CLASSIFICATION OF DYNAMIC EGG WEIGHTS USING FEATURE EXTRACTION METHODS

Authors : Gülin ELİBOL SEÇİL, Mehmet YUMURTACI, Semih ERGİN, İsmail YABANOVA

Pages : 499-513

Doi:10.18038/estubtda.658077

View : 18 | Download : 10

Publication Date : 2020-12-28

Article Type : Research Paper

Abstract :In this study, a feature vector is determined in order to classify chicken eggs into four different weight groups by using the dynamic weighing system and then the success rate of different classifiers in the process of weight classification are analyzed. The dynamic weighing system is made of three components; mechanic system, electronic control board, and software. Firstly, a data set is created on the basis of analogue egg weight data obtained from the dynamic weighing system. From the obtained data set, three different feature vectors are extracted by using Time-domain, Power Spectral Density insert ignore into journalissuearticles values(PSD); and Discrete Wavelet Transform insert ignore into journalissuearticles values(DWT);-based methods. The extracted feature vectors are then applied to Linear Bayes Normal Classifier, Fisher’s Linear Discriminant Analysis insert ignore into journalissuearticles values(FLDA);, Support Vector Machine insert ignore into journalissuearticles values(SVM);, Decision Tree insert ignore into journalissuearticles values(DT); and K-Nearest Neighborhood insert ignore into journalissuearticles values(k-NN); classifiers respectively and egg weight classes are determined. A five-fold cross validation is carried out in order to confidentially test the performance of classification. As can be seen from the experimental results, both feature vectors and classifiers are highly successful in determining the weight classes of eggs. It is observed that the most successful features are the entropy values of DWT with a classification rate of 97.01% for k-NN classifier.
Keywords : Dynamic weighing system, Measurement, Signal processing, Feature extraction, Egg classifying