Determination of endometrial carcinoma with gene expression based on optimized Elman neural network

Hongping Hu, Haiyan Wang, Yanping Bai, Maoxing Liu

    Research output: Contribution to journalArticle

    1 Citation (Scopus)

    Abstract

    Endometrial carcinoma is a life-threatening disease that causes serious damage to the women's health. This paper discusses classifications of 87 endometrial samples with gene expressions that are cancerous or cancer-free. Every sample has 5 indicators. For every indicator, the corresponding genes of the missing data are deleted and the signal noise ratios (SNRs) are calculated to filter the irrelevant genes. Then the obtained new samples use the principle component analysis to decrease the dimensions. Finally 10 random samples are selected to be the testing samples for classification. Thus the classification accuracy rate is given for every indicator. Based on cancer related to 5 indicators, the combination of the 5 indicators is used to classify to make new 87 endometrial samples as cancerous or cancer-free. We repeatedly process these new samples by deleting the missing data, filtering the irrelevant genes with SNRs, and decreasing the dimensions with PCA, an obtain the new data. The proposed method is that the particle swarm algorithm (PSO) and the grey wolf optimizer (GWO) is combined to optimize the parameters of Elman recurrent neural network (ERNN), written as PSOGWO-ERNN. The results show that PSOGWO-ERNN is superior to the single ERNN, ERNN optimized by PSO or GWO (PSO-ERNN or GWO-ERNN), and the classification accuracy rate of PSOGWO-ERNN reaches 88.8506%. The results also show that the neural networks optimized by some swarm intelligence algorithms are more useful for classification.

    Original languageEnglish (US)
    Pages (from-to)204-214
    Number of pages11
    JournalApplied Mathematics and Computation
    Volume341
    DOIs
    StatePublished - Jan 15 2019

    Fingerprint

    Elman Neural Network
    Recurrent neural networks
    Recurrent Neural Networks
    Gene expression
    Gene Expression
    Neural networks
    Particle Swarm Algorithm
    Cancer
    Genes
    Gene
    Missing Data
    Principle Component Analysis
    Swarm Intelligence
    Health
    Filtering
    Damage
    Classify
    Optimise
    Neural Networks
    Filter

    Keywords

    • Elman neural network
    • Endometrial carcinoma
    • Gene expression
    • Grey wolf optimizer
    • Leave-one-out cross validation
    • Particular swarm optimization

    ASJC Scopus subject areas

    • Computational Mathematics
    • Applied Mathematics

    Cite this

    Determination of endometrial carcinoma with gene expression based on optimized Elman neural network. / Hu, Hongping; Wang, Haiyan; Bai, Yanping; Liu, Maoxing.

    In: Applied Mathematics and Computation, Vol. 341, 15.01.2019, p. 204-214.

    Research output: Contribution to journalArticle

    @article{b9bca682577241689d3dcf72833046b3,
    title = "Determination of endometrial carcinoma with gene expression based on optimized Elman neural network",
    abstract = "Endometrial carcinoma is a life-threatening disease that causes serious damage to the women's health. This paper discusses classifications of 87 endometrial samples with gene expressions that are cancerous or cancer-free. Every sample has 5 indicators. For every indicator, the corresponding genes of the missing data are deleted and the signal noise ratios (SNRs) are calculated to filter the irrelevant genes. Then the obtained new samples use the principle component analysis to decrease the dimensions. Finally 10 random samples are selected to be the testing samples for classification. Thus the classification accuracy rate is given for every indicator. Based on cancer related to 5 indicators, the combination of the 5 indicators is used to classify to make new 87 endometrial samples as cancerous or cancer-free. We repeatedly process these new samples by deleting the missing data, filtering the irrelevant genes with SNRs, and decreasing the dimensions with PCA, an obtain the new data. The proposed method is that the particle swarm algorithm (PSO) and the grey wolf optimizer (GWO) is combined to optimize the parameters of Elman recurrent neural network (ERNN), written as PSOGWO-ERNN. The results show that PSOGWO-ERNN is superior to the single ERNN, ERNN optimized by PSO or GWO (PSO-ERNN or GWO-ERNN), and the classification accuracy rate of PSOGWO-ERNN reaches 88.8506{\%}. The results also show that the neural networks optimized by some swarm intelligence algorithms are more useful for classification.",
    keywords = "Elman neural network, Endometrial carcinoma, Gene expression, Grey wolf optimizer, Leave-one-out cross validation, Particular swarm optimization",
    author = "Hongping Hu and Haiyan Wang and Yanping Bai and Maoxing Liu",
    year = "2019",
    month = "1",
    day = "15",
    doi = "10.1016/j.amc.2018.09.005",
    language = "English (US)",
    volume = "341",
    pages = "204--214",
    journal = "Applied Mathematics and Computation",
    issn = "0096-3003",
    publisher = "Elsevier Inc.",

