Abstract
This study addresses the challenge of accurately estimating air pollution levels, which pose significant health, environmental, and economic risks. Variations in air quality across different regions, with urban and power plant areas typically experiencing higher pollution levels, highlight the need for effective monitoring methods beyond traditional sensor-based approaches. This study proposes a method to estimate air pollution levels from images using a Convolution Neural Network (CNN) model, aiming to overcome the limitations of traditional monitoring stations. The proposed method leverages the Resnet-152 architecture to accurately estimate Particulate Matter (PM2.5) concentrations, benefiting from its implicit and invariant distortion features tailored for particulate matter modeling. Hyperparameter tuning during image training and using max-pooling layers with three kernels and one stride helps mitigate overfitting issues. The application of max-group layers facilitates the extraction of relevant information from activation maps, enhancing estimation precision. The Resnet-152 architecture with fewer parameters and invariant distortion characteristics, accelerates particulate matter estimation. Experimental results demonstrate the effectiveness of the proposed method, with a root mean square error (RMSE) of 0.10 and a mean absolute percentage error (MAPE) of 19.38%, outperforming other models such as Inception-v3, VGG-19, and Googlenet, thus showcasing its potential for practical air pollution monitoring applications.
Similar content being viewed by others
Data Availability
Not applicable.
Change history
22 May 2024
The original online version of this article was revised: In this article the affiliation details for the author were incorrectly given as 'Komeru Lakshmaiah Education Foundation' but should have been 'Koneru Lakshmaiah Education Foundation'. The original article has been corrected.
References
Mcginnis, J. M., & William, H. F. (1993). Actual causes of death in the united states. The Journal of the American Medical Association, 270(18), 2207–2212.
Cheng, Y., Kebin, H., Zhen, V. D., Mei, Z., Fengkui, D., & Yong, L. M. (2015). Humidity plays an important role in the PM2.5 pollution in Beijing. Environmental Pollution, 197, 68–75.
Health Effect Institute. (2019). Retrieved 26 Dec 2020 from www.healtheffects.org
Guttikonda, S. (2017) Air pollution in Indian Cities: Understanding the causes and the knowledge gaps, Centre for policy research.
World’s most polluted cities in 2019 PM2.5 ranking—Air Visual. (2019). Empowering the world to breathe cleaner air—IQ Air. Retrieved 12 Jan 2022.
Chandra, P., & Singh, Y. (2004). An activation function adapting training algorithm for sigmoidal feedforward networks. Neurocomputing, 61, 429–4379.
Duch, W., & Jankowski, N. (1999). Survey of neural transfer functions. Neural Computing Surveys, 2, 163–212.
Duch, W., Jankowski, N. (2001). Transfer functions: Hidden possibilities for better neural networks. In 9th European symposium on artificial neural networks (pp. 81–94).
Singh, Y., & Chandra, P. A. (2003). Class1 sigmoidal activation functions for FFANNs. Journal of Economic Dynamics and Control, 28(1), 183–187.
Kaiming, H., Xiangyu, Z., Shaoqing, R., Jian, S. (2016). Deep residual learning for image recognition. In IEEE International conference on computer vision and pattern recognition (pp. 770–778).
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 (pp. 1–5).
Mao, J., Uthai, P., Shinava, W., & Hirovuki, S. (2014). Detecting foggy images and estimating the haze degree factor. Journal of computer science and systems Biology, 6, 1–10.
Liu, C., Tsow, F., Zou, Y., & Tao, N. (2016). Particle pollution estimation based on image analysis. PLoS ONE, 11(2), e0145955.
Schultz, A. A., Schauer, J. J., & Malecki, K. M. (2017). Allergic disease associations with regional and localized estimates of air pollution. Environmental Research, 1(155), 77–85.
Mousavi, S. E., Heydarpour, P., Reis, J., Amiri, M., & Sahraian, M. A. (2017). Multiple sclerosis and air pollution exposure: Mechanisms toward brain autoimmunity. Medical Hypotheses, 1(100), 23–30.
Barrea, L., Savastano, S., Di Somma, C., Savanelli, M. C., Nappi, F., Albanese, L., Orio, F., & Colao, A. (2017). Low serum vitamin D-status, air pollution and obesity: A dangerous liaison. Reviews in Endocrine and Metabolic Disorders, 18, 207–214.
Wacker, M., & Holick, M. F. (2013). Sunlight and vitamin D: A global perspective for health. Dermato-Endocrinology, 5(1), 51–108.
Procházka, A., Kolinova, M., Fiala, J., Hampl, P., Hlavaty, K. (2000). Satellite image processing and air pollution detection. In 2000 IEEE international conference on acoustics, speech, and signal processing. Proceedings (cat. No. 00CH37100) (Vol. 4, pp. 2282–2285). IEEE.
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). Imagenet classification with deep convolutional neural networks. Advanced Neural Information Processing System, 25, 1097–1105.
Zhang, C., Yan, J., Li, C., Rui, X., Liu, L., Bie, R. (2016). On estimating air pollution from photos using convolutional neural network. In ACM International conference on Multimedia (pp. 297–301).
Chakma, A., Vizena, B., Cao, T., Lin, J., Zhang, J. (2017). Image based air quality analysis using deep convolutional neural network. In International conference on Image Processing (pp. 3949–3952). IEEE.
Lu, C., Lin, D., Jia, J., & Tang, C. (2017). Two class weather classification. IEEE Transaction Pattern Analysis Machine Intelligence, 39, 2510–2524.
