Developing Fuzzy Models for Estimating the Quality of VoIP

Document Type: Research Paper


1 Computer and Information Technology Department, Institute of Sci- ence and High Technology and Environmental Sciences, Graduate University of Ad- vanced Technology, Kerman, Iran

2 Computer Engineering Department, Shahid Bahonar University of Kerman, Kerman, Iran

3 Computer Engineering Department, Iran University of Science and Tech- nology, Tehran, Iran


This paper presents a novel method for modeling the one-way quality prediction of VoIP, non-intrusively. Intrusive measures of voice quality suffer from common deficiency that is the need of reference signal for evaluating the quality of voice. Owing to this lack, a great deal of effort has been recently devoted for modeling voice quality prediction non-intrusively according to quality degradation parameters, while among the past proposed methods, intelligent techniques have been remarkably successful due to their abilities for modeling the non-linear processes. The present study introduces a procedure for developing fuzzy models, employing Genetic Algorithm (GA) and Adaptive Neuro-Fuzzy Inference System (ANFIS). The proposed method is able to generate optimized fuzzy models in terms of accuracy and complexity. The efficiency of this procedure is compared with and contrasted against 13 regression methods implemented in KEEL as one machine learning tool. Moreover, several experimental results are performed over voice data from 10 different languages. In order to complete the experiment, a comprehensive statistical comparison is also drawn between our proposed method and other previous ones. The results apparently show the efficiency and applicability of this novel method in terms of generating accurate and simple fuzzy models for estimating the VoIP quality.


J. Alcala-Fdez, L. Sanchez, S. Garcia, M. del Jesus, S. Ventura,
J. Garrell, J. Otero, C. Romero, J. Bacardit, V. Rivas, J.
Fernandez and F. Herrera, {it KEEL: a software tool to assess
evolutionary algorithms for data mining problems}, Journal of
Soft Computing - A Fusion of Foundations, Methodologies and
Applications, {bf 13}textbf{(3)} (2009), 307-318.


S. Andersen and A. Duric, {it Internet low bit rate codec (iLBC),IETF draft}, 2002.

J. G. Beerends, A. P. Hekstra, A. W. Rix and M. P. Hollier,
{it Perceptual evaluation of speech quality (PESQ): the new ITU
standard for end-to-end speech quality assessment part II -
psychoacoustic model}, Journal of Audio Eng. Soc., {bf
50}textbf{(10)} (2002), 765-778. 

J. Bolot, {it Characterizing end-to-end packet delay and loss
in the Internet}, Journal of High-Speed Networks, {bf
2}textbf{(3)} (1993), 305-323.

M. S. Borella, {it Measurement and interpretation of Internet
packet loss}, Journal of Communication and Networking, {bf
2} (2000), 93-102.

A. D. Clark, {it Modeling the effects of burst packet loss and
recency on subjective voice quality}, Proc. of IPTEL2001, New
York, USA, (2001), 123-127.

R. G. Cole and J. Rosenbluth, {it Voice over IP performance
monitoring}, Journal of ACM Computing Communication Review, {bf
31}textbf{(2)} (2001), 9-24.

R. Cox, {it Three new speech coders from the ITU cover a range
of applications}, Journal of IEEE Communications Magazine, {bf
35}textbf{(9)} (1997), 40-47.

J. Demsar, {it Statistical comparisons of classifiers over
multiple data sets}, Journal of Machine Learning Research, {bf
7} (2006), 1-30.

M. Eftekhari and S. D. Katebi, {it Extracting compact fuzzy rules
for nonlinear system modeling using subtractive clustering, GA
and unscented filter}, Journal of Applied Mathematical Modeling,
{bf 32} (2008), 2634-2651.

M. Eftekhari, S. D. Katebi, M. Karimi and A. H. Jahanmiri, {it
Eliciting transparent fuzzy model using differential evolution},
Journal of Applied Soft Computing , {bf 8} (2008), 466-476.

S. Garcia and F. Herrera, {it An Extension on statistical
comparisons of classifiers over multiple data sets for all
pairwise comparisons}, Journal of Machine Learning Research,
{bf 9} (2008), 2677-2694.

F. Herrera, {it Genetic fuzzy systems: taxonomy, current
research trends and prospects}, Journal of Evolutionary
Intelligence, {bf 1}textbf{(1)} (2008), 27-46.

International Telecommunication Union, {it Objective measuring
apparatus, Appendix 1: test signals}, ITU-T Recommendation
P.50, 1998.

International Telecommunication Union, {it Mean opinion score (MOS) terminology},
ITU-T Recommendation P.800.1, 2003.

International Telecommunication Union, {it Perceptual
evaluation of speech quality (PESQ), an objective method for
end-to-end speech quality assessment of narrow-band telephone
networks and speech codecs}, ITU-T Recommendation P.862, 2001.

