Dual-tone multifrequency signal detection using support vector machines

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

The need for efficient detection of Dual-tone Multifrequency (DTMF) tones for developing telecommunication equipment is justifiable. This paper presents an artificial intelligence based approach for efficient detection of DTMF tones under the influence of White Gaussian Noise (WGN) and frequency variation, using Support Vector Machines (SVM). Additive WGN in the DTMF input samples is removed by filtering out unwanted frequencies. Detection of DTMF carrier frequencies from input samples employs a traditional software based approach using the power spectrum analysis of the Discrete Fourier Transform (DFT) signals. The Goertzel's Algorithm is used to estimate the seven fundamental DTMF carrier frequencies. A SVM classifier is trained using the estimated fundamental DTMF carrier frequencies, and is validated using the input samples for classification of low and high DTMF frequency groups. The tone detection scheme employs decision logic using a rule-base expert system for classification of low and high DTMF frequency groups, corresponding to valid DTMF frequency groups. Comparison of this hybrid DTMF tone detection model with existing DTMF detection techniques proves the merits of this proposed scheme. This hybrid DTMF tone detection scheme is simulated in a MATLAB environment and results from performance tests are given in this paper.

Original languageEnglish
Title of host publicationProceedings of IEEE 2008 6th National Conference on Telecommunication Technologies and IEEE 2008 2nd Malaysia Conference on Photonics, NCTT-MCP 2008
Pages350-355
Number of pages6
DOIs
Publication statusPublished - 01 Dec 2008
EventIEEE 2008 6th National Conference on Telecommunication Technologies and IEEE 2008 2nd Malaysia Conference on Photonics, NCTT-MCP 2008 - Putrajaya, Malaysia
Duration: 26 Aug 200828 Aug 2008

Other

OtherIEEE 2008 6th National Conference on Telecommunication Technologies and IEEE 2008 2nd Malaysia Conference on Photonics, NCTT-MCP 2008
CountryMalaysia
CityPutrajaya
Period26/08/0828/08/08

Fingerprint

Signal detection
Support vector machines
Telecommunication equipment
Power spectrum
Discrete Fourier transforms
Spectrum analysis
Expert systems
MATLAB
Artificial intelligence
Classifiers
Group
knowledge-based system
artificial intelligence
logic
telecommunication
performance

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Electrical and Electronic Engineering
  • Communication

Cite this

Nagi, J., Tiong, S. K., Yap, K. S., & Khaleel Ahmed, S. (2008). Dual-tone multifrequency signal detection using support vector machines. In Proceedings of IEEE 2008 6th National Conference on Telecommunication Technologies and IEEE 2008 2nd Malaysia Conference on Photonics, NCTT-MCP 2008 (pp. 350-355). [4814301] https://doi.org/10.1109/NCTT.2008.4814301
Nagi, J. ; Tiong, Sieh Kiong ; Yap, Keem Siah ; Khaleel Ahmed, Syed. / Dual-tone multifrequency signal detection using support vector machines. Proceedings of IEEE 2008 6th National Conference on Telecommunication Technologies and IEEE 2008 2nd Malaysia Conference on Photonics, NCTT-MCP 2008. 2008. pp. 350-355
@inproceedings{2ffe93191688447291e08baaa5d5b45f,
title = "Dual-tone multifrequency signal detection using support vector machines",
abstract = "The need for efficient detection of Dual-tone Multifrequency (DTMF) tones for developing telecommunication equipment is justifiable. This paper presents an artificial intelligence based approach for efficient detection of DTMF tones under the influence of White Gaussian Noise (WGN) and frequency variation, using Support Vector Machines (SVM). Additive WGN in the DTMF input samples is removed by filtering out unwanted frequencies. Detection of DTMF carrier frequencies from input samples employs a traditional software based approach using the power spectrum analysis of the Discrete Fourier Transform (DFT) signals. The Goertzel's Algorithm is used to estimate the seven fundamental DTMF carrier frequencies. A SVM classifier is trained using the estimated fundamental DTMF carrier frequencies, and is validated using the input samples for classification of low and high DTMF frequency groups. The tone detection scheme employs decision logic using a rule-base expert system for classification of low and high DTMF frequency groups, corresponding to valid DTMF frequency groups. Comparison of this hybrid DTMF tone detection model with existing DTMF detection techniques proves the merits of this proposed scheme. This hybrid DTMF tone detection scheme is simulated in a MATLAB environment and results from performance tests are given in this paper.",
author = "J. Nagi and Tiong, {Sieh Kiong} and Yap, {Keem Siah} and {Khaleel Ahmed}, Syed",
year = "2008",
month = "12",
day = "1",
doi = "10.1109/NCTT.2008.4814301",
language = "English",
isbn = "9781424422159",
pages = "350--355",
booktitle = "Proceedings of IEEE 2008 6th National Conference on Telecommunication Technologies and IEEE 2008 2nd Malaysia Conference on Photonics, NCTT-MCP 2008",

