Machine Learning Based Approach to Identify Predictive Signal Models

Guona Chen; Yixuan Guo

doi:10.54097/gymg8963

Authors

Guona Chen
Yixuan Guo

DOI:

https://doi.org/10.54097/gymg8963

Keywords:

Machine Learning; Signal Recognition; Predictive Models; Feature Extraction; Data Analysis.

Abstract

In modern industrial, medical and communication fields, signal identification and prediction are key technologies to ensure system stability and efficiency. Traditional signal processing methods such as autoregressive modelling (AR), fast Fourier transform (FFT) and wavelet transform (WT) are able to satisfy the demand to some extent, but their performance is limited when dealing with complex and nonlinear signals. With the increase of computational power and data volume, machine learning methods are gradually occupying an important position in the field of signal processing due to their powerful feature extraction and pattern recognition capabilities. The aim of this study is to explore the application of machine learning based methods in signal recognition and prediction. We propose a systematic signal processing framework, including steps of data preprocessing, feature extraction, model training and validation. The advantages of deep learning models in complex signal processing are verified by comparing the performance of algorithms such as support vector machine (SVM), artificial neural network (ANN), random forest (RF) and convolutional neural network (CNN). The experimental results show that CNN performs best in signal recognition and prediction tasks, followed by ANN and RF, while SVM has relatively low performance. Deep learning models perform well in processing high-dimensional and nonlinear signals and can significantly improve the accuracy and robustness of signal processing. However, the training time of deep learning models is long and the demand for computational resources is high. The main contribution of this study is to propose a machine learning-based signal processing framework that systematically compares the performance of multiple algorithms and provides suggestions for selecting and optimising models in different application scenarios. Future research can further extend the diversity of datasets, optimise the computational efficiency of models, and explore more advanced machine learning methods to advance the development of signal processing techniques.

Downloads

Download data is not yet available.

References

Box, G. E. P., & Jenkins, G. M. (1970). Time Series Analysis: Forecasting and Control. Holden-Day.

Cooley, J. W., & Tukey, J. W. (1965). An algorithm for the machine calculation of complex Fourier series. Mathematics of Computation, 19(90), 297-301.

Daubechies, I. (1992). Ten Lectures on Wavelets. Society for Industrial and Applied Mathematics.

Vapnik, V. (1995). The Nature of Statistical Learning Theory. Springer.

Schölkopf, B., Smola, A., & Müller, K. R. (1997, October). Kernel principal component analysis. In International conference on artificial neural networks (pp. 583-588). Berlin, Heidelberg: Springer Berlin Heidelberg.

Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986). Learning representations by back-propagating errors. Nature, 323 (6088), 533-536.

Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5-32.

LeCun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998). Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11), 2278-2324.

Hinton, G., Deng, L., Yu, D., Dahl, G. E., Mohamed, A., Jaitly, N., ... & Kingsbury, B. (2012). Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups. IEEE Signal Processing Magazine, 29(6), 82-97.

Ogunpola, A., Saeed, F., Basurra, S., Albarrak, A. M., & Qasem, S. N. (2024). Machine learning-based predictive models for detection of cardiovascular diseases. Diagnostics, 14 (2), 144.

Pachiyannan, P., Alsulami, M., Alsadie, D., Saudagar, A. K. J., AlKhathami, M., & Poonia, R. C. (2024). A Novel Machine Learning-Based Prediction Method for Early Detection and Diagnosis of Congenital Heart Disease Using ECG Signal Processing. Technologies, 12(1), 4.