AI-powered cognitive modulation adaptation for energy-efficient underwater acoustic communication

Abstract

Underwater acoustic communication (UAC) is a fundamental component of various applications, including marine exploration, underwater robotics, and environmental monitoring. However, the dynamic conditions of underwater environments pose significant challenges to the development of high-performance communication systems. This study introduces a novel dynamic adaptive modulation approach that enables smooth switching between several communication approaches using machine learning methods such as decision trees (DT) and random forests (RF). Through continuous monitoring of environmental parameters, such as temperature, salinity, depth, and acoustic noise levels, the system gathers real-time information to serve as input features for the machine learning model. The model is trained and evaluated to identify the most suitable modulation approach for the prevailing underwater conditions. The DT model achieved an accuracy of 97%, whereas the RF model performed slightly better, reaching 98% accuracy. In addition, the switching delay for the DT model was 2.75 ms, whereas that for RF was 0.97 ms. The approach improves effective data transmission by reducing error rates, enhancing system robustness, and dynamically adjusting to changing underwater conditions, thereby ensuring optimal communication efficiency in challenging environments.

Keywords

Acoustic data transmission / Decision tree / Intelligent modulation switching / Energy efficiency / Subaquatic Jupyter AI

References

[1] Anand M, Velu A, Whig P. Prediction of loan behaviour with machine learning models for secure banking. J Comput Sci Eng, 2022, 3(1): 1-13

[2] Bolikulov F, Nasimov R, Rashidov A, Akhmedov F, Cho YI. Effective methods of categorical data encoding for artificial intelligence algorithms. Mathematics, 2024, 12(16 2553

[3] Busacca F, Galluccio L, Palazzo S, Panebianco A, Qi Z, Pompili D. Adaptive versus predictive techniques in underwater acoustic communication networks. Comput Netw, 2024, 252 110679

[4] Çavuşlu MA, Altuncu MA, Özcan H, Gülağız FK, Şahin S. Estimation of underwater acoustic channel parameters for Erdek/Turkey region. Appl Acoust, 2021, 181 108135

[5] Costa VG, Pedreira CE. Recent advances in decision trees: an updated survey. Artif Intell Rev, 2023, 56(5): 4765-4800

[6] Cui XR, Zhang ZJ, Li J, Jiang B, Li SB, Liu JH. Reinforcement learning-based adaptive modulation scheme over underwater acoustic OFDM communication channels. Phys Commun, 2023, 61 102207

[7] Dabiri H, Farhangi V, Moradi MJ, Zadehmohamad M, Karakouzian M. Applications of decision tree and random forest as tree-based machine learning techniques for analyzing the ultimate strain of spliced and non-spliced reinforcement bars. Appl Sci, 2022, 12(10 4851

[8] Dhawas P, Dhore A, Bhagat D, Pawar RD, Kukade A, Kalbande K (2024) Big data preprocessing, techniques, integration, transformation, normalisation, cleaning, discretization, and binning. In: Darwish D (ed) Big data analytics techniques for market intelligence. IGI Global Scientific Publishing, pp 159–182. https://doi.org/10.4018/979-8-3693-0413-6.ch006

[9] Heydarian M, Doyle TE, Samavi R. MLCM: multi-label confusion matrix. IEEE Access, 2022, 10: 19083-19095

[10] Hu YL, Bao JX, Sun WD, Fu XM. Modulation recognition method for underwater acoustic communication signals based on passive time reversal-autoencoder with the synchronous signals. Sensors, 2023, 23(13): 5997

[11] Jing LY, Dong CF, He CB, Shi WT, Yin HX. Adaptive modulation and coding for underwater acoustic communications based on data-driven learning algorithm. Remote Sens, 2022, 14(235959

[12] Junejo NUR, Sattar M, Adnan S, Sun H, Adam ABM, Hassan A, et al.. A survey on physical layer techniques and challenges in underwater communication systems. J Mar Sci Eng, 2023, 11(4885

[13] Kherif O, Benmahamed Y, Teguar M, Boubakeur A, Ghoneim SSM. Accuracy improvement of power transformer faults diagnostic using KNN classifier with decision tree principle. IEEE Access, 2021, 9: 81693-81701

[14] Li L, Jin XK, Lu CH, Wei ZB, Li J. Modelling and simulation on acoustic channel of underwater sensor networks. Wirel Commun Mob Comput, 2021, 2021(1 8263600

