Multi-population adaptive genetic algorithm for selection of microarray biomarkers

Improved genetic algorithm optimized LSTM model and its application in short-term traffic flow prediction

Considering that the road short-term traffic flow has strong time series correlation characteristics, a new long-term and short-term memory neural network (LSTM)-based prediction model optimized by the improved genetic algorithm (IGA) is proposed to improve the prediction accuracy of road traffic flow. Firstly, an improved genetic algorithm (IGA) is proposed by dynamically adjusting the mutation rate and crossover rate of standard GA. Secondly, the parameters of the LSTM, such as the number of hidden units, training times, gradient threshold and learning rate, are optimized by the IGA. Therefore, the optimal parameters are obtained. In the analysis stage, 5-min short-term traffic flow data are used to demonstrate the superiority of the proposed method over the existing neural network algorithms. Finally, the results show that the Root Mean Square Error achieved by the proposed algorithm is lower than that achieved by the other neural network methods in both the weekday and weekend data sets. This verifies that the algorithm can adapt well to different kinds of data and achieve higher prediction accuracy.

AI for Health-Related Data Modeling, DCN Application Analysis

Data modeling of health-related data from Data Center (DC) has positive effects for health monitoring, disease prevention, and healthcare research. However, health-related data has the characteristics of huge, high-dimensional, and non-normalized, which are not beneficial to direct analysis, so data needs to be preprocessed before data modeling. This paper focuses on the features of health-related data, and outlier detection during data preprocessing is studied. Meanwhile, we propose an improved algorithm for health-related data based outlier detection. The experimental results reveal that the proposed outlier detection algorithm has a smaller running time, and more outliers are detected compared to three baselines. In addition, local importance based random forest feature selection algorithm is proposed to measure the importance of each feature. The experimental results indicate that the proposed algorithm can select optimal feature subset to apply health-related data.

Detecting biomarkers from microarray data using distributed correlation based gene selection

BACKGROUND

Over the past few decades, DNA microarray technology has emerged as a prevailing process for early identification of cancer subtypes. Several feature selection (FS) techniques have been widely applied for identifying cancer from microarray gene data but only very few studies have been conducted on distributing the feature selection process for detecting cancer subtypes.

OBJECTIVE

Not all the gene expressions are needed in prediction, this research article objective is to select discriminative biomarkers by using distributed FS method which helps in accurately diagnosis of cancer subtype. Traditional feature selection techniques have several drawbacks like unrelated features that could perform well in terms of classification accuracy with a suitable subset of genes will be left out of the selection.

METHOD

To overcome the issue, in this paper a new filter-based method for gene selection is introduced which can select the highly relevant genes for distinguishing tissues from the gene expression dataset. In addition, it is used to compute the relation between gene-gene and gene-class and simultaneously identify subset of essential genes. Our method is tested on Diffuse Large B cell Lymphoma (DLBCL) dataset by using well-known classification techniques such as support vector machine, naïve Bayes, k-nearest neighbor, and decision tree.

RESULTS

Results on biological DLBCL dataset demonstrate that the proposed method provides promising tools for the prediction of cancer type, with the prediction accuracy of 97.62%, precision of 94.23%, sensitivity of 94.12%, F-measure of 90.12%, and ROC value of 99.75%.

CONCLUSION

The experimental results reveal the fact that the proposed method is significantly improved classification accuracy and execution time, compared to existing standard algorithms when applied to the non-partitioned dataset. Furthermore, the extracted genes are biologically sound and agree with the outcome of relevant biomedical studies.