#引用

##LaTex

@article{LV201613,
title = “A multi-objective heuristic algorithm for gene expression microarray data classification”,
journal = “Expert Systems with Applications”,
volume = “59”,
pages = “13 - 19”,
year = “2016”,
issn = “0957-4174”,
doi = “https://doi.org/10.1016/j.eswa.2016.04.020”,
url = “http://www.sciencedirect.com/science/article/pii/S0957417416301865”,
author = “Jia Lv and Qinke Peng and Xiao Chen and Zhi Sun”,
keywords = “Microarray, Gene selection, Small number of selected genes, Multi-objective, Heuristic algorithm”
}

##Normal

Jia Lv, Qinke Peng, Xiao Chen, Zhi Sun,
A multi-objective heuristic algorithm for gene expression microarray data classification,
Expert Systems with Applications,
Volume 59,
2016,
Pages 13-19,
ISSN 0957-4174,
https://doi.org/10.1016/j.eswa.2016.04.020.
(http://www.sciencedirect.com/science/article/pii/S0957417416301865)
Keywords: Microarray; Gene selection; Small number of selected genes; Multi-objective; Heuristic algorithm

---

#摘要

Microarray data 微陣列數(shù)據(jù)
analytic hierarchy process (AHP)
Univariate Marginal Distribution Algorithm

the fewer the selected genes are, the less cost the disease prognosis expert system is.

---

#主要內(nèi)容

---

##1 特征預(yù)選擇

a filter-based gene ranking algorithm — mRMR：
特征與類之間的相關(guān)性（max-relevance 最大相關(guān)）
特征之間的冗余度（min-redundancy 最小冗余）

單個特征的性能
為防止丟失在組中表現(xiàn)好的特征，選300個特征

---

##2 多目標(biāo)模型

---

##3 MOEDA

多目標(biāo)the estimation of distribution algorithm (EDA) — MOEDA

elite individuals ( EIs )
regenerated individuals ( RIs )

probabilistic model：

classification accuracy (ACC)
the number of selected features (NSF)

Higher and fewer rule. (HFR)
ACC絕對比NSF重要

• 根據(jù)ACC對個體排序
• 對于相同ACC，根據(jù)NSF排序

Forcibly decrease rule. (FDR)
隨著演化的進(jìn)行，計算NSF的上限 —$U{L}^l$（逐漸降低）
$N{L}^l=\frac{q}{2^{?\frac{l}{w}?}}$
$l$ — 代數(shù)
$q$ — 預(yù)選擇的特征數(shù)目
$w$ — 常數(shù)

每個特征對應(yīng)一個選擇概率

mutation rules — 防止落入局部最優(yōu)
the elite reserved strategy — 防止最優(yōu)個體丟失

SVM + the radial basis function (RBF)
SVM-RBF
參數(shù)：$c$與$\gamma$

同時優(yōu)化參數(shù)與特征

參數(shù)計算

$p\in \left\{c,\gamma \right\}$
${\max }_p$ — 參數(shù)最大值
${\min }_p$ — 參數(shù)最小值
$d$ — 二進(jìn)制字符串的十進(jìn)制值
$l_p$ — 二進(jìn)制字符串的長度
$l_c=l_{\gamma }=25$
${\max }_c=256$
${\max }_{\gamma }=16$

---

#4 試驗

10-fold cross validation

‘the N best features are always not the best N features’.

總結(jié)

以上是生活随笔為你收集整理的基因表达微阵列数据分类的多目标启发式算法的全部內(nèi)容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網(wǎng)站內(nèi)容還不錯，歡迎將生活随笔推薦給好友。