Guodong Li

Bio: Guodong Li is an academic researcher from Tsinghua University. The author has contributed to research in topics: Calibration (statistics) & Air quality index. The author has an hindex of 2, co-authored 3 publications receiving 4 citations.

RCH: robust calibration based on historical data for low-cost air quality sensor deployments

Abstract: Air pollution has become one of the major threats to human health. Conventional approaches for air pollution monitoring use precise professional devices, but cannot achieve dense deployment due to high cost. Therefore, systems consisting of low-cost sensors are applied as a supplement to obtain fine-grained pollution information. In order to maintain the accuracy of these low-cost sensors, it is essential to calibrate them to minimize the impact from sensor drifts. Existing field calibration methods utilize the real-time data from spatially-adjacent official air quality stations as reference. However, the real-time reference is not always accessible under existing station deployment. In this paper, we propose the Robust Calibration approach using Historical data (RCH) for low-cost air quality sensors. Our method corrects the sensor drift by adapting sensitivity and offset based on pollutant's concentration distribution. Experiments on NO2 data from real-world deployment in Foshan, China show that RCH has the similar performance compared with existing field calibration methods using real-time and spatially-adjacent references. It demonstrates that RCH can improve the accuracy and consistency of low-cost air quality sensors without the help of real-time and nearby reference data.

Poster Abstract: Robust Calibration for Low-Cost Air Quality Sensors using Historical Data

Abstract: As pollution problems become increasingly prominent nowadays, urban air quality monitoring has attracted more and more attention. In recent years, sensing systems based on low-cost sensors are proposed to achieve fine-grained monitoring with larger amount of deployment as supplyment to conventional monitoring stations. Calibration is critical to guarantee the accuracy and consistency of these sensing systems to fight against sensor drift. While conventional field calibration approaches often rely on real-time data from a nearby standard station, they are not applicable to low-cost sensors which cannot receive the latest reference data from nearby stations after deployment. In reality, it is very difficult for sensors to get access to nearby standard stations deployed sparsely. To reduce the dependency on real-time and nearby reference data, we present a Robust Calibration approach based on Historical data (RCH) for the low-cost air pollution sensor calibration. Our method corrects the sensor drift by adapting sensitivity and offset based on estimating the probability distribution of pollutant's concentration. Experiments with real-world NO 2 data in Foshan, China show that our proposed method acheives close performance to conventional field calibration methods but addresses above challenges. Moreover, our method can use historical data collected from the sensors in more distant geographic locations than the compared method.

Blind Calibration by Maximizing Correlation

Abstract: In large-scale IoT systems, blind calibration problem becomes increasingly prominent for sensor calibration without ground truth reference. Most of the existing blind calibration methods adopt either a handcrafted spatio-temporal model or a specific drift mechanism assumption. However, these assumptions may be over-simplified or introduce inappropriate bias, and therefore lead to great performance degradation in the real-world deployment. In this paper, we present a novel generative framework for blind calibration problems without specific data correlation or drift model assumption. We extract the most informative feature that maximizes correlation between reference data and target data using soft-HGR maximal correlation regression. Therefore, our method can be used in different blind calibration tasks especially where data correlation or drift model is unknown or deviated. Besides, our method can be conveniently augmented with a reliable drift model to further improve performance on specific tasks. We conduct comprehensive evaluations over a three-month real-world air pollution sensing dataset collected in Foshan, China. Results show our method can obtain the best performance compared to previous blind calibration methods in the absence of accurate drift model knowledge.

The rise of low-cost sensing for managing air pollution in cities

Abstract: Ever growing populations in cities are associated with a major increase in road vehicles and air pollution. The overall high levels of urban air pollution have been shown to be of a significant risk to city dwellers. However, the impacts of very high but temporally and spatially restricted pollution, and thus exposure, are still poorly understood. Conventional approaches to air quality monitoring are based on networks of static and sparse measurement stations. However, these are prohibitively expensive to capture tempo-spatial heterogeneity and identify pollution hotspots, which is required for the development of robust real-time strategies for exposure control. Current progress in developing low-cost micro-scale sensing technology is radically changing the conventional approach to allow real-time information in a capillary form. But the question remains whether there is value in the less accurate data they generate. This article illustrates the drivers behind current rises in the use of low-cost sensors for air pollution management in cities, whilst addressing the major challenges for their effective implementation.

