Classification of educational backgrounds of students using musical intelligence and perception with the help of genetic neural networks

In this study, we demonstrate that machine learning can be used to classify students who had backgrounds in positive-sciences (including engineering, science and math disciplines) vs. social-sciences (including arts and humanities disciplines) by the help of musical hearing and perception using genetic neural networks. Our 80 test subjects had an even mixture of both aforementioned disciplines. Each participant is asked to listen to a melody played on a piano and to repeat the melody himself verbally. Both the original melody and participants repetition is recorded and frequency and amplitude response is analyzed by using fast Fourier transform (FFT). This information is applied to hybrid genetic algorithm and neural networks as learning data and the training of the feed forward neural network is realized. Our results show that by using musical perception our genetic neural network classifies students with positive- and social-science backgrounds at a success rate of 95% and 90%, respectively.