Facial Skin Temperature Research Articles

Predicting Sleep Quality through Biofeedback: A Machine Learning Approach Using Heart Rate Variability and Skin Temperature.

Sleep quality (SQ) is a crucial aspect of overall health. Poor sleep quality may cause cognitive impairment, mood disturbances, and an increased risk of chronic diseases. Therefore, assessing sleep quality helps identify individuals at risk and develop effective interventions. SQ has been demonstrated to affect heart rate variability (HRV) and skin temperature even during wakefulness. In this perspective, using wearables and contactless technologies to continuously monitor HR and skin temperature is highly suited for assessing objective SQ. However, studies modeling the relationship linking HRV and skin temperature metrics evaluated during wakefulness to predict SQ are lacking. This study aims to develop machine learning models based on HRV and skin temperature that estimate SQ as assessed by the Pittsburgh Sleep Quality Index (PSQI). HRV was measured with a wearable sensor, and facial skin temperature was measured by infrared thermal imaging. Classification models based on unimodal and multimodal HRV and skin temperature were developed. A Support Vector Machine applied to multimodal HRV and skin temperature delivered the best classification accuracy, 83.4%. This study can pave the way for the employment of wearable and contactless technologies to monitor SQ for ergonomic applications. The proposed method significantly advances the field by achieving a higher classification accuracy than existing state-of-the-art methods. Our multimodal approach leverages the synergistic effects of HRV and skin temperature metrics, thus providing a more comprehensive assessment of SQ. Quantitative performance indicators, such as the 83.4% classification accuracy, underscore the robustness and potential of our method in accurately predicting sleep quality using non-intrusive measurements taken during wakefulness.

Overall and local environmental collaborative control based on personal comfort model and personal comfort system

Most methods for creating an indoor thermal environment are based on controlling heating, ventilation, and air conditioning (HVAC) systems and do not consider the various needs of individuals in a multiperson space. Personal comfort systems (PCS) and personal comfort models (PCM) are popular technologies for achieving personal thermal comfort. This paper presents a thermal environmental collaborative control system (TECCS) that regulates environments at different spatial scales by leveraging the advantages of the HVAC system, PCS, PCM, and PCM-based automatic control to address the issue of individual differences in thermal demand in multiperson environments. The TECCS predicts thermal sensation votes (TSV) by combining facial skin temperature data obtained by an infrared sensor with environmental parameters. Subsequently, it performs the corresponding PCS control and adjusts the air conditioner according to the operating state of the PCS. This study proposes a collaborative control strategy with PCS at the core, enabling communication between thermal state recognition, HVAC system, and PCS. Twenty-eight adult males participated in the experiments testing the TECCS's performance. The results indicate that the TECCS can automatically regulate environments at different spatial scales based on thermal sensation prediction and that the operating state of the PCS can effectively guide air conditioning operations. Compared with constant setpoint control, the TECCS offers the advantage of improving thermal comfort. This paper also proposes future optimization directions based on the research results, focusing on recognition, equipment, and control.

Effect of subjective health conditions on facial skin temperature distribution: a 1-year statistical analysis among four participants

Effect of subjective health conditions on facial skin temperature distribution: a 1-year statistical analysis among four participants

Exploring the correlation and synchronicity between environmental factors and occupant thermal response in dynamic outdoor cabin environments

To improve the cabin thermal environment and explore advanced automotive air-conditioning control methods, it is essential to understand the key factors affecting occupant thermal response as well as the synchronicity of the thermal response to environmental changes in outdoor conditions. Given the current gaps in research, this study conducted outdoor experiments in summer to analyze the correlation and synchronicity between the cabin thermal environment and occupant thermal sensation as well as facial skin temperature. Results showed that, during the cooling phases of experiments with high initial cabin air temperatures, occupant thermal sensation improved significantly within 7 min. After 15 min, facial skin temperature and thermal sensation reached quasi-steady states. Thermal sensation was primarily influenced by air temperature, followed by solar radiation, and exhibited significant synchronicity with changes in these factors. When the air temperature stabilized at around 26 °C, every 200 W/m2 of solar radiation exposure increased the thermal sensation unit during the 40-min experiment period. Cheek and nose skin temperatures were significantly correlated with air temperature and solar radiation, and were sensitive to environmental changes, synchronizing with changes in air temperature and relative humidity. Further analysis showed the feasibility of using cheek and nose skin temperatures to characterize the occupant thermal sensation in a cabin. Additionally, this study found sex differences in the occupant thermal response in a cabin. The results provide insight into the key optimization parameters for comfort-oriented cabin thermal environment design and offer support for future air conditioning control in cabins based on thermal imaging.

