Combining Deep Transfer Learning with Signal-image Encoding for Multi-Modal Mental Wellbeing Classification

TL;DR

This paper introduces a novel multi-modal emotion recognition framework combining image encoding of time series data, transfer learning, and CNNs, significantly improving wellbeing classification accuracy with limited data.

Contribution

It proposes a hybrid deep learning framework that encodes multimodal time series as images, leverages transfer learning, and combines models for enhanced emotion and stress recognition.

Findings

Achieved up to 98.5% accuracy in wellbeing classification.

Outperformed conventional CNNs by 4.5% in accuracy.

Demonstrated effectiveness of transfer learning from physical activity data.

Abstract

The quantification of emotional states is an important step to understanding wellbeing. Time series data from multiple modalities such as physiological and motion sensor data have proven to be integral for measuring and quantifying emotions. Monitoring emotional trajectories over long periods of time inherits some critical limitations in relation to the size of the training data. This shortcoming may hinder the development of reliable and accurate machine learning models. To address this problem, this paper proposes a framework to tackle the limitation in performing emotional state recognition on multiple multimodal datasets: 1) encoding multivariate time series data into coloured images; 2) leveraging pre-trained object recognition models to apply a Transfer Learning (TL) approach using the images from step 1; 3) utilising a 1D Convolutional Neural Network (CNN) to perform emotion classification from physiological data; 4) concatenating the pre-trained TL model with the 1D CNN. Furthermore, the possibility of performing TL to infer stress from physiological data is explored by initially training a 1D CNN using a large physical activity dataset and then applying the learned knowledge to the target dataset. We demonstrate that model performance when inferring real-world wellbeing rated on a 5-point Likert scale can be enhanced using our framework, resulting in up to 98.5% accuracy, outperforming a conventional CNN by 4.5%. Subject-independent models using the same approach resulted in an average of 72.3% accuracy (SD 0.038). The proposed CNN-TL-based methodology may overcome problems with small training datasets, thus improving on the performance of conventional deep learning methods.