[15] Li P, Rao X, Blase J, Zhang Y, Chu X, Zhang C (2021b) CleanML: a study for evaluating the impact of data cleaning on ML classification tasks. In: 2021 IEEE 37th International Conference on Data Engineering (ICDE). IEEE, pp 13–24. https://doi.org/10.1109/ICDE51399.2021.00009

[16] Li ZY, Sun WB, Zhan DN, Kang Y, Chen L, Bozzon A, et al.. Amalur: the convergence of data integration and machine learning. IEEE Trans Knowl Data Eng, 2024, 36(127353-7367

[17] Lin JM, Su W, Xiao L, Jiang XL (2018) Adaptive modulation switching strategy based on Q-learning for underwater acoustic communication channel. In: WUWNet '18: Proceedings of the 13th International Conference on Underwater Networks & Systems. ACM, pp 1–5. https://doi.org/10.1145/3291940.3291976

[18] Mackenzie KV. Nine-term equation for sound speed in the oceans. J Acoust Soc Am, 1981, 70(3): 807-812

[19] Maharana K, Mondal S, Nemade B. A review: data pre-processing and data augmentation techniques. Glob Transit Proc, 2022, 3(1): 91-99

[20] Nowsheen N, Benson C, Frater M (2010) Design of a high frequency FPGA acoustic modem for underwater communication. In: OCEANS’10 IEEE SYDNEY. IEEE, pp 1–6. https://doi.org/10.1109/OCEANSSYD.2010.5603819

[21] Radosevic A, Ahmed R, Duman TM, Proakis JG, Stojnovic M. Adaptive OFDM modulation or underwater acoustic communications: design considerations and experimental results. IEEE J Ocean Eng, 2014, 39(2): 357-370

[22] Rokach L, Maimon O (2014) Data mining with decision trees: theory and applications, 2nd edn. World Scientific. https://doi.org/10.1142/9097

[23] Saija K, Nethi S, Chaudhuri S, Karthik RM (2019) A machine learning approach for SNR prediction in 5G systems. In: 2019 IEEE International Conference on Advanced Networks and Telecommunications Systems (ANTS). IEEE, pp 1–6. https://doi.org/10.1109/ANTS47819.2019.9118097

[24] Sangeetha RG, Hemanth C, Jaiswal I. Performance of different modulation scheme in free space optical transmission–a review. Optik, 2022, 254 168675

[25] Singya PK, Shaik P, Kumar N, Bhatia V, Alouini MS. A survey on higher-order QAM constellations: technical challenges, recent advances, and future trends. IEEE Open J Commun Soc, 2021, 2: 617-655

[26] Stojanovic M, Preisig J. Underwater acoustic communication channels: propagation models and statistical characterization. IEEE Commun Mag, 2009, 47(1): 84-89

[27] Su W, Lin JM, Chen KY, Xiao L, En C. Reinforcement learning-based adaptive modulation and coding for efficient underwater communications. IEEE Access, 2019, 7: 67539-67550

[28] Sweta T, Ruthrapriya S, Sneka J, Alex JSR, Rohith G, Das M. Reinforcement learning-based automated modulation switching algorithm for an enhanced underwater acoustic communication. Results Eng, 2024, 23 102791

[29] Sudharsan B, Yadav P, Breslin JG, Ali MI (2021) Train++: an incremental ML model training algorithm to create self-learning IoT devices. In: 2021 IEEE SmartWorld, Ubiquitous Intelligence & Computing, Advanced & Trusted Computing, Scalable Computing & Communications, Internet of People and Smart City Innovation (SmartWorld/SCALCOM/UIC/ATC/IOP/SCI). IEEE, pp 97–106. https://doi.org/10.1109/SWC50871.2021.00023

[30] van Walree P, Otnes R, Tomasi B, Henriksen B, Danre JB, Bergh Ø (2025) SFI Smart Ocean dataset for underwater acoustic communications. IEEE Dataport. https://doi.org/10.21227/3aa6-4k33

[31] Wang MF, Zhu ZJ, Qian GF. Modulation signal recognition of underwater acoustic communication based on Archimedes optimization algorithm and random forest. Sensors, 2023, 23(5): 2764

[32] Wu FY, Song YC, Yang KD. An effective framework for underwater acoustic data acquisition. Appl Acoust, 2021, 182 108235

[33] Xiong F (2006) Digital modulation techniques, 2nd edn. Artech House

[34] Yang MY, Bian CH, Kim HS. OFDM-guided deep joint source channel coding for wireless multipath fading channels. IEEE Trans Cogn Commun Netw, 2022, 8(2584-599

RIGHTS & PERMISSIONS

The Author(s)