Simulating Personal Food Consumption Patterns using a Modified Markov Chain

TL;DR

This paper introduces a novel framework that uses a modified Markov chain and self-supervised learning to simulate personal food consumption patterns, improving data generation for personalized food image classification.

Contribution

The paper presents a new method combining a modified Markov chain with self-supervised learning to generate realistic personal food consumption data from limited initial data.

Findings

The method closely correlates simulated data with initial data patterns.

It outperforms random simulation and original Markov chain methods.

Effective evaluation metrics demonstrate the model's accuracy.

Abstract

Food image classification serves as the foundation of image-based dietary assessment to predict food categories. Since there are many different food classes in real life, conventional models cannot achieve sufficiently high accuracy. Personalized classifiers aim to largely improve the accuracy of food image classification for each individual. However, a lack of public personal food consumption data proves to be a challenge for training such models. To address this issue, we propose a novel framework to simulate personal food consumption data patterns, leveraging the use of a modified Markov chain model and self-supervised learning. Our method is capable of creating an accurate future data pattern from a limited amount of initial data, and our simulated data patterns can be closely correlated with the initial data pattern. Furthermore, we use Dynamic Time Warping distance and Kullback-Leibler divergence as metrics to evaluate the effectiveness of our method on the public Food-101 dataset. Our experimental results demonstrate promising performance compared with random simulation and the original Markov chain method.