Elhoseiny, M., Huang, S., Elgammal, A. (2015). Weather classification with deep convolution neural networks. In International Conference of on Image Processing (pp. 3349–3353).
Liu, F., Shen, C., Lin, G. (2015). Deep convolutional neural fields for depth estimation from a single image. In International conference on CVPR (pp. 5162–5170).
He, K., Sun, J., & Tang, X. (2011). Single image haze removal using dark channer prior. IEEE Transactions on Pattern Analysis and Machine Intelligence, 33(12), 2341–2353.
Jehong, A., Yunfan, C., Hyunchul, S. (2018). Weather classification usingconvolution neural networks. In International SOC design conference (ISOCC2018) (pp. 245–246).
Li, L., Zheng, Y., Zhang, L. (2014). Demonstration abstract: PiMi air box—A cost-effective sensor for participatory indoor quality monitoring. In International Symposium on information processing in sensor networks (pp. 327–328).
Christoph, G., Erik Rodner, Alexander, F., Joachim, D. (2014). Non-parametric part transfer for fine-grained recognition. In IEEE International conference on computer vision and pattern recognition (pp. 2489–2496).
Andrea, V., Brian, F. (2010). VLFeat: An open and portable library of computer vision algorithms. In ACM International conference on Multimedia (pp. 1469–1472).
Xing, H., Wang, F., Liu, C., & Suo, M. (2021). PM2.5 concentration modelling and prediction by using temperature based deep belief network. Neural Networks, 133, 157–165.
Liu, H., Li, F., Xu, F., & Lu, H. (2011). The evaluation of air quality using image quality. China Journal of Image Graph, 16, 1030–1037.
Song, Y. Z., Yang, H. L., Peng, J. H., Song, Y. R., Sun, Q., & Li, Y. (2015). Estimating PM2.5 concentrations in Xian city using a generalized additive model with multi-source monitoring data. PLoS ONE, 10, 1–15.
Abbey, D. E., Ostro, B. E., Fraser, G., Vancuren, T., & Burchette, R. J. (1995). Estimating fine particulates less than 2.5 microns in aerodynamic diameter (PM2.5) from airport visibility data in California. Journal of Exposure Analysis and Environmental Epidemiology, 5(2), 161–180.
Wang, J. L. (2006). Quantiative relationship between visibility and mass concentration of PM2.5 in Beijing. Journal of Environmantal Science, 18(3), 475–481.
Gu, K., Qiao, X., & Li, X. (2019). Highly effiecient picture based prediction of PM2.5 concentration. IEEE Transactions Industrial Electronics, 66, 3176–3184.
Zhang, H., Peng, D., Chen, W., & Xu, X. (2019). Extremely efficient PM2.5 estimator based on analysis of sailency and statistics. Electronics Letters, 55, 30–32.
Kezheng, S., Lijuan, T., Jiansheng, Q., Guangcheng, W., & Cairong, L. (2021). A deep learning based PM2.5 concentration estimator. Displays, 69, 1–6.
Predic, B., Yan, Z., Eberle, J., Stojanovic, D., Aberer, K. (2013). Exposuresense: Integrating daily activities with air quality using mobile participatory sensing. In IEEE PERCOM workshop (pp. 303–305).
Nikzad, N., Verma, N., Ziftci, C., Bales, E., Quick, N., Zappi, K. et al. (2012). Citisense: Improving geospatial environmental assessment of air quality using a wireless personal exposure monitring system. In ACM conference on wireless health (pp. 11.1–11.8).
Kim, K. W., & Kim, Y. J. (2005). Perceived visibility measurement using the HSI color difference method. Journal of the Korean Physical Society, 46(5), 1243–1250.
Zhan, Y., Zhang, R., Wu, Q., Wu, Y. (2016). A new haze image database with detailed air quality information and a novel no-reference image quality assessment method for haze images. In 2016 IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp. 1095–1099). IEEE.
Steininger, M., Kobs, K., Zehe, A., Lautenschlager, F., Becker, M., & Hotho, A. (2020). Maplur: Exploring a new paradigm for estimating air pollution using deep learning on map images. ACM Transactions on Spatial Algorithms and Systems (TSAS), 6(3), 1–24.
Andhra Pradesh Central Pollution Control Board (APPCB). Air Quality Status of Andhra Pradesh. http://aprtpms.ap.gov.in/publicview.html
Allison JS, Betsch S, Ebner B, Visagie J. (2022). On testing the adequacy of the inverse Gaussian distribution. Mathematics, 10(3), 350.
Mingjie, H., Jie, Z., Shiguang, S., Meina, K., Xillin, C. (2019). Deformable Facenet: Learning pose invariant feature with pose aware feature alignment for face recognition. In IEEE International Conference on Automatic Face and gesture recognition (pp. 1–10).
Enas, E., Awny, S., Ahmed, R. G., & Alaa, M. Z. (2021). Hyperparameter tuning for machine learning algorithms for Arabic sentiment analysis. Informatics, 8(4), 1–13.
Saad, A., Tareq, A. M., Saad, A. Z. (2017). Understanding of a convolutional neural network. In International Conference on Engineering and Technology (pp. 1–15). IEEE.
Funding
The authors have not disclosed any funding.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Bhimavarapu, U. An Improved Activation Function in Convolution Neural Network to Estimate the Hazardous Air Pollutant Based on Images. Wireless Pers Commun 135, 2401–2420 (2024). https://doi.org/10.1007/s11277-024-11174-4
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11277-024-11174-4