The hot-film sensor has been used extensively for many years as a research tool in fluid mechanics to yield velocity information. A hot-film sensor calibration must be carried out to determine the relation between the probe current and fluid velocity before measurements, because of variation in the ambient conditions. So the sensor nonlinear calibration is one of the main techniques to enhance its reliability and performance, an ANFIS (Adaptive Neural-fuzzy Inference System) based inverse modeling technique has been proposed to find the best-fit curve for sensor characteristics. Learning process and simulation analyses were conducted in the MATLAB environment. The results demonstrate the effectiveness of the ANFIS inverse model for hot-film sensor calibration.