Determining what food is consumed during a meal is a central research challenge of Automated Dietary Monitoring (ADM). During chewing, food breaks down and generates unique vibration signals which can be recorded with sensor-integrated wearables. Chewing vibration data usually contain rich information highly related to the food intake, thus can be used to infer the food categories.
Build machine learning models to classify food categories with chewing vibration data.
- Apply audio signal processing techniques.
- Apply machine learning algorithms to solve practical classification problems.
|Period||Winter term 2020/21|
|Presense time||Virtual seminar, working from remote|
|Useful knowledge||Machine learning, signal processing|
|Work distribution||100% programming|
|Med. Eng. designation||Advanced Context Recognition (ACR)|
|First meeting||online-introduction-vorbesprechung-of-summer-term-2020-seminars, on 4th November 2020 at 16:15|
|Registration||Via StudOn, obligatory after introduction|
Up-to-date literature recommendations are provided during the meetings.
Final presentation and final report.