Date of Graduation

8-2020

Document Type

Thesis

Degree Name

Bachelor of Science in Industrial Engineering

Degree Level

Undergraduate

Department

Industrial Engineering

Advisor/Mentor

Chimka, Justin

Committee Member/Reader

Rainwater, Chase

Abstract

One of the most common tools for evaluating data is regression. This technique, widely used by industrial engineers, explores linear relationships between predictors and the response. Each observation of the response is a fixed linear combination of the predictors with an added error element. The method is built on the assumption that this error is normally distributed across all observations and has a mean of zero. In some cases, it has been found that the inherent variation is not the result of a random variable, but is instead the result of self-symmetric properties of the observations. For data with these characteristics, fractal analysis can be used to explain the variation. There has been evidence from previous work that musical pieces have to some degree a fractal structure, but there remains to be more work done on performing fractal analysis to musical pieces. In this research, a computationally efficient method of performing fractal analysis on time-series data is applied to a musical recording. It is then determined whether this fractal dimension is a suitable measure to distinguish between musical genres.

Keywords

fractal dimension, fractals, music categorization, time-series data, GTZAN, machine learning

full_data.csv (78 kB)

Share

COinS