End-to-end learning for image-based air quality level estimation

End-to-end learning for image-based air quality level estimation
复制标题

基于图像的空气质量水平估计的端到端学习

DOI:
10.1007/s00138-018-0919-x
复制
发表时间:
2018-03
影响因子:
3.3
通讯作者:
Rongfang Bie
Rongfang Bie
中科院分区:
计算机科学4区
文献类型:
--
作者:
Chao Zhang;Junchi Yan;Changsheng Li;Hao Wu;Rongfang Bie

文献摘要

参考文献

被引文献

相似文献

空气质量评价是环境保护中一个重要的基础性问题。在过去的几十年中,已经做出了一些努力,使用昂贵的基于传感器或间接的方法,如基于社交网络;然而,基于图像的空气污染估计仍然远远没有解决。本文设计了一种有效的卷积神经网络(CNN)来估计基于图像的空气质量。我们的方法由三个部分组成:首先,我们设计了一个用于空气质量估计的集成CNN,预计它将获得比单个分类器更准确和稳定的结果。其次,在每个CNN的最后一层设计了三个序分类器,即负对数-对数序分类器、cauchit序分类器和互补对数-对数序分类器,以提高模型的序判别能力。第三,作为整流线性单元的变型,引入了调整的激活函数。我们从官方机构收集具有相应空气质量水平的露天图像作为地面实况。实验结果证明了我们的方法在真实世界数据集上的有效性。
Air quality estimation is an important and fundamental problem in environmental protection. Several efforts have been made in the past decades using expensive sensor-based or indirect methods like based on social networks; however, image-based air pollution estimation is still far from solved. This paper devises an effective convolutional neural network (CNN) to estimate air quality based on images. Our method is comprised of three ingredients: We first design an ensemble CNN for air quality estimation which is expected to obtain more accurate and stable results than a single classifier. Second, three ordinal classifiers, namely negative log–log ordinal classifier, cauchit ordinal classifier and complementary log–log ordinal classifier, are devised in the last layer of each CNN, to improve the ordinal discriminative ability of the model. Third, as a variant of the rectified linear units, an adjusted activation function is introduced. We collect open air images with corresponding air quality levels from an official agency as the ground truth. Experimental results demonstrate the effectiveness of our method on the real-world dataset.
DOI: 10.1198/tas.2003.s212
发表时间: 2003-02
期刊: The American Statistician
影响因子: --
作者:
R. D. Cook;S. Weisberg
通讯作者: R. D. Cook;S. Weisberg
DOI: 10.1145/2964284.2967230
发表时间: 2016-10
期刊: Proceedings of the 24th ACM international conference on Multimedia
影响因子: --
作者:
Chao Zhang;Junchi Yan;Changsheng Li;Xiaoguang Rui;Liang Liu;R. Bie
通讯作者: Chao Zhang;Junchi Yan;Changsheng Li;Xiaoguang Rui;Liang Liu;R. Bie
具有物理干扰的分布式扳手构造:恒定拉伸和线性稀疏
DOI: 10.1109/tnet.2017.2684831
发表时间: 2017
期刊: IEEE/ACM Transactions on Networking
影响因子: --
作者:
Yu Dongxiao;Ning Li;Zou Yifei;Yu Jiguo;Cheng Xiuzhen;Lau Francis C M
通讯作者: Lau Francis C M
DOI: 10.1198/004017002320256422
发表时间: 2002-08
期刊: Technometrics
影响因子: 2.5
作者:
E. Ziegel
通讯作者: E. Ziegel
DOI: 10.1109/tkde.2013.49
发表时间: 2014-09
影响因子: 8.9
作者:
A. Jurek;Y. Bi;Shengli Wu;C. Nugent
通讯作者: A. Jurek;Y. Bi;Shengli Wu;C. Nugent