密集标签识别场景的改进DFSA算法应用

In the process of RFID tag recognition, the reading and recognition efficiency of dense tag environment is low and affects the accuracy of recognition. Aiming at this problem, this paper analyzes the defects of the traditional DFSA algorithm, and proposes an RFID tag grouping scheme based on the improved K-Means clustering algorithm. The scheme uses unique identifiers to label tags for clustering and analysis. Secondly, this scheme improves the traditional K-Means clustering method, and obtains new centroids through the maximum and minimum distance and Euclidean distance, so as to solve the limitation that the traditional K-Means clustering method relies too much on the initial centroid. In this paper, the proposed DFSA radio frequency tag grouping scheme based on improved K-Means clustering is simulated and verified, and its performance is compared with the traditional DFSA algorithm and the DFSA algorithm based on the traditional K-Means clustering algorithm for performance comparison and total recognition time calculation analysis. The results show that in the dense RFID deployment, the DFSA algorithm based on the improved K-Means clustering proposed in this paper has obvious advantages in both recognition accuracy and total recognition time.