A Hybrid Model Integrating Improved Fuzzy c-means and Optimized Mixed Kernel Relevance Vector Machine for Classification of Coal and Gas Outbursts

The class labels of collected coal and gas outbursts sample data may be wrong, if these collected sample data are directly used for outbursts classification, the accuracy and efficiency are very low. In this paper, a novel hybrid model that integrates fuzzy c-means clustering based on isometric mapping feature extraction and Bayesian optimized mixed kernel relevance vector machine classifier is proposed and applied to improve the classification performance of coal and gas outbursts. First, the isometric mapping is used to extract the non-linear information, then the significant features are selected, in order to improve the classification performance of coal and gas outbursts, the fuzzy c-means is used to perform clustering analysis on the effective features obtained from isometric mapping, mining the structural information and internal regularity of the sample data and estimating classification labels of sample data. Second, A mixed kernel relevance vector machine classifier is proposed to classify coal and gas outbursts, improving the learning and generalization ability of outbursts classification, and the classifier parameters are optimized by Bayesian optimization with global and local search capability remarkably. Finally, the improved fuzzy c-means clustering is integrated into the mixed kernel relevance vector machine classifier model, and Bayesian optimization algorithm is used to help train a better classifier for outbursts classification. The obtained experimental results on the collected actual dataset of coal and gas outbursts show that proposed clustering method can improve the clustering effect and efficiency, decrease the feature vector size up to 50% and achieves the accuracy and running time of 100% and 5.26 s, respectively, which outperforms prior methods with 98% and 5.38 s,the proposed outbursts combined classification model based on classification and clustering model outperforms other methods by 4%-6% with respect to average accuracy. It is believed that the proposed model is very effective for outbursts classification.