Next Article in Journal
An Approach to Determining the Spatially Contiguous Zone of a Self-Organized Urban Agglomeration
Next Article in Special Issue
Sustainable Local Currency Debt: An Analysis of Foreigners’ Korea Treasury Bonds Investments Using a LA-VARX Model
Previous Article in Journal
Rural-Urban Migration and the Growth of Informal Settlements: A Socio-Ecological System Conceptualization with Insights Through a “Water Lens”
Previous Article in Special Issue
Policy Reforms and Productivity Change in the Dutch Drinking Water Industry: A Time Series Analysis 1980–2015
Open AccessArticle

Loss-Driven Adversarial Ensemble Deep Learning for On-Line Time Series Analysis

Industrial Engineering, Seoul National University, Seoul 08826, Korea
Industrial and Mathematical Data Analytics Research Center, Seoul National University, Seoul 08826, Korea
Author to whom correspondence should be addressed.
Sustainability 2019, 11(12), 3489;
Received: 28 May 2019 / Revised: 18 June 2019 / Accepted: 20 June 2019 / Published: 25 June 2019
(This article belongs to the Special Issue Application of Time Series Analyses in Business)
Developing a robust and sustainable system is an important problem in which deep learning models are used in real-world applications. Ensemble methods combine diverse models to improve performance and achieve robustness. The analysis of time series data requires dealing with continuously incoming instances; however, most ensemble models suffer when adapting to a change in data distribution. Therefore, we propose an on-line ensemble deep learning algorithm that aggregates deep learning models and adjusts the ensemble weight based on loss value in this study. We theoretically demonstrate that the ensemble weight converges to the limiting distribution, and, thus, minimizes the average total loss from a new regret measure based on adversarial assumption. We also present an overall framework that can be applied to analyze time series. In the experiments, we focused on the on-line phase, in which the ensemble models predict the binary class for the simulated data and the financial and non-financial real data. The proposed method outperformed other ensemble approaches. Moreover, our method was not only robust to the intentional attacks but also sustainable in data distribution changes. In the future, our algorithm can be extended to regression and multiclass classification problems. View Full-Text
Keywords: ensemble deep learning; on-line learning; time series analysis; adaptive learning ensemble deep learning; on-line learning; time series analysis; adaptive learning
Show Figures

Figure 1

MDPI and ACS Style

Ko, H.; Lee, J.; Byun, J.; Son, B.; Park, S. Loss-Driven Adversarial Ensemble Deep Learning for On-Line Time Series Analysis. Sustainability 2019, 11, 3489.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

Back to TopTop