Combining Fuzzy C-Means Clustering with Fuzzy Rough Feature Selection

Abstract

With the rapid development of the network, data fusion becomes an important research hotspot. Large amounts of data need to be preprocessed in data fusion; in practice, the features of datasets can be filtered to reduce the amount of data. The feature selection based on fuzzy rough sets can process a large number of continuous and discrete data to reduce the data dimension, making the selected feature subset highly correlated with the classification but less dependent on other features. In this paper, a new method of fuzzy rough feature selection is proposed which combines the membership function determination method of fuzzy c-means clustering and fuzzy equivalence to the original selection. Different from the existing research, our method takes full advantage of knowledge about the dataset itself and the differences between datasets, which makes the features selected have a higher correlation with the classification, improves the classification accuracy, and reduces the data dimension. Experimental results on the UCI machine learning repository datasets confirmed the performance and effectiveness of our method. Compared to the existing method, smaller subsets of features and an average of 1% higher classification accuracies were achieved.

Distance Functions Study in Fuzzy C-Means Core and Reduct Clustering

“…As for the low dimension dataset, it tends to be difficult to determine the core of the analyzed data. These results are consistent with research in the same field [21]. Data with low dimensions will make the computation load lower and the computation time can be increased significantly.…”

“…R. Zhao, L. Gu, dan X. Zhu also did research in the same field as this research. Their research resulted in the combination of the C-Means Clustering and Reduct functioned as Rough Set Feature Selection which able to improve the accuracy with a value averaged in 1% [21]. The addition of the Core process applied in this research guaranteed that the result of the dimension reduction was only acquired from the core of the dataset only.…”

A Fuzzy Rough Model Using Genetic Algorithm for Accuracy Enhancement

“…Also we compare our model with FRFS (Fuzzy Rough Feature Selection) [22], T-FRFS (Threshold Fuzzy Rough Feature Selection) [23] and C-FRFS (C-Means Fuzzy Rough Feature Selection) [24] algorithms on iris and Wine UCI machine learning repository datasets in term of Accuracy and reduct size. The result shows that our algorithm is better than the others in term of Accuracy with this reduct size.…”

“…Our algorithm using Genetic algorithm technique to generate another new fuzzy rule from the initial rules then calculates their accuracy again which will be greater than the old rules before using genetic algorithm. The proposed model is applied on the Iris and Wine datasets and the results compared with other models: Preselection with niches [16], NSGA-II (Non dominated sorting genetic algorithm II) [17,18], ENORA (Evolutionary Non dominated sorting with Radial slots) [19,20], AP-NSGA-II (Average-Point dominated sorting genetic algorithm II) [21], FRFS (Fuzzy Rough Feature Selection) [22], T-FRFS (Threshold Fuzzy Rough Feature Selection) [23] and C-FRFS (C-Means Fuzzy Rough Feature Selection) [24] algorithms in term of number of fuzzy sets (L) and classification rate for evaluating the accuracy of training and test instances (CR) to show its validity.…”

Classification of the mechanism of toxicity as applied to human cell line ECV304

“…In addition, the resulting data sets experience a bias and error from the measurement process as well as from the nature of the biological entity being studied (Kihm et al 2018;William et al 2019). This problem raises new opportunities for data processing using an algorithmic approach rather than the usual statistical methods (Wang 2006;Zhao et al 2019). The algorithm must provide information on the differences, categories and treatments associated with the measurement data sets.…”