Data reconstruction applications for IoT air pollution sensor networks using graph signal processing

Ferrer-Cid, Pau; Barceló-Ordinas, José M.; García-Vidal, Jorge

doi:10.1016/j.jnca.2022.103434

Cited by 10 publications

(6 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ferrer-Cid et al [16] developed a graph-based data reconstructed model to perform postprocessing application that arises in real-time lower cost sensor deployment for monitoring air pollution. This data reconstructed model initially defines the relationship among the dissimilar network sensors through a graph learned in the measured dataset, later a signal reconstruction method is employed for reconstructing the sensor dataset.…”

Section: Literature Reviewmentioning

confidence: 99%

“…Local movement depends on the decision of whether a fox needs for moving close to the possible victim or stop moving and rest. It can be modelled using the arbitrary selective of variable 𝜇 ∈ 0,1 [19]: 𝑥 = { 𝜇 > 0.75 move closer, 𝜇 ≤ 0.75 𝑠𝑡𝑎𝑦 𝑖𝑛 𝑡ℎ𝑒 𝑐𝑢𝑟𝑟𝑒𝑛𝑡 𝑝𝑜𝑠𝑖𝑡𝑖𝑜𝑛 (16) In such cases, if the fox decided to move, the position change can be defined by using Eq. ( 17)…”

Section: Hyperparameter Tuning Modelmentioning

confidence: 99%

See 1 more Smart Citation

Modeling of Internet of Things Enabled Sustainable Environment Air Pollution Monitoring System

2023

Global NEST: The International Journal

View full text Add to dashboard Cite

<p>Air quality, radiation pollution, and water pollution were thekey featuresthat possess genuine challenges to the environment. Proper monitoring wasneededin such a way that the world couldaccomplish sustainable development, withkeeping a healthy society. Recently, environment monitoring is become a smart environment monitoring (SEM) scheme, with development of modern sensors and the advancements in the internet of things (IoT). IoT devices were mainly used in WSN for pollution control, vehicle marking, temperature control, and effective waste management. Consequently, modern method of environmental monitoring is called as SEM system, owing to usage of wireless sensors, IoT and AI.This paper leverages IoT devices for sustainable air pollution monitoring. The presented model derives an improved red fox optimizer with deep learning based air pollution monitoring system (IRFODL-APMS) using IoT devices. The presented IRFODL-APMS technique makes use of different IoT devices to collect data. Besides, the IRFODL-APMS model performs prediction process using deep learning based on long short term memory (LSTM). At last, IRFO technique is exploited as a hyperparameter tuning process of the LSTM model to accomplish enhanced prediction performance. The presented IRFODL-APMS model is simulated under distinct measures and the outcomes reported the enhanced predictive outcomes of the IRFODL-APMS approach over other existing models.</p>

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Section: Hyperparameter Tuning Modelmentioning

confidence: 99%

Modeling of Internet of Things Enabled Sustainable Environment Air Pollution Monitoring System

2023

Global NEST: The International Journal

View full text Add to dashboard Cite

show abstract

“…In order to have daily 24-hour samples, in case of data loss, e.g. due to communication subsystem failures or node maintenance, any imputation method can be applied [31]. In our case, we perform an interpolation (average between previous and next value) if only one sample is missing and discard the whole day if there is more than one loss in one day.…”

Section: Data Setsmentioning

confidence: 99%

“…Although there are several techniques for discovering the relationships between network sensors, graph signal processing tools have been successfully applied in learning the graph that encodes the implicit relationships between sensors measuring natural phenomena. Thus, we have applied a smoothness-based graph learning technique [31], [32] in order to find the reference instruments most related to the node of interest and include these instruments in the reference station database. The results indicate that two nearby reference instruments can be included in the database for the TPB-D mechanism.…”

Section: Tpb-d Performance Using Nearby Reference Stationsmentioning

confidence: 99%

Temporal Pattern-Based Denoising and Calibration for Low-Cost Sensors in IoT Monitoring Platforms

Allka

Ferrer-Cid

Barceló-Ordinas

et al. 2023

IEEE Trans. Instrum. Meas.

