METODE UNIVERSAL THRESHOLD DALAM TRANSFORMASI WAVELET DISKRET PADA KASUS SINYAL SUARA

Andriyani Andriyani, Moch. Hamsyi

Abstract


Masalah yang terjadi pada sinyal suara adalah terjadinya noise yang mengkontaminasi proses pengolahannya. Dalam hal ini, diperlukan suatu proses reduksi noise untuk mengurangi noise yang terdapat pada sinyal suara. Reduksi noise di sini dilakukan dengan menerapkan transformasi wavelet diskri yang terdiri dari tiga langkah utama yaitu: dekomposisi sinyal, proses thresholding dan rekonstruksi sinyal. Penelitian ini bertujuan untuk mengkaji metode universal threshold untuk mendapatkan nilai threshold dan aplikasinya pada kasus sinyal suara yang terkontaminasi Gaussian noise. Metode yang dilakukan adalah kajian literatur referensi-referensi terkait transformasi wavelet diskrit dan sinyal suara. Nilai threshold yang digunakan dalam proses thresholding ditentukan dengan metode universal threshold yang dikaji agar threshold yang diperoleh memberikan hasil optimal ketika dibandingkan dengan koefisien wavelet  hasil penerapan aturan hard atau soft thresholding. Hasil aplikasi dan simulasi reduksi noise dengan wavelet menunjukkan bahwa nilai SNR berbanding terbalik dengan nilai MSE, sedangkan nilai nilai threshold sebanding dengan nilai MSE.


Keywords


transformasi wavelet diskrit, universal threshold, sinyal suara.

Full Text:

PDF

References


Amiri, G. G, and Asadi, A. 2000, Comparison of Different Methods of Wavelet and Wavelet Packet Transform, International Journal of Civil Engineering. 7(4): 248-257.

Antoniadis, A., Bigot, J. and Sapatinas, T., 2001, Wavelet Estimators in Nonparametric Regresión: A Comparative Simulation Study, Journal of Statistical Software, 6(6):1-83.

Daubechies I., 1992, Ten lectures on wavelets. Vermont: CBMS - NSF Conference Series in Applied Mathematics, Montpelier.

Delyon, B. and Juditsky, A., 1995. Estimating Wavelet Coefficients in Wavelets and Statistics. Antoniadis, A. dan Oppenheim, G. (Eds), Lect. Notes Statist., 103, pp. 15-168.

Effern, A., Lehnertz, k., Schreiber, T., Grundwald, T., David, P. and Elger, C. E. 2000, Nonlinear Denoising of Transient Signals with Application to Event-related Potentials, Physica, 140: 257-266.

Ergen, B. 2013, “Comparison of Wavelet Types and Thresholding Methods on Wavelet Based Denoising of Heart Sounds” in Journal of Signal and Information Processing, pp. 164-167

Fan X, and Zuo MZ. 2006, Gearbox fault detection using Hilbert and wavelet packet transform, Mechanical Systems and Signal Processing, 20: 966 -982.

Greiff, H. F.C, Garcia, R.R and L-Ginori, J. V. 2002, Signal De-noising in Magnetic Resonance Spectroscopy Using Wavelet Transforms, 14(6): 388-401.

Mahdavi, F. A., Ahmad, S. A., Marhaban, M. H. and Akbarzadeh-T,M-R. 2013, The Utility of Wavelet Transform in Surface Electromyography Feature Extraction - A Comparative Study of Different Mother Wavelets. International Journal of Biomedical and Biological Engineering, 7(2): 107-112.

Mallat, S. G., 1999, A Wavelet Tour of Signal Processing, London : Second edition Academic press.

Meyer, Y., 1992, Wavelets and Operator, Cambridge: Cambridge University Press.

Nikolaev N, Nikolov Z, Gotchev A, Egiazarian K. 2000, “Wavelet domain Wiener filtering for ECG denoising using improved signal estimate” in IEEE International Conference on Acoustics, Speech, and Signal Processing, pp 3578–3581.

Phinyomark, A., Limsakul, C. and Phukpattaranont, P. 2011, Application of wavelet analysis in EMG feature extraction for pattern classification. Measurement Science Review, 11(2): 45-52.

Rajasekaran, S., Latha, V. and Lee, S.C. 2006, Generation of artificial earthquake motion records using wavelets and principal component analysis, Journal of Earthquake Engineering, 10(5): 665-691.

Rioul, O., 1993, “Discrete-Time Multiresolution Theory,” in IEEE Trans. on Signal Processing: pp. 2591-2605.




DOI: http://dx.doi.org/10.12928/admathedu.v8i1.11115

Article Metrics

Abstract view : 0 times
PDF - 0 times

Refbacks

  • There are currently no refbacks.


Copyright (c) 2021 Andriyani Andriyani, Moch. Hamsyi

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.



AdMathEdu : Jurnal Ilmiah Pendidikan Matematika, Ilmu Matematika dan Matematika Terapan
P-ISSN: 2088-687X || E-ISSN: 2656-7040
Organized by: Department of Mathematics Education, Faculty of Teacher Training and Education
Publisher: Universitas Ahmad Dahlan, Yogyakarta, Indonesia
Email: admathedu@gmail.com