Incremental Hyper-Sphere Partitioning for Classification

Abstract

In this paper, an Incremental Hyper-Sphere Partitioning (IHSP) approach to classification on the basis of Incremental Linear Encoding Genetic Algorithm (ILEGA) is proposed. Hyper-spheres approximating boundaries to a given classification problem, are searched with an incremental approach based on a unique combination of genetic algorithm (GA), output partitioning and pattern reduction. ILEGA is used to cope with the difficulty of classification problems caused by the complex pattern relationship and curse of dimensionality. Classification problems are solved by a simple and flexible chromosome encoding scheme which is different from that was proposed in Incremental Hyper-plane Partitioning (IHPP) for classification. The algorithm is tested with 7 datasets. The experimental results show that IHSP performs better compared with those classified using hyper-planes and normal GA.

Incremental Maximum Gaussian Mixture Partition For Classification

“…IMGMP extends the previous research of IHPP [5] and IHSP [12,13]. It breaks through the restriction of classifiers' shape and raises a self-adaptive method to create classifiers.…”

“…In order to flexibly represent the decision boundary, researchers try to combine a set of boundaries to simulate the actual boundary. For instance, Jinghao and Binge use a set of hyper-planes [11] or hyper-spheres [12,13] (HSP [13] use PSO algorithm, and ILEGA [12] use GA algorithm ) to form a complex decision hyper-surface. In generally, the patterns of a class are scatted over the space and form a group of dispersed clusters [14].…”

“…IHPP (Incremental Hyper-Plane Partitioning) [11] employs hyper-planes to incrementally slice the space until the area of target class can be distinguished from other classes. IHSP (Incremental Hyper-Spheres Partitioning) [12,13] uses GA or PSO to dynamically search the whole data space to find the clusters of each class and then a group of hyper spheres will be employed to represent the clusters as classifiers. Research also describes above method as an expert system.…”

“…In order to flexibly represent the decision boundary, researchers try to combine a set of boundaries to simulate the actual boundary. For instance, Jinghao and Binge use a set of hyper-planes [11] or hyper-spheres [12,13] [12,13] uses GA or PSO to dynamically search the whole data space to find the clusters of each class and then a group of hyper spheres will be employed to represent the clusters as classifiers. Research also describes above method as an expert system.…”

Density and Distance Based KNN Approach to Classification

“…This information shows how far the training datum can influence. That is to say, it is a method that can classify the data sets with any-shape clustering conditions comparing to some methods that select a geometric shape to enclose data within it belonging to a specific class (Song and Guan, 2014). After the training stage, in the space, every training datum contains a region that represents how far this training datum can influence in space.…”