International Telecommunication Union, {it Packet based
multimedia communications systems}, ITU-T Recommendation H.323,

International Telecommunication Union, {it The E-model, a
computational model for use in transmission planning}, ITU-T
Recommendation G.107, 2000.

International Telecommunication Union, {it Methods for
subjective determination of transmission quality}, ITU-T
Recommendation P.800, 1996.

J. S. R. Jang, {it ANFIS: adaptive network-based fuzzy
inference systems}, Journal of IEEE Transactions on System, Man
and Cybernetics, {bf 23} (1993), 665-685.

J. S. R. Jang, C. T. Sun and E. Mizutani, {it Neuro-fuzzy and soft
computing}, Prentice Hall, Engleeood Cliffs, 1977.

W. Jiang and H. Schulzrinne, {it Modeling of packet loss and
delay and their effect on real-time multimedia service quality},
Proc. of Int.Workshop Network and Operating Systems Support for
Digital Audio and Video NOSSDAV, Chapel Hill, NC, 2000.

J. F. Kurose and K. W. Ross, {it Computer networking: a top-down
approach featuring the Internet}, Pearson Addison-Wesley, 2000.

A. P. Markopoulou, F. A. Tobagi and M. Karam, {it Assessment
of VoIP quality over Internet backbones}, Proc. of IEEE Infocom,
(2002), 150-159.

O. Nelles, {it Nonlinear system identification: from classical
approaches to neural networks and fuzzy models}, Springer, Berlin
Heidelberg, 2000.

C. Perkins, O. Hodson and V. Hardman, {it A survey of packet
loss recovery techniques for streaming audio}, Journal of IEEE
Network, {bf 12} (1998), 40-48.

F. Rahdari and M. Eftekhari, {it Developing fuzzy models for
estimating quality of VoIP using a hybrid of GA and
neuro-fuzzy}, Proc. of 2nd Int. Conf. on Contemporary Issues in
Computer and Information Sciences (CICIS), Zanjan, Iran, (2011),

F. Rahdari and M. Eftekhari, {it Modeling the perceived voice
quality for VoIP system based on Neuro-Fuzzy}, Proc. of Int.
Conferences on Computer and knowledge Engineering (ICCKE),
Mashhad, Iran, (2011), 81-86

F. Rahdari and M.Eftekhari, {it Using bayesian classifiers for
estimating quality of VoIP}, Proc. of 16th CSI Int. symposium on
Artificial Intelligence and Signal Processing (AISP), Shiraz,
Iran, (2012), 348-353.

A. Raja, R. Azad, C. Flanagan and C. Ryan, {it Non-intrusive
quality evaluation of VoIP using genetic programming}, Proc. of
1st Int. Conference on Bio- inspired Models of Network,
Information and Computing Systems, (2006), 1-8

J. Rosenberg, H. Schulzrinne, G. Camarillo, A. Johnston, J.
Peterson, R. Sparks, M. Handley and E. Schooler, {it
SIP: Session Initiation Protocol}, RFC 3261, 2002.

L. Sanchez, {it A random sets-based method for identifying
fuzzy models}, Journal of Fuzzy Sets and Systems, {bf
98}textbf{(3)} (1998), 343-354.

H. Sanneek, G. Carle and R. Koodli, {it A framework model for
packet loss metrics based on run length}, Proc. of SPIE/ACM
SIGMM Multimedia Computing and Networking Conf., 2000.

H. Schulzrinne, S. Casner, R. Frederick and V. Jacobson, {it
RTP: a transport protocol for real-time applications}, RFC 1889,

L. Sun and E. Ifeachor, {it Perceived speech quality prediction
for voice over IP-based networks}, Proc. of IEEE Int. Conf.
Communications ICC02, New York, (2002), 2573-2577.

L. Sun and E. Ifeachor, {it Voice quality prediction models and
their application in VoIP network}, Journal of IEEE Trans. On
Multimedia, {bf 8}textbf{(4)} (2006), 809-820.

L. Sun and E. Ifeachor, {it Subjective and objective speech
quality evaluation under bursty losses}, Proc. of on-line
Workshop Measurement of Speech and Audio Quality in Networks
(MESAQIN), Prague, Czech, (2002), 25-29

L. X. Wang and J. M. Mendel, {it Generating fuzzy rules by learning
from examples}, Journal of IEEE Transactions on Systems, Man and
Cybernetics, {bf 22}textbf{(6)} (1992), 1414-1427.

I. Wang and I. H. Witten, {it Induction of model trees for
predicting continuous classes}, Proc. of 9th European Conf. on
Machine Learning, Czech Republic, (1997), 128-137.