Drying kinetics of semi-finished cassava crackers was investigated in this paper using ahot air dryer at seven levels of drying air temperatures in the rage of 50–80 °C, a fixed airflow velocity using a fan speed of 0.18 kW, and a fixed level of thickness at 1.5 mm. Acomparative study was performed among mechanistic and empirical models: thediffusion model, Newton model, Page model, Modified Page model, Henderson andPabis model, MFNN (Multilayer Feedforward Neural Network), and ANFIS (Adaptive-Network-based Fuzzy Inference System), to estimate dynamic drying behaviors of semi-finished cassava crackers. Among these models, MFNN was found to be the mostsuitable for predicting moisture ratio of the product based on r2 (regression coefficient),and MSE (mean squared errors between the experimental data and predicted values).KeywordsCassava cracker; Drying process; Diffusion model; Artificial Neural Network; Fuzzy