SensAI+Expanse Adaptation on Human Behaviour Towards Emotional Valence Prediction

TL;DR

This paper presents a distributed mobile-cloud system, SensAI+Expanse, that adaptively predicts human emotional valence efficiently and robustly, using various adaptive mechanisms and state-of-the-art machine learning algorithms.

Contribution

It introduces a novel adaptive mobile-cloud framework for emotional valence prediction that is resource-efficient, resilient, and capable of auto-adjusting its learning parameters.

Findings

Extreme Gradient Boosting achieved the best prediction performance.

The system demonstrated robustness to environmental and behavioral disruptions.

Energy-efficient prediction with explainability was confirmed.

Abstract

An agent, artificial or human, must be continuously adjusting its behaviour in order to thrive in a more or less demanding environment. An artificial agent with the ability to predict human emotional valence in a geospatial and temporal context requires proper adaptation to its mobile device environment with resource consumption strict restrictions (e.g., power from battery). The developed distributed system includes a mobile device embodied agent (SensAI) plus Cloud-expanded (Expanse) cognition and memory resources. The system is designed with several adaptive mechanisms in a best effort for the agent to cope with its interacting humans and to be resilient on collecting data for machine learning towards prediction. These mechanisms encompass homeostatic-like adjustments such as auto recovering from an unexpected failure in the mobile device, forgetting repeated data to save local memory, adjusting actions to a proper moment (e.g., notify only when human is interacting), and the Expanse complementary learning algorithms' parameters with auto adjustments. Regarding emotional valence prediction performance, results from a comparison study between state-of-the-art algorithms revealed Extreme Gradient Boosting on average the best model for prediction with efficient energy use, and explainable using feature importance inspection. Therefore, this work contributes with a smartphone sensing-based system, distributed in the Cloud, robust to unexpected behaviours from humans and the environment, able to predict emotional valence states with very good performance.