Optimal Call Failure Rates Modelling with Joint Support Vector Machine and Discrete Wavelet Transform

Full Text (PDF, 524KB), PP.46-57

Views: 0 Downloads: 0

Author(s)

Isabona Joseph 1,* Agbotiname Lucky Imoize 2,3 Stephen Ojo 4 Ikechi Risi 5

1. Federal University Lokoja, Department of Physics, Lokoja, Kogi State, Nigeria

2. Department of Electrical and Electronics Engineering, Faculty of Engineering, University of Lagos, Akoka, Lagos 100213, Nigeria

3. Department of Electrical Engineering and Information Technology, Institute of Digital Communication, Ruhr University, 44801 Bochum, Germany

4. Department of Electrical and Computer Engineering, Anderson University, Anderson, SC 29621, USA

5. River State University Port Harcourt Nigeria

* Corresponding author.

DOI: https://doi.org/10.5815/ijigsp.2022.04.04

Received: 5 Feb. 2022 / Revised: 18 Mar. 2022 / Accepted: 25 Apr. 2022 / Published: 8 Aug. 2022

Index Terms

Wavelet transform, Service quality, Failure rate, Failure modeling, Support Vector Machine.

Abstract

Failure modeling is an essential component of reliability engineering. Enhanced failure rate modeling techniques are vital to the effective development of predictive and analytical methodologies, demonstration of the engineering procedure, allocation of procedures, design, and control of procedures. However, failure rate modeling has not been given adequate treatment in the literature. The need to investigate failure rate modeling leveraging cutting-edge techniques cannot be overemphasized. This paper proposed and applied a joint support vector regression (SVR) and wavelet transform (WT) approach termed (WT-SVR) to training and learning the call failures rate in wireless system networks. The wavelet transform has been accomplished using the wavelet compression sensing technique. In this technique, the standardized call failure rate data first go through a wavelet filtering transformation matrix. This is followed by separating and outputting the transformed filtered components in the compression phase. Finally, the transformed filtered output components were trained and evaluated using the SVR based on statistical learning theory. The resultant outcome revealed that the proposed WT-SVR learning method is by far better than using only the SVR method for call rate prognostic analysis. As a case in point, the WT-SVR attained STD values of 0.12, 0.21, 2.32, 0.22, 0.90, 0.81 and 0.34 on call failure data estimation compared to the basic SVR that attained higher STD values of 0.45, 0.98, 0.99, 0.46, 1.44, 2.32 and 3.22, respectively.

Cite This Paper

Isabona Joseph, Agbotiname Lucky Imoize, Stephen Ojo, Ikechi Risi, "Optimal Call Failure Rates Modelling with Joint Support Vector Machine and Discrete Wavelet Transform", International Journal of Image, Graphics and Signal Processing(IJIGSP), Vol.14, No.4, pp. 46-57, 2022. DOI:10.5815/ijigsp.2022.04.04

