Medical and pharmaceutical applications
Farzaneh Salami; Ali Bozorgi-Amiri; Reza Tavakkoli-Moghaddam
Abstract
Feature selection is the process of picking the most effective feature among a considerable number of features in the dataset. However, choosing the best subset that gives a higher performance in classification is challenging. This study constructed and validated multiple metaheuristic algorithms to ...
Read More
Feature selection is the process of picking the most effective feature among a considerable number of features in the dataset. However, choosing the best subset that gives a higher performance in classification is challenging. This study constructed and validated multiple metaheuristic algorithms to optimize Machine Learning (ML) models in diagnosing Alzheimer’s. This study aims to classify Cognitively Normal (CN), Mild Cognitive Impairment (MCI), and Alzheimer’s by selecting the best features. The features include Freesurfer features extracted from Magnetic Resonance Imaging (MRI) images and clinical data. We have used well-known ML algorithms for classifying, and after that, we used multiple metaheuristic methods for feature selection and optimizing the objective function of the classification. We considered the objective function a macro-average F1 score because of the imbalanced data. Our procedure not only reduces the irreverent features but also increases the classification performance. Results showed that metaheuristic algorithms could improve the performance of ML methods in diagnosing Alzheimer’s by 20%. We found that classification performance can be significantly enhanced by using appropriate metaheuristic algorithms. Metaheuristic algorithms can help find the best features for medical classification problems, especially Alzheimer’s.
B. Zahiri; M. Mousazadeh; A. Bozorgi-Amiri
Volume 3, Issue 2 , May 2014, , Pages 1-11
Abstract
Blood supply chain network design isanessentialpart of the total blood management systems.In this paper, a mixed integer non-linear programming (MINLP) model for the concerned problem is developed. Optimizing the facility location and flows between each echelon of the considered supply chain is our main ...
Read More
Blood supply chain network design isanessentialpart of the total blood management systems.In this paper, a mixed integer non-linear programming (MINLP) model for the concerned problem is developed. Optimizing the facility location and flows between each echelon of the considered supply chain is our main focus in this study. Also, in order to handle uncertain nature of model parameters, a mix robust stochastic programming approach is applied to the model. Finally, to test the applicability of the proposed model, a numerical example is proposed using random generated data and then sensitivity analysis is done on a model parameter which play a rolein making trade-off between model robustness and optimality robustness.