№2, 2023

Ramin R. Rzayev, Azer B. Kerimov

Existing signal recognition methods have both their advantages and disadvantages, which are found when recognizing signals from classes defined by different characteristic standards. Therefore, for signals from different classes, the indicators of recognition quality by one method or another can differ significantly. There is a need to create a more balanced method capable of providing the necessary stability relative to the accuracy and reliability of the final results in the process of recognizing signals from various classes. As such signal recognition method, the article proposes to use an approach based on the combine using of weighted signal proximity criteria within the additive convolution. Euclidean distances between reference points are used as evaluation criteria, which are used in the context of applying the four most well-known recognition methods: the amplitude method (the trivial Euclid method), the DDTW method using the values of the first derivatives, and methods based on the Wavelet transform and the Fourier transform (pp.24-31).

Keywords:Signal recognition, Euclidean metric, Evaluation criterion, Convolution, Recognition method
DOI : 10.25045/jpis.v14.i2.03

Al-Qerem, A., Kharbat, F. Nashwan, Sh., Ashra, S. (2020). General model for best feature extraction of EEG using discrete wavelet transform wavelet family and differential evolution. International Journal of Distributed Sensor Networks 16(3). https://doi.org/10.1177/1550147720911009

Cedro, L., Janecki, D. (2011). Determining of signal derivatives in identification problems, FIR Differential Filters, Acta Montanistica Slovaca Rocník 16(1), 47-54.

Hindarto, H., Anshory, I., Efiyanti, A. (2017). Feature extraction of heart signals using fast Fourier transform, UNEJ e-Proceeding 165-167. https://jurnal.unej.ac.id/index.php/prosiding/article/view/4187

Keogh, E.J., Pazzani, M.J. Derivative Dynamic Time Warping. https://epubs.siam.org/doi/epdf/10.1137/1.9781611972719.1

Kerimov, A.B. (2022, a). Accuracy comparison of signal recognition methods on the example of a family of successively horizontally displaced curves, Informatics and Control Problems 42(2), 80-91.

Kerimov, A.B. (2022, b).Comparison of some signal recognition methods for their adequacy, Proceedings of the 8th International Conference on Control and optimization with industrial applications, Vol. I.

Leszek, C., Janecki, D., Determining of signal derivatives in identification problems, FIR Differential Filters, Acta Montanistica Slovaca Rocník 16(1), 47-54 (2011).

Liu, Y., Lin, J. (2019). A general-purpose signal processing algorithm for biological profiles using only first-order derivative information. BMC Bioinformatics 20, 611 https://doi.org/10.1186/s12859-019-3188-4

Novozhilov, B.M. (2016). Calculation of the derivative of an analog signal in a programmable logic controller. Aerospace Scientific Journal of the Moscow State Technical University N.E. Bauman, Electron Journal 4, 1-12 (In Russian).

Ponomarev, S., Wallace, N., Atkison, T. Fourier transform as feature extraction for malware classification. http://atkison.cs.ua.edu/papers/FT_as_FE.pdf

Santos, M., Morais, C., Nascimento, Y., Araujo, J., Lima, K. (2017).  Spectroscopy with computational analysis in biological studies: a decade (2006–2016). TrAC Trends Anal Chem 97, 244-256

Saraswat, S., Srivastava, G., Sachchidanand, N. (2017). Wavelet transform based feature extraction and classification of atrial fibrillation arrhythmia. Biomed Pharmacol J 10(4) http://biomedpharmajournal.org/?p=17470

Song T., Yu X., Yu S., Ren Z., and Qu Y. (2021). Feature extraction processing method of medical image fusion based on neural network algorithm, Hindawi Complexity https://doi.org/10.1155/2021/7523513

Taghavirashidizadeh, A., Sharifi, F., Vahabi, S.A., Hejazi, A., Torbati, M.S., Mohammed, A.S. (2022). WTD-PSD: presentation of novel feature extraction method based on discrete Wavelet transformation and tme-dependent power spectrum descriptors for diagnosis of Alzheimer’s disease, Computational Intelligence and Neuroscience https://doi.org/10.1155/2022/9554768