ADF: An Anomaly Detection Framework for Large-Scale PM2.5 Sensing Systems

Chen, Ling-Jyh; Ho, Yen-Hung; Hsieh, Hsin-Hung; Huang, Shih‐Ting; Lee, Hu-Cheng; Mahajan, Sachit

doi:10.1109/jiot.2017.2766085

Cited by 104 publications

(54 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In contrast, a low negative value of r t ( s i ) suggests that z t ( s i ) is comparatively lower. Different from the work of Chen et al (), we do not need to specify a specific neighborhood range because it is automatically taken care of by the proposed kriging method.…”

Section: Methodologiesmentioning

confidence: 99%

Real‐time PM_2.5 mapping and anomaly detection from AirBoxes in Taiwan

et al. 2018

View full text Add to dashboard Cite

Fine particulate matter (PM2.5) has gained increasing attention due to its adverse health effects to human. In Taiwan, it was conventionally monitored by large environmental monitoring stations of the Environmental Protection Administration. However, only a small number of 77 monitoring stations are currently established. Recently, a project using a large number of small devices, called AirBoxes, was launched in March 2016 to monitor PM2.5 concentrations. Although thousands of AirBoxes have been deployed across Taiwan to give a broader coverage, they are mostly located in big cities and their measurements are less accurate. In this paper, we apply a robust kriging method that provides a smoothly varied real‐time PM2.5 concentration map and its associated standard error map. In addition, we develop a novel spatio‐temporal control chart that monitors anomalous measurements by utilizing neighboring AirBox information. Our method automatically adapts to different neighboring structures at different AirBox locations without the need to specify a neighborhood range. The proposed method has abilities to detect potential emission sources, malfunctioned AirBoxes, and AirBoxes that are wrongly put indoors.

show abstract

Section: Methodologiesmentioning

confidence: 99%

Real‐time PM_2.5 mapping and anomaly detection from AirBoxes in Taiwan

et al. 2018

View full text Add to dashboard Cite

show abstract

“…However, we included the large PM2.5 data if it was an inclining or declining pattern within 5 min. From the raw data with 10 s intervals, if less than 5 missing values were detected in an interval of less than 5 min, we applied the linear regression-based interpolation method and substitute the missing values with expected values obtained from models [10,18,19]. If the missing value interval was longer than 5 min, we excluded them.…”

Section: Pm25 Data Preprocessingmentioning

confidence: 99%

Assessment of Daily Personal PM2.5 Exposure Level According to Four Major Activities among Children

2019

View full text Add to dashboard Cite

Particulate matters less than 2.5 micrometers in diameter (PM2.5), whose concentration has increased in Korea, has a considerable impact on health. From a risk management point of view, there has been interest in understanding the variations in real-time PM2.5 concentrations per activity in different microenvironments. We analyzed personal monitoring data collected from 15 children aged 6 to 11 years engaged in different activities such as commuting in a car, visiting a commercial building, attending an education institute, and resting inside home from October 2018 to March 2019. The fraction of daily mean exposure duration per activity was 72.7 ± 18.7% for resting inside home, 27.2 ± 14.4% for attending an education institute, and 11.5 ± 9.6% and 5.3 ± 5.9% for visiting a commercial building, commuting in a car, respectively. Daily median (interquartile range) PM2.5 exposure amount was 88.9 (55.9–159.7) μg in houses and that in education buildings was 43.3 (22.9–55.6) μg. Real-time PM2.5 exposure levels varied by person and time of day (p-value < 0.05). This study demonstrated that our real-time personal monitoring and data analysis methodologies were effective in detecting polluted microenvironments and provided a potential person-specific management strategy to reduce a person’s exposure level to PM2.5.

show abstract

“…The IoT devices provide real-time PM2.5 data, temperature and humidity levels for different regions. The data collection was a continuous process and any anomaly in that process was directly reported to the administrator [ 22 ]. The collected data were stored in the database and easily accessible.…”

Section: System Overviewmentioning

confidence: 99%

Short-Term PM2.5 Forecasting Using Exponential Smoothing Method: A Comparative Analysis

Mahajan

Chen

Tsai

2018

Sensors

Self Cite

View full text Add to dashboard Cite

Air pollution is a global problem and can be perceived as a modern-day curse. One way of dealing with it is by finding economical ways to monitor and forecast air quality. Accurately monitoring and forecasting fine particulate matter (PM2.5) concentrations is a challenging prediction task but Internet of Things (IoT) can help in developing economical and agile ways to design such systems. In this paper, we use a historical data-based approach to perform PM2.5 forecasting. A forecasting method is developed which uses exponential smoothing with drift. Experiments and evaluation were performed using the real-time PM2.5 data obtained from large scale deployment of IoT devices in Taichung region in Taiwan. We used the data from 132 monitoring stations to evaluate our model’s performance. A comparison of prediction accuracy and computation time between the proposed model and three widely used forecasting models was done. The results suggest that our method can perform PM2.5 forecast for 132 monitoring stations with error as low as 0.16 μg/normalm3 and also with an acceptable computation time of 30 s. Further evaluation was done by forecasting PM2.5 for next 3 h. The results show that 90 % of the monitoring stations have error under 1.5 μg/normalm3 which is significantly low.

show abstract

ADF: An Anomaly Detection Framework for Large-Scale PM2.5 Sensing Systems

Cited by 104 publications

References 24 publications

Real‐time PM_2.5 mapping and anomaly detection from AirBoxes in Taiwan

Real‐time PM_2.5 mapping and anomaly detection from AirBoxes in Taiwan

Assessment of Daily Personal PM2.5 Exposure Level According to Four Major Activities among Children

Short-Term PM2.5 Forecasting Using Exponential Smoothing Method: A Comparative Analysis

Contact Info

Product

Resources

About

ADF: An Anomaly Detection Framework for Large-Scale PM2.5 Sensing Systems

Cited by 104 publications

References 24 publications

Real‐time PM2.5 mapping and anomaly detection from AirBoxes in Taiwan

Real‐time PM2.5 mapping and anomaly detection from AirBoxes in Taiwan

Assessment of Daily Personal PM2.5 Exposure Level According to Four Major Activities among Children

Short-Term PM2.5 Forecasting Using Exponential Smoothing Method: A Comparative Analysis

Contact Info

Product

Resources

About

Real‐time PM_2.5 mapping and anomaly detection from AirBoxes in Taiwan

Real‐time PM_2.5 mapping and anomaly detection from AirBoxes in Taiwan