RCH: robust calibration based on historical data for low-cost air quality sensor deployments

Abstract: Air pollution has become one of the major threats to human health. Conventional approaches for air pollution monitoring use precise professional devices, but cannot achieve dense deployment due to high cost. Therefore, systems consisting of low-cost sensors are applied as a supplement to obtain fine-grained pollution information. In order to maintain the accuracy of these low-cost sensors, it is essential to calibrate them to minimize the impact from sensor drifts. Existing field calibration methods utilize the real-time data from spatially-adjacent official air quality stations as reference. However, the real-time reference is not always accessible under existing station deployment. In this paper, we propose the Robust Calibration approach using Historical data (RCH) for low-cost air quality sensors. Our method corrects the sensor drift by adapting sensitivity and offset based on pollutant's concentration distribution. Experiments on NO2 data from real-world deployment in Foshan, China show that RCH has the similar performance compared with existing field calibration methods using real-time and spatially-adjacent references. It demonstrates that RCH can improve the accuracy and consistency of low-cost air quality sensors without the help of real-time and nearby reference data.

Blind Calibration by Maximizing Correlation

Abstract: In large-scale IoT systems, blind calibration problem becomes increasingly prominent for sensor calibration without ground truth reference. Most of the existing blind calibration methods adopt either a handcrafted spatio-temporal model or a specific drift mechanism assumption. However, these assumptions may be over-simplified or introduce inappropriate bias, and therefore lead to great performance degradation in the real-world deployment. In this paper, we present a novel generative framework for blind calibration problems without specific data correlation or drift model assumption. We extract the most informative feature that maximizes correlation between reference data and target data using soft-HGR maximal correlation regression. Therefore, our method can be used in different blind calibration tasks especially where data correlation or drift model is unknown or deviated. Besides, our method can be conveniently augmented with a reliable drift model to further improve performance on specific tasks. We conduct comprehensive evaluations over a three-month real-world air pollution sensing dataset collected in Foshan, China. Results show our method can obtain the best performance compared to previous blind calibration methods in the absence of accurate drift model knowledge.

A Variational Bayesian Blind Calibration Approach for Air Quality Sensor Deployments

Abstract: Air pollution has become a global threat to urban environments and public health. Low-cost air quality sensor systems have been deployed to support fine-grained monitoring, and in-field calibration methods are necessary to assure the accuracy of sensor observation. Existing methods use in-field reference to train some specific calibration models. Nevertheless, collecting sufficient reference data after deployment is challenging. First, the synchronized data pair of reference observation is hard to obtain. Thus, many blind calibration approaches rely on some alternative reference like a historical reference before sensor observation. However, since the relationship model between alternative reference and sensor observation becomes more complicated, the amount of collected data is still insufficient to learn the complex model. To address the above challenge, we propose a Variational Bayesian Blind Calibration Algorithm. Our method introduces a supplement set that only involves historical reference and synchronized reference measurement without sensor observation to alleviate the few-reference pressure. Large amounts of the introduced supplement sets have been collected in different cities by accurate stations, which we adopt to conduct prediction tasks and build a Bayesian model to learn how to combine the formulated prediction task and target calibration task in a theoretically better way. Furthermore, we design a variational Bayesian framework to make good use of the easily obtained supplement set to train a better prediction model for improving calibration performance and relieving the pressure of collecting costly reference measurements after deployment. Evaluations of real-world and synthetic datasets show that the proposed approach has a better performance than previous baselines.

Clustering-Based Segmented Regression for Particulate Matter Sensor Calibration

Abstract: Nowadays, sensor-based air pollution sensing systems are widely deployed for fine-grained pollution monitoring. In-field calibration plays an important role in maintaining sensory data quality. Determining the model structure is challenging using existing methods of variable global fitting models for in-field calibration. This is because the mechanism of interference factors is complex and there is often insufficient prior knowledge on a specific sensor type. Although Artificial-Neuron-Net-based (ANN-based) methods ignore the complex conditions above, they also have problems regarding generalization, interpretability, and calculation cost. In this paper, we propose a clustering-based segmented regression method for particulate matter (PM) sensor in-field calibration. Interference from relative humidity and temperature are taken into consideration in the particulate matter concentration calibration model. Samples for modeling are divided into clusters and each cluster has an individual multiple linear regression equation. The final calibrated result of one sample is calculated from the regression model of the cluster the sample belongs to. The proposed method is evaluated under in-field deployment and performs better than a global multiple regression method both on PM2.5 and PM10 pollutants with, respectively, at least 16% and 9% improvement ratio on RMSE error. In addition, the proposed method is insensitive to reduction of training data and increase in cluster number. Moreover, it may bear lighter calculation cost, less overfitting problems and better interpretability. It can improve the efficiency and performance of post-deployment sensor calibration.