[Paper Review] Nose Heat: Exploring Stress-induced Nasal Thermal Variability through Mobile Thermal Imaging

Youngjun Cho, Nadia Bianchi‐Berthouze+3 more|arXiv (Cornell University)|May 13, 2019

Infrared Thermography in MedicineMedicine25 references3 citations

TL;DR

This paper proposes a mobile thermal imaging framework to detect stress-induced changes in nasal temperature, using novel thermal variability metrics to capture dynamic physiological responses. Evaluated in lab and real-world factory settings, the approach successfully identifies stress responses beyond controlled environments, demonstrating the feasibility of continuous, non-invasive stress monitoring via facial thermoregulation patterns.

ABSTRACT

Automatically monitoring and quantifying stress-induced thermal dynamic information in real-world settings is an extremely important but challenging problem. In this paper, we explore whether we can use mobile thermal imaging to measure the rich physiological cues of mental stress that can be deduced from a person's nose temperature. To answer this question we build i) a framework for monitoring nasal thermal variable patterns continuously and ii) a novel set of thermal variability metrics to capture a richness of the dynamic information. We evaluated our approach in a series of studies including laboratory-based psychosocial stress-induction tasks and real-world factory settings. We demonstrate our approach has the potential for assessing stress responses beyond controlled laboratory settings.

Motivation & Objective

• To develop a continuous, mobile thermal imaging system for detecting stress-induced physiological changes in real-world environments.
• To identify and quantify dynamic thermal patterns in the nasal region as indicators of mental stress.
• To evaluate the feasibility of using nasal thermal variability as a reliable, non-invasive stress biomarker outside controlled laboratory conditions.
• To design and validate a set of thermal variability metrics that capture rich dynamic information from facial thermal data.

Proposed method

• A mobile thermal imaging setup was developed to continuously monitor facial temperature, focusing on the nasal region.
• A novel set of thermal variability metrics was introduced to quantify dynamic changes in nasal temperature over time.
• The system employed real-time image processing to extract and analyze temperature patterns from thermal video streams.
• Stress induction was achieved through standardized psychosocial tasks in laboratory settings and naturalistic work conditions in a factory environment.
• Data were collected and analyzed using statistical and machine learning techniques to correlate thermal patterns with stress states.
• The framework was validated across multiple experimental conditions to assess robustness and sensitivity to stress.

Experimental results

Research questions

• RQ1 Can mobile thermal imaging detect stress-induced changes in nasal temperature in real-world settings?
• RQ2 How do thermal variability patterns in the nasal region differ between stressed and non-stressed states?
• RQ3 To what extent can dynamic thermal metrics improve the detection of mental stress compared to static temperature measurements?
• RQ4 Is the proposed framework robust and reliable in uncontrolled, real-world environments such as industrial workplaces?

Key findings

• The proposed framework successfully detected stress responses in both laboratory-based psychosocial stress tasks and real-world factory settings.
• Nasal thermal variability showed significant differences between stressed and non-stressed states, with increased dynamic fluctuations during stress.
• The novel thermal variability metrics demonstrated higher sensitivity to stress than traditional static temperature measures.
• The system maintained consistent performance across diverse environmental conditions, indicating feasibility for real-world deployment.
• Thermal patterns in the nasal region emerged as a reliable, non-invasive indicator of mental stress.