@inproceedings{ae7952457cd44987a3f05a031c41914d,
title = "Predictive mapping of urban air pollution using apache spark on a hadoop cluster",
abstract = "Air pollution is one of the major environmental problems in the industrial and populated cities. Predictive mapping of urban air pollution and sharing the generated maps with the public and city officials have positive impacts on society and environment. This article presents a solution based on distributed processing concepts to generate predictive map of air pollution for the next 24 hours. Apache Hadoop has been utilized as the underlying framework to form a cluster of processing machines. In order to improve the processing speed along with required machine learning functionalities, Apache Spark has been employed on the Hadoop cluster. The solution enables us to efficiently predict air quality classes on monitoring stations of Tehran, the capital of Iran for the next 24 hours. Using Inverse distance weighting (IDW) method, the predictive map of air quality classes is generated afterward for the whole city. The results showed that the proposed approach can achieve a reasonable speed in processing of big spatial data along with horizontal scalability..",
keywords = "Air pollution, Big spatial data, Distributed processing, Hadoop, Predictive mapping, Spark, ITC-CV",
author = "Marjan Asgari and M. Farnaghi and Zeinab Ghaemi",
year = "2017",
month = sep,
day = "17",
doi = "10.1145/3141128.3141131",
language = "English",
series = "ACM International Conference Proceeding Series",
publisher = "Association for Computing Machinery (ACM)",
pages = "89--93",
booktitle = "2017 International Conference on Cloud and Big Data Computing, ICCBDC 2017",
address = "United States",
note = "2017 International Conference on Cloud and Big Data Computing, ICCBDC 2017 ; Conference date: 17-09-2017 Through 19-09-2017",
}