The Feature Extraction and Classification of Maternal Cigarette-Smoking Signatures by Euclidean Distance Method and Alternative Neural Networks

Tuğba Saatçı-Ayten, Umut E. Ayten, Oğuzhan Yavuz, and Lale Özyılmaz


Euclidean distance, feature extraction, FLDA


The aim of this study is to propose an efficiency simulation method to determine and classify smoker and non-smoker mother. First, since the length of dataset is large, the features extraction method based on Euclidean distance is applied to dataset for determining informative genes. Then support vector machine (SVM), multi-layer perceptron (MLP) and radial basis function (RBF) are employed to classify the smoker and the non-smoker. SVM is the best classifier among all the classifiers tested using the smoking data set.

Important Links:

Go Back