x-axis and power show the highest and lowest rates of median variable importance, respectively. Increasing the window size from 1 to 5 s leads to a gain in performance for almost all food items. The RF classifier reaches the highest performance in identifying meatballs (89.4% sensitivity and 81.6% specificity) and the lowest in identifying sandwiches (74.6% sensitivity and 72.5% specificity). Conclusions: Monitoring food items using simple wristband-mounted wearable devices is feasible and accurate for some foods while unsatisfactory for others. Machine learning tools are necessary to deal with the complexity of signals gathered by the devices, and research is ongoing to improve accuracy further and work on large-scale and real-time implementation and testing.https://www.mdpi.com/2304-8158/14/2/276wearable devicesdietary monitoringacceleration datakinetic datarandom forestfood recognition |
| spellingShingle | Ileana Baldi Corrado Lanera Mohammad Junayed Bhuyan Paola Berchialla Luca Vedovelli Dario Gregori Classifying Food Items During an Eating Occasion: A Machine Learning Approach with Slope Dynamics for Windowed Kinetic Data Foods wearable devices dietary monitoring acceleration data kinetic data random forest food recognition |
| title | Classifying Food Items During an Eating Occasion: A Machine Learning Approach with Slope Dynamics for Windowed Kinetic Data |
| title_full | Classifying Food Items During an Eating Occasion: A Machine Learning Approach with Slope Dynamics for Windowed Kinetic Data |
| title_fullStr | Classifying Food Items During an Eating Occasion: A Machine Learning Approach with Slope Dynamics for Windowed Kinetic Data |
| title_full_unstemmed | Classifying Food Items During an Eating Occasion: A Machine Learning Approach with Slope Dynamics for Windowed Kinetic Data |
| title_short | Classifying Food Items During an Eating Occasion: A Machine Learning Approach with Slope Dynamics for Windowed Kinetic Data |
| title_sort | classifying food items during an eating occasion a machine learning approach with slope dynamics for windowed kinetic data |
| topic | wearable devices dietary monitoring acceleration data kinetic data random forest food recognition |
| url | https://www.mdpi.com/2304-8158/14/2/276 |
| work_keys_str_mv | AT ileanabaldi classifyingfooditemsduringaneatingoccasionamachinelearningapproachwithslopedynamicsforwindowedkineticdata AT corradolanera classifyingfooditemsduringaneatingoccasionamachinelearningapproachwithslopedynamicsforwindowedkineticdata AT mohammadjunayedbhuyan classifyingfooditemsduringaneatingoccasionamachinelearningapproachwithslopedynamicsforwindowedkineticdata AT paolaberchialla classifyingfooditemsduringaneatingoccasionamachinelearningapproachwithslopedynamicsforwindowedkineticdata AT lucavedovelli classifyingfooditemsduringaneatingoccasionamachinelearningapproachwithslopedynamicsforwindowedkineticdata AT dariogregori classifyingfooditemsduringaneatingoccasionamachinelearningapproachwithslopedynamicsforwindowedkineticdata |