Current approaches to the evaluation of modulation parameters of Long Range (LoRa) radio signals

M.A. Romashchenko; D.V. Vasil’chenko; R.S. Sukhomlinov; N.V. Astahov; O.Yu. Makarov

doi:10.18127/j00338486-202607-02

Current approaches to the evaluation of modulation parameters of Long Range (LoRa) radio signals

M.A. Romashchenko¹, D.V. Vasil’chenko², R.S. Sukhomlinov³, N.V. Astahov⁴, O.Yu. Makarov⁵

research article UDC 621.396.669.8 Pages: 13-17 doi.org/10.18127/j00338486-202607-02

^1,2,3,4 FSBEI of HE “Voronezh State Technical University” (Voronezh, Russia)
⁵ ФГБОУ ВО «Воронежский государственный технический университет» (г. Воронеж, Россия)

Keywords: LoRa spreading factor modulation parameters preamble spectrum analysis signal separation artificial intelligence

Abstract

Formulation of the problem. As the number of wireless devices operating in unlicensed frequency bands increases, the radio-frequency spectrum becomes more congested, which leads to stronger mutual interference and degraded communication quality. In LoRa networks, this problem is further aggravated by the fact that transmission robustness and channel utilization efficiency are largely determined by the modulation parameters, primarily the spreading factor and signal bandwidth. Under these conditions, the problem of determining the modulation parameters of the received signal becomes important both for the design of interference-resistant communication channels and for spectrum monitoring and electromagnetic environment analysis.

Purpose. To review current methods for determining the modulation parameters of LoRa signals, with emphasis on spreading factor estimation under different reception conditions.

Results. A review of current methods for determining the modulation parameters of LoRa signals under different reception conditions was carried out. It is shown that the existing approaches can be divided into three main groups: methods for preliminary estimation of modulation parameters at the receiver side; methods for parameter estimation from a pre-isolated signal using artificial intelligence; and methods for wideband data processing aimed at analyzing multiple simultaneous transmissions. It was established that the use of the preamble is the most appropriate approach for preliminary estimation of signal parameters, whereas for methods based on the analysis of a pre-isolated signal, the choice of the most informative signal representation is of major importance.

Received: 28.05.2026
Approved after review: 01.06.2026
Accepted: 30.06.2026

How to cite

Ромащенко М.А., Васильченко Д.В., Сухомлинов Р.С., Астахов Н.В., Макаров О.Ю. Актуальные подходы к вопросам оценки параметров модуляции радиосигналов по технологии LongRange (LoRa) // Радиотехника. 2026. Т. 90. № 7. С. 13-17. DOI: https://doi.org/10.18127/j00338486-202607-02

References

Romashchenko M.A., Suhomlinov R.S., Vasil'chenko D.V., Puhov D.A. Parametrizaciya koefficienta rasshireniya spektra LoRa-radiosignala dlya identifikacii bespilotnyh letatel'nyh apparatov. Teoriya i tekhnika radiosvyazi. 2026. № 1. S. 15-23 (In Russian).
Atapattu S., Tellambura C., Jiang H. Energy detection for spectrum sensing in cognitive radio. 2014. DOI: 10.1007/978-1-4939-0494-5.
Koch D.J., Shahid M.O., Krishnaswamy B. Spreading factor detection for low-cost adaptive data rate in LoRaWAN gateways. The 20th ACM Conference on Embedded Networked Sensor Systems (SenSys ’22). New York: ACM. 2022. P. 1–7. DOI: 10.1145/3560905.3568112.
Ghanaatian R., Afisiadis O., Cotting M., Burg A. LoRa digital receiver analysis and implementation. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). 2019. P. 1498–1502.
West N.E., O’Shea T. Deep architectures for modulation recognition. 2017. DOI: 10.1109/DYSPAN.2017.7920754.
Rajendran S., Meert W., Giustiniano D., Lenders V., Pollin S. Deep learning models for wire-less signal classification with distributed low-cost spectrum sensors. 2018. DOI: 10.1109/TCCN.2018.2835460.
Shahid A. et al. A convolutional neural network approach for classification of LPWAN technologies: Sigfox, LoRa and IEEE 802.15.4g. 2019. DOI: 10.1109/SAHCN.2019.8824856.
Mutescu P.M., Lavric A., Petrariu A.I., Popa V. Deep learning enhanced spectrum sensing for LoRa spreading factor detection. 2023 13th International Symposium on Advanced Topics in Electrical Engineering (ATEE). 2023. DOI: 10.1109/ATEE58038.2023.10108224.
Almohamad A., Hasna M., Althunibat S., Tekbıyık K., Qaraqe K. A Deep learning model for LoRa signals classification using cyclostationay features. 2021 International Conference on Information and Communication Technology Convergence (ICTC). 2021. DOI: 10.1109/ICTC52510.2021.9621015.
Rachel G., Prema S.Ch. Cyclostationary feature detection based blind approach for spectrum sensing and classification. 2019. DOI: 10.13164/re.2019.0298.
Lavric A., Popa V. Performance evaluation of LoRaWAN communication scalability in large-scale wireless sensor networks. 2018. DOI: 10.1155/2018/6730719.
Mutescu P.-M., Popa V., Lavric A. LoRa communications spectrum sensing based on artificial intelligence: IoT sensing. Sensors. 2025. V. 25. Art. 2748. DOI: 10.3390/s25092748.

