Programação por Metas para Ajuste Não Linear

Authorship SCIMAGO INSTITUTIONS RANKINGS

The aim of this work was to compare the effectiveness of Goal Programming models, as a nonlinear regression tool, with the classical nonlinear fitting methods. The models were applied to experimental data of inactivation Salmonella spp. in ground pork. The investigation of the methods’ efficiency was made by calculation of the maximum and absolute errors.

Keywords:
nonlinear regression; goal programming; Least Square Method; Levenberg-Marquardt

i	1	2	3	4	5	6	7	8
u _i	0,0001	0,1249	0,1249	0,1249	0,1249	0,0001	0,0001	0,0001
v _i	0,1249	0,0001	0,0001	0,0001	0,0001	0,1249	0,1249	0,1249

	MMQ	LM	PMP	PMC	PME
a ₀	8,5473	8,0183	8,1273	8,0591	8,0433
a ₁	-2,0513	-1,7770	-1,8845	-1,7596	-1,7545
Norma do Máximo	0,9073	0,4678	0,5361	0,4191	0,4227
Norma 1	2,6627	2,3583	2,3144	2,3542	2,3415

location_on

Sociedade Brasileira de Matemática Aplicada e Computacional Rua Maestro João Seppe, nº. 900, 16º. andar - Sala 163 , 13561-120 São Carlos - SP, Tel. / Fax: (55 16) 3412-9752 - São Carlos - SP - Brazil
E-mail: sbmac@sbmac.org.br

rss_feed Acompañe los números de esta revista en su lector de RSS

x_i = Tempo (h)	0	0,08	0,25	0,33	0,42	0,50	0,67	0,83
y_i = Log UFC/g	7,64	6,99	5,61	4,82	3,89	3,00	2,06	1,48