}

Nagi, J, Tiong, SK, Yap, KS & Khaleel Ahmed, S 2008, Dual-tone multifrequency signal detection using support vector machines. in Proceedings of IEEE 2008 6th National Conference on Telecommunication Technologies and IEEE 2008 2nd Malaysia Conference on Photonics, NCTT-MCP 2008., 4814301, pp. 350-355, IEEE 2008 6th National Conference on Telecommunication Technologies and IEEE 2008 2nd Malaysia Conference on Photonics, NCTT-MCP 2008, Putrajaya, Malaysia, 26/08/08. https://doi.org/10.1109/NCTT.2008.4814301

Dual-tone multifrequency signal detection using support vector machines. / Nagi, J.; Tiong, Sieh Kiong; Yap, Keem Siah; Khaleel Ahmed, Syed.

Proceedings of IEEE 2008 6th National Conference on Telecommunication Technologies and IEEE 2008 2nd Malaysia Conference on Photonics, NCTT-MCP 2008. 2008. p. 350-355 4814301.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Dual-tone multifrequency signal detection using support vector machines

AU - Nagi, J.

AU - Tiong, Sieh Kiong

AU - Yap, Keem Siah

AU - Khaleel Ahmed, Syed

PY - 2008/12/1

Y1 - 2008/12/1

N2 - The need for efficient detection of Dual-tone Multifrequency (DTMF) tones for developing telecommunication equipment is justifiable. This paper presents an artificial intelligence based approach for efficient detection of DTMF tones under the influence of White Gaussian Noise (WGN) and frequency variation, using Support Vector Machines (SVM). Additive WGN in the DTMF input samples is removed by filtering out unwanted frequencies. Detection of DTMF carrier frequencies from input samples employs a traditional software based approach using the power spectrum analysis of the Discrete Fourier Transform (DFT) signals. The Goertzel's Algorithm is used to estimate the seven fundamental DTMF carrier frequencies. A SVM classifier is trained using the estimated fundamental DTMF carrier frequencies, and is validated using the input samples for classification of low and high DTMF frequency groups. The tone detection scheme employs decision logic using a rule-base expert system for classification of low and high DTMF frequency groups, corresponding to valid DTMF frequency groups. Comparison of this hybrid DTMF tone detection model with existing DTMF detection techniques proves the merits of this proposed scheme. This hybrid DTMF tone detection scheme is simulated in a MATLAB environment and results from performance tests are given in this paper.

AB - The need for efficient detection of Dual-tone Multifrequency (DTMF) tones for developing telecommunication equipment is justifiable. This paper presents an artificial intelligence based approach for efficient detection of DTMF tones under the influence of White Gaussian Noise (WGN) and frequency variation, using Support Vector Machines (SVM). Additive WGN in the DTMF input samples is removed by filtering out unwanted frequencies. Detection of DTMF carrier frequencies from input samples employs a traditional software based approach using the power spectrum analysis of the Discrete Fourier Transform (DFT) signals. The Goertzel's Algorithm is used to estimate the seven fundamental DTMF carrier frequencies. A SVM classifier is trained using the estimated fundamental DTMF carrier frequencies, and is validated using the input samples for classification of low and high DTMF frequency groups. The tone detection scheme employs decision logic using a rule-base expert system for classification of low and high DTMF frequency groups, corresponding to valid DTMF frequency groups. Comparison of this hybrid DTMF tone detection model with existing DTMF detection techniques proves the merits of this proposed scheme. This hybrid DTMF tone detection scheme is simulated in a MATLAB environment and results from performance tests are given in this paper.

UR - http://www.scopus.com/inward/record.url?scp=67650162423&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=67650162423&partnerID=8YFLogxK

U2 - 10.1109/NCTT.2008.4814301

DO - 10.1109/NCTT.2008.4814301

M3 - Conference contribution

SN - 9781424422159

SP - 350

EP - 355

BT - Proceedings of IEEE 2008 6th National Conference on Telecommunication Technologies and IEEE 2008 2nd Malaysia Conference on Photonics, NCTT-MCP 2008

ER -

Nagi J, Tiong SK, Yap KS, Khaleel Ahmed S. Dual-tone multifrequency signal detection using support vector machines. In Proceedings of IEEE 2008 6th National Conference on Telecommunication Technologies and IEEE 2008 2nd Malaysia Conference on Photonics, NCTT-MCP 2008. 2008. p. 350-355. 4814301 https://doi.org/10.1109/NCTT.2008.4814301