When you eat matters: Automatic Recognition of Eating Activities

Updated: Nov 12

Status: On-going

Study Level

Visiting researcher, postdoc, PhD, master, undergraduate, intern, exchange/visiting student



Overview

Chronic metabolic diseases such as diabetes are increasingly prevalent in modern society. While traditional interventions focus dominantly on the control of “what to eat”, a recent study on mice found that restricting the timing of eating prevents obesity and metabolic syndrome, suggesting a potential role of “when to eat” in metabolic regulation [1]. This gives hint to the development of new mobile health technologies that support the management and prevention of metabolic diseases such as diabetes by helping users to track and to adjust mealtime rhythm. However, it is often difficult for people to keep tracking the time of each meal from day to day —a phenomena known as tracking fatigue. This project aims to develop algorithms for automatic detection and modelling of mealtime rhythm based on bio-signals that can be readily measured with wearable devices such as activity trackers, continuous glucose monitoring sensors and hearables.


[1] A Chaix, T Lin, HD Le, et al. (2019) Time-restricted feeding prevents obesity and metabolic syndrome in mice lacking a circadian clock. Cell Metabolism 28:303-319.


Research activities

This research project may involve the following activities:

  • systematic literature reviews to identify the merits and demerits of existing meal-detection algorithms and systems

  • design data collection protocol and conduct longitudinal data collection experiment

  • retrieve and preprocess physiological data collected using a variety of wearable and mobile devices

  • design and evaluate new meal-detection algorithms and systems

  • model meal activity cycle

  • co-author research papers and give presentations in academic conferences

Outcomes

Upon conclusion of this research, you will gain:

  • experience in designing and conducting data collection experiments with human subjects

  • skills in data engineering and data science

  • expertise in activity recognition and mobile health

  • domain knowledge in glucose metabolism

  • skills in project management and technical communication.

Skills and experience

As the ideal candidate, you'll have a passion for improving health outcomes and a strong background in machine learning/signal processing and programming using Python or R.



Contributors

  • Ms. Lauriane Bertrand (exchange student from INP-ENSEEIHT, France)

  • Mr. Nathan Cleyet-Marrel (exchange student from INP-ENSEEIHT, France)

  • Dr. Mario Alberto Chapa-Martell (Silver Egg Technology, Japan)


Publications


Conferences proceedings


#mealDetection #circadianRhythm #activityRecognition #wearableComputing #mobileComputing #machineLearning #signalProcessing #smartwatches #continuousGlucoseMonitoring

© 2020 by Dr Zilu Liang.