Self Cite

View full text Add to dashboard Cite

The introduction of low-cost sensors (LCSs) in air quality Internet of Things (IoT) monitoring platforms presents the challenge of improving the quality of the data that these sensors provide. In this paper, we propose two algorithms to perform denoising and calibration for LCSs used in IoT monitoring platforms. Sensors are first calibrated in-situ using linear or nonlinear machine learning models that only take into account instantaneous measurements. The best calibration model is used to estimate the values measured by the sensor during the sensor deployment. To improve the values of the estimates produced by the in-situ calibration model, we propose to take into account the temporal patterns present in signals such as temperature or tropospheric ozone that have regular patterns, e.g. daily. The first method, which we call temporal pattern-based denoising (TPB-D), performs signal denoising by projecting the daily signals of the in-situ calibrated LCS onto a subspace generated by the daily signals stored in a database taken by reference instruments. The second method, which we call temporal pattern-based calibration (TPB-C), considers that if we also have a reference instrument co-located to the LCSs over a period of time, we can correct with a linear mapping with regularization the daily LCS signals projected in the subspace produced by the reference database to be as similar as possible to the projected signals of the co-located reference instrument. The results show that TPB-D improves the estimates made by in-situ calibration by up to 10-20% while the TPB-C improves the estimates made by in-situ calibration by up to 20-40%.

show abstract

“…One simple approach to include neighboring data to predict or impute air quality data is to consider spatial distances or correlations between the stations. − A more advanced solution to this is graph machine learning, , a subfield of graph signal processing , which allows machine learning on irregularly structured data such as a monitoring network. Graph-based methods have been adopted for air quality-related tasks, such as outlier detection, postprocessing of low-cost sensor data, or high-resolution forecasting. − Graph machine learning was shown to be suitable for the imputation of different data sets, − yet, to the best of our knowledge, they have not yet been used to impute missing air quality data.…”

Section: Introductionmentioning

confidence: 99%

Graph Machine Learning for Improved Imputation of Missing Tropospheric Ozone Data

Betancourt,

Li,

Kleinert

et al. 2023

Environ. Sci. Technol.

View full text Add to dashboard Cite

Gaps in the measurement series of atmospheric pollutants can impede the reliable assessment of their impacts and trends. We propose a new method for missing data imputation of the air pollutant tropospheric ozone by using the graph machine learning algorithm “correct and smooth”. This algorithm uses auxiliary data that characterize the measurement location and, in addition, ozone observations at neighboring sites to improve the imputations of simple statistical and machine learning models. We apply our method to data from 278 stations of the year 2011 of the German Environment Agency (Umweltbundesamt – UBA) monitoring network. The preliminary version of these data exhibits three gap patterns: shorter gaps in the range of hours, longer gaps of up to several months in length, and gaps occurring at multiple stations at once. For short gaps of up to 5 h, linear interpolation is most accurate. Longer gaps at single stations are most effectively imputed by a random forest in connection with the correct and smooth. For longer gaps at multiple stations, the correct and smooth algorithm improved the random forest despite a lack of data in the neighborhood of the missing values. We therefore suggest a hybrid of linear interpolation and graph machine learning for the imputation of tropospheric ozone time series.

show abstract

Data reconstruction applications for IoT air pollution sensor networks using graph signal processing

Cited by 10 publications

References 43 publications

Modeling of Internet of Things Enabled Sustainable Environment Air Pollution Monitoring System

Modeling of Internet of Things Enabled Sustainable Environment Air Pollution Monitoring System

Temporal Pattern-Based Denoising and Calibration for Low-Cost Sensors in IoT Monitoring Platforms

Graph Machine Learning for Improved Imputation of Missing Tropospheric Ozone Data

Contact Info

Product

Resources

About