Intuitionistic Fuzzy Broad Learning System: Enhancing Robustness Against Noise and Outliers

by   M. Sajid, et al.

In the realm of data classification, broad learning system (BLS) has proven to be a potent tool that utilizes a layer-by-layer feed-forward neural network. It consists of feature learning and enhancement segments, working together to extract intricate features from input data. The traditional BLS treats all samples as equally significant, which makes it less robust and less effective for real-world datasets with noises and outliers. To address this issue, we propose the fuzzy BLS (F-BLS) model, which assigns a fuzzy membership value to each training point to reduce the influence of noises and outliers. In assigning the membership value, the F-BLS model solely considers the distance from samples to the class center in the original feature space without incorporating the extent of non-belongingness to a class. We further propose a novel BLS based on intuitionistic fuzzy theory (IF-BLS). The proposed IF-BLS utilizes intuitionistic fuzzy numbers based on fuzzy membership and non-membership values to assign scores to training points in the high-dimensional feature space by using a kernel function. We evaluate the performance of proposed F-BLS and IF-BLS models on 44 UCI benchmark datasets across diverse domains. Furthermore, Gaussian noise is added to some UCI datasets to assess the robustness of the proposed F-BLS and IF-BLS models. Experimental results demonstrate superior generalization performance of the proposed F-BLS and IF-BLS models compared to baseline models, both with and without Gaussian noise. Additionally, we implement the proposed F-BLS and IF-BLS models on the Alzheimers Disease Neuroimaging Initiative (ADNI) dataset, and promising results showcase the models effectiveness in real-world applications. The proposed methods offer a promising solution to enhance the BLS frameworks ability to handle noise and outliers.


page 1

page 8

page 14

page 15

page 16


Hybrid Adaptive Fuzzy Extreme Learning Machine for text classification

In traditional ELM and its improved versions suffer from the problems of...

Graph Embedded Intuitionistic Fuzzy RVFL for Class Imbalance Learning

The domain of machine learning is confronted with a crucial research are...

Fuzzy Least Squares Twin Support Vector Machines

Least Squares Twin Support Vector Machine (LSTSVM) is an extremely effic...

Three-way Imbalanced Learning based on Fuzzy Twin SVM

Three-way decision (3WD) is a powerful tool for granular computing to de...

Curse of Dimensionality for TSK Fuzzy Neural Networks: Explanation and Solutions

Takagi-Sugeno-Kang (TSK) fuzzy system with Gaussian membership functions...

Data-OOB: Out-of-bag Estimate as a Simple and Efficient Data Value

Data valuation is a powerful framework for providing statistical insight...

Improving Generalization of Deep Fault Detection Models in the Presence of Mislabeled Data

Mislabeled samples are ubiquitous in real-world datasets as rule-based o...

Please sign up or login with your details

Forgot password? Click here to reset