SVM-Based Currency Identification System with Naive Bayes Prediction Accuracy Comparison

To precisely identify the currency's worth using machine learning languages like Support Vector Machine and evaluate the quality of the predictions using Naive Bayes. The Currency Recognition System makes use of machine learning algorithms such as Naive Bayes (n=10) and Support Vector Machine (n=10). Here, a pretest power analysis was performed using a sample size of 20 for each of the two groups and an 80% G-power. Support vector machines with an accuracy of 87.09% and Naive Bayes with an accuracy of 51.61% were used to create the currency recognition system. According to the experiment, the independent samples t-tests and the statistically significant difference of 2-tailed accuracy for both algorithms is <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$0.001(\mathrm{p}&lt;0.05)$</tex>. In the currency recognition system, SVM outperforms Naive Bayes by a wide margin.