The booming implementation of Internet of Things (IoT) and edge computing devices is requiring the
implementation of efficient signal transmission mechanisms to balance between performance and energy
efficiency. The current paper introduces an AI-assisted conversion and optimization system of the analog-to-digital (A/D) signal transmission, aimed at low-power IoT and edge devices. The given strategy combines both machine learning algorithms and adaptive sampling and quantization methods to optimize the A/D conversion process in real-time depending on the context data patterns and the network characteristics. The framework uses reinforcement learning and neural network models to predict optimal sampling rates and bit resolutions that use the least amount of energy at the expense of signal fidelity. The experimental measurements show a maximum reduction of power consumption (up to 35 percent) and 25 percent more efficiency in the transmission of any conventional fixed-rate A/D systems. Moreover, AI-aided system guarantees reliability in communication when the environmental and channel conditions vary, which can be applied in settings with limited resources. This study will bring a scalable, intelligent, and energy-conscious signal processing paradigm that is capable of supporting the increasing need to have sustainable and autonomous IoT and edge device ecosystems.

AI-assisted A/D conversion; signal-to-noise ratio (SNR); edge computing; low-power IoT; adaptive signal
processing; energy efficiency; intelligent transmission; machine learning; quantization optimization; embedded intelligence .

1. Zhang J, Sun T, Huang Z, Tao W, Wang N, Tian L, Zhu Y, Wang H. The Design of a Low-Power Pipelined ADC for IoT Applications. Sensors. 2025 Feb 22;25(5):1343. 2. Pareschi F, Albertini P, Frattini G, Mangia M, Rovatti R, Setti G. Hardware-algorithms co-design and implementation of an analog-to-information converter for biosignals based on compressed sensing. IEEE transactions on biomedical circuits and systems. 2015 Aug 12;10(1):149-62. 3. Chen Y, Nie Q, Zhong C, Song J, Huang Y, Lin C, Zeng Q, Cao J, Xue Y. A 24 nW 10-bit 10 kS/s ultra-low-power SAR ADC for biomedical devices. AIP Advances. 2023 Feb 1;13(2). 4. Chen R, Kung HT, Chandrakasan A, Lee HS. A bit-level sparsity-aware SAR ADC with direct hybrid encoding for signed expressions for AIoT applications. InProceedings of the ACM/IEEE International Symposium on Low Power Electronics and Design 2022 Aug 1 (pp. 1-6). 5. Li T, Ma Y, Endoh T. From algorithm to module: adaptive and energy-efficient quantization method for edge artificial intelligence in IoT society. IEEE Transactions on Industrial Informatics. 2022 Nov 18;19(8):8953-64. 6. Shen S, Shan Y, Sun L, Sun J, Zou Z, Wang R. Design and implementation of low-power analog-to- information conversion for environmental information perception. Energies. 2017 May 27;10(6):753. 7. Trakimas M, D'Angelo R, Aeron S, Hancock T, Sonkusale S. A compressed sensing analog-to- information converter with edge-triggered SAR ADC core. IEEE Transactions on Circuits and Systems I: Regular Papers. 2013 Apr 15;60(5):1135-48. 8. Azamat A, Asim F, Lee J. Quarry: Quantization-based ADC reduction for ReRAM-based deep neural network accelerators. In2021 IEEE/ACM International Conference On Computer Aided Design (ICCAD) 2021 Nov 1 (pp. 1-7). IEEE. 9. Oya JR, Chavero FM, Clemente RM. Analog‐to‐Digital Conversion for Cognitive Radio: Subsampling, Interleaving, and Compressive Sensing. InCognitive Radio 2017 Jul 5. IntechOpen. 10. Harpe P. Ultra-low power analog-digital converters for IoT. InEnabling the Internet of Things: From Integrated Circuits to Integrated Systems 2017 Jan 26 (pp. 361-383). Cham: Springer International Publishing. 