Q.C. Pham1, E.I. Glushankov2, V.A. Sorotskiy3
1, 2 The Bonch-Bruevich Saint-Petersburg State University of Telecommunications (St. Petersburg, Russia) 3 Peter the Great St. Petersburg Polytechnic University (St. Petersburg, Russia) 1 fam.kk@sut.ru; 2 glushankov.ei@sut.ru; 3 sorotsky@spbstu.ru

Formulation of the problem. The cubic computational complexity associated with channel correlation matrix inversion in linear Minimum Mean Square Error (MMSE) equalizers constitutes a critical barrier to the implementation of energy-efficient receivers in Quasi-Orthogonal Space-Time Block Coding MIMO systems. This issue is particularly acute given the stringent hardware constraints inherent in the Internet of Things and 5G/6G networks.

Objective. The synthesis of computationally efficient hybrid detection architectures that integrate iterative numerical methods with proactive control based on Deep Neural Networks, aiming to minimize floating-point operations without degrading noise immunity.

Results. Simulation results demonstrate that the proposed algorithms reduce asymptotic complexity to a near-quadratic level while maintaining Bit Error Rate performance comparable to that of the exact MMSE detector. The scalability of the approach for large-scale antenna arrays is also established.

Practical significance. The proposed hybrid algorithms are tailored for hardware implementation in Massive MIMO systems, specifically for Ultra-Reliable Low-Latency Communication scenarios. By mitigating the computational burden, they enable the deployment of less powerful, energy-efficient processors in IoT terminals and base stations for real-time signal processing.

Pham C.Q., Glushankov E.I., Sorotskiy V.A. Hybrid MIMO detectors with quasi-orthogonal space-time block c oding and adaptive complexity management based on deep learning. Radiotekhnika. 2026. V. 90. № 3. P. 53−65. DOI: https://doi.org/10.18127/j00338486202603-05 (In Russian)

1. Fam K.K., Glushankov E.I. Issled ovanie i razrabotka algoritmov obrabotki signalov v sistemah MIMO s primeneniem prostranstvenn ovremennyh kodov. Trudy uchebny h zavedenij svyazi. 2025. T. 11. № 3. S. 59 −70. DOI: 10.31854/1813-324X-2025-11-3-59-70 (in Russian).
2. Bakulin M.G., Krejndelin V.B., Pankratov D.Yu., Stepanova A.G. Analiz pomekhoustojchivosti algoritmov demodulyacii v Massive M IMO, ispol'zuyushchih negaussovskuyu approksimaciyu. Informacionnye processy. 2025. T. 25. № 1. S. 62−77 (in Russian).
3. Albreem M.A., Juntti M., Shahabuddin S. Massive MIMO detection techniques: a survey. IEEE Communications Surveys & Tutorials. 2019. V. 21. № 4. P. 3109−3132. DOI: 10.1109/COMST.2019.2935810. 4. L i u Q. IterativealgorithmsandarchitecturesinmassiveMIMO detection. Applied and Computat ional Engineering. 2023. V. 6. P. 1143−1150. DOI: 10.54254/2755-2721/6/20230491.
4. Seema S.A.M.K., Reddy B. Data detection in large MIMO system wi th reduced computational complexity for QOSTBC transmission. 2023 3rd International Conference on Advancement in Electronics & Communication Engineering (AECE). Ghaziabad. India. 2023. P. 46-50. DOI: 10.1109/AECE59614.2023.10428602.
5. Wu C., Yang S., Xiao Y., Xiao M. Quasi-orthogonal space-time bl ock coded spatial modulation. IEEE Transactions on Commu-nications. 2022. V. 70. № 12. P. 7872−7885. DOI: 10.1109/TCOMM.2022.3216805.
6. Fam K.K., Glushankov E.I. Issled ovanie metodov raznesennogo pri ema v radiokanalah s zamiraniyam i. Modelirovanie, optimizaciya i informacionnye tekhnologii. 2025. T. 13. № 3. URL: https://moit vivt.ru/ru/journal/pdf?id=1944. DOI: 10.26102/23106018/2025.50.3.002.
7. Zhang X., Zeng H., Ji B., Zhang G. Low-complexity implicit dete ction for massive MIMO using neumann series. IEEE Transactions on Vehicular Technology. 2022. V. 71. № 8. P. 9044−9049. DOI: 10.1109/TVT.2022.3172950.
8. Glushankov E.I., Fam K.K. Adaptivnyj algoritm vybora rezhimov p rostranstvennogo razneseniya i mul'tipleksirovaniya v sistemah MIMO-OFDM. Elektrosvyaz'. 2025. № 9. S. 91−102. DOI: 10.34832/ELSV.2025.71.9.009 (in Russian). 1
9. Olutayo T., Champagne B. Dynamic conjugate gradient unfolding f or symbol detection in time-varying massive MIMO. IEEE Open Journal of Vehicular Technology. 2024. V. 5. P. 792−806. DOI: 10.1109/OJVT.2024.3410834. 1
10. Yin B., Wu M., Cavallaro J.R., Studer C. Conjugate gradient-based soft-output detection and precoding in massive MIMO systems. 2014 IEEE Global Communications Conference. Austin. USA. 2014. P. 3696−3701. DOI: 10.1109/GLOCOM.2014.7037382. 1
11. Bacci G., D'Amico A.A., Sanguinetti L. MMSE channel estimation in large-scale MIMO: improved robustness with reduced complexit y. IEEE Transactions on Wireless Communications. 2024. V. 23. № 12. P. 18563−18575. DOI: 10.1109/TWC.2024.3470124. 1
12. Bobrov E., Kropotov D., Lu H., Zaev D. Massive MIMO adaptive mo dulation and coding using onli ne deep learning algorithm. IEEE Communications Letters. 2022. V. 26. № 4. P. 818−822. DOI: 10.1109/LCOMM.2021.3132947. 1
13. Hunger R. Floating point operations in matrix-vector calculus. Tech. Rep. v. 1.
14. Munich: Munich University of Technology. 2007. 1
15. Guo J., Wen C.-K., Jin S., Li G.Y. Overview of deep learning-ba sed CSI feedback in massive MIMO systems. IEEE Transactions on Communications. 2022. V. 70. № 12. P. 8017−8045. DOI: 10.1109/TCOMM.2022.3217777.