Smart City Air Quality Prediction using Machine Learning

Murugan, R. Arul; Naveen, P.

doi:10.1109/iciccs51141.2021.9432074

Cited by 22 publications

(4 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Zamani Joharestani et al, found that longitude, latitude and elevation were some of the most important variables for their RF model to predict PM 2.5 concentrations in Teheran and demonstrated that they could even replace other correlated variables [40]. Furthermore, Stafoggia et al as well as Murugan and Palanichamy showed that spatial coordinates have high importance for the accuracy of their RF PM 2.5 prediction models for Italy and Malaysia, respectively [30,44]. Hu et al, trained a PM 2.5 prediction model for the US and found that land use and population density had a significant influence on model accuracy [41].…”

Section: Feature Importancementioning

confidence: 99%

“…ML methods have been proven to efficiently combine information on PM 2.5 , AOD and other spatialtemporal varying predictors. Several studies have compared the performance of different ML methods for PM 2.5 predictions, such as simple decision trees, random forests, support vector machines or Gradient Boosting, and a majority of them found random forest (RF) to perform the best [30][31][32][33][34][35]. The RF models allow for the consideration of numerous parameters for very accurate PM 2.5 predictions and provide importance measures to assess the influence of the respective parameters on the model's accuracy.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Systematic Evaluation of Four Satellite AOD Datasets for Estimating PM2.5 Using a Random Forest Approach

2023

View full text Add to dashboard Cite

The latest epidemiological studies have revealed that the adverse health effects of PM2.5 have impacts beyond respiratory and cardio-vascular diseases and also affect the development of the brain and metabolic diseases. The need for accurate and spatio-temporally resolved PM2.5 data has thus been substantiated. While the selective information provided by station measurements is mostly insufficient for area-wide monitoring, satellite data have been increasingly applied to comprehensively monitor PM2.5 distributions. Although the accuracy and reliability of satellite-based PM2.5 estimations have increased, most studies still rely on a single sensor. However, several datasets have become available in the meantime, which raises the need for a systematic analysis. This study presents the first systematic evaluation of four satellite-based AOD datasets obtained from different sensors and retrieval methodologies to derive ground-level PM2.5 concentrations. We apply a random forest approach and analyze the effect of the resolution and coverage of the satellite data and the impact of proxy data on the performance. We examine AOD data from the Moderate resolution Imaging spectroradiometer (MODIS) onboard Terra and Aqua satellites, including Dark Target (DT) algorithm products and the Multi-Angle Implementation of Atmospheric Correction (MAIAC) product. Additionally, we explore more recent datasets from the Sea and Land Surface Temperature Radiometer (SLSTR) onboard Sentinel-3a and from the Tropospheric Monitoring Instrument (TROPOMI) operating on the Sentinel-5 precursor (S5p). The method is demonstrated for Germany and the year 2018, where a dense in situ measurement network and relevant proxy data are available. Overall, the model performance is satisfactory for all four datasets with cross-validated R2 values ranging from 0.68 to 0.77 and excellent for MODIS AOD reaching correlations of almost 0.9. We find a strong dependency of the model performance on the coverage and resolution of the AOD training data. Feature importance rankings show that AOD has less weight compared to proxy data for SLSTR and TROPOMI.

show abstract

Section: Feature Importancementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Systematic Evaluation of Four Satellite AOD Datasets for Estimating PM2.5 Using a Random Forest Approach

2023

View full text Add to dashboard Cite

show abstract

“…However, this study is limited to regression techniques, although other machine learning algorithms also perform better at predicting air quality. The research in [37] addresses the before-mentioned limitation by comparing multi-layer convolution and random forest methods on a Malaysian air pollution dataset. The findings suggest that Random Forest outperformed MLP in forecasting the PM2.5 air pollution index in Malaysia's smart city.…”

Section: Smart Gridsmentioning

confidence: 99%

AI-assisted Distributed Cloud Services Framework for Enhanced Safety in Urban Smart Cities Environment

Niveshitha,

Amsaad,

Sherif

et al. 2024

Preprint

View full text Add to dashboard Cite

Smart cities have emerged to tackle life critical challenges that can thwart the overwhelming urbanization process, such as expensive health care, increasing energy demand, traffic jams, and environmental pollution. This paper proposes efficient and high-quality cloud-based machine-learning solutions for safe urban smart city environment. For that, supervised MLbased models, i.e., regression and classification, are developed utilizing cloud-based solutions to forecast high performance in execution time and enhanced quality of the solution in terms of the accuracy of the implemented cloud-based ML solution. To predict AQI, i.e. air quality index, ML models utilize pollutants in the air data sets. The mean absolute error, mean squared error, root means the squared error, R2 score are used to validate and test the designed models. As classification models, we perform the support vector machine and random forest algorithms, which are measured using the accuracy score and confusion matrix. Execution times and accuracy of the developed models are computed and contrasted with the times for the cloud-based versions of these models. The results show that among the regression algorithms, lasso regression has an r2 score of 80 percent, while linear regression has an r2 score of 75 percent. Furthermore, among the classification models, the random forest algorithm performs better with an accuracy of 99 percent than the support vector machine approach with 95 percent accuracy. In conclusion, our findings demonstrate that run-time is minimized when models are executed on a cloud platform compared to a desktop machine. Moreover, the accuracy of our models is maintained with reduced execution time.

show abstract

“…The ML part of this framework is formed by the gradient-boosting model, which has been trained with a total of 51,831 records of patients with and without COVID-19. This work [92] has the objective of predicting the concentration of polluted air in smart cities.…”

Section: ) Applicationsmentioning

confidence: 99%

A Survey on Intelligent Gesture Recognition Techniques

et al. 2022

View full text Add to dashboard Cite

Gesture recognition is an ideal means of interaction because it allows users not to have to make contact with any surface, which is a safe and hygienic means, especially in the pandemic situation that is occurring worldwide. However, gesture recognition is not a new discipline and it has been researched for many years but this type of interaction has not succeeded in replacing the keyboard and mouse. It is very useful to know about the advances that are being made with artificial intelligence in gesture recognition to be able to perform a more robust and reliable gesture recognition with a low response time. As it is, deep learning is being integrated into various areas to increase improvement in performance and one such area is artificial intelligence. In this way, there is the possibility that in the future the recognition of gestures will be a viable option as a means of daily interaction for the user and the main objective of this paper is to contribute to that process. For this reason, this study has analyzed 571 papers related to gesture recognition and artificial intelligence. This analysis has extracted relevant information related to scientific production, such as the most productive authors and journals or the most pertinent articles on the subject. Furthermore, we have developed our own model, which shows the relationship between the types of gesture recognition and the artificial intelligence techniques that have been applied for this task.

show abstract

Smart City Air Quality Prediction using Machine Learning

Cited by 22 publications

References 1 publication

Systematic Evaluation of Four Satellite AOD Datasets for Estimating PM2.5 Using a Random Forest Approach

Systematic Evaluation of Four Satellite AOD Datasets for Estimating PM2.5 Using a Random Forest Approach

AI-assisted Distributed Cloud Services Framework for Enhanced Safety in Urban Smart Cities Environment

A Survey on Intelligent Gesture Recognition Techniques

Contact Info

Product

Resources

About