Automatic Recognition of Food Ingestion Environment from the AIM-2 Wearable Sensor
This work addresses the problem of dietary intake monitoring for health and nutrition applications, but it is incremental as it builds on existing neural network methods with a two-stage training framework.
The paper tackles the problem of automatically recognizing food ingestion environments from wearable sensor data, addressing challenges like data imbalance and perceptual aliasing, and achieves a promising overall classification accuracy of 96.63% on a newly collected dataset.
Detecting an ingestion environment is an important aspect of monitoring dietary intake. It provides insightful information for dietary assessment. However, it is a challenging problem where human-based reviewing can be tedious, and algorithm-based review suffers from data imbalance and perceptual aliasing problems. To address these issues, we propose a neural network-based method with a two-stage training framework that tactfully combines fine-tuning and transfer learning techniques. Our method is evaluated on a newly collected dataset called ``UA Free Living Study", which uses an egocentric wearable camera, AIM-2 sensor, to simulate food consumption in free-living conditions. The proposed training framework is applied to common neural network backbones, combined with approaches in the general imbalanced classification field. Experimental results on the collected dataset show that our proposed method for automatic ingestion environment recognition successfully addresses the challenging data imbalance problem in the dataset and achieves a promising overall classification accuracy of 96.63%.