Study of Various Feature Extraction and Selection Techniques for Drought Prediction in Precision Agriculture

  • Nikhil Gaikwad
  • Gaurav Chavan
  • Hemant Palivela
  • Preeja Ravishankar Babu
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 340)

Abstract

In recent times, many algorithms have been applied on hyper spectral images to extract useful patterns and graph kernel method (Shervashidze et al., in International conference on artificial intelligence and statistics, pp. 488–495, 2009 [1]) is one of them. This paper proposes a method of applying graphlet kernel to extract obstacles from small land holdings and comparing them with existing templates so as to get the required field features. On these extracted field images NDVI (Jalili et al., in Nation-wide prediction of drought conditions in Iran based on remote sensing data, IEEE, p. 1, 2013 [2]) and TCI calculations can be performed in between the crop harvesting stages for example “kharif” in India. This technique is helpful for land covers that are having various obstacles that can cause hindrances in the parametric calculations. NDVI calculations are very common in other countries as they have large holdings and many papers have proved NDVI as an important parameter for vegetation calculation. Graph based kernel function helps in analyzing the small land cover vegetation index with NDVI calculations.

Keywords

NDVI Image segmentation Graphlet kernel Classification 

References

  1. 1.
    Shervashidze, N., Petri, T., Mehlhorn, K., Borgwardt, K.M., Vishwanathan, S.: Efficient graphlet kernels for large graph comparison. In: International Conference on Artificial Intelligence and Statistics, pp. 488–495 (2009)Google Scholar
  2. 2.
    Jalili, M., et al.: Nation-Wide Prediction of Drought Conditions in Iran Based on Remote Sensing Data, p. 1. IEEE (2013) Google Scholar
  3. 3.
    Camps-Valls, G., Shervashidze, N., Borgwardt, K.M.: Spatio-spectral remote sensing image classification with graph kernels. IEEE Geosci. Remote Sens. Lett. 7(4), 741–745 (2010)CrossRefGoogle Scholar
  4. 4.
    Camps-Valls, G., Bandos Marsheva, T., Zhou, D.: Semi-supervised graph-based hyperspectral image classification. IEEE Trans. Geosci. Remote Sens. 45(10), 3044–3054 (2007)Google Scholar
  5. 5.
    Borgwardt, K.M., Kriegel, H-P.: Shortest-path kernels on graphs. In: Fifth IEEE International Conference on Data Mining. IEEE (2005) Google Scholar
  6. 6.
    Choudhary, S.S., Garg, P.K., Ghosh, S.K.: Mapping of agriculture drought using remote sensing and GIS. Int. J. Sci. Eng. Technol. 1(4), 149–157 (2012)Google Scholar

Copyright information

© Springer India 2015

Authors and Affiliations

  • Nikhil Gaikwad
    • 1
  • Gaurav Chavan
    • 2
  • Hemant Palivela
    • 3
  • Preeja Ravishankar Babu
    • 3
  1. 1.Sardar Patel Information TechnologyMumbaiIndia
  2. 2.A.C. Patil College of EngineeringNavi MumbaiIndia
  3. 3.Department of ITMukesh Patel School of Technology, Management and EngineeringMumbaiIndia

Personalised recommendations