Multirate, multiresolution, recursive Kalman filter

Cristi, R.; Tummala, Murali

doi:10.1016/s0165-1684(00)00104-3

Cited by 53 publications

(19 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There have been different approaches to reduce and predict time series using wavelets. For instance: in Aussem and Murtagh [6], Gonghui et al [7] and Lotric [8] the wavelet is combined with neural networks; in Cristi and Tummala [9], Hong et al [10] and Renaud et al [11] with Kalman filter, in Renaud et al [12] with autoregressive model and in Antoniadis et al [1] with kernel methodology, among others.…”

Section: Wavelet Methodologymentioning

confidence: 99%

Can thewavelet-kernelmethodology improve other kernel techniques?

Gago

Juaristi

2008

WIT Transactions on Information and Communication Technologies

View full text Add to dashboard Cite

Our aim in this paper is to compare different ways of forecasting using the wavelet transform and the kernel regression. We consider that working with block (or segment) of data is richer than working with individual data (as in traditional kernel), as we assume there is some kind of pattern inside each block which will improve the estimation, and therefore the prediction. We choose the wavelet transform because this transform is able to separate components of data in different locations and with different location in time and frequency. To test the performance of the different methodologies we have carried out a Monte Carlo Study in which we have compared the four methodologies: Ordinary Least Square (OLS), Traditional Kernel (TK), Block Kernel (BK) and Wavelet-Kernel (WK). Two real life applications have been realized. On the one hand, volatility smile has been forecast and on the other, the rated temperature of the steel coils' furnace is predicted. Surprisingly contradictory results had been obtained.

show abstract

Section: Wavelet Methodologymentioning

confidence: 99%

Can thewavelet-kernelmethodology improve other kernel techniques?

Gago

Juaristi

2008

WIT Transactions on Information and Communication Technologies

View full text Add to dashboard Cite

show abstract

“…Subsequently, Hong proposed multiscale system and multi sensor information fusion theory [2] ， Wen etal presented multiscale estimation theory of dynamic systems [3], Cristi and Tummala introduced a multirate, multiresolution, recursive Kalman filter algorithm [4], Chen etal presented the multirate Kalman comprehensive filtering method [5], multirate filtering estimation algorithm [6] of Andrisani etal, asynchronous data fusion estimation [7] of Alouani etal, all these, have contributed to the research of asynchronous multirate multisensor information fusion.…”

Section: Introductionmentioning

confidence: 99%

State Fusion Estimation Based on Asynchronous Multirate Multisensor

Li¹,

Zhang²

2014

Proceedings of the 2014 International Conference on Mechatronics, Electronic, Industrial and Control Engineering

View full text Add to dashboard Cite

Abstract-On theory of multisensor state fusion estimation, more research is a single rate synchronization problem, however, it is the multirate asynchronous problem often encountered in practice. Therefore, research on the state fusion estimation of asynchronous multirate multisensor have more practice application value. In this paple, by expand the dimension of the system state and measurements and by dividing them into proper data blocks, the multirate asynchronous sampling system is formalized into a synchronous sampling system with single sampling rate, therefore, by use of Kalman filter and Carlson optimal data fusion criterion, the optimal state fusion estimation in the sense of linear minimum variance is achieved. The experiment of state fusion estimation on radar tracking shows that this algorithm is better than the result of directed Kalman filtering on smallest scale, the estimation error is less than single sensor Kalman filtering. The method can also be used for integrated navigation, signal processing, image processing and many fields.

show abstract

“…Many algorithms have been presented. Cristi and Tummala (2000), introduced a multirate, multiresolution, recursive Kalman filter algorithm, where they decomposed the state and the state prediction of the finest scale to the coarser scales by use of Haar wavelet transform. By doing so, it could hold the white noise property of the established dynamic models at each scale, and the time delay problem was solved simultaneously.…”

Section: Introductionmentioning

confidence: 99%