A novel Euclidean quality threshold ARTMAP network and its application to pattern classification

Abstract

This paper introduces a novel neural network model known as the Euclidean quality threshold ARTMAP (EQTAM) network and its application to pattern classification. The model is constructed based on fuzzy ARTMAP (FAM) and the quality threshold clustering principle. The main objective of EQTAM is to overcome the effects of training data sequences on FAM and, at the same time, to improve its classification performance. Several artificial data sets and benchmark medical data sets are used to evaluate the effectiveness of the proposed model. Performance comparisons between EQTAM and ARTMAPbased as well as other classifiers are made. From the experimental results, it can be observed that EQTAM is able to produce good results. More importantly, the performance of EQTAM is robust against the effect of training data orders or sequences.

Improving the iterative back projection estimation through Lorentzian sharp infinite symmetrical filter

“…Therefore, the proposed technique and technique proposed by Patel give a trusty result during the highly blurry effect given. In the future, it is planning to utilize this LSISEF method to improve the effectiveness of quality threshold ARTMAP [95], [96] in pattern recognition problems. In addition, further investigation will be done to increase the performance of the moment invariant technique [97] for the feature extraction process with the use of the LSISEF technique…”

An insect classification analysis based on shape features using quality threshold ARTMAP and moment invariant

“…Quality Threshold ARTMAP (QTAM) [58] is a technique that was developed based on the fundamental concept of FAM neural network and QT clustering strategy [18]. This network is also a supervised learning technique that has the same architecture as FAM (for further details of FAM algorithm please see [6][7][8]).…”

“…In this work, several types of neural networks were used as comparison to QTAM [58] in classifying the insect images. These neural networks are Fuzzy ARTMAP (FAM) [6][7][8], Gaussian ARTMAP (GAM) [55,57], Symmetrical ARTMAP (SyAM) [4], Fully Self-Organizing ARTMAP (FSOAM) [5] and Bayesian ARTMAP (BaAM) [49].…”

“…The main objective of this paper is to investigate the use of Moment Invariant technique as global shape descriptors with a combination of QTAM neural network in order to classify insect images. QTAM network [58] was developed based on the combination between Fuzzy ARTMAP (FAM) [6][7][8] architecture and the fundamental concept Quality Threshold (QT) clustering technique [17]. The network is designed in order to eliminate the effect of data ordering factor which exaggerated the ability of FAM network in classification task.…”

“…The network is designed in order to eliminate the effect of data ordering factor which exaggerated the ability of FAM network in classification task. In addition, the QTAM network also had been demonstrated to generate better prediction accuracy compared to original FAM [58]. Meanwhile moment invariant had been proven as an effective technique especially for shape descriptor either for binary or grey scaled images in many vision applications.…”