    }

    TY - JOUR

    T1 - Determination of endometrial carcinoma with gene expression based on optimized Elman neural network

    AU - Hu, Hongping

    AU - Wang, Haiyan

    AU - Bai, Yanping

    AU - Liu, Maoxing

    PY - 2019/1/15

    Y1 - 2019/1/15

    N2 - Endometrial carcinoma is a life-threatening disease that causes serious damage to the women's health. This paper discusses classifications of 87 endometrial samples with gene expressions that are cancerous or cancer-free. Every sample has 5 indicators. For every indicator, the corresponding genes of the missing data are deleted and the signal noise ratios (SNRs) are calculated to filter the irrelevant genes. Then the obtained new samples use the principle component analysis to decrease the dimensions. Finally 10 random samples are selected to be the testing samples for classification. Thus the classification accuracy rate is given for every indicator. Based on cancer related to 5 indicators, the combination of the 5 indicators is used to classify to make new 87 endometrial samples as cancerous or cancer-free. We repeatedly process these new samples by deleting the missing data, filtering the irrelevant genes with SNRs, and decreasing the dimensions with PCA, an obtain the new data. The proposed method is that the particle swarm algorithm (PSO) and the grey wolf optimizer (GWO) is combined to optimize the parameters of Elman recurrent neural network (ERNN), written as PSOGWO-ERNN. The results show that PSOGWO-ERNN is superior to the single ERNN, ERNN optimized by PSO or GWO (PSO-ERNN or GWO-ERNN), and the classification accuracy rate of PSOGWO-ERNN reaches 88.8506%. The results also show that the neural networks optimized by some swarm intelligence algorithms are more useful for classification.

    AB - Endometrial carcinoma is a life-threatening disease that causes serious damage to the women's health. This paper discusses classifications of 87 endometrial samples with gene expressions that are cancerous or cancer-free. Every sample has 5 indicators. For every indicator, the corresponding genes of the missing data are deleted and the signal noise ratios (SNRs) are calculated to filter the irrelevant genes. Then the obtained new samples use the principle component analysis to decrease the dimensions. Finally 10 random samples are selected to be the testing samples for classification. Thus the classification accuracy rate is given for every indicator. Based on cancer related to 5 indicators, the combination of the 5 indicators is used to classify to make new 87 endometrial samples as cancerous or cancer-free. We repeatedly process these new samples by deleting the missing data, filtering the irrelevant genes with SNRs, and decreasing the dimensions with PCA, an obtain the new data. The proposed method is that the particle swarm algorithm (PSO) and the grey wolf optimizer (GWO) is combined to optimize the parameters of Elman recurrent neural network (ERNN), written as PSOGWO-ERNN. The results show that PSOGWO-ERNN is superior to the single ERNN, ERNN optimized by PSO or GWO (PSO-ERNN or GWO-ERNN), and the classification accuracy rate of PSOGWO-ERNN reaches 88.8506%. The results also show that the neural networks optimized by some swarm intelligence algorithms are more useful for classification.

    KW - Elman neural network

    KW - Endometrial carcinoma

    KW - Gene expression

    KW - Grey wolf optimizer

    KW - Leave-one-out cross validation

    KW - Particular swarm optimization

    UR - http://www.scopus.com/inward/record.url?scp=85053809597&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=85053809597&partnerID=8YFLogxK

    U2 - 10.1016/j.amc.2018.09.005

    DO - 10.1016/j.amc.2018.09.005

    M3 - Article

    VL - 341

    SP - 204

    EP - 214

    JO - Applied Mathematics and Computation

    JF - Applied Mathematics and Computation

    SN - 0096-3003

    ER -