Prediction of Bodyfat using a Linear Regression Model and Body Measurements Abstract
Bodyfat percentage is an important estimator for health. The most accurate method for measuring bodyfat is by underwater weighing which is time-intensive. Predictive analytics (linear regression) using indirect measurements offer a faster method to compute bodyfat percentage. This study analyzes bodyfat data determined by underwater weighing with their corresponding indirect measurements. To predict the bodyfat using these measurements, we compare a traditional linear model, regularized model, subset models (indicator, dichotomous, piecewise, polynomial), and feature engineering models (principal components analysis).
Predicting the Diagnosis of Autism using Classification Models based on fMRI Abstract
Autism spectrum disorder is a lifelong neurodevelopmental disorder that is diagnosed based on behavioral and social interaction patterns. Predictive algorithms provide a novel approach in identifying key neurological biomarkers and subsequent psychiatric diagnosis using functional magnetic resonance imaging (fMRI) data. This study analyzes a dataset collected from studies at 17 international locations as part of the Autism Brain Imaging Dataset Exchange (ABIDE).
Predicting Colon Cancer Using Clustering Models based on DNA Microarray Data Abstract
Colon cancer is a significant public health concern and leading cause of death in the older human population. The healthcare burden can be significantly reduced with earlier detection and preventative measures. Although genetic information has been shown to be altered in the early stage of the disease, DNA sequencing data is highly dimensional and must be analyzed using predictive algorithms.
