On Estimating Air Pollution from Photos Using Convolutional Neural Network

ABSTRACT

Air pollution has raised people's intensive concerns especially in developing countries such as China and India. Different from using expensive or unreliable methods like sensor-based or social network based one, photo based air pollution estimation is a promising direction, while little work has been done up to now. Focusing on this immediate problem, this paper devises an effective convolutional neural network to estimate air's quality based on photos. Our method is comprised of two ingredients: first a negative log-log ordinal classifier is devised in the last layer of the network, which can improve the ordinal discriminative ability of the model. Second, as a variant of the Rectified Linear Units (ReLU), a modified activation function is developed for photo based air pollution estimation. This function has been shown it can alleviate the vanishing gradient issue effectively. We collect a set of outdoor photos and associate the pollution levels from official agency as the ground truth. Empirical experiments are conducted on this real-world dataset which shows the capability of our method.

References

1. http://210.72.1.216:8080/gzaqi/Document/gjzlbz.pdf. Accessed: 2016-07--19.
2. http://zx.bjmemc.com.cn/. Accessed: 2016-07--19.
3. Y. Bengio, P. Simard, and P. Frasconi. Learning long-term dependencies with gradient descent is difficult. Neural Networks, IEEE Transactions on, 5(2):157--166, 1994.
4. J. Chen, H. Chen, G. Zheng, J. Z. Pan, H. Wu, and N. Zhang. Big smog meets web science: smog disaster analysis based on social media and device data on the web. In Proceedings of the companion publication of the 23rd international conference on World wide web companion, pages 505--510. International World Wide Web Conferences Steering Committee, 2014.
5. Y. Chung. Air pollution detection by satellites: The transport and deposition of air pollutants over oceans. Atmospheric Environment (1967), 20(4):617--630, 1986.
6. S. Greenland. Alternative models for ordinal logistic regression. Statistics in medicine, 13(16):1665--1677, 1994.
7. H. Hauck, A. Berner, B. Gomiscek, S. Stopper, H. Puxbaum, M. Kundi, and O. Preining. On the equivalence of gravimetric pm data with teom and beta-attenuation measurements. Journal of Aerosol Science, 35(9):1135--1149, 2004.
8. K. He, X. Zhang, S. Ren, and J. Sun. Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. In Proceedings of the IEEE International Conference on Computer Vision, pages 1026--1034, 2015.
9. G. E. Hinton and R. R. Salakhutdinov. Replicated softmax: an undirected topic model. In Advances in neural information processing systems, pages 1607--1614, 2009.
10. J. Hodgeson, W. McClenny, and P. Hanst. Air pollution monitoring by advanced spectroscopic techniques a variety of spectroscopic methods are being used to detect air pollutants in the gas phase. Science, 182(4109):248--258, 1973.
11. K. J. and J. K. Cumulated gain-based evaluation of ir techniques. ACM Transactions on Information Systems, 20:2002, 2002.
12. A. Krizhevsky, I. Sutskever, and G. E. Hinton. Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems, pages 1097--1105, 2012.
13. Y. LeCun, B. Boser, J. S. Denker, D. Henderson, R. E. Howard, W. Hubbard, and L. D. Jackel. Backpropagation applied to handwritten zip code recognition. Neural computation, 1(4):541--551, 1989.
14. C. Li, Q. Liu, J. Liu, and H. Lu. Learning ordinal discriminative features for age estimation. In Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on, pages 2570--2577, 2012.
15. C. Li, Q. Liu, J. Liu, and H. Lu. Ordinal distance metric learning for image ranking. IEEE transactions on neural networks and learning systems, 26(7):1551--1559, 2015.
16. Y. Li, Y. Zhou, J. Yan, J. Yang, and X. He. Tensor error correction for corrupted values in visual data. In 2010 IEEE International Conference on Image Processing, pages 2321--2324. IEEE, 2010.
17. C. Ma, J.-B. Huang, X. Yang, and M.-H. Yang. Hierarchical convolutional features for visual tracking. In Proceedings of the IEEE International Conference on Computer Vision, pages 3074--3082, 2015.
18. A. L. Maas, A. Y. Hannun, and A. Y. Ng. Rectifier nonlinearities improve neural network acoustic models. In Proc. ICML, volume 30, page 1, 2013.
19. S. Mei, H. Li, J. Fan, X. Zhu, and C. R. Dyer. Inferring air pollution by sniffing social media. In Advances in Social Networks Analysis and Mining (ASONAM), 2014 IEEE/ACM International Conference on, pages 534--539. IEEE, 2014.
20. V. Nair and G. E. Hinton. Rectified linear units improve restricted boltzmann machines. In Proceedings of the 27th International Conference on Machine Learning (ICML-10), pages 807--814, 2010.
21. J. A. Nelder and R. J. Baker. Generalized linear models. Encyclopedia of Statistical Sciences, 1972.
22. C. A. Pope III and D. W. Dockery. Health effects of fine particulate air pollution: lines that connect. Journal of the air & waste management association, 56(6):709--742, 2006.
23. J. D. Smith and D. B. Atkinson. A portable pulsed cavity ring-down transmissometer for measurement of the optical extinction of the atmospheric aerosol. Analyst, 126(8):1216--1220, 2001.
24. N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov. Dropout: A simple way to prevent neural networks from overfitting. The Journal of Machine Learning Research, 15(1):1929--1958, 2014.
25. J. Yan, M. Zhu, H. Liu, and Y. Liu. Visual saliency detection via sparsity pursuit. IEEE Signal Processing Letters, 17(8):739--742, 2010.

Index Terms

• Computing methodologies

  • Machine learning

    • Learning paradigms

      • Supervised learning

        • Ranking

        • Supervised learning by regression

    • Machine learning approaches

      • Learning latent representations

        • Deep belief networks