Semantic Information Classification of IoT Perception Data Based on Density Peak Fast Search Clustering Algorithm

Abstract

In the rapidly developing field of the Internet of Things today, effective processing and analysis of perceptual data has become crucial. The perception data of the Internet of Things is usually large, diverse, and presents high-dimensional characteristics, which poses new challenges to data clustering algorithms. This study utilizes the K-center point algorithm to optimize the density peak fast search clustering algorithm, proposes a new clustering algorithm, and applies it to the research of semantic classification of perception data in the Internet of Things. Firstly, the K-center algorithm was used to optimize the clustering center optimization process of the density peak fast search clustering algorithm. Then, the optimized algorithm was applied to the automatic semantic classification model. Thus, a new automatic semantic annotation model for IoT aware data has been established. The research results showed that the classification accuracy of the proposed optimization algorithm was as high as 0.98, and the running stability of the automatic semantic annotation model optimized using this algorithm was as high as 0.99, with a running time as low as 1s. In summary, the automatic semantic annotation model built in this study can effectively improve the efficiency and accuracy of semantic classification, thereby providing more accurate and efficient data support for intelligent services.