[1] Romashchenko M.A., Suhomlinov R.S., Vasil'chenko D.V., Puhov D.A. Parametrizaciya koefficienta rasshireniya spektra LoRa-radiosignala dlya identifikacii bespilotnyh letatel'nyh apparatov. Teoriya i tekhnika radiosvyazi. 2026. № 1. S. 15-23 (In Russian).

[2] Atapattu S., Tellambura C., Jiang H. Energy detection for spectrum sensing in cognitive radio. 2014. DOI: 10.1007/978-1-4939-0494-5.

[3] Koch D.J., Shahid M.O., Krishnaswamy B. Spreading factor detection for low-cost adaptive data rate in LoRaWAN gateways. The 20th ACM Conference on Embedded Networked Sensor Systems (SenSys ’22). New York: ACM. 2022. P. 1–7. DOI: 10.1145/3560905.3568112.

[4] Ghanaatian R., Afisiadis O., Cotting M., Burg A. LoRa digital receiver analysis and implementation. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). 2019. P. 1498–1502.

[5] West N.E., O’Shea T. Deep architectures for modulation recognition. 2017. DOI: 10.1109/DYSPAN.2017.7920754.

[6] Rajendran S., Meert W., Giustiniano D., Lenders V., Pollin S. Deep learning models for wire-less signal classification with distributed low-cost spectrum sensors. 2018. DOI: 10.1109/TCCN.2018.2835460.

[7] Shahid A. et al. A convolutional neural network approach for classification of LPWAN technologies: Sigfox, LoRa and IEEE 802.15.4g. 2019. DOI: 10.1109/SAHCN.2019.8824856.

[8] Mutescu P.M., Lavric A., Petrariu A.I., Popa V. Deep learning enhanced spectrum sensing for LoRa spreading factor detection. 2023 13th International Symposium on Advanced Topics in Electrical Engineering (ATEE). 2023. DOI: 10.1109/ATEE58038.2023.10108224.

[9] Almohamad A., Hasna M., Althunibat S., Tekbıyık K., Qaraqe K. A Deep learning model for LoRa signals classification using cyclostationay features. 2021 International Conference on Information and Communication Technology Convergence (ICTC). 2021. DOI: 10.1109/ICTC52510.2021.9621015.

[10] Rachel G., Prema S.Ch. Cyclostationary feature detection based blind approach for spectrum sensing and classification. 2019. DOI: 10.13164/re.2019.0298.

[11] Lavric A., Popa V. Performance evaluation of LoRaWAN communication scalability in large-scale wireless sensor networks. 2018. DOI: 10.1155/2018/6730719.

[12] Mutescu P.-M., Popa V., Lavric A. LoRa communications spectrum sensing based on artificial intelligence: IoT sensing. Sensors. 2025. V. 25. Art. 2748. DOI: 10.3390/s25092748.

Abstract

How to cite

Related articles