华法林剂量预测的多目标特征选择

#引用

##LaTex

@article{SOHRABI2017126,
title = “Multi-objective feature selection for warfarin dose prediction”,
journal = “Computational Biology and Chemistry”,
volume = “69”,
pages = “126 - 133”,
year = “2017”,
issn = “1476-9271”,
doi = “https://doi.org/10.1016/j.compbiolchem.2017.06.002”,
url = “http://www.sciencedirect.com/science/article/pii/S1476927116303437”,
author = “Mohammad Karim Sohrabi and Alireza Tajik”,
keywords = “Warfarin, Feature selection, Multi-objective optimization, Artificial neural networks”
}

##Normal

Mohammad Karim Sohrabi, Alireza Tajik,
Multi-objective feature selection for warfarin dose prediction,
Computational Biology and Chemistry,
Volume 69,
2017,
Pages 126-133,
ISSN 1476-9271,
https://doi.org/10.1016/j.compbiolchem.2017.06.002.
(http://www.sciencedirect.com/science/article/pii/S1476927116303437)
Keywords: Warfarin; Feature selection; Multi-objective optimization; Artificial neural networks

---

#摘要

decision support systems
Drug’s dose prediction

• Mean Square Error (MSE)
• root mean square error (RMSE)
• mean absolute error (MAE)

---

#主要内容

Multi-Layer Perceptron (MLP)

1. filter
2. wrapper
3. embedded

quantitative structure-activity relationship (QSAR) model

Multiple linear regression (MLR)
partial least squares regression (PLS)
support-vector machine regression (SVMR)

Monte Carlo

---

##算法

---

###NSGA-II

---

###MOPSO

crowding archive — gbest
concept of the grid — diversity

---

###提出的算法

数据集

indexes MSE, RMSE and MAE were used to evaluate the network

算法

---

###试验