Drought Monitoring: A Performance Investigation of Three Machine Learning Techniques

Pheeha Machaka

Context-Aware Systems and Applications. Second International Conference, ICCASA 2013, Phu Quoc Island, Vietnam, November 25-26, 2013, Revised Selected Papers

Research Article

Drought Monitoring: A Performance Investigation of Three Machine Learning Techniques

Download

874 downloads

Cite: BibTeX Plain Text

@INPROCEEDINGS{10.1007/978-3-319-05939-6_5,
    author={Pheeha Machaka},
    title={Drought Monitoring: A Performance Investigation of Three Machine Learning Techniques},
    proceedings={Context-Aware Systems and Applications. Second International Conference, ICCASA 2013, Phu Quoc Island, Vietnam, November 25-26, 2013, Revised Selected Papers},
    proceedings_a={ICCASA},
    year={2014},
    month={6},
    keywords={Machine learning Algorithms Neural networks Artificial immune systems NaiveBayes
 Standard precipitation index},
    doi={10.1007/978-3-319-05939-6_5}
}

Pheeha Machaka
Year: 2014
Drought Monitoring: A Performance Investigation of Three Machine Learning Techniques
ICCASA
Springer
DOI: 10.1007/978-3-319-05939-6_5

Pheeha Machaka¹^,*

1: University of South Africa

*Contact email: machap@unisa.ac.za

Abstract

This paper investigates the use of Soft Computing techniques on a drought monitoring case study. This is in effort to create an intelligent middleware for Ubiquitous Sensor Networks (USN) using machine learning techniques. Algorithms in Artificial Immune System, Neural Networks and Bayesian Networks were used. The paper reveals the results from an experiment on data collected over 95 years in the Trompsburg region of the Free State Province, South Africa.

Keywords: Machine learning Algorithms Neural networks Artificial immune systems NaiveBayes Standard precipitation index

Published: 2014-06-19

: http://dx.doi.org/10.1007/978-3-319-05939-6_5