A search for patterns in uncertain time series is time-expensive in today's large databases using the currently available methods. To accelerate the search process for uncertain time series data, in this paper, we explore a spatial index structure, which uses uncertain information stored in minimum bounding rectangle and ameliorates the general prune/search process along the path from the root to leaves. To get a better performance, we normalize the uncertain time series using the weighted variance before the prune/hit process. Meanwhile, we add two goodness measures with respect to the variance to improve the robustness. The extensive experiments show that, compared with the primitive probabilistic similarity search algorithm, the prune/hit process of the spatial index can be more efficient and robust using the specific preprocess and variant index operations with just a little loss of accuracy. ACM CCS (2012) Classification: Mathematics of computing → Probability and statistics → Statistical paradigms → Time series analysis Information systems → Information retrieval → Retrieval models and ranking → Similarity measures

To achieve fast retrieval of online data, it is needed for the retrieval algorithm to increase throughput while reducing latency. Based on the traditional online processing algorithm for time series data, we propose a spatial index structure that can be updated and searched quickly in a real-time environment. At the same time, we introduce an adaptive segmentation method to divide the space corresponding to nodes. Unlike traditional retrieval algorithms, for uncertain time series, the distance threshold used for screening will dynamically change due to noise during the search process. Extensive experiments are conducted to compare the accuracy of the query results and the timeliness of the algorithm. The results show that the index structure proposed in this paper has better efficiency while maintaining a similar true positive ratio.