Optimization of Sky Image Enhancement to the Performance of Air Quality Classification Model Using Mobilenet V3

Wempy Aditya Wiryawan; Christian Sri Kusuma  Aditya

doi:10.51454/decode.v5i3.1412

Authors

Wempy Aditya Wiryawan Informatics Universitas Muhammadiyah Malang
Christian Sri Kusuma Aditya Informatics Universitas Muhammadiyah Malang

DOI:

https://doi.org/10.51454/decode.v5i3.1412

Keywords:

Air Quality, Deep Learning, Image Preprocessing, Mo-bileNetV3, Sky Image

Abstract

Air quality monitoring based on sky imagery is an alternative solution to the limitations of conventional monitoring tools. However, raw sky imagery often has low contrast and visual noise that can hinder the performance of deep learning models in recognizing atmosphere patterns. Therefore, this study aims to develop an efficient and accurate Air Quality Index (AQI) estimation model using MobileNetV3. The novelty of this research lies in the systematic investigation of image enhancement techniques using the public Air Pollution Image Dataset from India and Nepal, an aspect that has not been deeply explored in previous studies. To achieve this goal, four pre-processing techniques—Histogram Equalization (HE), Contrast Limited Adaptive Histogram Equalization (CLAHE), Gamma Correction, and Contrast Stretching—were applied and compared. The results consistently show that Histogram Equalization (HE) is the most superior technique for regression tasks with an R² value of 0.913, as well as for classification tasks with the highest category accuracy of 0.690. These findings significantly outperform models without pre-processing, confirming that HE is the most recommended technique for maximizing accuracy on resource-constrained devices.

References

Ajit, A., Acharya, K., & Samanta, A. (2020). A Review Of Convolutional Neural Networks. IEEE Xplore, 1–5. https://doi.org/10.1109/ic-ETITE47903.2020.049

Alzami, F., Naufal, M., Al Azies, H., Winarno, S., & Soeleman, M. A. (2024). Time Distributed MobileNetV2 with Auto-CLAHE for Eye Region Drowsiness Detection in Low Light Conditions. (IJACSA) International Journal of Advanced Computer Science and Applications, 15(11), 488-500. https://dx.doi.org/10.14569/IJACSA.2024.0151146

Amahoru, A. H., Dulhasyim, A. B. P., & Pulu, S. R. (2024). Analisis Citra Visual Fase-Fase Bulan dalam Tinjauan Sistem Koordinat Bola Langit. Jurnal Pendidikan Mipa, 14(1), 114–123. https://doi.org/10.37630/jpm.v14i1.1492

Azlansyah, M., Setiyono, B., & Komputasi, F. M. (2019). Penyisipan Pesan pada Citra Digital Menggunakan Metode Least Significant Bit. Jurnal Sains Dan Seni ITS, 8(1), 2337-3520.

Azmi, K., Defit, S., & Sumijan, S. (2023). Implementasi Convolutional Neural Network (CNN) Untuk Klasifikasi Batik Tanah Liat Sumatera Barat. Jurnal Unitek, 16(1), 28–40. https://doi.org/10.52072/unitek.v16i1.504

Bismi, W., & Qomaruddin, M. (2023). Klasifikasi Citra Genus panthera Menggunakan Pendekatan Deep learning Berbasis Convolutional Neural network (CNN). Jurnal Informatika Dan Rekayasa Perangkat Lunak, 5(2), 172–179.

