An Evolutionary Multitasking-Based Feature Selection Method for High-Dimensional Classification

2021 ◽  
pp. 1-15
Author(s):  
Ke Chen ◽  
Bing Xue ◽  
Mengjie Zhang ◽  
Fengyu Zhou
Keyword(s):  
Feature Selection ◽  
Feature Selection Method ◽  
Selection Method ◽  
High Dimensional ◽  
Dimensional Classification ◽  
Evolutionary Multitasking

A Novel Feature Selection Method based on MRMR and Enhanced Flower Pollination Algorithm for High Dimensional Biomedical Data

2021 ◽  
Vol 16 ◽  
Author(s):  
Chaokun Yan ◽  
Mengyuan Li ◽  
Jingjing Ma ◽  
Yi Liao ◽  
Huimin Luo ◽  
...  
Keyword(s):  
Feature Selection ◽  
Feature Selection Method ◽  
Selection Method ◽  
High Dimensional ◽  
Flower Pollination Algorithm ◽  
Filter Method ◽  
Biomedical Data ◽  
Local Optima ◽  
Flower Pollination ◽  
Wrapper Method

Background: The massive amount of biomedical data accumulated in the past decades can be utilized for diagnosing disease. Objective: However, its high dimensionality, small sample sizes, and irrelevant features often have a negative influence on the accuracy and speed of disease prediction. Some existing machine learning models cannot capture the patterns on these datasets accurately without utilizing feature selection. Methods: Filter and wrapper are two prevailing feature selection methods. The filter method is fast but has low prediction accuracy, while the latter can obtain high accuracy but has a formidable computation cost. Given the drawbacks of using filter or wrapper individually, a novel feature selection method, called MRMR-EFPATS, is proposed, which hybridizes filter method minimum redundancy maximum relevance (MRMR) and wrapper method based on an improved flower pollination algorithm (FPA). First, MRMR is employed to rank and screen out some important features quickly. These features are further chosen into population individual of the following wrapper method for faster convergence and less computational time. Then, due to its efficiency and flexibility, FPA is adopted to further discover an optimal feature subset. Result: FPA still has some drawbacks such as slow convergence rate, inadequacy in terms of searching for new solutions, and tends to be trapped in local optima. In our work, an elite strategy is adopted to improve the convergence speed of the FPA. Tabu search and Adaptive Gaussian Mutation are employed to improve the search capability of FPA and escape from local optima. Here, the KNN classifier with the 5-fold-CV is utilized to evaluate the classification accuracy. Conclusion: Extensive experimental results on six public high dimensional biomedical datasets show that the proposed MRMR-EFPATS has achieved superior performance compared with other state-of-the-art methods.

PERFORMANCE ANALYSIS OF FEATURE SELECTION METHOD USING ANOVA FOR AUTOMATIC WHEEZE DETECTION

2015 ◽  
Vol 77 (7) ◽  
Author(s):  
Syamimi Mardiah Shaharum ◽  
Kenneth Sundaraj ◽  
Khaled Helmy
Keyword(s):  
Feature Selection ◽  
Classification Accuracy ◽  
Feature Selection Method ◽  
Classification Performance ◽  
Selection Method ◽  
Performance Measure ◽  
High Dimensional ◽  
Artificial Neural Network Ann ◽  
Performance Rate ◽  
One Way Anova

In this work, we show that the classification performance of a high-dimensional features data can be improved by applying feature selection method. One-way ANOVA were utilized and to evaluate the performance measure of the feature selection method, Artificial Neural Network (ANN) was used. From the results obtained, it can be concluded that ANN performance using feature that undergo feature selection method produce a better classification accuracy compared to the ANN performance using feature that did not undergo feature selection method with 93.33% against 80.00% accuracy achieved. Therefore can be conclude that feature selection is a process that is crucial to be done in order to produce a good performance rate. 

Coordinating Computational and Visual Approaches for Interactive Feature Selection and Multivariate Clustering

2003 ◽  
Vol 2 (4) ◽  
pp. 232-246 ◽  
Author(s):  
Diansheng Guo
Keyword(s):  
Feature Selection ◽  
High Dimensional Data ◽  
Feature Selection Method ◽  
Selection Method ◽  
High Dimensional ◽  
Cancer Dataset ◽  
Data Space ◽  
Exploration Environment ◽  
Interactive Feature ◽  
High Dimensional Datasets

Unknown (and unexpected) multivariate patterns lurking in high-dimensional datasets are often very hard to find. This paper describes a human-centered exploration environment, which incorporates a coordinated suite of computational and visualization methods to explore high-dimensional data for uncovering patterns in multivariate spaces. Specifically, it includes: (1) an interactive feature selection method for identifying potentially interesting, multidimensional subspaces from a high-dimensional data space, (2) an interactive, hierarchical clustering method for searching multivariate clusters of arbitrary shape, and (3) a suite of coordinated visualization and computational components centered around the above two methods to facilitate a human-led exploration. The implemented system is used to analyze a cancer dataset and shows that it is efficient and effective for discovering unknown and unexpected multivariate patterns from high-dimensional data.

Sign in / Sign up

Export Citation Format

Share Document