Time series classification based on temporal features

Along with the widespread application of Internet of things technology, time series classification have been becoming a research hotspot in the field of data mining for massive sensing devices generate time series all the time. However, how to accurately classify time series based on intuitively interpretable features is still a huge challenge. For this, we proposed a new Time Series Classification method based on Temporal Features (TSC-TF). TSC-TF firstly generates some temporal feature candidates through time series segmentation. And then, TSC-TF selects temporal feature according the importance measures with the help of a random forest. Finally, TSC-TF trains a fully convolutional network to obtain high accuracy. Experiments on various datasets from the UCR time series classification archive demonstrate the superiority of our method. Besides, we have released the codes and parameters to facilitate the community research. (c) 2022 Elsevier B.V. All rights reserved.

Automated summary

With the increasing application of Internet of Things technology, time series classification has become a research hotspot in the field of data mining. This paper proposes a new method for time series classification based on temporal features (TSC-TF), which generates temporal feature candidates through time series segmentation and selects important features with the help of a random forest. The experimental results on various datasets demonstrate the superiority of the proposed method.