This study aimed to enhance the real-time performance and accuracy of vigilance assessment by developing a hidden Markov model (HMM). Electrocardiogram (ECG) signals were collected and processed to remove noise and baseline drift. A group of 20 volunteers participated in the study. Their heart rate variability (HRV) was measured to train parameters of the modified hidden Markov model for a vigilance assessment. The data were collected to train the model using the Baum–Welch algorithm and to obtain the state transition probability matrix $\widehat{A}$ and the observation probability matrix $\widehat{B}$. Finally, the data of three volunteers with different transition patterns of mental state were selected randomly and the Viterbi algorithm was used to find the optimal state, which was compared with the actual state. The constructed vigilance assessment model had a high accuracy rate, and the accuracy rate of data prediction for these three volunteers exceeded 80%. Our approach can be used in wearable products to improve their vigilance level assessment functionality or in other fields that have key positions with high concentration requirements and monotonous repetitive work.

Purpose: Exposure to artificial light influences human performance, which is essential for maintaining healthy work and sleep. However, existing research has not explored the intrinsic links between sleep performance and human states over time under prebedtime light exposure interventions (LEIs). Methods: To investigate the time-dependent effects of altered prebedtime light exposure, four LEI groupings (#L1 - #L4) and a Time factor (D8, D9, and D10) were chosen for sleep experiments in enclosed spaces. Forty-eight young adults recruited were available for data analysis. Subjective alertness (SA), negative affect (NA), subjective sleep, and objective sleep were measured via the Karolinska Sleepiness Scale, Positive and Negative Affect Schedule, Next-day Self-assessment Sleep Quality, and joint assessment of wrist actigraphy and sleep diaries, respectively. Statistical analysis was used for the effects of light exposure on the human states (corresponding to the SA and NA) and sleep performance, while the process model helped construct the associations between the two. Results: The statistical effects revealed that the Time had a significant main effect on subjective sleep and changes in prebedtime alertness; the LEI had a significant main effect only on sleep onset latency (SOL). After undergoing altered prebedtime light exposure, the mean SA increased at prebedtime of D9 (p = 0.022) and D10 (p = 0.044); No significant effect on the NA was observed; Mean subjective sleep had a significant increase from D8 to D10. Moreover, five actigraphy-estimated sleep parameters were interrelated. In light of this, a chained pathway relationship was identified. The SOL played a mediating predictor between prebedtime state and objective sleep, which was linked to the awakening state through subjective sleep. Conclusion: Our study suggests that time-dependent effects of altered prebedtime light exposure on sleep performance are associated with human states at prebedtime and awakening, with implications for its prediction of sleep health.

In the field of psychology and cognition within closed cabins, noncontact vital sign detection holds significant potential as it can enhance the user’s experience by utilizing objective measurements to assess emotions, making the process more sustainable and easier to deploy. To evaluate the capability of noncontact methods for emotion recognition in closed spaces, such as submarines, this study proposes an emotion recognition method that employs a millimeter-wave radar to capture respiration signals and uses a machine-learning framework for emotion classification. Respiration signals were collected while the participants watched videos designed to elicit different emotions. An automatic sparse encoder was used to extract features from respiration signals, and two support vector machines were employed for emotion classification. The proposed method was experimentally validated using the FaceReader software, which is based on audiovisual signals, and achieved an emotion classification accuracy of 68.21%, indicating the feasibility and effectiveness of using respiration signals to recognize and assess the emotional states of individuals in closed cabins.

The sleep monitoring terminal display (SMTD) designated for sleep cabins provides data visualizations of sleep profiles, yet poses challenges concerning visually informed interfaces. Given the scarcity of research on the SMTD interface, this study aims to evaluate the influence of SMTD-related factors, including stimulus areas of interest (AOIs), user experiences and tasks, on user visual perceptions while interacting with the SMTD system. Eye-tracking experimental contexts drawn from authentic settings are used to examine how the SMTD interfaces affect visual perceptions under varying tasks. Forty valid samples were collected, and pupil sizes (PSs), task performances, satisfaction, and usability were statistically compared and evaluated. The findings indicated that tasks had no significant effects, but user experiences and stimuli AOIs had significant main effects on PSs. In addition, task completion time ratio and tracking ratio between the two tasks varied; physical demand exceeded mental demand in task 1, whereas it was the opposite in task 2. The effectiveness of post-optimized interfaces was additionally substantiated through combining subjective ratings and objective metrics. The SMTD study provides novel insights for digital interface development and helps enhance users’ integrated visual perception.