The characterisation of heat transfer in oscillatory flow of thermo-acoustic based heat exchangers is a cumbersome issue. This is due to the nature of the heat transfer between the gas particles moving along the device at high amplitude and the solid surface of the heat exchangers. In addition, the change in velocity, pressure and temperature induces nonlinear effect. As a result, the performance of heat exchangers negatively affects the efficiency of thermo-acoustic systems. Hence, it is necessary to determine to oscillatory heat transfer coefficient in order to measure the performance of heat exchangers in thermo-acoustic systems. Although it is possible to conduct experimental investigation or perform numerical analysis in order to determine oscillatory heat transfer coefficient, the former requires costly time consuming experiment while the latter involves the resolution of complex mathematical models. In this paper, an improved adaptive neurofuzzy inference system and artificial neural network trained by particle swarm optimization are proposed to predict oscillatory heat transfer coefficient. This paper is intending to provide clarity on the benefits of these new approaches on the computation of geometrical configuration and the working parameters of heat exchangers in thermo-acoustic systems.