Calibration of Portable Particulate Matter–Monitoring Device using Web Query and Machine Learning

BACKGROUND: Monitoring and control of PM(2.5) are being recognized as key to address health issues attributed to PM(2.5). Availability of low-cost PM(2.5) sensors made it possible to introduce a number of portable PM(2.5) monitors based on light scattering to the consumer market at an affordable price. Accuracy of light scattering–based PM(2.5) monitors significantly depends on the method of calibration. Static calibration curve is used as the most popular calibration method for low-cost PM(2.5) sensors particularly because of ease of application. Drawback in this approach is, however, the lack of accuracy.METHODS: This study discussed the calibration of a low-cost PM(2.5)-monitoring device (PMD) to improve the accuracy and reliability for practical use. The proposed method is based on construction of the PM(2.5) sensor network using Message Queuing Telemetry Transport (MQTT) protocol and web query of reference measurement data available at government-authorized PM monitoring station (GAMS) in the republic of Korea. Four machine learning (ML) algorithms such as support vector machine, k-nearest neighbors, random forest, and extreme gradient boosting were used as regression models to calibrate the PMD measurements of PM(2.5). Performance of each ML algorithm was evaluated using stratified K-fold cross-validation, and a linear regression model was used as a reference.RESULTS: Based on the performance of ML algorithms used, regression of the output of the PMD to PM(2.5) concentrations data available from the GAMS through web query was effective. The extreme gradient boosting algorithm showed the best performance with a mean coefficient of determination (R²) of 0.78 and standard error of 5.0 μg/m³, corresponding to 8% increase in R² and 12% decrease in root mean square error in comparison with the linear regression model. Minimum 100 hours of calibration period was found required to calibrate the PMD to its full capacity. Calibration method proposed poses a limitation on the location of the PMD being in the vicinity of the GAMS. As the number of the PMD participating in the sensor network increases, however, calibrated PMDs can be used as reference devices to nearby PMDs that require calibration, forming a calibration chain through MQTT protocol.CONCLUSIONS: Calibration of a low-cost PMD, which is based on construction of PM(2.5) sensor network using MQTT protocol and web query of reference measurement data available at a GAMS, significantly improves the accuracy and reliability of a PMD, thereby making practical use of the low-cost PMD possible.

Control of Industrial Safety Based on Dynamic Characteristics of a Safety Budget-Industrial Accident Rate Model in Republic of Korea

BACKGROUND: Despite the recent efforts to prevent industrial accidents in the Republic of Korea, the industrial accident rate has not improved much. Industrial safety policies and safety management are also known to be inefficient. This study focused on dynamic characteristics of industrial safety systems and their effects on safety performance in the Republic of Korea. Such dynamic characteristics are particularly important for restructuring of the industrial safety system. METHODS: The effects of damping and elastic characteristics of the industrial safety system model on safety performance were examined and feedback control performance was explained in view of cost and benefit. The implications on safety policies of restructuring the industrial safety system were also explored. RESULTS: A strong correlation between the safety budget and the industrial accident rate enabled modeling of an industrial safety system with these variables as the input and the output, respectively. A more effective and efficient industrial safety system could be realized by having weaker elastic characteristics and stronger damping characteristics in it. A substantial decrease in total social cost is expected as the industrial safety system is restructured accordingly. CONCLUSION: A simple feedback control with proportional–integral action is effective in prevention of industrial accidents. Securing a lower level of elastic industrial accident-driving energy appears to have dominant effects on the control performance compared with the damping effort to dissipate such energy. More attention needs to be directed towards physical and social feedbacks that have prolonged cumulative effects. Suggestions for further improvement of the safety system including physical and social feedbacks are also made.