Time series analysis is a key technology for medical diagnosis,weather forecasting and financial prediction systems.However,missing data frequently occur during data recording,posing a great challenge to data mining tasks.In this study,we propose a novel time series data representation-based denois-ing autoencoder (DAE) for the reconstruction of missing values.Two data representation methods,namely,recurrence plot (RP)and Gramian angular field (GAF),are used to transform the raw time series to a 2D matrix for establishing the temporal correla-tions between different time intervals and extracting the structu-ral patterns from the time series.Then an improved DAE is pro-posed to reconstruct the missing values from the 2D representa-tion of time series.A comprehensive comparison is conducted amongst the different representations on standard datasets.Results show that the 2D representations have a lower recon-struction error than the raw time series,and the RP representa-tion provides the best outcome.This work provides useful in-sights into the better reconstruction of missing values in time series analysis to considerably improve the reliability of time-varying system.