USING DIGITAL FILTERS FOR REAL-TIME SIGNAL CLASSIFICATION
https://doi.org/10.26583/vestnik.2024.314
EDN: RETWVK
Abstract
A technique for using digital filters to classify control signals in real time is proposed. Signals can come from various control sensors installed on a controlled device, such as a mobile robot. Control signals come from sensors, are processed, classified, and are subsequently used to control a mobile robotic device. There are a large number of signal classification algorithms, which are based on identifying the characteristic features of the signal, such as amplitude, frequency, average value, etc. Most algorithms classify signals based on characteristics in the time domain. In this work, it is proposed to use the frequency characteristics of the signal and, on their basis, carry out classification using narrow-band «comb» digital filters. The base frequencies of the control signal are pre-staged using fast Fourier transform. Once the base frequencies are determined, the classification process consists of filtering the raw signal with a set of digital narrow-band «comb» filters. This approach allows you to classify control actions «on the fly» in real time. Digital filters can be used to classify different types of signals, which are further converted into control commands for a mobile robotic device.
References
1. Kapur A., Kapur S., Maes P. Alterego: A personalized wearable silent speech interface. In 23rd International conference on intelligent user interfaces, 2018. Pp. 43–53. DOI:10.1145/3172944.3172977.
2. Voznenko T.I., Gridnev A.A., Kudryavtsev K.Y., Chepin E.V. The Decomposition Method of Multi-channel Control System Based on Extended BCI for a Robotic Wheelchair. Advances in Intelligent Systems and Computing, 2020. Vol. 948. Pp. 562–567. DOI: 10.1007/978-3-030-25719-4_73.
3. Voznenko T.I., Gridnev A.A., Chepin E.V., Kudryavtsev K.Y. The command interpretation in decomposition method of multi-channel control for a robotic device. Procedia Computer Science, 2020. Vol. 169. Pp. 152–157. DOI: 10.1016/j.procs. 2020.02.127.
4. Khokhar Z.O., Xiao Z.G., Menon C. Surface EMG pattern recognition for real-time control of a wrist exoskeleton. Biomedical engineering online, 2010. Vol. 9. No. 1. Pp. 1–17. DOI:10.1186/1475-925X-9-41.
5. Soledad G. Alternative Feature Selection Methods in Machine Learning. Available at: https://www.kdnuggets.com/2021/12/alternative-feature-selection-methods-machinelearning (accessed: 04.04. 2022).
6. Brownlee J. How to choose a feature selection method for machine learning. Machine LearningMastery, 2019. Vol. 10.
7. Tagunov V.V., Kudryavtsev K.Ya, Petrova A.I., Voznenko T.I. Methodology for selecting input features for machine learning algorithms. Vestnik NIYaU MIFI, 2022. Vol. 11. No. 1. Pp. 51–58 (in Russian). DOI: 10.56304/S2304487X22010114.
8. Igrevskaya A., Kachina A., Petrova A., Kudryavtsev K. The Research of Characteristic Frequencies for Gesture-based EMG Control Channels. In: Klimov V.V., Kelley D.J. (eds) Biologically Inspired Cognitive Architectures 2021. BICA 2021 : Proceedings of the 12th Annual Meeting of the BICA Society. Springer Nature, 2022. 623p. doi: 10.1007/978-3-030-96993-6_14.
9. Ifeachor E.C., Jervis B.W. Digital Signal Processing: A Practical Approach. Pearson Education, 2002. 933 р.
10. Ifeachor E.C., Jervis W. Digital signal processing: a practical approach: Trans. from English. Moscow. Williams Publishing House, 2004. 992 p.
Review
For citations:
Kudryavtsev K.Yu. USING DIGITAL FILTERS FOR REAL-TIME SIGNAL CLASSIFICATION. Vestnik natsional'nogo issledovatel'skogo yadernogo universiteta "MIFI". 2024;13(3):169-175. (In Russ.) https://doi.org/10.26583/vestnik.2024.314. EDN: RETWVK
Views:
129
Email this article 