Normalized Sampling Strategical Random Oversampling towards Improving Classifier Performance of Chemical Composition based Ceramic Sample Classification.

Clay, earthen elements, powders, and water mixtures are typically manipulated into desired shapes to create ceramics. The ceramic is then dispersed in a blast furnace, which is a high-temperature oven, after it has been molded. Varnishes are paint-like materials that are used to decorate ceramics and are resistant to water. Manually identifying ceramic samples can lead to the discovery of flaws. The chemical composition of the finished ceramic tiles is not visible. Exact identification of ceramic samples is still a difficult task for the user, as it necessitates more hands-on experience. With this overview, this paper focus on designing an effective workflow for classifying the ceramic samples based on chemical composition. The ceramic chemical sample dataset from KAGGLE with the dataset size of 88 with 19 features having 5 classes of ceramic as 0-"FLQ Ceramic", 1- "DYBS Ceramic", 2-"DYNS Ceramic", 3- "DYY Ceramic", 4- "DYMQC Ceramic". The data is preprocessed and normalized for splitting the training and testing dataset. The normalized dataset is fitted to Anova test analysis to extract the significant features. The insignificant features from Anova test is deleted from the original database dataset and anova normalized dataset is fitted to Exhaustive feature selection using KNN, Naive Bayes, Logistic regression, Decision Tree and Random Forest classifier. The exhaustive feature selected dataset is applied to the above-mentioned classifier algorithms to examine the efficiency with the presence and absence of feature scaling. The exhaustive feature selected dataset is again applied to random oversampling in order to improve the classifier performance. The random oversampled exhaustive feature selected dataset is applied to the above mentioned classifier algorithms to compare the performance metrics like precision, accuracy, fscore, recall and run time. Experimental results shows that the decision tree exhibits 49% accuracy with exhaustive feature selected dataset. The same decision tree classifier shows 100% accuracy after applying random oversampling with exhaustive feature selected dataset. [ABSTRACT FROM AUTHOR]