A RPLC-based approach for identification of Markov model with unknown noise and number of states

Yiu ming Cheung; Lei Xu

doi:10.1109/IJCNN.2000.860726

A RPLC-based approach for identification of Markov model with unknown noise and number of states

Yiu ming Cheung^*
, Lei Xu

^*Corresponding author for this work

Department of Computer Science

Research output: Chapter in book/report/conference proceeding › Conference proceeding › peer-review

Abstract

(Krishnamurthy et al. 1993) studied one type of Hidden Markov Model (HMM) with identifying its state sequence and parameters based on the Expectation-Maximization (EM) algorithm, thus requiring extensive computing resources and a prior knowledge of state number. In this paper, we further study this model and present a new identification approach, which estimates the state sequence and HMM parameters through using the clustering information obtained via Rival Penalized Competitive Learning (RPCL) algorithm. Compared to Krishnamurthy's method, our approach can not only fast identify the HMM, but also automatically find out the correct number of states. Experiments have successfully shown the performance of this approach.

Original language	English
Title of host publication	Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000
Subtitle of host publication	Neural Computing: New Challenges and Perspectives for the New Millennium
Place of Publication	Italy
Publisher	IEEE
Pages	3-8
Number of pages	6
ISBN (Print)	0769506194
DOIs	https://doi.org/10.1109/IJCNN.2000.860726
Publication status	Published - 27 Jul 2000
Event	IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium - Como, Italy Duration: 24 Jul 2000 → 27 Jul 2000 https://doi.org/10.1109/IJCNN.2000 (Conference proceedings) https://www.computer.org/csdl/proceedings/ijcnn/2000/12OmNxWcH0R (Conference proceedings)

Publication series

Name	International Joint Conference on Neural Networks (IJCNN)
ISSN (Print)	1098-7576

Conference

Conference	IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium
Abbreviated title	IJCNN 2000
Country/Territory	Italy
City	Como
Period	24/07/00 → 27/07/00
Internet address	https://doi.org/10.1109/IJCNN.2000 (Conference proceedings) https://www.computer.org/csdl/proceedings/ijcnn/2000/12OmNxWcH0R (Conference proceedings)

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 9 Industry, Innovation, and Infrastructure

Access to Document

10.1109/IJCNN.2000.860726

Cite this

Cheung, Y. M., & Xu, L. (2000). A RPLC-based approach for identification of Markov model with unknown noise and number of states. In Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000: Neural Computing: New Challenges and Perspectives for the New Millennium (pp. 3-8). (International Joint Conference on Neural Networks (IJCNN)). IEEE. https://doi.org/10.1109/IJCNN.2000.860726

Cheung, Yiu ming ; Xu, Lei. / A RPLC-based approach for identification of Markov model with unknown noise and number of states. Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000: Neural Computing: New Challenges and Perspectives for the New Millennium. Italy : IEEE, 2000. pp. 3-8 (International Joint Conference on Neural Networks (IJCNN)).

@inproceedings{eb23f20c0e824a49ac49d88536771f16,

title = "A RPLC-based approach for identification of Markov model with unknown noise and number of states",

abstract = "(Krishnamurthy et al. 1993) studied one type of Hidden Markov Model (HMM) with identifying its state sequence and parameters based on the Expectation-Maximization (EM) algorithm, thus requiring extensive computing resources and a prior knowledge of state number. In this paper, we further study this model and present a new identification approach, which estimates the state sequence and HMM parameters through using the clustering information obtained via Rival Penalized Competitive Learning (RPCL) algorithm. Compared to Krishnamurthy's method, our approach can not only fast identify the HMM, but also automatically find out the correct number of states. Experiments have successfully shown the performance of this approach.",

author = "Cheung, \{Yiu ming\} and Lei Xu",

year = "2000",

month = jul,

day = "27",

doi = "10.1109/IJCNN.2000.860726",

language = "English",

isbn = "0769506194",

series = "International Joint Conference on Neural Networks (IJCNN)",

publisher = "IEEE",

pages = "3--8",

booktitle = "Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000",

address = "United States",

note = "IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium, IJCNN 2000 ; Conference date: 24-07-2000 Through 27-07-2000",

url = "https://doi.org/10.1109/IJCNN.2000, https://www.computer.org/csdl/proceedings/ijcnn/2000/12OmNxWcH0R",

}

Cheung, YM & Xu, L 2000, A RPLC-based approach for identification of Markov model with unknown noise and number of states. in Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000: Neural Computing: New Challenges and Perspectives for the New Millennium. International Joint Conference on Neural Networks (IJCNN), IEEE, Italy , pp. 3-8, IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium, Como, Italy, 24/07/00. https://doi.org/10.1109/IJCNN.2000.860726

A RPLC-based approach for identification of Markov model with unknown noise and number of states. / Cheung, Yiu ming; Xu, Lei.
Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000: Neural Computing: New Challenges and Perspectives for the New Millennium. Italy : IEEE, 2000. p. 3-8 (International Joint Conference on Neural Networks (IJCNN)).

Research output: Chapter in book/report/conference proceeding › Conference proceeding › peer-review

TY - GEN

T1 - A RPLC-based approach for identification of Markov model with unknown noise and number of states

AU - Cheung, Yiu ming

AU - Xu, Lei

PY - 2000/7/27

Y1 - 2000/7/27

N2 - (Krishnamurthy et al. 1993) studied one type of Hidden Markov Model (HMM) with identifying its state sequence and parameters based on the Expectation-Maximization (EM) algorithm, thus requiring extensive computing resources and a prior knowledge of state number. In this paper, we further study this model and present a new identification approach, which estimates the state sequence and HMM parameters through using the clustering information obtained via Rival Penalized Competitive Learning (RPCL) algorithm. Compared to Krishnamurthy's method, our approach can not only fast identify the HMM, but also automatically find out the correct number of states. Experiments have successfully shown the performance of this approach.

AB - (Krishnamurthy et al. 1993) studied one type of Hidden Markov Model (HMM) with identifying its state sequence and parameters based on the Expectation-Maximization (EM) algorithm, thus requiring extensive computing resources and a prior knowledge of state number. In this paper, we further study this model and present a new identification approach, which estimates the state sequence and HMM parameters through using the clustering information obtained via Rival Penalized Competitive Learning (RPCL) algorithm. Compared to Krishnamurthy's method, our approach can not only fast identify the HMM, but also automatically find out the correct number of states. Experiments have successfully shown the performance of this approach.

UR - https://www.computer.org/csdl/proceedings-article/ijcnn/2000/06194003/12OmNBIWXA3

UR - https://dl.acm.org/doi/10.5555/846231.849029

UR - https://www.scopus.com/pages/publications/0033720884

U2 - 10.1109/IJCNN.2000.860726

DO - 10.1109/IJCNN.2000.860726

M3 - Conference proceeding

AN - SCOPUS:0033720884

SN - 0769506194

T3 - International Joint Conference on Neural Networks (IJCNN)

SP - 3

EP - 8

BT - Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000

PB - IEEE

CY - Italy

T2 - IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium

Y2 - 24 July 2000 through 27 July 2000

ER -

Cheung YM, Xu L. A RPLC-based approach for identification of Markov model with unknown noise and number of states. In Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000: Neural Computing: New Challenges and Perspectives for the New Millennium. Italy : IEEE. 2000. p. 3-8. (International Joint Conference on Neural Networks (IJCNN)). doi: 10.1109/IJCNN.2000.860726

A RPLC-based approach for identification of Markov model with unknown noise and number of states

Abstract

Publication series

Conference

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this