The average heat transfer coefficient is determined between the fluidizing bed and horizontal tube surface immersed in the bed of large particles. The mustard (d(p) = 1.8 mm), raagi (d(p) = 1.4 mm) and bajara (d(p) = 2.0 mm) were used as particles in the bed. The effect of fluidizing gas velocity on the heat transfer coefficient in the immersed horizontal tube is discussed. The results obtained by experiment are compared with correlations and artificial neural network modeling. The parameters particle size, temperature difference between bed and immersed surface were used in the neural network modeling along with fluidizing velocity. The feed-forward network with back propagation structure implemented using Levenberg-Marquardt's learning rule in the neural network approach. The network's performance tested with regression analysis. The predictions of the artificial neural network were found to be in good agreement with the experiment's values, as well as the results achieved by the developed correlations. (C) 2013 Elsevier Ltd. All rights reserved.