Online EM algorithm for joint state and mixture measurement noise estimation

Date

2012-07-09

Author

Zhao, Yuxin
Yin, Feng
Gunnarsson, Fredrik
Amirijoo, Mehdi
Özkan, Emre
Gustafsson, Fredrik

Metadata

Show full item record

Item Usage Stats

168
views

0
downloads

In this study, we aim to estimate the unknown multimodal measurement noise distribution of nonlinear state space models. The unknown noise distribution is modeled as a mixture of exponential family of distributions. We use the ExpectationMaximization (EM) method in order to jointly estimate the unknown parameters as well as the states. The online version of the EM algorithm is implemented by using particle filtering techniques. The resulting algorithm is a noise adaptive particle filter which is applicable to many sensor models having multimodal noise distributions with unknown parameters.

Subject Keywords

Algorithms, Information fusion, Monte Carlo methods, Sensors, Signal filtering and prediction, State space methods

URI

https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6290537
https://hdl.handle.net/11511/78046

Conference Name

15th International Conference on Information Fusion, FUSION 2012; (7 September 2012 through 12 September 2012)

Collections

Department of Electrical and Electronics Engineering, Conference / Seminar

Suggestions

OpenMETU
Core

Exact kalman filtering of respiratory motion Çetinkaya, Mehmet; Erkmen, Aydan Müşerref (2018-10-01) In this paper we propose a novel Exact Kalman Filter for state estimation of quasi-periodic signals such as respiratory motion. Nonlinear functions of interest are approximations as truncated Fourier series. Instead of relying on approximations provided by Extended Kalman Filter or Unscented Kalman Filter, our filter performs exact calculation of the mean and covariances of interest. We then compare, through simulations, the performance of our filter to the two. Our results show that the theoretically deriv...
Investigation of digital elevation model uncertainty in GIS-based solar radiation models using Markov Chain Monte Carlo simulation Ismaila, Abdur-Rahman Belel; Düzgün, H. Şebnem; Ediger, Volkan; Department of Geodetic and Geographical Information Technologies (2013) In this study, a Markov chain Monte Carlo (MCMC) simulation approach that incorporates digital elevation model's (DEM) spatial autocorrelation is developed with the aim of assessing the impact of DEM uncertainty in GIS-based solar radiation models. The method utilized the error probability distribution function (pdf) of Shuttle Radar Topography Mission (SRTM) DEM, and variogram model parameters of the study area's SRTM DEM as a priori information for the formulation of Metropolis-Hasting algorithm. Statisti...
Numerical modelling of wave-structure interaction problems through cfd methods Güler, Hasan Gökhan; Yalçıner, Ahmet Cevdet; Department of Civil Engineering (2020) The major focus of this study is the computational fluid dynamics (CFD) modelling of wave-structure interaction problems. In the first part of this study, the performance of Haydarpaşa Breakwater under tsunami attack is assessed both experimentally and numerically. It is concluded that the major failure mechanism of this breakwater is the sliding of the crown-wall, and the stability of the stones located at the harbour side is also significant. Design recommendations are given based on the stability of the ...
Uniform and Non-Uniform V-shaped Arrays for 2-D DOA Estimation Filik, Tansu; Tuncer, Temel Engin; Yasar, T. Kaya (2008-04-22) In this study, a new method for optimum design of uniform and non-uniform V-shaped arrays is presented for azimuth and elevation angle estimation. The proposed design method finds an optimum angle between the linear sub-arrays of the V-array by using the Cramer-Rao Bound (CRB) where statistical coupling effect between azimuth and elevation angle estimation is considered This method can be used to obtain directional and isotropic angle performances for uniform and non-uniform V-arrays. For non-uniform isotro...
Robust Attitude Estimation Using IMU-Only Measurements Candan, Batu; Söken, Halil Ersin (2021-01-01) © 1963-2012 IEEE.This article proposes two novel covariance-tuning methods to form a robust Kalman filter (RKF) algorithm for attitude (i.e., roll and pitch) estimation using the measurements of only an inertial measurement unit (IMU). KF-based and complementary filtering (CF)-based approaches are the two common methods for solving the attitude estimation problem. Efficiency and optimality of the KF-based attitude filters are correlated with appropriate tuning of the covariance matrices. Manual tuning proce...

Citation Formats

Y. Zhao, F. Yin, F. Gunnarsson, M. Amirijoo, E. Özkan, and F. Gustafsson, “Online EM algorithm for joint state and mixture measurement noise estimation,” presented at the 15th International Conference on Information Fusion, FUSION 2012; (7 September 2012 through 12 September 2012), Singapore, 2012, Accessed: 00, 2021. [Online]. Available: https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6290537.