IMAGE-BASED CLASSIFICATION OF AIR POLLUTION USING DIFFERENT PRETRAINED CNN MODELS AND A SMALL DATASET

RAYAN AWNI  MATLOOB; MOHAMMED AHMED  SHAKIR

doi:10.26682/sjuod.2023.26.1.37

RAYAN AWNI MATLOOB Dept. of Electrical and computer Engineering, College of Engineering, University of Duhok, Kurdistan Region-Iraq
MOHAMMED AHMED SHAKIR Dept. of Electrical and computer Engineering, College of Engineering, University of Duhok, Kurdistan Region-Iraq

DOI: https://doi.org/10.26682/sjuod.2023.26.1.37

Keywords: Deep Learning, Convolutional Neural Network (CNN), Air Quality, Particulate Matter, Image Classification, Pretrained Models

Abstract

Because contaminants and particles are volatile, dynamic, and highly variable in both time and place, predicting air quality is a challenging endeavor. At the same time, the ability for modeling, predicting, and monitoring the quality of air is becoming increasingly pertinent. In this study, we demonstrate that utilizing several pretrained convolutional neural network models, such as ResNet18, ResNet50, ResNet101, Mobilenetv2 and Shufflenet is feasible to anticipate fine particulate matter (PM2.5) concentrations with minimal computation time. The results show that, it is possible to estimate the PM2.5 level through pretrained models using a small single scene dataset. The models are tested with 2500 images and trained with (50% for training, 25% for validation, and 25% for testing). Among all the models, ResNet101 has the highest accuracy prediction (Acc = 86.27% at LR = 0.0007) with an average learning time about (92 minutes) followed by ResNet50 that achieved a prediction accuracy equal to (Acc = 84.19% at LR=0.00007) with about half the needed learning time that is about (40 minutes). These followed by Shufflenet (Acc = 83.97% with about 44 minutes), and Mobilenetv2 (Acc = 82.70% with about 40 minutes). It is also noticeable that ResNet18 has a reasonable accuracy (Acc = 83.28%) with the least needed learning time about (16 minutes)

Downloads

Download data is not yet available.

