ws 15(5): e2

Research Article

Activation Force-based Air Pollution Observation Station Clustering

Download276 downloads
  • @ARTICLE{10.4108/eai.19-8-2015.2259688,
        author={Di Huang and Ni Zhang and Hong Yu and Huanyu Zhou and Zhanyu Ma and Weisong Hu and Jun Guo},
        title={Activation Force-based Air Pollution Observation Station Clustering},
        journal={EAI Endorsed Transactions on Wireless Spectrum},
        volume={1},
        number={5},
        publisher={EAI},
        journal_a={WS},
        year={2015},
        month={9},
        keywords={air pollution, subnetworks, activiation force, clustering},
        doi={10.4108/eai.19-8-2015.2259688}
    }
    
  • Di Huang
    Ni Zhang
    Hong Yu
    Huanyu Zhou
    Zhanyu Ma
    Weisong Hu
    Jun Guo
    Year: 2015
    Activation Force-based Air Pollution Observation Station Clustering
    WS
    EAI
    DOI: 10.4108/eai.19-8-2015.2259688
Di Huang1, Ni Zhang2, Hong Yu1, Huanyu Zhou1, Zhanyu Ma1,*, Weisong Hu2, Jun Guo1
  • 1: Beijing University of Posts and Telecommunications
  • 2: NEC Labs China
*Contact email: mazhanyu@bupt.edu.cn

Abstract

With huge amount of observed air quality and components data, it is of great challenge to analyze and trace the pollutant diffusion path. Partitioning the air pollution sources (air quality observation stations) into subnetworks will help a lot in tracing the air pollution diffusion path. Conventional air pollution sources clustering methods, which are based on geography or pollutant levels, present weak correlation with pollution transmission links. In order to overcome such problem, a method of air pollution sources clustering via activation force (AF) model is introduced in this paper. We model the connections of the pollution sources by AF so that the relationship among the observation stations and the coincidence of the transmission links can be modeled effectively. With the affinity matrix obtained via AF modeling, we conduct clustering of the air pollution sources via modularity measurement. Compared to K-means clustering method purely, which is based on the air quality index of pollutants, the proposed approach shows several advantages in air pollution network clustering.