“…Specifically, our method uses a hyperspectral imaging (HSI) camera to obtain tissue oxygen saturation (StO2) data as a feature for detecting human stress. In our previous work [8], [9], we discussed a preliminary StO2-generating algorithm that lacked details and exhibited StO2 elevation in only one stressed participant, without statistical results. This pilot study reported, for the first time, that HSI could be a promising technique for remotely sensing human stress.…”
The detection of stress at early stages is beneficial to both individuals and communities. However, traditional stress detection methods that use physiological signals are contact-based and require sensors to be in contact with test subjects for measurement. In this paper, we present a method to detect psychological stress in a non-contact manner using a human physiological response. In particular, we utilize a hyperspectral imaging (HSI) technique to extract the tissue oxygen saturation (StO2) value as a physiological feature for stress detection. Our experimental results indicate that this new feature may be independent from perspiration and ambient temperature. Trier Social Stress Tests (TSSTs) on 21 volunteers demonstrated a significant difference (p < 0:005) and a large practical discrimination (d ¼ 1.37) between normalized baseline and stress StO2 levels. The accuracy for stress recognition from baseline using a binary classifier was 76.19 and 88.1 percent for the automatic and manual selections of the classifier threshold, respectively. These results suggest that the StO2 level could serve as a new modality to recognize stress at standoff distances.
“…Specifically, our method uses a hyperspectral imaging (HSI) camera to obtain tissue oxygen saturation (StO2) data as a feature for detecting human stress. In our previous work [8], [9], we discussed a preliminary StO2-generating algorithm that lacked details and exhibited StO2 elevation in only one stressed participant, without statistical results. This pilot study reported, for the first time, that HSI could be a promising technique for remotely sensing human stress.…”
The detection of stress at early stages is beneficial to both individuals and communities. However, traditional stress detection methods that use physiological signals are contact-based and require sensors to be in contact with test subjects for measurement. In this paper, we present a method to detect psychological stress in a non-contact manner using a human physiological response. In particular, we utilize a hyperspectral imaging (HSI) technique to extract the tissue oxygen saturation (StO2) value as a physiological feature for stress detection. Our experimental results indicate that this new feature may be independent from perspiration and ambient temperature. Trier Social Stress Tests (TSSTs) on 21 volunteers demonstrated a significant difference (p < 0:005) and a large practical discrimination (d ¼ 1.37) between normalized baseline and stress StO2 levels. The accuracy for stress recognition from baseline using a binary classifier was 76.19 and 88.1 percent for the automatic and manual selections of the classifier threshold, respectively. These results suggest that the StO2 level could serve as a new modality to recognize stress at standoff distances.
“…As the pressure increases, the generated piezoelectric voltage was linearly increased until it reached 1,000 kPa, and then it was saturated due to the maximum displacement of piezoelectric at that pressure 29 . It indicates that this pressure-induced EL light can be applicable to some applications in energy harvesting device as well as in remote stress sensor under a power-off situation 30 . Figure 5 Piezoelectric voltage versus the mechanical pressure ( V g −p ); the top inset is the voltage pulse waveform, and the bottom is the pressure-driven EL spectrum.…”
We demonstrated the tri-functional device based on all powder-processing methods by using ZnS powder as phosphor layer and piezoelectric material as dielectric layer. The fabricated device generated the electroluminescent (EL) light from phosphor and the sound from piezoelectric sheet under a supply of external electric power, and additionally harvested the reverse-piezoelectric energy to be converted into EL light. Under sinusoidal applied voltage, EL luminances were exponentially increased with a maximum luminous efficiency of 1.3 lm/W at 40 V and 1,000 Hz, and sound pressure levels (SPLs) were linearly increased. The EL luminances were linearly dependent on applied frequency while the SPLs showed the parabolic increase behavior below 1,000 Hz and then the flat response. The temperature dependence on EL luminances and SPLs was demonstrated; the former was drastically increased and the latter was slightly decreased with the increase of temperature. Finally, as an energy harvesting application, the piezoelectric-induced electroluminescence effect was demonstrated by applying only mechanical pressure to the device without any external electric power.
“…This technology combines traditional imaging and spectral technology and simultaneously acquires the spatial and spectral information of an object to determine its material characteristics [46][47][48][49]. Our research is the first to apply multispectral imaging (MSI) technology to assess the stress state [50][51][52][53][54][55]. We realize that the StO2 is a sensitive and important information in stress recognition [51][52] [53].…”
Section: Literature Reviewmentioning
confidence: 99%
“…Our research is the first to apply multispectral imaging (MSI) technology to assess the stress state [50][51][52][53][54][55]. We realize that the StO2 is a sensitive and important information in stress recognition [51][52] [53].…”
Section: Literature Reviewmentioning
confidence: 99%
“…To address these problems, we developed an emotion recognition algorithm called spatial-spectral-temporal adjustment convolutional neural network (SACNN) based on nose tissue oxygen saturation (StO2) information and multispectral signals. We applied MSI to determine the stress state in the past few years and discovered that StO2 is a sensitive and important parameter for stress assessment [50][51][52][53][54][55]. We believe that multiple emotion recognition features can be identified through spectral vision and StO2 signals.…”
An emotion recognition method based on multispectral imaging technology and tissue oxygen saturation (StO2) is proposed in this study. This method is called spatial-spectral-temporal adjustment convolutional neural network (SACNN). First, we use the algorithm to extract the StO2 content of an emotionally sensitive nose area through real-time multispectral imaging technology. Compared with facial expression data, StO2 data are more objective and cannot be controlled and changed artificially. Second, we construct a clustering algorithm based on the emotional state by extracting the spectral, StO2, and spatial features of the nose image to obtain accurate signals of emotionally sensitive areas. To utilize the correlation between spectral and spatial signals, we propose an adjustment-based CNN module, which reorganizes the relationship between all previous layers of the feature map, thereby making the relationship among layers close and highly quantitative. The features extracted through this method are consistent with spatial-spectral features. Third, we incorporate the extracted temporal feature signal into the long short-term memory module and finally complete the correlation between the spatial-spectral-temporal features. Experimental results show that the accuracy of the SACNN algorithm in emotional recognition reaches 90%, and the proposed method is more competitive than state-of-the-art approaches. To the best of our knowledge, this study is the first to use time-series StO2 signals for emotion recognition. INDEX TERMS Multispectral imaging, oxygen saturation, spatial-spectral-temporal adjustment convolutional neural network. I.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
