Towards proactive food diaries

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. Dataset and PreprocessingWe performed our investigation on anonymised data obtained from bathroom scales and wearables of the Nokia Digital Health -Withings range, gathered using the Withings smartphone application.

show abstract

Towards proactive food diaries

Cited by 3 publications

References 6 publications

Identifying and Evaluating User Requirements for Smartphone Group Fitness Applications

Identifying and Evaluating User Requirements for Smartphone Group Fitness Applications

MW4HBI: Mobile and Wearable Human-Building Interactions with a Multi-Platform User Interface

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

Contact Info

Product

Resources

About