References

Hvidtfeldt, U. A., Ketzel, M., Sørensen, M., Hertel, O., Khan, J., Brandt, J., & Raaschou-Nielsen, O. (2018). Evaluation of the Danish AirGIS air pollution modeling system against measured concentrations of PM2.5, PM10, and black carbon. In Environmental Epidemiology (Vol. 2, Issue 2, p. e014). Ovid Technologies (Wolters Kluwer Health). https://doi.org/10.1097/ee9.0000000000000014
Pimpin, L., Retat, L., Fecht, D., de Preux, L., Sassi, F., Gulliver, J., Belloni, A., Ferguson, B., Corbould, E., Jaccard, A., & Webber, L. (2018). Estimating the costs of air pollution to the National Health Service and social care: An assessment and forecast up to 2035. In A. Sheikh (Ed.), PLOS Medicine (Vol. 15, Issue 7, p. e1002602). Public Library of Science (PLoS). https://doi.org/10.1371/journal.pmed.1002602
Mokdad, A. H. (2004). Actual Causes of Death in the United States, 2000. In JAMA (Vol. 291, Issue 10, p. 1238). American Medical Association (AMA). https://doi.org/10.1001/jama.291.10.1238
Zhang, S., & Chau, K.-W. (2009). Dimension Reduction Using Semi-Supervised Locally Linear Embedding for Plant Leaf Classification. In Emerging Intelligent Computing Technology and Applications (pp. 948–955). Springer Berlin Heidelberg. https://doi.org/10.1007/978-3-642-04070-2_100
Gholami, V., Chau, K. W., Fadaee, F., Torkaman, J., & Ghaffari, A. (2015). Modeling of groundwater level fluctuations using dendrochronology in alluvial aquifers. In Journal of Hydrology (Vol. 529, pp. 1060–1069). Elsevier BV. https://doi.org/10.1016/j.jhydrol.2015.09.028
Sefeedpari, P., Rafiee, S., Akram, A., Chau, K., & Pishgar-Komleh, S. H. (2016). Prophesying egg production based on energy consumption using multi-layered adaptive neural fuzzy inference system approach. In Computers and Electronics in Agriculture (Vol. 131, pp. 10–19). Elsevier BV. https://doi.org/10.1016/j.compag.2016.11.004
Vahdatpour, M. S., Sajedi, H., & Ramezani, F. (2018). Air pollution forecasting from sky images with shallow and deep classifiers. In Earth Science Informatics (Vol. 11, Issue 3, pp. 413–422). Springer Science and Business Media LLC. https://doi.org/10.1007/s12145-018-0334-x
Bo, Q., Yang, W., Rijal, N., Xie, Y., Feng, J., & Zhang, J. (2018). Particle Pollution Estimation from Images Using Convolutional Neural Network and Weather Features. In 2018 25th IEEE International Conference on Image Processing (ICIP). 2018 25th IEEE International Conference on Image Processing (ICIP). IEEE. https://doi.org/10.1109/icip.2018.8451306
Rijal, N., Gutta, R. T., Cao, T., Lin, J., Bo, Q., & Zhang, J. (2018). Ensemble of Deep Neural Networks for Estimating Particulate Matter from Images. In 2018 IEEE 3rd International Conference on Image, Vision and Computing (ICIVC). 2018 IEEE 3rd International Conference on Image, Vision and Computing (ICIVC). IEEE. https://doi.org/10.1109/icivc.2018.8492790
Castelli, M., Clemente, F. M., Popovič, A., Silva, S., & Vanneschi, L. (2020). A Machine Learning Approach to Predict Air Quality in California. In Complexity (Vol. 2020, pp. 1–23). Hindawi Limited. https://doi.org/10.1155/2020/8049504
Li, K., Ma, J., Li, H., Han, Y., Yue, X., Chen, Z., & Yang, J. (2020). Discern Depth Under Foul Weather: Estimate PM$_{2.5}$ for Depth Inference. In IEEE Transactions on Industrial Informatics (Vol. 16, Issue 6, pp. 3918–3927). Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/tii.2019.2943631
Kow, P.-Y., Hsia, I.-W., Chang, L.-C., & Chang, F.-J. (2022). Real-time image-based air quality estimation by deep learning neural networks. In Journal of Environmental Management (Vol. 307, p. 114560). Elsevier BV. https://doi.org/10.1016/j.jenvman.2022.114560
Liu, C., Tsow, F., Zou, Y., & Nongjian Tao. (2016). Particle pollution estimation based on image analysis. figshare.
https://doi.org/10.6084/M9.FIGSHARE.1603556.V2
US embassies and consulates. In: US Embassies and Consulates | AirNow.gov.
https://www.airnow.gov/international/us-embassies-and-consulates/#China$Shanghai. Accessed 10 Oct 2022 Elmannai, H., Hamdi, M., & AlGarni, A. (2021). Deep Learning Models Combining for Breast Cancer Histopathology Image Classification. In International Journal of Computational Intelligence Systems (Vol. 14, Issue 1, p. 1003). Springer Science and Business Media LLC. https://doi.org/10.2991/ijcis.d.210301.002
Shahinfar, S., Meek, P., & Falzon, G. (2020). “How many images do I need?” Understanding how sample size per class affects deep learning model performance metrics for balanced designs in autonomous wildlife monitoring. In Ecological Informatics (Vol. 57, p. 101085). Elsevier BV. https://doi.org/10.1016/j.ecoinf.2020.101085
Allena Venkata Sai Abhishek,Dr. Venkateswara Rao Gurrala,Dr. Laxman Sahoo, "RESNET18 MODEL WITH SEQUENTIAL LAYER FOR COMPUTING ACCURACY ON IMAGE CLASSIFICATION DATASET", International Journal of Creative Research Thoughts (IJCRT), ISSN:2320-2882, Volume.10, Issue 5, pp.c176-c181, May 2022, Available at :http://www.ijcrt.org/papers/IJCRT2205235.pdf/Li, Y., Huang, J., & Luo, J. (2015). Using user generated online photos to estimate and monitor air pollution in major cities. In Proceedings of the 7th International Conference on Internet Multimedia Computing and Service - ICIMCS ’15. the 7th International Conference. ACM Press. https://doi.org/10.1145/2808492.2808564
He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep Residual Learning for Image Recognition. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE. https://doi.org/10.1109/cvpr.2016.90
Demir, A., Yilmaz, F., & Kose, O. (2019). Early detection of skin cancer using deep learning architectures: resnet-101 and inception-v3. In 2019 Medical Technologies Congress (TIPTEKNO). 2019 Medical Technologies Congress (TIPTEKNO). IEEE. https://doi.org/10.1109/tiptekno47231.2019.8972045/
Nguyen, H. (2020). FAST OBJECT DETECTION FRAMEWORK BASED ON MOBILENETV2 ARCHITECTURE AND ENHANCED FEATURE PYRAMID.