An Application of Machine Learning to Thalassemia Diagnosis

Mediterranean anemia is a genetic disease that currently relies heavily on expert clinical experience to determine whether patients are affected. This method is overly reliant on expert experience and is not precise enough. This paper proposes two modeling methods to predict whether patients have Mediterranean anemia. The first method involves using Principal Component Analysis (PCA) to reduce the dimensionality of the data, followed by logistic regression modeling (PCA-LR) on the reduced dataset. The second method involves building a Partial Least Squares Regression (PLS) model. Experimental results show that the prediction accuracy of the PCA-LR model is 87.5% (degree = 2, λ=4), and the prediction accuracy of the PLS model is 92.5% (ncomp = 4), indicating good predictive performance of the models.

Viscoelastic Models for Passive Arterial Wall Dynamics

This paper compares two models predicting elastic and viscoelastic properties of large arteries.Models compared include a Kelvin(standard linear)model and an extended 2-term exponential linear viscoelastic model.Models were validated against in-vitro data from the ovine thoracic descending aorta and the carotid artery.Measurements of blood pressure data were used as an input to predict vessel cross-sectional area.Material properties were predicted by estimating a set of model parameters that minimize the difference between computed and measured values of the cross-sectional area.The model comparison was carried out using generalized analysis of variance type statistical tests.For the thoracic descending aorta,results suggest that the extended 2-term exponential model does not improve the ability to predict the observed cross-sectional area data,while for the carotid artery the extended model does statistically provide an improved fit to the data.This is in agreement with the fact that the aorta displays more complex nonlinear viscoelastic dynamics,while the stiffer carotid artery mainly displays simpler linear viscoelastic dynamics.

A Wireframe Model-Based Method for Automated Internal Design

This paper proposes a wireframe model-based method for automated internal design. The method is used to extract geometric structure of an internal wireframe model and find out all loop structures of furniture models. The wireframe models are classified as the multiple independent sub-models according to the geometric structure by statistical analysis. The corresponding models are selected from a 3D model database to build an internal scene based on characteristic points of furniture wireframe models. In the experiments 3D database via manually selected 268 3D furniture models from Google 3D warehouse is built up. The experiments show that the method can construct 3D scenes in 1.1×103 ms. This method costs less time compared with traditional hierarchical method and depth-sensing camera method in the same experimental conditions. The method can be also used for 3D visualization either with complex backgrounds.