Association Rule Mining Method Based on the Similarity Metric of Tuple-Relation in Indoor Environment

Abstract

Association rules can detect the association pattern between POIs (point of interest) and serve the application of indoor location. In this paper, a new index, tuple-relation, is defined, which reflects the association strength between POI sets in indoor environment. This index considers the potential association information such as spatial and semantic information between indoor POI sets. On this basis, a new R-FP-growth (tuple-relation frequent pattern growth) algorithm for mining association rules in indoor environment is proposed, which makes comprehensive use of the co-occurrence probability, conditional probability, and multiple potential association information among POI sets, to form a new support-confidence-relation constraint framework and to improve the quality and application value of mining results. Experiments are performed, using real Wi-Fi positioning trajectory data from a shopping mall. Experimental results show that the tuple-relation calculation method based on cosine similarity has the best effect, with an accuracy of 87%, and 19% higher than that of the traditional FP-growth algorithm. INDEX TERMS Association rule, data mining, indoor trajectory, network embedding.

A Stacked Denoising Autoencoder and Long Short-Term Memory Approach With Rule-Based Refinement to Extract Valid Semantic Trajectories

“…This approach, nonetheless, still requires the 2D/3D position to associate with the semantic position. On the other hand, the network-embedding and FP-growth [40] extracts the association rule from the Wi-Fi indoor positioning-based semantic trajectories. Nonetheless, the discovered association rule may not be fully maximized because the size of trajectory dataset is highly reduced due to positioning errors and bad data quality.…”