Search

Cost-sensitive learning is a popular approach to addressing the problem of class imbalance for many classification algorithms in machine learning. However, most cost-sensitive algorithms are dependent on manually designed cost matrices. Unfortunately, in many cases, it is often not easy for humans, even experts, to accurately specify misclassification costs for different mistakes due to the lack of domain knowledge related to actual situations in some complex unbalanced problems. As a result, these cost-sensitive algorithms cannot be directly applied. This paper proposes a new genetic programmingbased approach to developing cost-sensitive classifiers that are independent of manually designed cost matrices. The proposed method is able to construct classifiers and learn cost intervals automatically and simultaneously. In the proposed method, a tree representation, terminal sets and function sets are designed and developed. We examine the effectiveness of the proposed method on ten high-dimensional unbalanced datasets. The experimental results show that the proposed method often outperforms compared methods for highdimensional unbalanced classification. Furthermore, according to the analysis of evolved trees, the constructed classifiers often only need a small number of features to achieve a good classification performance.

In classification, when class overlap is intertwined with the issue of class imbalance, it is often challenging to discover useful patterns because of an ambiguous boundary between the majority class and the minority class. This becomes more difficult if the data is high-dimensional. To date, very few pieces of work have investigated how the class overlap issue can be effectively addressed or alleviated in classification with high-dimensional unbalanced data. In this paper, we propose a new genetic programming based method, which is able to automatically and directly detect borderline instances, in order to address the class overlap issue in classification with high-dimensional unbalanced data. In the proposed method, each individual has two trees to be trained together based on different classification rules. The proposed method is examined and compared with baseline methods on high-dimensional unbalanced datasets. Experimental results show that the proposed method achieves better classification performance than the baseline methods in almost all cases.

Class imbalance is an unavoidable issue in many real-world applications. Learning from unbalanced data, classifiers are often biased toward the majority class, while the minority class is important as well (even more important in many cases). How the issue of class imbalance is addressed becomes more challenging if a classification task further encounters the high dimensionality issue. This paper proposes a new genetic programming (GP) approach to high-dimensional unbalanced classification. A new classification mechanism is proposed for GP to improve its classification performance. This new classification mechanism is independent of a classification threshold to separate the majority class and the minority class. The effectiveness of the proposed method is examined on seven high-dimensional unbalanced datasets. Experimental results indicate that the proposed GP method often performs better than other GP methods that use a fitness function to solve the issue of class imbalance, in terms of classification performance and training time.

Many real-world classification problems encounter the problem of class imbalance. Genetic programming (GP) is one of the most important evolutionary algorithms, making crucial contributions to classification, particularly in the high-dimensional case. However, like other classification algorithms, GP may also develop biased classifiers when the class distribution is unbalanced or skewed. This is because standard GP treats each instance equally and assumes the same cost of different misclassification. In unbalanced classification, misclassification cost of the minority class is often serious than that of the majority class. Cost-sensitive learning has been successfully applied to solve the problem of class imbalance for many classification algorithms, but it has not been heavily investigated in GP. This paper investigates how cost-sensitive learning can be effectively used by GP to address the problem of class imbalance in high-dimensional unbalanced classification. Experimental results on six high-dimensional unbalanced datasets show the better performance of the proposed methods than the compared methods.

High-dimensionality and class imbalance represent two main challenges in classification. Recently, there is a growing number of datasets exhibiting the characteristics of the combination of the class imbalance and high-dimensionality. Genetic programming (GP) has been successfully applied to solve high-dimensional classification tasks. However, most existing GP methods may also suffer from a performance bias if the class distribution is unbalanced. Using fitness functions for cost adjustment is one of the most important methods in GP to address the class imbalance issue. This paper develops new fitness functions in GP to address the class imbalance issue in classification with high-dimensional unbalanced data. Two fitness functions are proposed to increase the performance of the traditional accuracy measures, and one fitness function is proposed to approximate Area Under Curve (AUC) with the goal to save the training time. Experiments on six high-dimensional unbalanced datasets show the better performance of the proposed fitness functions, compared to existing fitness functions.

Genetic programming (GP) has the built-in ability for feature selection when developing classifiers for classification with high-dimensional data. However, due to the problem of class imbalance, the developed classifiers by GP are prone to be biased towards the majority class. Cost-sensitive learning has shown to be effective in addressing the problem of class imbalance. In cost-sensitive learning, cost matrices are often manually designed and then considered by classification algorithms to treat different mistakes differently. However, in many real-world applications, cost matrices are unknown because of the limited domain knowledge in complex situations. Therefore, in this paper, we propose a novel GP method to develop cost-sensitive classifiers, where a cost matrix is automatically learned, instead of requiring it from domain experts. The proposed method is examined and compared with existing methods on ten high-dimensional unbalanced datasets. Experimental results show that the proposed method outperforms the compared GP methods in most cases.

Classification tasks become more challenging when having the curse of dimensionality issue. Recently, there has been an increasing number of datasets with thousands of features. Some classification algorithms often need feature selection to avoid the curse of dimensionality. Genetic programming (GP) has shown success in classification tasks. GP does not require to do feature selection because of its built-in capability to automatically select informative features. However, GP-based methods are often computationally intensive to achieve a good classification accuracy. Based on perspectives from granular computing (GrC), this paper proposes a new approach to linking features hierarchically for GP-based classification. Experiments on seven high-dimensional datasets show the effectiveness of the proposed algorithm in terms of saving training time and enhancing the classification accuracy, compared to baseline methods.