INTEGRATION OF GRAPHENE-SENSOR-BASED ELECTRONIC NOSE TECHNOLOGY INTO MOBILE MICROCONTROLLER PLATFORM

Igor Olenych, Yaroslav Boyko, Bohdana Kukharska, Roman Yaremyk, Oleh Sinkevych, Mykhaylo Pavlyk, Ivan Karbovnyk

Abstract


Background. The integration of sensors, in particular electronic nose technology, into mobile platforms is a fundamental element in the development of modern robotics and autonomous intelligent systems. This combination opens up new possibilities for automated air quality monitoring, detection of pollution sources, and the execution of rescue operations in hazardous conditions. An important aspect in this context is the use of artificial intelligence and machine learning algorithms to analyze sensor data and predict environmental changes. Consequently, particular attention was focused on implementing the microcontroller architecture of the intelligent sensor system.

Materials and methods. The developed mobile sensor platform architecture comprises a graphene FET-based sensor module, an impedance analyzer module, and a control module based on the ESP32 microcontroller. Normalized graphene channel resistance profiles and normalized gate resistance measured in atmospheres of acetone, ammonia, ethanol, and toluene vapor were used to develop a neural network-based machine learning model and test the intelligent sensor system.

Results. The developed model provided 90.9 % sensor data classification accuracy. The weighted average values for Precision, Recall, and F1-score are 0.94, 0.91, and 0.92, respectively, confirming the high quality of the classification and the model balance across the different classes of the target gases. The machine learning model deployed on the ESP32 microcontroller uses about 26% of flash memory and 6% of RAM for target gas recognition. The gas identification time, which does not exceed 1 ms, is small enough for the real-time intelligent sensor system.

Conclusions. The distributed architecture for the mobile sensor system based on the ESP32 microcontroller, combining control, sensor data measurement and acquisition, and data analysis functions, was proposed. It is demonstrated that the developed machine learning model provides high accuracy of target gas identification. The obtained results confirm the feasibility of implementing the proposed solutions on real-time platforms with limited computing resources.

Keywords: Graphene field-effect transistor, sensor platform, measuring system, microcontroller, machine learning model, gas recognition.


Full Text:

PDF

References


[1] Boleraczki, M. & Gyurika, I.G. (2025). Industrial mobile robot-based manufacturing system modeling potential. Data-Centric Engineering, 6, e46. https://doi.org/10.1017/dce.2025.10020

[2] Pavel, M.-D., Stamatescu, G., Chodnicki, M., & Amza, C. G. (2026). LLM-Enhanced Control of a Mobile Robotic Platform for Smart Industry. Applied Sciences, 16(4), 1680.
https://doi.org/10.3390/app16041680

[3] Al-Tawil, B., Candemir, A., Jung, M., & Al-Hamadi, A. (2025). Mobile Robot Navigation with Enhanced 2D Mapping and Multi-Sensor Fusion. Sensors, 25(8), 2408.
https://doi.org/10.3390/s25082408

[4] Placed, J.A., Strader, J., Carrillo, H., Atanasov, N., Indelman, V., Carlone, L., & Castellanos, J.A. (2023). A survey on active simultaneous localization and mapping: State of the art and new frontiers. IEEE Trans. Robot., 39, 1686–1705. https://doi.org/10.1109/TRO.2023.3248510

[5] Fan, Z., Zhang, L., Wang, X., Shen, Y., & Deng, F. (2025). LiDAR, IMU, and camera fusion for simultaneous localization and mapping: a systematic review. Artif. Intell. Rev., 58, 174.
https://doi.org/10.1007/s10462-025-11187-w

[6] Usinskis, V., Nowicki, M., Dzedzickis, A., & Bucinskas, V. (2025). Sensor-Fusion Based Navigation for Autonomous Mobile Robot. Sensors, 25(4), 1248. https://doi.org/10.3390/s25041248

[7] Zhai, Z., Liu, Y., Li, C., Wang, D., & Wu, H. (2024). Electronic Noses: From Gas-Sensitive Components and Practical Applications to Data Processing. Sensors, 24(15), 4806.
https://doi.org/10.3390/s24154806

[8] Ma, D., Gao, J., Zhang, Z., & Zhao, H. (2021). Gas recognition method based on the deep learning model of sensor array response map. Sensor Actuat. B Chem., 330, 129349.
https://doi.org/10.1016/j.snb.2020.129349

[9] Zhang, W., Tang, W., Wan, Z., & Fan, Z. (2026). Advanced electronic noses for future robotic olfaction. npj Robot, 4, 11.
https://doi.org/10.1038/s44182-025-00071-y

[10] Liu, H., Chu, R.Z., & Tang, Z.A. (2015). Metal oxide gas sensor drift compensation using a two-dimensional classifier ensemble. Sensors, 15, 10180. https://doi.org/10.3390/s150510180

[11] Huang, J.R., Gu, C.P., Meng, F.L., Li, M.Q., & Liu, J.H. (2007). Detection of volatile organic compounds by using a single temperature-modulated SnO2 gas sensor and artificial neural network. Smart Mater. Struct. 16, 701.
https://doi.org/10.1088/0964-1726/16/3/017

[12] Su, S. & Hu, J. (2019). Gas identification by a single metal-oxide-semiconductor sensor assisted by ultrasound, ACS Sens. 4, 2491. https://doi.org/10.1021/acssensors.9b01113

[13] Hayasaka, T., Lin, A., Copa, V. C., Lopez Jr., L.P., Loberternos, R.A., Ballesteros, L.I.M., Kubota, Y., Liu, Y., Salvador, A.A., & Lin, L. (2020). An electronic nose using a single graphene FET and machine learning for water, methanol, and ethanol. Microsyst. Nanoeng. 6, 50.
https://doi.org/10.1038/s41378-020-0161-3

[14] Olenych, I. (2025). Field-effect transistor based on reduced graphene oxide – porous silicon hybrid structure for application in e-nose technology. Mol. Cryst. Liq. Cryst., 769, 1527–1537.
https://doi.org/10.1080/15421406.2025.2540098

[15] Olenych, I., Yaremyk, R., & Parandiy, P. (2025). Microprocessor system for measuring sensor characteristics of gas-sensitive field-effect transistors based on porous silicon and reduced graphene oxide film. Computer-Integrated Technologies: Education, Science, Production, 61, 171–177 (in Ukrainian). https://doi.org/10.36910/6775-2524-0560-2025-61-24

[16] Simiс, M. (2015). Complex Impedance Measurement System for the Frequency Range from 5 kHz to 100 kHz. Key Engineering Materials. 644, 133–136. https://doi.org/10.4028/www.scientific.net/KEM.644.133

[17] van der Maaten, L. & Hinton, G. (2008). Visualizing Data using t-SNE. Journal of Machine Learning Research. 9, 2579-2605. http://jmlr.org/papers/v9/vandermaaten08a.html

[18] Olenych, I. & Osadchuk, O. (2024). Application of Machine Learning Algorithms in Electronic Nose Technology. Electronics and Information Technologies. 25, 56–66 (in Ukrainian).
https://doi.org/10.30970/eli.25.5




DOI: http://dx.doi.org/10.30970/eli.35.13

Refbacks

  • There are currently no refbacks.