A Shallow ResNet with Layer Enhancement for Image-Based Particle Pollution Estimation

Yang, Wenwen; Feng, Jun; Bo, Qirong; Yang, Yixuan; Jiang, Bo

doi:10.1007/978-3-030-03335-4_33

Cited by 4 publications

(4 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The authors described the phases presented in Figure 4 in the following parts of this paper. The proposed method is a transitive method between the use of neural networks to predict air quality based on photos presented in publications [ 13 , 14 , 15 ] and the approach based on modeling numerical data presented by the authors in [ 16 , 23 , 24 ]. In the first step, texture analysis for each of the average photo frames has been performed, using three complementary methods.…”

Section: Proposed Methodsmentioning

confidence: 99%

“…Artificial neural networks are a powerful data modeling tool with a high proven efficiency in dealing with nonlinearity in a dataset as well as complex problems in the classification, regression, and clustering fields [ 17 , 37 , 38 ]. An extensive description of neural networks has been provided by the authors in [ 15 , 17 , 37 , 38 , 39 ]. For the regression problem, a neural network with a multilayer perceptron (MLP) was selected [ 16 , 17 , 40 ].…”

Section: Theorymentioning

confidence: 99%

“…The R was between 0.67 and 0.77, depending on measurement localization for the regression model. Better regression results were obtained with CNN models with the PMIE method: R 2 was between 0.68 (multiple-scene images) and 0.91 (single-scene images) for PM 2.5 prediction [ 15 ]. The main limitation in using CNN is a small dataset of images.…”

Section: Conclusion Limitations and Future Researchmentioning

confidence: 99%

“…In neural network-based methods, Vahdatpour et al proposed a method to estimate pollution forecast with Convolutional Neural Network based on sky images and Gabor transform [ 13 , 14 ]. Yang et al presented shallow ResNet with layer enhancement for PM 2.5 index prediction [ 15 ] based on image data from Beijing, Shanghai in China. The usage of MLP was presented by the authors in [ 16 , 17 ].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Application of Photo Texture Analysis and Weather Data in Assessment of Air Quality in Terms of Airborne PM10 and PM2.5 Particulate Matter

Chuchro

Sarlej

Grzegorczyk

et al. 2021

Sensors

View full text Add to dashboard Cite

The study was undertaken in Krakow, which is situated in Lesser Poland Voivodeship, where bad PM10 air-quality indicators occurred on more than 100 days in the years 2010–2019. Krakow has continuous air quality measurement in seven locations that are run by the Province Environmental Protection Inspectorate. The research aimed to create regression and classification models for PM10 and PM2.5 estimation based on sky photos and basic weather data. For this research, one short video with a resolution of 1920 × 1080 px was captured each day. From each film, only five frames were used, the information from which was averaged. Then, texture analysis was performed on each averaged photo frame. The results of the texture analysis were used in the regression and classification models. The regression models’ quality for the test datasets equals 0.85 and 0.73 for PM10 and 0.63 for PM2.5. The quality of each classification model differs (0.86 and 0.73 for PM10, and 0.80 for PM2.5). The obtained results show that the created classification models could be used in PM10 and PM2.5 air quality assessment. Moreover, the character of the obtained regression models indicates that their quality could be enhanced; thus, improved results could be obtained.

show abstract