BSPST:A classification algorithm based on shape transformation

With the rapid development of sensor components, a large number of time series have been generated by various sensors, and many time series classification (TSC) algorithms have been proposed to process these data. Among them, the algorithm based on hapelet attracts much attention because of its high accuracy and explanability. However, the high time complexity of the algorithm based on Shapelet and the poor quality of the selected Shapelet limit the accuracy and running time of the classification. This paper presents an improved time series classification algorithm based on Shapelet transformation (BSPST), which greatly reduces the time for Shapelet selection and greatly improves the quality of Shapelet discrimination. A high-quality set of candidate Shapelets is preserved to build classification models using Bloom filters and similarity matching. Data is converted using Shapelet conversion technology. Sufficient experimental validation was performed with 44 common datasets. Testing the classification accuracy and running time, experiments show that BSPST keeps a high accuracy and is significantly faster than the existing Shapelet selection algorithm. It effectively solves the problem of time series classification for a variety of sensor instruments.