Convolutional Neural Network Based Detection of Seasonal Features in Time Series Data

Abstract

Seasonal features of various kinds of time-varying nodes in large-scale complex networks could facilitate the effective network optimization. It is necessary to find the nodes with seasonal features from the limited labeled training set. In this paper, we proposed a sequence convolutional neural network model to detect the seasonal features in time series data, as well as the method of time series upscaling and subsequence embedding as data preprocessing. Experimental results show the effectiveness of our proposed model.