Journal of Applied Spectroscopy, Vol. 80, No. 3, July, 2013 (Russian Original Vol. 80, No. 3, May–June, 2013) ARTIFICIAL NEURAL NETWORK APPROACH FOR MODELING COBALT EXTRACTION FROM BIOLOGICAL AND WATER SAMPLES BY MAGNETIC NANOPARTICLES M. Khajeh UDC 620.3:546.73 In this study, an artificial neural network (ANN) model was used to predict the extraction efficiency of cobalt from biological and water samples by magnetic nanoparticles based on batch solid-phase extraction and inductively coupled plasma-optical emission spectrometry (ICP-OES). The effect of operational parameters, including solution pH, amounts of the complexing agent (1-(2-pyridylazo)-2-naphthol) and nanoparticles, and extraction time was studied. The parameters were optimized for the maximum extraction of cobalt ions. The optimum conditions were as follows: initial pH 11.0, contents of complexing agent and nanoparticles 0.75 mg/l and 125 mg, respectively, and extraction time 12.5 min. After backpropagation (BP) training, the ANN model was able to predict the extraction efficiency of cobalt ions with a tangent sigmoid transfer function (tansig) at a hidden layer with 15 neurons and a linear transfer function (purelin) at an output layer. The Levenberg–Marquardt algorithm (LMA) was found as the best of 11 BP algorithms with a minimum mean squared error (MSE) of 0.009895. The linear regression between the corresponding targets and the network outputs was shown to be satisfactory with a correlation coefficient (R 2 ) of 0.978. Under optimum conditions, the detection limit (LOD) of this method was 7.0 ng/l, and the relative standard deviation (RSD%) was 2.1% (n = 10, c = 10 μg/l). The method of magnetic nanoparticles based on batch solid- phase extraction was applied to the separation, pre-concentration, and determination of cobalt both in biological and water samples and in a certified reference material. Keywords: artificial neural network, cobalt, magnetic nanoparticle, biological samples, water samples. Introduction. A trace amount of cobalt is considered to be either toxic or essential depending on its concentration range. For instance, cobalt is the core of vitamin B 12 and has anti-anemic properties. However, some compounds of cobalt are carcinogenic at higher concentrations. Because of these properties, the determination of cobalt at trace levels in water and in biological and environmental samples is of great significance from environmental and public health points of view [1, 2]. Analytical problems arise due to the fact that coexisting matrices in complex biological samples may interfere with the determination of this element. Therefore, the development of efficient new materials and devising new procedures for cobalt determination are necessary [2, 3]. Modern instrumental procedures such as spectrometry, inductively coupled plasma-atomic emission spectrometry (ICP-AES), ICP-mass spectrometry (ICP-MS), and atomic absorption spectrometry (AAS) [4] have been used to determine traces of the element in different media. However, in these methods, low concentrations of analytes and high levels of matrices are the main problems [1]. To solve them, separation and pre-concentration steps prior to analysis are needed. Up to now, several procedures have been designed to separate and pre-concentrate cobalt ions from different matrices. Baliza et al. [5] studied determination of cobalt in water samples after dispersive liquid-liquid microextraction. Gil et al. [6] dealt with the cloud point extraction for cobalt pre-concentration with on-line phase separation in a knotted reactor. Bidabadi et al. [1] investigated solidified floating organic drop microextraction to extract cobalt. Wang et al. [2] have reported the extraction and pre-concentration of trace levels of cobalt using functionalized magnetic nanoparticles. In recent year, nanoparticle materials as adsorbents have attracted much interest and been widely used due to their properties such as a high surface to volume ratio and a short diffusion route [7, 8]. Due to comparatively high surface areas, nano-sized sorbents with strong affinity towards cobalt ion are likely to be useful in improving the adsorption capacity in biological and water treatment. However, because of their small particle size, isolation of nanomaterial adsorbents Department of Chemistry, University of Zabol, P. O. Box 98615-538, Zabol, Iran; e-mail: m_khajeh@uoz.ac.ir. Published in Zhurnal Prikladnoi Spektroskopii, Vol. 80, No. 3, pp. 417–426, May–June, 2013. Original article submitted June 18, 2012. 0021-9037/13/8003-0403 ©2013 Springer Science+Business Media New York 403