Buriboev, A. S., Khashimov, A., Abduvaitov, A., & Jeon, H. S. (2024). CNN-Based Kidney Segmentation Using a Modified CLAHE Algorithm. Sensors, 24(23), 1-24. https://doi.org/10.3390/s24237703

Chicco, D., Warrens, M. J., & Jurman, G. (2021). The Coefficient Of Determination R-Squared Is More Informative Than SMAPE, MAE, MAPE, MSE And RMSE In Regression Analysis Evaluation. Peerj Computer Science, 7, 1-24. https://doi.org/10.7717/peerj-cs.623

Dede, M., Widiawaty, M. A., Nurhanifah, N., Ismail, A., Artati, A. R. P., Ati, A., & Ramadhan, Y. R. (2020). Estimasi Perubahan Kualitas Udara Berbasis Citra Satelit Penginderaan Jauh Di Sekitar PLTU Cirebon. Jambura Geoscience Review, 2(2), 78–87. https://doi.org/10.34312/jgeosrev.v2i2.5951

Enggari, S., Sumijan, & Tajuddin, M. (2024). The Development Of Color Histogram Method To Identify Air Quality Index Based On Sky Images. Indonesian Journal of Electrical Engineering and Computer Science, 34(1), 186–196. https://doi.org/10.11591/ijeecs.v34.i1.pp186-196

Fitriyah, H., & Wihandika, R. C. (2021). Dasar-Dasar Pengolahan Citra Digital. Universitas Brawijaya Press.

Heydarian, M., Doyl, T. E., & Samavi, R. (2022). MLCM_Multi-Label_Confusion_Matrix. IEEE Access, 10, 19083-19095. https://doi.org/10.1109/ACCESS.2022.3151048

Jochsen, E., & Handhayani, T. (2024). Pengenalan Bangunan Bersejarah Pura Dengan Arsitektur InceptionV3 dan Xception. Jurnal Eksplora Informatika, 14(1), 1–11. https://doi.org/10.30864/eksplora.v14i1.1064

Kamil, G. Z. (2022). Dilated Convolutional Vision Transformer dalam Kasus Rekonstruksi Citra Image Companding untuk Peningkatan Kualitas Citra Digital.

Lubis, L., & Darmawan, D. (2021). Perbandingan Metode Contrast Stretching. http://repository.uinsu.ac.id/id/eprint/14936

Mukundan, A., Huang, C. C., Men, T. C., Lin, F. C., & Wang, H. C. (2022). Air Pollution Detection Using a Novel Snap-Shot Hyperspectral Imaging Technique. Sensors, 22(16), 6231. https://doi.org/10.3390/s22166231

Qian, S., Ning, C., & Hu, Y. (2021). MobileNetV3 for image classification. 2021 IEEE 2nd International Conference on Big Data, Artificial Intelligence and Internet of Things Engineering (ICBAIE), Nanchang, China, 2021, 490-497. https://doi.org/10.1109/ICBAIE52039.2021.9389905

Rokom, R. (2023). Polusi Udara Sebabkan Angka Penyakit Respirasi Tinggi. Sehat Negeriku.

Rouniyar, A. (2024). Air Pollution Image Dataset from India and Nepal. Kaggle.

Samsami, M. M., Shojaee, N., Savar, S., & Yazdi, M. (2019). Classification Of The Air Quality Level Based On Analysis Of The Sky Images. 2019 27th Iranian Conference on Electrical Engineering (ICEE), 1492–1497. https://doi.org/10.1109/IranianCEE.2019.8786738

Septiyana, D., Sukmono, A., & Yusuf, M. A. (2023). Pemantauan Kualitas Udara ISPU (PM10, SO2, NO2) Menggunakan Citra Landsat 8 dan 9 untuk Kecamatan Mijen Selama Pandemi Covid-19. Jurnal Geodesi Undip, 12(3), 271–280.

Utomo, S., Rouniyar, A., Jiang, G. H., Chang, C. H., Tang, K. C., Hsu, H. C., & Hsiung, P. A. (2023). Eff-AQI: An Efficient CNN-Based Model for Air Pollution Estimation: A Study Case in India. ACM International Conference Proceeding Series, 165–172. https://doi.org/10.1145/3582515.3609531

Zhao, X., Wang, L., Zhang, Y., Han, X., Deveci, M., & Parmar, M. (2024). A Review Of Convolutional Neural Networks In Computer Vision. Artificial Intelligence Review, 57(4). https://doi.org/10.1007/s10462-024-10721-6