Digital thermography complements Laser Speckle Contrast Imaging for the diagnosis of quantified severe mesenteric traction syndrome — A prospective cohort study

IntroductionThe diagnosis of severe mesenteric traction syndrome (MTS) is based on assessing the developed degree of facial flushing. Only one validated objective diagnostic method, Laser Speckle Contrast Imaging (LSCI), exists. However, this method is sensitive to distance, motion, and angulation. Digital thermography is known to correlate well with LSCI without the same limitations, but has never been tested in relation to MTS. This study aimed to examine the thermographic changes during the development of severe MTS and to calculate a cut-off value for identifying severe MTS. MethodsA prospective cohort study was performed on patients planned for open esophagectomy and pancreatic surgery from March 2021 to April 2022. All patients underwent continuous measurement on their forehead using LSCI and digital thermography during the first hour of surgery. The validated LSCI cut-off value was used to grade the severity of MTS. Blood samples and hemodynamics were collected at predefined time points. ResultsFifty-seven patients were included. Patients developing severe MTS had increased facial skin temperature 15 min (p = 0.002) and 30 min into surgery (p < 0.001). A cut-off value for identifying severe MTS using thermography was identified (35.55 °C, p < 0.001). Patients identified as developing severe MTS using this cut-off value had a higher level of prostacyclin (p = 0.001) and lower systemic vascular resistance (p < 0.001) 15 min into surgery, as compared with patients not developing severe MTS. ConclusionThis study shows that digital thermography may complement LSCI in the objective identification of severe MTS.

Analysis of spatial distribution characteristics of facial skin temperature on stress coping

Analysis of spatial distribution characteristics of facial skin temperature on stress coping

Combining protection with skin health: In vivo studies of an innovative gelatin/tannic acid-based hydrogel patch to prevent PPE-related skin lesions

The prolonged use of Personal Protective Equipment (PPE) can lead to skin problems due to persistent pressure, friction, and tension. This issue has prompted the exploration of solutions to protect the skin while maintaining the effectiveness of the PPE. This study aimed to evaluate the in vivo effectiveness of a gelatin/tannic acid-based hydrogel patch positioned beneath a mask to alleviate skin damage resulting from mask-wearing. To understand the pressure exerted by PPE, in vitro tests were conducted to measure the tensile strength of three types of facial masks. The FFP2 masks exhibited the highest tensile strength and were selected for subsequent in vivo biometric investigations. Biometric parameters were evaluated using the Flir E50bx® thermographic camera, Corneometer®, MoistureMap®, Sebumeter®, Tewameter®, and VISIA® systems. The results showed that when the hydrogel patch was used under the mask, there were no significant differences in facial skin temperature, sebum levels, or TEWL values (p > 0.05). However, a statistically significant increase in skin hydration and a decrease in frontal redness (p < 0.05) were observed. Consumer acceptance was assessed through sensory analysis questionnaires. In summary, the observed attenuation of physiological changes in the facial area and the positive consumer feedback suggest that this polymeric film-forming system is a simple yet effective solution to prevent PPE use-related skin issues.

Characteristics of facial electromyography during cold exposure and feasibility of evaluating thermal comfort

A comfortable building environment plays a vital role in enhancing both the physical and mental well-being of its occupants. In recent years, the assessment of building thermal environments has gained significant attention. The assessment methodology is shifting from subjective evaluations to more physiological assessments. However, the exploration of facial muscles in this context has remained largely uncharted territory. The primary objective of this research was to investigate the characteristics of facial electromyography (fEMG) in a cold environment and examine its potential for assessing thermal comfort. The experiment was divided into two parts. The first part focused on understanding fEMG characteristics in the time domain, frequency domain, and phase during activities like speaking, expressing emotions, and exposure to cold conditions. The second part aimed to study the recovery process of fEMG after cold exposure, achieved by increasing clothing insulation and raising air temperature. The findings revealed significant distinctions in fEMG characteristics when subjects engaged in speaking (notably in the low-frequency component of the anguli oris muscle), expressing emotions (with a prominent low-frequency component in the zygomatic muscle), or experiencing cold conditions (highlighted by the high-frequency component of the masseter muscle). Interestingly, augmenting clothing insulation in the body region posed challenges in improving facial muscle electrical activity, while raising air temperature effectively alleviated facial muscle tension. This study represents the pioneering application of fEMG in indoor thermal comfort evaluation. It offers a physiological foundation for assessing thermal comfort based on facial skin temperature and facial expressions. Furthermore, the research contributes valuable data that can support the advancement of wearable devices and smart building systems.

