An Application of Principal Component Analysis in Aspergillus Species Identification

Abstract

Aspergillus sp. is one of the filamentous fungi that has a number of benefits in the food industry. Despite its important roles in industry level, they have several shortcomings especially to immunocompromised individuals that appear to be highly susceptible to disease or infection. Normally, the identification of species was manually screened by the trained microscopists but, the machine learning application becomes as an alternative to identify the species of Aspergillus. However, the development of machine learning is not straightforward and time consuming if the data is not well presented. In order to fasten the identification process of Aspergillus while retaining its characteristics, principal component analysis (PCA) and principal component analysis and Histogram of Oriented Gradient (PCAHOG) were employed to reduce the dimensionality of the dataset. Different values of eigen in PCA were executed and the classification by support vector machine (SVM) with two different kernels such as polynomial and radial basis function (RBF) was done afterwards. Based on the performance evaluation, PCAHOG-SVM (Polynomial) with eigenvalue of 48 outperformed the others with accuracy of 99.43% for training number of 18. Moreover, three Aspergillus sp. have been recorded 100% of accuracy with the same number of trainings.