Hotspot clustering using DBSCAN algorithm and shiny web framework

Forest fires are a serious problem that occurs repeatedly in Indonesia. Fire events can be predicted by monitoring the datasets of hotspots which are recorded through remote sensing satellite. This study aims to build a web application that performs clustering on the hotspots data. This application implements DBSCAN algorithm using Shiny web framework for R programming language. Clustering is performed on a dataset of hotspots on Kalimantan Island and South Sumatra Province in 2002-2003. The spread pattern of hotspots resulted by this clustering can be used as a predictive model of forest fires occurence and can be accessed through the internet browser.

[1]  Sushmita Mitra,et al.  KDDClus : A Simple Method for Multi-Density Clustering , 2011 .

[2]  Manisha Naik Gaonkar,et al.  AutoEpsDBSCAN : DBSCAN with Eps Automatic for Large Dataset , 2013 .

[3]  D. X. Viegas,et al.  Burnt area mapping in southern Europe using IRS-WiFS. , 2002 .

[4]  Florian Siegert,et al.  The 1998 Forest Fires in East Kalimantan (Indonesia): A Quantitative Evaluation Using High Resolution, Multitemporal ERS-2 SAR Images and NOAA-AVHRR Hotspot Data , 2000 .

[5]  C. Elvidge,et al.  Night-time lights of the world: 1994–1995 , 2001 .

[6]  C. Justice,et al.  Emissions of trace gases and aerosol particles due to vegetation burning in southern hemisphere Africa , 1996 .

[7]  Diane K. Davies,et al.  Fire Information for Resource Management System: Archiving and Distributing MODIS Active Fire Data , 2009, IEEE Transactions on Geoscience and Remote Sensing.

[8]  Hans-Peter Kriegel,et al.  A Density-Based Algorithm for Discovering Clusters in Large Spatial Databases with Noise , 1996, KDD.

[9]  T. Stein.  International Geoscience And Remote Sensing Symposium , 1992, [Proceedings] IGARSS '92 International Geoscience and Remote Sensing Symposium.

[10]  Soo Chin Liew,et al.  A study of the 1997 forest fires in south east Asia using SPOT quicklook mosaics , 1998, IGARSS '98. Sensing and Managing the Environment. 1998 IEEE International Geoscience and Remote Sensing. Symposium Proceedings. (Cat. No.98CH36174).

[11]  Peng Liu,et al.  VDBSCAN: Varied Density Based Spatial Clustering of Applications with Noise , 2007, 2007 International Conference on Service Systems and Service Management.

[12]  D. Roy,et al.  Burned area mapping using multi-temporal moderate spatial resolution data—a bi-directional reflectance model-based expectation approach , 2002 .