Periodic Time Series Data Analysis by Deep Learning Methodology
Open Access
- 1 December 2020
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 223078-223088
Abstract
The detection of periodicity in a time series is considered a challenge in many research areas. The difficulty of period length extraction involves the varying noise levels among working environments. A system that performs well in one environment may not be accurate in another. Different methods, including deep neural networks, have been proposed across many applications to find suitable solutions to the period length extraction problem. This paper proposes a convolutional neural network (CNN) based period classification algorithm, named PCA, to detect the dataset periods. In particular, assuming that a data stream contains periodical features, the PCA utilizes historical labeled data as training material and classifies new instances accordingly based on their periods. Its performance has been tested on both synthetic and real-world periodic time series data (PTSD) with very encouraging results. In particular, We have observed that the PCA is capable of achieving 100% accuracy in the case of low noise PTSD. Even the training of the PCA is not economical if the data do not contain much noise, it still demonstrates high performance on both synthetic and real-world datasets. Besides, we have shown that our new algorithm can capture the relationship between the shape of the waves and the target period, which is significantly different from the classical methods that mainly focus on the wave’s amplitude.Keywords
This publication has 27 references indexed in Scilit:
- Using dynamic time warping distances as features for improved time series classificationData Mining and Knowledge Discovery, 2015
- Time-Series Classification with COTE: The Collective of Transformation-Based EnsemblesIEEE Transactions on Knowledge and Data Engineering, 2015
- The BOSS is concerned with time series classification in the presence of noiseData Mining and Knowledge Discovery, 2014
- A review of unsupervised feature learning and deep learning for time-series modelingPattern Recognition Letters, 2014
- A time series forest for classification and feature extractionInformation Sciences, 2013
- Classification of time series by shapelet transformationData Mining and Knowledge Discovery, 2013
- A Bag-of-Features Framework to Classify Time SeriesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- Time-series data miningACM Computing Surveys, 2012
- 10 CHALLENGING PROBLEMS IN DATA MINING RESEARCHInternational Journal of Information Technology & Decision Making, 2006
- Dropout from Higher Education: A Theoretical Synthesis of Recent ResearchReview of Educational Research, 1975