Outlier detection in time series data is crucial for various applications including fraud detection, system health monitoring, and predictive maintenance. However, existing methods often struggle to capture complex temporal dependencies in the presence of noise and high dimensionality. A novel adversarial approach called ARIMA-DCGAN Synergy has been investigated to handle these challenges, which combines the strengths of Autoregressive Integrated Moving Average (ARIMA) models and Deep Convolutional Generative Adversarial Networks (DCGANs). The ARIMA component captures linear and short-term dependencies, while the DCGAN learns nonlinear and long-term patterns in the data. The proposed approach enables generating of realistic time series samples using DCGAN and the outliers detection based on the reconstruction error using ARIMA. Experimental outputs on both synthetic and original datasets exhibit excellent results of ARIMA-DCGAN Synergy compared to sophisticated outlier detection techniques. The proposed model delivers superior results and surpasses all other cutting-edge models with an accuracy of 98.81%, a precision of 98.92%, a recall of 98.97%, and an F1-score of 98.94%.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    ARIMA-DCGAN Synergy: A Novel Adversarial Approach to Outlier Detection in Time Series Data


    Contributors:


    Publication date :

    2024-07-15


    Size :

    1947921 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    An Adversarial Optimization Approach to Efficient Outlier Removal

    Yu, J. | British Library Online Contents | 2014


    DCGAN Method and apparatus for recognizing vehicle using DCGAN in parking lot

    LEE JIN HEE / JEONG BO SUN | European Patent Office | 2024

    Free access

    ARIMA Approach to the Unit Root Analysis of Macro Economic Time Series

    Morimune, K. / Miyazaki, K. / Modelling and Simulation Society of Australia | British Library Conference Proceedings | 1995


    A new algorithm of outlier mining in time series data

    Zheng, B.-x. / Du, X.-h. / Xi, Y.-g. | British Library Online Contents | 2002


    DCGAN-Based Power Trading Market Dispatch Model Design

    Peng, Zewu / Liang, Yingwei / Shao, Yanning | IEEE | 2022