Prototype Smart Home Environment With Biofeedback

TL;DR

This paper introduces a prototype smart home system that uses physiological data to classify emotional arousal levels and actuate environmental responses, aiming to enhance comfort and assistive living.

Contribution

It presents a novel biofeedback-based smart home prototype with embedded subsystems for emotion detection and environment actuation, validated through experiments and modeling.

Findings

System classifies emotional arousal with 41% accuracy

FSM model is deterministic and robust to communication disruptions

Prototype demonstrates potential for emotion-driven environmental control

Abstract

In this paper we present a prototype of a smart home system which can actuate different peripherals based on the emotional "arousal" level of an user. The system is comprised of two embedded subsystems named "Wearable" and "Benchtop" which communicates with one another over UPD/IP protocol. The Wearable unit can differentiate the emotional arousal into three distinct classes (Normal, Medium and High) based on physiological data whilst the Benchtop unit can display different colors on a 16 digit NEOPIXEL ring and, play tones to emulate actuation of peripheral devices in the smart home environment. Experiments with three video clips were performed which showed that the system can classify emotional arousal with an average accuracy of 41%. An FSM model of the Benchtop unit was created using Ptolemy II which showed the model to be fully deterministic and robust to communication disruption between the two units. The proposed project will add a new paradigm in smart home and IoT research by incorporating emotional feedback to automatically adjust the indoor environment for greater comfort, ease of living and in-home assisted ambulatory care for the residents.