Potential use of an extended-distance thermal imaging camera for the assessment of thermal comfort in multi-occupant spaces

Thermographic cameras integrated with artificial intelligence (AI) models have recently become widespread to assess thermal comfort via extracted facial skin temperature. The study aimed to examine the potential use of camera-extracted facial skin temperature to predict thermal sensation for a group of people. To deal with the limitations of previous works, this study extended the camera-subject distance, enabling the detection of multiple faces facing different orientations. Thermal sensation and thermographic data were collected from 32 subjects under transient conditions, where the air temperature gradually changed between 21 °C and 29 °C. The relationship between their subjective votes and extracted skin temperatures across five facial regions and the whole face was analyzed. Using analysis of variance, results showed that the facial skin temperatures at each sensation scale were significant differences and provided a good prediction for the 3-point thermal sensation scale. The right cheek temperature was the most potential predictor of human thermal sensation, while the forehead temperature was less accurate due to noise interference. The proposed method is cost-effective and acceptably assesses thermal comfort for multi-occupant spaces.

The optimization of sparse modeling for drowsiness estimation based on general facial skin temperature distribution

The optimization of sparse modeling for drowsiness estimation based on general facial skin temperature distribution

Airflow rates and breathlessness recovery from submaximal exercise in healthy adults: prospective, randomised, cross-over study

ObjectivesFacial airflow from a hand-held fan may reduce breathlessness severity and hasten postexertion recovery. Data from randomised controlled trials are limited and the optimal airflow speed remains unknown. We aimed...

The influencing factors and an error correction method of the use of infrared thermography in human facial skin temperature

This study analyzed the influencing factors of the thermal infrared imager's measurement of facial skin temperature based on infrared radiation theory, temperature measurement principle, and a proposed simplified operation range estimation method. Climate-controlled experiments were carried out to determine the influencing factors further. The experiments include nine temperature levels (12, 15, 18, 21, 24, 26, 28, 30, and 32 °C), three target-object distances (1,2 and 3 m), and two view angles (0° and 38.7°). A total of 866 valid samples from 40 participants were collected. The results revealed that the factors influencing operation range are the specifications of the infrared camera and human body height. The main factors impacting measurement are the measured skin temperature, the surrounding air temperature and the position between the camera and the human. Among them, the measured skin and air temperatures contributed 54.3% and 26.7% to the measurement difference. Compared to the distance, the influencing degree of the angle is more prominent. Considering these factors, we proposed an error correction method. The correction results show that the mean difference is −0.01 °C (95% confidence interval is −0.19 to 0.17 °C) with the 95% limits of agreement (LoA) within ±0.53 °C, which significantly reduces the original measurement difference with the mean difference of −0.58 °C (95%LoA: ±1.31 °C). The results of this study provide a theoretical basis for providing high-quality facial skin temperature data when subsequent thermal infrared imagers are used in the human body.

GNN-Based Embedded Framework for Consumer Affect Recognition Using Thermal Facial ROIs

Recently consumer electronics products for the human device or machine interaction in smart healthcare systems have been widespread due to progress in health monitoring hardware and remote diagnostic services. Affect recognition through thermal facial signatures is significant in real-time Human-machine Interaction (HMI) studies. The distribution of facial skin temperature displays explicit characteristics related to affect arousal. During human interacts with a machine or computer, it is challenging to detect face and track the facial regions of interest (ROI) in a thermal video because of head motion artifacts. Our proposed embedded portable HMI product integrated with the required hardware and deep learning architecture is used to recognize the human affect in real-time. The transfer learning approach (Faster R-CNN) and the Multiple Instance Learning (MIL) algorithm are applied to thermal video for thermal face and ROIs detection and tracking. The multivariate time series (MTS) features generated from specific ROIs' calculated mean intensity variations. This study proposes a k-Nearest Neighbor (k-NN) algorithm-based graph neural network (GNN) architecture that utilizes MTS features to recognize affects in the facial thermal video. The effectiveness of the proposed algorithm for the In-house and NVIE thermal data-set gives better accuracy of 76.05% and 71.91% compared with state-of-the-art approaches.

