@article{scholars5604,
             doi = {10.1007/s00500-015-1833-z},
          volume = {19},
            note = {cited By 22},
          number = {12},
           title = {Scaled UKF{\^a}??NARX hybrid model for multi-step-ahead forecasting of chaotic time series data},
            year = {2015},
           pages = {3479--3496},
       publisher = {Springer Verlag},
         journal = {Soft Computing},
            issn = {14327643},
          author = {Abdulkadir, S. J. and Yong, S.-P.},
        keywords = {Backpropagation algorithms; Time series, Auto-regressive; Bayesian regulation; Chaotic time series; Forecasting models; Hybrid model; Multi-step; NARX; Unscented Kalman Filter, Forecasting},
             url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-84947127920&doi=10.1007\%2fs00500-015-1833-z&partnerID=40&md5=bac3037dcc6506253e1ce33dde90eb2c},
        abstract = {Accurate forecasting is critically important in many time series applications. In this paper, we consider forecasting chaotic problems by proposing a hybrid model composed of scaled unscented Kalman filter with reduced sigma points and non-linear autoregressive network with exogenous inputs, trained using a modified Bayesian regulation backpropagation algorithm. To corroborate developments of the proposed hybrid model, real-life chaotic and simulated time series which are both non-linear in nature are applied to validate the proposed hybrid model. Experiment results show that the proposed hybrid model outperforms other forecasting models reported in the literature in forecasting of chaotic time series. {\^A}{\copyright} 2015, Springer-Verlag Berlin Heidelberg.}
}