Convergence and objective functions of noise-injected multilayer perceptrons with hidden multipliers

Wang, Xiangyu; Wang, Jian; Zhang, Kai; Feng, Lin; Chang, Qin

doi:10.1016/j.neucom.2020.03.119

Cited by 35 publications

(4 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Note that the accuracy in the table refers to the balanced accuracy calculated using Eq. (21). The running time in Table 3 is in minutes and in Table 4 the running time is in seconds.…”

Section: Resultsmentioning

confidence: 99%

“…A multilayer perceptron is a classical feed-forward neural network that efficiently solves nonlinear problems [21], such as classification and regression. For classification problems, it maps a set of input sample data into the category space and obtains the posterior probability that a sample belongs to a class, thus classifying the sample.…”

Section: Neural Networkmentioning

confidence: 99%

See 1 more Smart Citation

Two-stage improved Grey Wolf optimization algorithm for feature selection on high-dimensional classification

Shen¹,

Zhang

2021

Complex Intell. Syst.

Self Cite

View full text Add to dashboard Cite

In recent years, evolutionary algorithms have shown great advantages in the field of feature selection because of their simplicity and potential global search capability. However, most of the existing feature selection algorithms based on evolutionary computation are wrapper methods, which are computationally expensive, especially for high-dimensional biomedical data. To significantly reduce the computational cost, it is essential to study an effective evaluation method. In this paper, a two-stage improved gray wolf optimization (IGWO) algorithm for feature selection on high-dimensional data is proposed. In the first stage, a multilayer perceptron (MLP) network with group lasso regularization terms is first trained to construct an integer optimization problem using the proposed algorithm for pre-selection of features and optimization of the hidden layer structure. The dataset is compressed using the feature subset obtained in the first stage. In the second stage, a multilayer perceptron network with group lasso regularization terms is retrained using the compressed dataset, and the proposed algorithm is employed to construct the discrete optimization problem for feature selection. Meanwhile, a rapid evaluation strategy is constructed to mitigate the evaluation cost and improve the evaluation efficiency in the feature selection process. The effectiveness of the algorithm was analyzed on ten gene expression datasets. The experimental results show that the proposed algorithm not only removes almost more than 95.7% of the features in all datasets, but also has better classification accuracy on the test set. In addition, the advantages of the proposed algorithm in terms of time consumption, classification accuracy and feature subset size become more and more prominent as the dimensionality of the feature selection problem increases. This indicates that the proposed algorithm is particularly suitable for solving high-dimensional feature selection problems.

show abstract

“…Note that the accuracy in the table refers to the balanced accuracy calculated using Eq. (21). The running time in Table 3 is in minutes and in Table 4 the running time is in seconds.…”

Section: Resultsmentioning

confidence: 99%

Section: Neural Networkmentioning

confidence: 99%

Two-stage improved Grey Wolf optimization algorithm for feature selection on high-dimensional classification

Shen¹,

Zhang

2021

Complex Intell. Syst.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Precision was defined as the number of true biomarkers selected out of the total number of metabolites identified by the BioMark program. A recently developed neural network was used to evaluate accuracy of predicting group assignment [ 29 ]. The MLPHM method uses a gate function that is applied to the hidden layers to reduce the number of hidden nodes and can incorporate noise to perturb the weights.…”

Section: Methodsmentioning

confidence: 99%

Comparison of Two Automated Targeted Metabolomics Programs to Manual Profiling by an Experienced Spectroscopist for 1H-NMR Spectra

et al. 2022

Self Cite

View full text Add to dashboard Cite

Automated programs that carry out targeted metabolite identification and quantification using proton nuclear magnetic resonance spectra can overcome time and cost barriers that limit metabolomics use. However, their performance needs to be comparable to that of an experienced spectroscopist. A previously analyzed pediatric sepsis data set of serum samples was used to compare results generated by the automated programs rDolphin and BATMAN with the results obtained by manual profiling for 58 identified metabolites. Metabolites were selected using Student’s t-tests and evaluated with several performance metrics. The manual profiling results had the highest performance metrics values, especially for sensitivity (76.9%), area under the receiver operating characteristic curve (0.90), precision (62.5%), and testing accuracy based on a neural net (88.6%). All three approaches had high specificity values (77.7–86.7%). Manual profiling by an expert spectroscopist outperformed two open-source automated programs, indicating that further development is needed to achieve acceptable performance levels.

show abstract

“…A multilayer perceptron (MLP), also known as an artificial neural network (ANN), is a forward structure of artificial neural networks. MLP is one of the most popular networks and possesses a powerful ability to solve nonlinear problems and is highly efficient at calculation [37][38][39].…”

Section: Machine Learning Methodsmentioning

confidence: 99%

Analysis and Prediction of Gestational Diabetes Mellitus by the Ensemble Learning Method

Wang

Zhang

et al. 2022

Int J Comput Intell Syst

View full text Add to dashboard Cite

Gestational diabetes mellitus (GDM) is the most common disease in pregnancy and can cause a series of maternal and infant complications. A new study shows that GDM affects one in six deliveries. Identifying and screening for risk factors for GDM can effectively help intervene and improve the condition of women and their children. Therefore, the aim of this paper is to determine the risk factors for GDM and to use the ensemble learning method to judge whether pregnant women suffer from GDM more accurately. First, this study involves six commonly used machine learning algorithms to analyze the GDM data from the Tianchi competition, selects the risk factors according to the ranking of each model, and uses the Shapley additive interpreter method to determine the importance of the selected risk factors. Second, the combined weighting method was used to analyze and evaluate the risk factors for gestational diabetes and to determine a group of important factors. Lastly, a new integrated light gradient-boosting machine-extreme gradient boosting-gradient boosting tree (LightGBM-Xgboost-GB) learning method is proposed to determine whether pregnant women have gestational diabetes mellitus. We used the gray correlation degree to calculate the weight and used a genetic algorithm for optimization. In terms of prediction accuracy and comprehensive effects, the final model is better than the commonly used machine learning model. The ensemble learning model is comprehensive and flexible and can be used to determine whether pregnant women suffer from GDM. In addition to disease prediction, the model can also be extended for use to many other areas of research.

show abstract

Convergence and objective functions of noise-injected multilayer perceptrons with hidden multipliers

Cited by 35 publications

References 22 publications

Two-stage improved Grey Wolf optimization algorithm for feature selection on high-dimensional classification

Two-stage improved Grey Wolf optimization algorithm for feature selection on high-dimensional classification

Comparison of Two Automated Targeted Metabolomics Programs to Manual Profiling by an Experienced Spectroscopist for 1H-NMR Spectra

Analysis and Prediction of Gestational Diabetes Mellitus by the Ensemble Learning Method

Contact Info

Product

Resources

About