11. Refaai MR, Dhanesh L, Ganthia BP, Mohanty M, Subbiah R, Anbese EM. Design and implementation of a floating PV model to analyse the power generation. International Journal of Photoenergy. 2022;2022(1):3891881. 12. Pahadasingh S, Jena C, Panigrahi CK, Ganthia BP. JAYA algorithm-optimized load frequency control of a four-area interconnected power system tuning using PID controller. Engineering, Technology & Applied Science Research. 2022 Jun 6;12(3):8646-51. 13. Mishra S, Ganthia BP, Sridharan A, Rajakumar P, Padmapriya D, Kaliappan S. Optimization of load forecasting in smartgrid using artificial neural network based NFTOOL and NNTOOL. InJournal of Physics: Conference Series 2022 (Vol. 2161, No. 1, p. 012068). IOP Publishing. 14. Pritam A, Sahu S, Rout SD, Ganthia S, Ganthia BP. Automatic generation control study in two area reheat thermal power system. InIOP Conference Series: Materials Science and Engineering 2017 Aug 1 (Vol. 225, No. 1, p. 012223). IOP Publishing. 15. Xie H, Wang Y, Gao Z, Ganthia BP, Truong CV. Research on frequency parameter detection of frequency shifted track circuit based on nonlinear algorithm. Nonlinear Engineering. 2021 Jan 1;10(1):592-9. 16. Xie H, Wang Y, Gao Z, Ganthia BP, Truong CV. Research on frequency parameter detection of frequency shifted track circuit based on nonlinear algorithm. Nonlinear Engineering. 2021 Jan 1;10(1):592-9. 17. Pragati A, Ganthia BP, Panigrahi BP. Genetic algorithm optimized direct torque control of mathematically modeled induction motor drive using PI and sliding mode controller. InRecent Advances in Power Electronics and Drives: Select Proceedings of EPREC 2020 2020 Dec 4 (pp. 351- 366). Singapore: Springer Singapore. 18. Satpathy SR, Pradhan S, Pradhan R, Sahu R, Biswal AP, Ganthia BP. Direct torque control of mathematically modeled induction motor drive using PI-Type-I fuzzy logic controller and sliding mode controller. InIntelligent Systems: Proceedings of ICMIB 2020 2021 Apr 20 (pp. 239-251). Singapore: Springer Singapore. 19. Ganthia BP, Sahu PK, Mohanty A. Minimization of total harmonic distortion using pulse width modulation technique. IOSR Journal of Electrical and Electronics Engineering (IOSR-JEEE) e-ISSN. 2015:2278-1676. 20. Mohanty M, Nayak N, Ganthia BP, Behera MK. Power Smoothening of Photovoltaic System using Dynamic PSO with ESC under Partial Shading Condition. In2023 International Conference in Advances in Power, Signal, and Information Technology (APSIT) 2023 Jun 9 (pp. 675-680). IEEE. 21. Ganthia BP, Rana PK, Patra T, Pradhan R, Sahu R. Design and analysis of gravitational search algorithm based TCSC controller in power system. Materials Today: Proceedings. 2018 Jan 1;5(1):841- 7. 22. Ganthia BP, Panda S, Remamany KP, Chaturvedi A, Begum AY, Mohan G, Prasad SJ, Ishwarya S. Experimental techniques for enhancing PV panel efficiency through temperature reduction using water cooling and colour filters. Electrical Engineering. 2025 Apr 19:1-27. 23. Chakole N, Remamany KP, Mohan G, Sasirekha P, Kumar NM, Kumar CR, Shunmugasundaram M, Alagarsamy M, Ganthia BP. Optimal Energy Management for Hybrid PV-Wind-Battery Microgrids through Markov Decision Processes Technique. International Journal of Smart Grid-ijSmartGrid. 2025 Sep 5;9(3):127-45. 24. Maherchandani JK, Joshi RR, Tirole R, Swami RK, Ganthia BP. Performance comparison analysis of energy management strategies for hybrid electric vehicles. InRecent Advances in Power Electronics and Drives: Select Proceedings of EPREC 2021 2022 May 27 (pp. 245-254). Singapore: Springer Nature Singapore. 25. Kabat SR, Panigrahi CK. Power quality and low voltage ride through capability enhancement in wind energy system using unified power quality conditioner (UPQC). ECS transactions. 2022 Apr 24;107(1):5655.