In this work we proposed a system based on metal oxide gas micro-sensors to estimate diesel or gasoline contamination in different engine oil samples. The gas-sensing layers (undoped, Pt, Pd, Rh-doped SnO 2 , In 2 O 3 and mixed In 2 O 3 -SnO 2 ) have been synthetized by the sol-gel method and deposited by spin-coating onto 2 mm times 2 mm silicon substrates equipped by Pt heater on the back and Pt interdigitated electrodes on the front. The sensor array has been exposed to no-used and used commercial engine oil samples contaminated with different amounts of unburned fuel. The results of data analysis (DWT-based feature extraction, PCA and Gaussian mixture model classifier (GMM)) showed that different fuel contaminated used engine oils can be discriminated and successfully classified by the sensor array.