University of Twente Student Theses
Using accelerometer and gyroscope sensors to differentiate between eating movements associated with different foods
Tonchev, Viktor (2022) Using accelerometer and gyroscope sensors to differentiate between eating movements associated with different foods.
|
PDF
381kB |
| Abstract: | Dietary monitoring is a tool used to track and alter the eating habits of individuals, specifically those that are overweight or obese. Automated Dietary Monitoring (ADM) aims to automate this process, in order to make it more accurate and efficient. Existing ADM systems have used various sensors worn on the body to detect eating events, such as gestures, chewing and swallowing, via machine learning algorithms. This research set up an experiment, where an IMU (Inertial Measurement Unit) with accelerometer and gyroscope sensors was worn on the wrist and participants consumed 7 different types of foods. The data from the experiment was used to train classification algorithms using machine learning in an attempt to differentiate individual foods based on the movements recorded by the sensors. The models are effective at recognizing when food is being eat, but the results suggest that they are not sufficient on their own to recognize the food itself. |
| Item Type: | Essay (Bachelor) |
| Faculty: | EEMCS: Electrical Engineering, Mathematics and Computer Science |
| Subject: | 54 computer science |
| Programme: | Computer Science BSc (56964) |
| Link to this item: | https://purl.utwente.nl/essays/91713 |
| Export this item as: | BibTeX EndNote HTML Citation Reference Manager |
Show download statistics for this publication
Show download statistics for this publicationRepository Staff Only: item control page