Premium
Pedagogy of Bayes’ rule, confusion matrix, transition matrix, and receiver operating characteristics
Author(s) -
Shankar P. Mohana
Publication year - 2019
Publication title -
computer applications in engineering education
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.478
H-Index - 29
eISSN - 1099-0542
pISSN - 1061-3773
DOI - 10.1002/cae.22093
Subject(s) - confusion matrix , computer science , confusion , bridging (networking) , bayes' theorem , a priori and a posteriori , stochastic matrix , machine learning , analytics , matrix (chemical analysis) , naive bayes classifier , artificial intelligence , data mining , data science , bayesian probability , support vector machine , psychology , computer network , philosophy , materials science , epistemology , markov chain , psychoanalysis , composite material
A module has been developed to expand the scope of the undergraduate course in engineering probability to include data analytics. Starting with demos using data from hypothetical experiments in machine vision, students were exposed to the topics of confusion matrix, transition matrix, receiver operating characteristic curves, Bayes’ rule, and concepts of random variables bridging the gap between theory and applications. Student were given unique data sets requiring estimation of a priori and conditional probabilities, positive predictive values, and error rates in the machine vision classifier. Student surveys conducted at the start and conclusion of the course seem to suggest that they gained an enhanced understanding of the applications of probability concepts to data analytics. The methodology can easily be extended to cover other topics such as hypothesis testing and diversity analysis to shift the emphasis of the engineering probability course from pure theory to applications.