Cover Image

Improved expectation maximization algorithm for Gaussian mixed model using the kernel method

Fraud activities have contributed to heavy losses suffered by telecommunication companies. In this paper, we attempt to use Gaussian mixed model, which is a probabilistic model normally used in speech recognition to identify fraud calls in the telecommunication industry. We look at several issues en...

Full description

Saved in:
Bibliographic Details
Main Authors: Mohd Yusoff, Mohd Izhan, Mohamed, Ibrahim, Abu Bakar, Mohd Rizam
Format: Article
Language:English
Published: Hindawi Publishing Corporation 2013
Online Access:http://psasir.upm.edu.my/id/eprint/30397/1/Improved%20expectation%20maximization%20algorithm%20for%20Gaussian%20mixed%20model%20using%20the%20kernel%20method.pdf
http://psasir.upm.edu.my/id/eprint/30397/
http://www.hindawi.com/journals/mpe/2013/757240/
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.upm.eprints.30397
record_format eprints
spelling my.upm.eprints.303972015-10-08T03:16:19Z http://psasir.upm.edu.my/id/eprint/30397/ Improved expectation maximization algorithm for Gaussian mixed model using the kernel method Mohd Yusoff, Mohd Izhan Mohamed, Ibrahim Abu Bakar, Mohd Rizam Fraud activities have contributed to heavy losses suffered by telecommunication companies. In this paper, we attempt to use Gaussian mixed model, which is a probabilistic model normally used in speech recognition to identify fraud calls in the telecommunication industry. We look at several issues encountered when calculating the maximum likelihood estimates of the Gaussian mixed model using an Expectation Maximization algorithm. Firstly, we look at a mechanism for the determination of the initial number of Gaussian components and the choice of the initial values of the algorithm using the kernel method. We show via simulation that the technique improves the performance of the algorithm. Secondly, we developed a procedure for determining the order of the Gaussian mixed model using the log-likelihood function and the Akaike information criteria. Finally, for illustration, we apply the improved algorithm to real telecommunication data. The modified method will pave the way to introduce a comprehensive method for detecting fraud calls in future work. Hindawi Publishing Corporation 2013 Article PeerReviewed application/pdf en http://psasir.upm.edu.my/id/eprint/30397/1/Improved%20expectation%20maximization%20algorithm%20for%20Gaussian%20mixed%20model%20using%20the%20kernel%20method.pdf Mohd Yusoff, Mohd Izhan and Mohamed, Ibrahim and Abu Bakar, Mohd Rizam (2013) Improved expectation maximization algorithm for Gaussian mixed model using the kernel method. Mathematical Problems in Engineering, 2013. art. no. 757240. pp. 1-9. ISSN 1024-123X http://www.hindawi.com/journals/mpe/2013/757240/ 10.1155/2013/757240
institution Universiti Putra Malaysia
building UPM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Putra Malaysia
content_source UPM Institutional Repository
url_provider http://psasir.upm.edu.my/
language English
description Fraud activities have contributed to heavy losses suffered by telecommunication companies. In this paper, we attempt to use Gaussian mixed model, which is a probabilistic model normally used in speech recognition to identify fraud calls in the telecommunication industry. We look at several issues encountered when calculating the maximum likelihood estimates of the Gaussian mixed model using an Expectation Maximization algorithm. Firstly, we look at a mechanism for the determination of the initial number of Gaussian components and the choice of the initial values of the algorithm using the kernel method. We show via simulation that the technique improves the performance of the algorithm. Secondly, we developed a procedure for determining the order of the Gaussian mixed model using the log-likelihood function and the Akaike information criteria. Finally, for illustration, we apply the improved algorithm to real telecommunication data. The modified method will pave the way to introduce a comprehensive method for detecting fraud calls in future work.
format Article
author Mohd Yusoff, Mohd Izhan
Mohamed, Ibrahim
Abu Bakar, Mohd Rizam
spellingShingle Mohd Yusoff, Mohd Izhan
Mohamed, Ibrahim
Abu Bakar, Mohd Rizam
Improved expectation maximization algorithm for Gaussian mixed model using the kernel method
author_facet Mohd Yusoff, Mohd Izhan
Mohamed, Ibrahim
Abu Bakar, Mohd Rizam
author_sort Mohd Yusoff, Mohd Izhan
title Improved expectation maximization algorithm for Gaussian mixed model using the kernel method
title_short Improved expectation maximization algorithm for Gaussian mixed model using the kernel method
title_full Improved expectation maximization algorithm for Gaussian mixed model using the kernel method
title_fullStr Improved expectation maximization algorithm for Gaussian mixed model using the kernel method
title_full_unstemmed Improved expectation maximization algorithm for Gaussian mixed model using the kernel method
title_sort improved expectation maximization algorithm for gaussian mixed model using the kernel method
publisher Hindawi Publishing Corporation
publishDate 2013
url http://psasir.upm.edu.my/id/eprint/30397/1/Improved%20expectation%20maximization%20algorithm%20for%20Gaussian%20mixed%20model%20using%20the%20kernel%20method.pdf
http://psasir.upm.edu.my/id/eprint/30397/
http://www.hindawi.com/journals/mpe/2013/757240/
_version_ 1643830046848188416
score 13.211869

Similar Items