Coal-Gangue-Image Classification Method Based on Wolf-Pack-Optimization Using Adaptive Adjustment Factor

To improve the classification accuracy about K-means model for Coal-Gangue-Image, this paper proposed an Coal-Gangue-Image Classification Method (AF-WPOA-Kmeans-CCM) based on K-means and an improved wolf-pack-optimization using Adaptive Adjustment Factor.Firstly, this paper proposed an improved wolf-pack-optimization algorithm(AF-WPOA) using Adaptive Adjustment Factor Strategy(AF) aimed to dynamically adjust the update amount of the population for maintaining the genetic diversity of the population while accelerating convergence speed as well as ASGS devoted to enhance the algorithm's global exploration capability in hunting mechanism and local exploitation power in siege mechanism.Secondly,different weights for each feature dimension were adopted to more accurately reflect the varying importance of different feature dimensions in the classification results while Hilbert space was used to eliminate the drawback of low feature dimensions of the images from this paper resulted to achieving higher classification accuracy in high-dimensional space.Finally,AF-WPOA-Kmeans-CCM was formed by adopting the AF-WOPA to optimize K-means clustering model dedicated to accurate classification of Coal-Gangue-Image. Experimental results show that AF-WPOA outperforms GA, PSO and LWCA, while AF-WPOA-Kmeans-CCM performs better than Kmeans-CCM, GA-Kmeans-CCM, PSO-Kmeans-CCM, and LWCA-Kmeans-CCM—achieving 93.03% and 91.55% classification ac-curacy on the training and testing sets, respectively. Unfortunately, Coal-Gangue-Image often have diverse sources and significant feature differences. This makes it hard for fixed cluster centers to fully represent the numerous, multi-source, and highly variable unknown samples to be predicted.