Parameter Estimation for Gaussian Mixture Processes based on Expectation-Maximization Method
Xue Xia, Xuebo Zhang, Xiaohui Chen
Available Online January 2017.
- https://doi.org/10.2991/icmmita-16.2016.96How to use a DOI?
- Gaussian mixture processes; expectation-maximization; parameters estimation.
- Expectation-Maximization (EM) iteration is one of the most efficient algorithms for parameter estimation for Gaussian mixture model, which is a characteristic probability density function model for non-Gaussian processes. In general, EM iteration for multi-dimensional Gaussian mixture is too complicated to realize in practice. Fortunately, for fitting of the background's probability density function in active detection, the single dimensional Gaussian mixture is adequate. Therefore, EM iteration can be simplified efficiently. In view of active detection, followed with descriptions of single-dimensional Gaussian mixture model and its parameter estimation problem, a practicable simplified EM iteration is derived. Initialization and order determination is important in EM iteration. Schemes for initialization and order determining are proposed for high calculating speed, high estimation accuracy, and for the compromise of the two cases. Finally, a numerical simulation is given.
- Open Access
- This is an open access article distributed under the CC BY-NC license.
Cite this article
TY - CONF AU - Xue Xia AU - Xuebo Zhang AU - Xiaohui Chen PY - 2017/01 DA - 2017/01 TI - Parameter Estimation for Gaussian Mixture Processes based on Expectation-Maximization Method BT - Proceedings of the 2016 4th International Conference on Machinery, Materials and Information Technology Applications PB - Atlantis Press SP - 519 EP - 523 SN - 2352-538X UR - https://doi.org/10.2991/icmmita-16.2016.96 DO - https://doi.org/10.2991/icmmita-16.2016.96 ID - Xia2017/01 ER -