Automatic Recognition of Food Ingestion Environment from the AIM-2 Wearable Sensor

TL;DR

This paper presents a neural network approach with a two-stage training framework for recognizing food ingestion environments using wearable sensors, achieving high accuracy despite data imbalance.

Contribution

It introduces a novel two-stage training framework combining fine-tuning and transfer learning for ingestion environment recognition.

Findings

Achieved 96.63% classification accuracy on the UA Free Living Study dataset.

Effectively addressed data imbalance issues in ingestion environment recognition.

Validated the approach on a new egocentric wearable sensor dataset.

Abstract

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%.