RESUMEN
Background: Indoor CO2 concentration is an important metric of indoor air quality (IAQ). The dynamic temporal pattern of CO2 levels in intensive care units (ICUs), where healthcare providers experience high cognitive load and occupant numbers are frequently changing, has not been comprehensively characterized. Objective: We attempted to describe the dynamic change in CO2 levels in the ICU using an Internet of Things-based (IoT-based) monitoring system. Specifically, given that the COVID-19 pandemic makes hospital visitation restrictions necessary worldwide, this study aimed to appraise the impact of visitation restrictions on CO2 levels in the ICU. Methods: Since February 2020, an IoT-based intelligent indoor environment monitoring system has been implemented in a 24-bed university hospital ICU, which is symmetrically divided into areas A and B. One sensor was placed at the workstation of each area for continuous monitoring. The data of CO2 and other pollutants (e.g., PM2.5) measured under standard and restricted visitation policies during the COVID-19 pandemic were retrieved for analysis. Additionally, the CO2 levels were compared between workdays and non-working days and between areas A and B. Results: The median CO2 level (interquartile range [IQR]) was 616 (524-682) ppm, and only 979 (0.34%) data points obtained in area A during standard visitation were ≥ 1,000 ppm. The CO2 concentrations were significantly lower during restricted visitation (median [IQR]: 576 [556-596] ppm) than during standard visitation (628 [602-663] ppm; p < 0.001). The PM2.5 concentrations were significantly lower during restricted visitation (median [IQR]: 1 [0-1] µg/m3) than during standard visitation (2 [1-3] µg/m3; p < 0.001). The daily CO2 and PM2.5 levels were relatively low at night and elevated as the occupant number increased during clinical handover and visitation. The CO2 concentrations were significantly higher in area A (median [IQR]: 681 [653-712] ppm) than in area B (524 [504-547] ppm; p < 0.001). The CO2 concentrations were significantly lower on non-working days (median [IQR]: 606 [587-671] ppm) than on workdays (583 [573-600] ppm; p < 0.001). Conclusion: Our study suggests that visitation restrictions during the COVID-19 pandemic may affect CO2 levels in the ICU. Implantation of the IoT-based IAQ sensing network system may facilitate the monitoring of indoor CO2 levels.
RESUMEN
This research combines the application of artificial intelligence in the production equipment fault monitoring of aerospace components. It detects three-phase current abnormalities in large hot-pressing furnaces through smart meters and provides early preventive maintenance. Different anomalies are classified, and a suitable monitoring process algorithm is proposed to improve the overall monitoring quality, accuracy, and stability by applying AI. We also designed a system to present the heater's power consumption and the hot-pressing furnace's fan and visualize the process. Combining artificial intelligence with the experience and technology of professional technicians and researchers to detect and proactively grasp the health of the hot-pressing furnace equipment improves the shortcomings of previous expert systems, achieves long-term stability, and reduces costs. The complete algorithm introduces a model corresponding to the actual production environment, with the best model result being XGBoost with an accuracy of 0.97.
