Improved classification of black tea employing feature level fusion of electronic nose and tongue responses

Electronic nose and electronic tongue have wide application in discriminations among food and beverage samples. Electronic nose, an array of gas sensor classifies samples based on their aroma profile whereas electronic tongue, an array of electrodes employs taste as a classifying feature. In this work these artificial sensory systems are used to classify black tea. In this work we are fusing features extracted from both the sensor systems employing principal component analysis and analyze fused features with ANN classifiers. Both data level and feature level fusion of two sensory systems are performed. In each case the results show that combined sensor signature is improved compared to individual sensors.