Cross-modal Recurrent Models for Weight Objective Prediction from Multimodal Time-series Data

TL;DR

This paper introduces a novel cross-modal LSTM architecture for predicting weight goal achievement from multimodal time-series data, demonstrating improved accuracy and efficiency over existing methods.

Contribution

The paper proposes a new cross-modal LSTM model with a hyperparameter optimization technique, enhancing prediction performance and parameter efficiency for multimodal weight management data.

Findings

X-LSTM outperforms baseline models in accuracy

Hyperparameter optimization significantly improves model performance

Model visualizations reveal insights into latent variables

Abstract

We analyse multimodal time-series data corresponding to weight, sleep and steps measurements. We focus on predicting whether a user will successfully achieve his/her weight objective. For this, we design several deep long short-term memory (LSTM) architectures, including a novel cross-modal LSTM (X-LSTM), and demonstrate their superiority over baseline approaches. The X-LSTM improves parameter efficiency by processing each modality separately and allowing for information flow between them by way of recurrent cross-connections. We present a general hyperparameter optimisation technique for X-LSTMs, which allows us to significantly improve on the LSTM and a prior state-of-the-art cross-modal approach, using a comparable number of parameters. Finally, we visualise the model's predictions, revealing implications about latent variables in this task.