Thermal stress, hydration, and salivary and respiratory stress markers in curling players performing a match in the cold.

Curling is a target-based team sport played in a cold environment. The type of stress curling players face during a curling match remains to be determined. In the present study, 16 Japanese curling players performed a practice curling match (six ends lasting 90 min), wherein the following variables were documented: core and skin temperatures, heart rate, thermal sensation and comfort, urine-specific gravity, body fluid loss, salivary cortisol, α-amylase activity, salivary secretory immunoglobulin A (SIgA), and fractionated exhaled nitric oxide (FeNO, a respiratory stress marker). Pre-match resting core temperature was 37.24 ± 0.31°C, which increased up to 37.73 ± 0.41°C during the match (p < 0.001). Facial skin temperatures decreased after the match (all p ≤ 0.015), whereas finger skin temperatures remained unchanged (p ≥ 0.375). Thermal discomfort increased following the match but thermal sensation remained unchanged. Following the match, players lost 0.29 ± 0.15 L body fluid (sweat, respiratory evaporation, and urine), which was nearly compensated by fluid ingestion of 0.22 ± 0.13 L (p = 0.119). Nevertheless, urine-specific gravity increased from 1.021 ± 0.010 to 1.024 ± 0.008 after the match (p = 0.012), with 31% and 50% players being dehydrated at pre- and post-match, respectively. Salivary cortisol decreased (p < 0.001) after the match without changes in salivary SIgA, α-amylase activity, and FeNO (all p ≥ 0.113). Therefore, during a curling match, the core temperature and thermal discomfort increase, whereas the face skin temperature decreases. Additionally, players may undergo dehydration before the match, which could be exacerbated after the match.

A thermal comfort evaluation model based on facial skin temperature

This study realized a Fisher discriminant analysis method for thermal comfort evaluation based on facial skin temperature. These models directly determine whether an individual is in a neutral state through neutral facial skin temperature thresholds and have physiological significance. The implementation of the models was based on climate-controlled experimental data. The air temperatures considered included 12, 15, 18, 21, and 24 °C (winter) and 24, 26, 28, 30, and 32 °C (summer). During the experiments, the thermal sensation votes of 40 participants were documented using subjective questionnaires, and facial skin temperatures were continuously measured using high-precision corrected iButtons. The results show that the highest precision of the evaluation model was 80%, and the corresponding false-negative rate (FNR) was 27%. The neutral facial skin temperature ranges were higher during summer than during winter. After 15 min of exposure, the models exhibited higher reliability. The average skin temperature from multiple facial parts was more suitable for evaluating neutral thermal sensations than that from a single facial part. The average skin temperature of the nose, cheeks, and chin is the most appropriate index for future applications of infrared thermal imaging. To a certain extent, the models were further improved by sex. Considering air-conditioning energy conservation, this study provides expanded evaluation models. The recommended average skin temperature exhibited a higher evaluation performance: the highest precision was 86%, and the FNR was 19%. These results provide a theoretical basis for the future use of the facial skin temperature as a feedback signal for air conditioners.

A novel method based on thermal image to predict the personal thermal comfort in the vehicle

A passenger-centered Heating, Ventilation, and Air Conditioning (HVAC) system is an urgent need with the innovative development of intelligent vehicles. A prerequisite for such a system is precise real-time estimation of human thermal comfort. This paper introduces a new method based on deep learning to predict the personal thermal comfort in the vehicle via facial thermal image. Specifically, a deep learning-based ResNet34 coupled with a spatial attention mechanism (SAM-ResNet34) is designed for feature extraction from the facial thermal image. Unlike the existing methods, this method extracts the gray features from the different areas of facial thermal images instead of measuring the facial skin temperature to predict the thermal comfort states. The thermal comfort data were collected from the experiment with 22 subjects. It has highlighted that the model trained with the thermal image dataset can achieve an accuracy as high as 93.75% in the test set. The result suggests that the non-invasive method proposed in this study could accurately predict personal thermal comfort in the vehicular environment and holds great potential to be applied to the HVAC control system of a vehicle in the future.

