Multiple Filter-Based Rankers to Guide Hybrid Grasshopper Optimization Algorithm and Simulated Annealing for Feature Selection With High Dimensional Multi-Class Imbalanced Datasets

Abstract

DNA microarray data analysis is infamous due to a massive number of features, imbalanced class distribution, and limited available samples. In this paper, we focus on high-dimensional multi-class imbalanced problems. The high dimensional and multi-class imbalanced problem has posed acute challenges for the conventional classifiers to effectively perform classification tasks on both the minority and majority classes. Numerous efforts have been devoted to addressing either high dimensionality dataset or class imbalance problems. Nonetheless, few methods have been proposed to address the intersection of multi-class imbalanced and high-dimensional problems concurrently due to their intricate interactions. This paper presents novel hybrid algorithms for feature selection with the high dimensional multi-class imbalanced problem using multiple filter-based rankers (MFR) and hybrid Grasshopper optimization algorithm (GOA). The Simulated Annealing (SA) algorithm is incorporated into GOA. SA is used to enhance the best solution found by the GOA algorithm. The aim of using the SA here is to tackle the slow convergence and improve the exploitation by searching the high-quality regions found by the GOA. The experimental results confirm the effectiveness of the proposed methods in improving the classification performance in terms of area under the curve (AUC) compared to other well-known methods, which guarantees the ability of the proposed methods in searching the feature space and identifying very robust and discriminative features that best predict the minority class.

Artificial Intelligence Techniques for Fraud Detection

“…Common fraud detection datasets share certain characteristics essential for the effectiveness of machine learning models. Imbalanced class distribution, where the majority of instances are nonfraudulent, mirrors the real-world scenario but necessitates careful handling to prevent model bias [70]. Temporal aspects, such as time-based patterns in transaction data, are often present to capture the dynamic nature of fraudulent activities.…”

Fractal feature selection model for enhancing high-dimensional biological problems

“…Using statistical models for feature selection has several advantages. These models can help identify the most essential features in a dataset, reduce the dimensionality of the data, and improve the performance of machine learning algorithms [ 13 – 15 ]. However, wrapper models for feature selection can have drawbacks, such as randomness and unstable results.…”

Recognition of Air Passengers' Willingness to Pay for Seat Selection for Imbalanced Data Based on Improved XGBoost

“…Shahee et al(Shahee & Ananthakumar, 2020) used the effective complex distance measure to properly select the iteratively modified features, so as to obtain the final feature ranking and the unbalanced features between and within the classes are combined. Sharifai et al(Sharifai & Zainol, 2021) combined the feature ranking of the six filters to select the feature set that exceeds the set threshold, then searched the feature space and mine high-quality features to enhance the capability to predict minority classes. Kim et al(Kim, Kang, & Sohn, 2021) applied the ensemble learning paradigm to the feature evaluation process through the feature evaluation scheme based on filtering method, which accurately recognized the features with good robustness and greatly reduces the calculation time.…”