Classification of potatoes according to their cultivated field by SVM and KNN approaches using an electronic nose

In this article, we propose a homemade electronic nose to distinguish between two types of potatoes: the first type is traditionally treated with donkey and sheep manure, other chicken manure. The proposed tool consists network commercial metal oxide sensors, data acquisition card, personal computer for pre-processing processing. Two methods were used, namely, support vector machines (SVM) k-nearest neighbors (KNN) 5-fold cross-validation which achieved same success rate 97.5%. These results demonstrate that our concept, quick, simple, inexpensive, can discriminate potatoes based on method fertilization used in field.