Facial skin temperature and overall thermal sensation of sub-tropically acclimated Chinese subjects in summer

This study explored the facial skin temperature and thermal sensation of sub-tropically acclimated subjects in summer. We conducted a summer experiment that simulated the common indoor temperatures in Changsha, China. Twenty healthy subjects experienced five exposure conditions: 24, 26, 28, 30 and 32 °C with a relative humidity of 60%. During exposure (140min), the sitting participants documented their thermal sensation, comfort and acceptability of the environment. Their facial skin temperatures were continuously and automatically recorded by using iButtons. These facial parts include the forehead, nose, left and right ears, left and right cheeks and chin. The results found that the maximum facial skin temperature difference increased with air temperature reduction. The forehead skin temperature was the highest. Nose skin temperature is lowest when air temperature is not higher than 26 °C during summer. Correlation analysis confirmed that the nose is the potential facial part that is most suitable to evaluate thermal sensation. Based on the published winter experiment, we further explored their seasonal effects. The seasonal analysis showed that, compared with winter, thermal sensation is more sensitive to indoor temperature changes and facial skin temperatures were less susceptible to thermal sensation changes in summer. Facial skin temperatures were higher in summer under the same thermal conditions. It suggests that seasonal effects should be considered when facial skin temperature can be used as an important parameter for indoor environment control in the future through monitoring thermal sensation.

Attempt to extract features and classify subjective poor physical conditions in facial images using deep metric learning.

With the spread of COVID-19, the need for remote detection of physical conditions is increasing, for example, there are several situations wherein the body temperature has to be measured remotely to detect febrile individuals. Aiming to remotely detect physical conditions, the study attempted to investigate anomaly detection based on facial color and skin temperature, which are indicators related to hemodynamics. Triplet loss was used to extract features related to subjective health feelings from facial images to evaluate whether there is a relationship between subjective health feelings and facial images. A classification of subjective health feelings related to poor physical conditions based on these features was also attempted. To obtain the data, an experiment was conducted for approximately 1 year to measure facial visual and thermal images, and subjective feelings related to physical conditions. Anomaly levels were defined based on subjective health feelings. Anomaly detection models were constructed by classifying anomaly and normal data based on subjective health feelings. Facial visible and thermal images were applied to the trained model to quantitatively evaluate the accuracy of the classification of anomaly conditions related to subjective health. At higher levels of anomaly, a combination of facial visible and thermal images resulted in the classification of subjective health feelings with moderate accuracy. Further, the results suggest that the eyes and sides of the nose may indicate subjective health feelings.

Prolonged Use of Surgical Masks and Respirators Affects the Protection and Comfort for Healthcare Workers.

This study explored the ideal period for wearing masks to prevent the physiological and psychological problems associated with long-term face mask use during respiratory infections by healthcare workers. Breathing simulators, surgical masks (SM) and medical respirators (PM) were prepared for two to eight hours. Changes in the comfort of masks (facial skin temperature, breathing resistance, and moisture permeability) and protection (filtration efficiency, resistance to blood penetration, and colony count) were assessed. The results demonstrated that the masks offered efficient liquid-particle filtering even after eight hours of use. However, the number of bacterial colonies using PM and SM grew significantly after two and four hours, respectively. Concerning comfort, the inspiratory resistance of masks rose dramatically after two hours, whereas the moisture permeability declined considerably after four hours. In addition, skin temperature had a significant increase within two hours, which may result in facial discomfort. When conditions permitted, the hospital staff was instructed to replace their masks every two hours.

Feature analysis for drowsiness detection based on facial skin temperature using variational autoencoder : a preliminary study

ABSTRACT Technology to detect signs of drowsiness in drivers is essential even in the age of automated driving to prevent traffic accidents. In this study, facial skin temperature, which can be measured remotely using infrared thermography, as a measure for determining drowsiness was in focus. Facial skin temperature is an autonomic nervous system index that depends on skin blood flow. It is known that facial skin temperature changes depending on the physiological and psychological state, and that it is affected by drowsiness. We focused on an anomaly detection algorithm called the variational autoencoder (VAE). In this study, a model to detect drowsiness was constructed using VAE with only the facial skin temperature during arousal from sleep and search was made for facial areas where skin temperature fluctuates with drowsiness using the model. As a result, it was found that the side of the nasal dorsum may fluctuate with drowsiness and that facial skin temperature may fluctuate asymmetrically with drowsiness. Skin temperature around the orbit was shown to be an area of possible physiological and psychological significance related to autonomic nervous system activity. Based on the above, the degree of anomaly was confirmed to vary depending on the degree of drowsiness, indicating the usefulness of using VAE for drowsiness detection based on facial skin temperature.