Novel Global Harmony Search Algorithm for Least Absolute Deviation

Autor: Longquan Yong
Jazyk: angličtina
Rok vydání: 2014
Předmět:
Zdroj: Journal of Applied Mathematics, Vol 2014 (2014)
Druh dokumentu: article
ISSN: 1110-757X
1687-0042
DOI: 10.1155/2014/632975
Popis: The method of least absolute deviation (LAD) finds applications in many areas, due to its robustness compared to the least squares regression (LSR) method. LAD is robust in that it is resistant to outliers in the data. This may be helpful in studies where outliers may be ignored. Since LAD is nonsmooth optimization problem, this paper proposed a metaheuristics algorithm named novel global harmony search (NGHS) for solving. Numerical results show that the NGHS method has good convergence property and effective in solving LAD.
Databáze: Directory of Open Access Journals