Feature selection using neighborhood entropy-based uncertainty measures for gene expression data classification

Sun, Lin; Zhang, Xiaoyu; Qian, Yuhua; Xu, Jiucheng; Zhang, Shiguang

doi:10.1016/j.ins.2019.05.072

Cited by 210 publications

(83 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many practical applications display that polynomial and Gaussian kernels perform well under general smooth assumptions. In this case study, polynomial and Gaussian kernel functions are utilized in models

-SVR, the

-SVR model of Gauss homoscedastic noise (GN-SVR), and GLM-SVR as below [ 51 , 52 ].

and

where d is a positive integer and

is positive.…”

Section: Case Studymentioning

confidence: 99%

ν-Support Vector Regression Model Based on Gauss-Laplace Mixture Noise Characteristic for Wind Speed Prediction

Zhang

Zhou

Sun

et al. 2019

Entropy

Self Cite

View full text Add to dashboard Cite

Most regression techniques assume that the noise characteristics are subject to single noise distribution whereas the wind speed prediction is difficult to model by the single noise distribution because the noise of wind speed is complicated due to its intermittency and random fluctuations. Therefore, we will present the ν -support vector regression model of Gauss-Laplace mixture heteroscedastic noise (GLM-SVR) and Gauss-Laplace mixture homoscedastic noise (GLMH-SVR) for complex noise. The augmented Lagrange multiplier method is introduced to solve models GLM-SVR and GLMH-SVR. The proposed model is applied to short-term wind speed forecasting using historical data to predict future wind speed at a certain time. The experimental results show that the proposed technique outperforms the single noise technique and obtains good performance.

show abstract

-SVR, the

-SVR model of Gauss homoscedastic noise (GN-SVR), and GLM-SVR as below [ 51 , 52 ].

and

where d is a positive integer and

is positive.…”

Section: Case Studymentioning

confidence: 99%

ν-Support Vector Regression Model Based on Gauss-Laplace Mixture Noise Characteristic for Wind Speed Prediction

Zhang

Zhou

Sun

et al. 2019

Entropy

Self Cite

View full text Add to dashboard Cite

show abstract

“…(5) In (5), indicates the weight of the classifier, the main aim of ensemble classifier is to minimize the objective function or criterion. Here, the objective function is also called as a cost loss function or error function.…”

Section: Figure 3 Bivariate Regression Treementioning

confidence: 99%

“…But the method failed to minimize the computational complexity of cancer prediction. A neighborhood entropy-based uncertainty measures were introduced in [5] for selecting the relevant feature to perform the cancer classification. The designed method failed to improve the classification performance of cancer detection.…”

mentioning

confidence: 99%

Neighbor Embedding Feature Selected Light Gradient Boosting Classification for Breast Cancer Detection with Gene Expression Data

2019

IJITEE

View full text Add to dashboard Cite

Breast cancer is one of the most frequently diagnosed cancers among women worldwide. Accurate detection of Breast cancer is essential for providing better treatment and risk minimization of the patients. Recently, the collection of biological data like gene expression, protein sequences, DNA sequences are used due to improvements of accessible data mining techniques to diagnosis the disease at an earlier stage. The current state-of-art methods reported to have certain limitations in their diagnostic capability. In order to improve the breast cancer classification, an efficient technique called Gaussian Kernelized Neighbor Embedding based Light Gradient Boost Classification (GKNE-LGBC) technique is introduced. The GKNE-LGBC technique considers the benchmark microarray dataset and performs two processes such as feature selection and classification for detecting breast cancer using gene expression data. The number of gene and the data are collected from the microarray dataset. After collecting, the Gaussian Kernelized stochastic neighbor embedding algorithm is applied to select the relevant features (i.e. genes) and remove the irrelevant features based on the distance similarity. Next, the classification of the gene expression data is done with the help of steepest descent light gradient boosting algorithm. The boosting algorithm initially constructs’ number of weak learners i.e. bivariate regression tree to classify the input expression data into normal or cancerous with the selected features. Then the weak classifiers are combined into strong by minimizing the training error. This helps to improve breast cancer detection accuracy and minimizes the false positive rate. The experimental evaluation is carried out using gene microarray dataset with various parameters such as breast cancer detection accuracy, false positive rate and breast cancer detection time with a number of genes. The experimental results confirm that the proposed GKNE-LGBC technique accurately identifies breast cancer with higher accuracy, and minimal time complexity as well as false positive rate as compared to the state-of-art- methods.

show abstract

“…Using a suitable kernel function

, nonlinear-mappings can be estimated by kernel

, which is an extended

with kernel techniques. In recent years,

as a data-rich nonlinear forecasting tool has been increasingly welcomed [ 7 ], which is applicable in many different contexts [ 8 , 9 , 10 ], such as machine learning, optical character recognition, and especially wind speed/power forecasting.…”

Section: Introductionmentioning

confidence: 99%

LSSVR Model of G-L Mixed Noise-Characteristic with Its Applications

Zhang

Zhou

Sun

et al. 2020

Entropy

Self Cite

View full text Add to dashboard Cite

Due to the complexity of wind speed, it has been reported that mixed-noise models, constituted by multiple noise distributions, perform better than single-noise models. However, most existing regression models suppose that the noise distribution is single. Therefore, we study the Least square S V R of the Gaussian–Laplacian mixed homoscedastic ( G L M − L S S V R ) and heteroscedastic noise ( G L M H − L S S V R ) for complicated or unknown noise distributions. The ALM technique is used to solve model G L M − L S S V R . G L M − L S S V R is used to predict short-term wind speed with historical data. The prediction results indicate that the presented model is superior to the single-noise model, and has fine performance.

show abstract

Feature selection using neighborhood entropy-based uncertainty measures for gene expression data classification

Cited by 210 publications

References 42 publications

ν-Support Vector Regression Model Based on Gauss-Laplace Mixture Noise Characteristic for Wind Speed Prediction

ν-Support Vector Regression Model Based on Gauss-Laplace Mixture Noise Characteristic for Wind Speed Prediction

Neighbor Embedding Feature Selected Light Gradient Boosting Classification for Breast Cancer Detection with Gene Expression Data

LSSVR Model of G-L Mixed Noise-Characteristic with Its Applications

Contact Info

Product

Resources

About