Reference

[1]J. Isabona, “Parametric Maximum Likelihood Estimator combined with Bayesian and Akaike Information Criterion for Realistic Field Strength Attenuation Estimation in Open and Shadow urban Microcells,” J. Emerg. Trends Eng. Appl. Sci., vol. 10, no. 4, pp. 151–156, 2019.
[2]R. Elliot, “Mobile phone penetration throughout sub-Saharan Africa.” 2020, [Online]. Available: https://www.geopoll.com/blog/mobile-phone-penetration-africa/.
[3]GSMA, “The Mobile Economy Sub-Sahara Africa 2020,” GSMA Assoc., pp. 1–41, 2020, [Online]. Available: https://www.gsma.com/mobileeconomy/sub-saharan-africa/.
[4]A. Igbinovia and J. Isabona, “Empirical Investigation of Field Strength Spatial Coverage Variability in Mobile Radio Communication Networks,” Int. J. Res. Stud. Electr. …, vol. 4, no. 4, pp. 33–41, 2018, doi: 10.20431/2454-9436.0404004.
[5]J. Isabona and V. M. Srivastava, “User-centric methodology for objective assessment of service quality in established Wireless Mobile Communication Networks,” Int. J. Commun. Antenna Propag., vol. 7, no. 1, pp. 26–30, 2017, doi: 10.15866/irecap.v7i1.10475.
[6]J. Isabona and Emughedi, O. Modelling based Quantitative Assessment of Operational LTE Mobile Broadband Networks Reliability: a Case Study of University Campus Environ, IOSR Journal of Electronics and Communication Engineering (IOSR-JECE) e-ISSN: 2278-2834,p- ISSN: 2278-8735.Vol.15, Issue 1, Ser. I (Jan-Feb 2020), PP 22-31 www.iosrjournals.org
[7]A. L. Imoize, K. Orolu, and A. A.-A. Atayero, “Analysis of key performance indicators of a 4G LTE network based on experimental data obtained from a densely populated smart city,” Data Br., vol. 29, no. 105304, pp. 1–17, 2020, doi: 10.1016/j.dib.2020.105304.
[8]A. L. Imoize and O. D. Adegbite, “Measurements-Based Performance Analysis of a 4G LTE Network in and Around Shopping Malls and Campus Environments in Lagos Nigeria,” Arid Zo. J. Eng. Technol. Environ., vol. 14, no. 2, pp. 208–225, 2018.
[9]X. Wang, C. Yu, and Y. Li, “A New Finite Interval Lifetime Distribution Model for Fitting Bathtub-Shaped Failure Rate Curve,” Math. Probl. Eng., vol. 2015, p. 954327, 2015, doi: 10.1155/2015/954327.
[10]S. J. Almalki and J. Yuan, “A new modified Weibull distribution,” Reliab. Eng. Syst. Saf., vol. 111, pp. 164–170, 2013, doi: https://doi.org/10.1016/j.ress.2012.10.018.
[11]J. M. F. Carrasco, E. M. M. Ortega, and G. M. Cordeiro, “A generalized modified Weibull distribution for lifetime modeling,” Comput. Stat. Data Anal., vol. 53, no. 2, pp. 450–462, 2008, doi: https://doi.org/10.1016/j.csda.2008.08.023.
[12]A. J. Lemonte, “A new exponential-type distribution with constant, decreasing, increasing, upside-down bathtub and bathtub-shaped failure rate function,” Comput. Stat. Data Anal., vol. 62, pp. 149–170, 2013, doi: https://doi.org/10.1016/j.csda.2013.01.011.
[13]G. D. C. Barriga, F. Louzada-Neto, and V. G. Cancho, “The complementary exponential power lifetime model,” Comput. Stat. Data Anal., vol. 55, no. 3, pp. 1250–1259, 2011, doi: https://doi.org/10.1016/j.csda.2010.09.005.
[14]G. S. Mudholkar and D. K. Srivastava, “Exponentiated Weibull family for analyzing bathtub failure-rate data,” IEEE Trans. Reliab., vol. 42, no. 2, pp. 299–302, 1993, doi: 10.1109/24.229504.
[15]G. S. Mudholkar, K. O. Asubonteng, and A. D. Hutson, “Transformation of the bathtub failure rate data in reliability for using Weibull-model analysis,” Stat. Methodol., vol. 6, no. 6, pp. 622–633, 2009, doi: https://doi.org/10.1016/j.stamet.2009.07.003.
[16]M. E. Ghitany, “The monotonicity of the reliability measures of the beta distribution,” Appl. Math. Lett., vol. 17, no. 11, pp. 1277–1283, 2004, doi: https://doi.org/10.1016/j.aml.2003.12.007.
[17]M. Xie, Y. Tang, and T. N. Goh, “A modified Weibull extension with bathtub-shaped failure rate function,” Reliab. Eng. Syst. Saf., vol. 76, no. 3, pp. 279–285, 2002, doi: https://doi.org/10.1016/S0951-8320(02)00022-4.
[18]Ivan Izonina and R. Tkachenko. An approach towards the response surface linearization via ANN-based cascade scheme for regression modeling in Healthcare, international workshop on Small and Big Data Approaches in Healthcare (SBDaH) November 1-4, 2021, Leuven, Belgium, Procedia Computer Science 198 (2022) 724–729.
[19]R. Tkachenko, I. Izonin, I. Dronyuk, M. Logoyda and P. Tkachenko , Recovery of Missing Sensor Data with GRNN-based Cascade Scheme, International Journal of Sensors, Wireless Communications and Control 2021; 11(5) . https://dx.doi.org/10.2174/2210327910999200813151904.
[20]J.Isabona and K Rotimi.“Multi-Resolution Based Discrete Wavelet Transform for Enhanced Signal Coverage Processing and Prediction Analysis,” FUDMA J. Sci., vol. 3, no. 1, pp. 6–15, 2019.
[21]J. Cheng, D. Yu, and Y. Yang, “Application of support vector regression machines to the processing of end effects of Hilbert–Huang transform,” Mech. Syst. Signal Process., vol. 21, no. 3, pp. 1197–1211, 2007, doi: https://doi.org/10.1016/j.ymssp.2005.09.005.
[22]P. A. M. B. Henrique, P. H. M. Albuquerque, S. S. D. F. Marcelino, and Y. Peng, “Portfolio selection with support vector regression: multiple kernels comparison,” Int. J. Bus. Intell. Data Min., vol. 18, no. 4, pp. 395–410, 2021, doi: 10.1504/IJBIDM.2021.115476.
[23]K. Cheng and Z. Lu, “Active learning Bayesian support vector regression model for global approximation,” Inf. Sci. (Ny)., vol. 544, pp. 549–563, 2021, doi: https://doi.org/10.1016/j.ins.2020.08.090.
[24]L. Wu et al., “Artificial Neural Network Based Path Loss Prediction for Wireless Communication Network,” IEEE Access, vol. 8, pp. 199523–199538, 2020, doi: 10.1109/ACCESS.2020.3035209.
[25]V. C. Ebhota, J. Isabona, and V. M. Srivastava, Environment-Adaptation Based Hybrid Neural Network Predictor for Signal Propagation Loss Prediction in Cluttered and Open Urban Microcells,” Wirel. Pers. Commun., vol. 104, no. 3, pp. 935–948. doi: 10.1007/s11277-018-6061-2
[26]Joseph Isabona, Divine O. Ojuh, "Application of Levenberg-Marguardt Algorithm for Prime Radio Propagation Wave Attenuation Modelling in Typical Urban, Suburban and Rural Terrains", International Journal of Intelligent Systems and Applications, Vol.13, No.3, pp.35-42, 2021.
[27]Isabona Joseph, Divine O. Ojuh, " Adaptation of Propagation Model Parameters toward Efficient Cellular Network Planning using Robust LAD Algorithm", International Journal of Wireless and Microwave Technologies, Vol.10, No.5, pp. 13-24, 2020.
[28]Divine O. Ojuh, Joseph Isabona," Empirical and Statistical Determination of Optimal Distribution Model for Radio Frequency Mobile Networks Using Realistic Weekly Block Call Rates Indicator ", International Journal of Mathematical Sciences and Computing, Vol.7, No.3, pp. 12-23, 2021.