Article

Received 09.02.2025

Revised 02.06.2025

Accepted 24.06.2025

Retrieved from Iss. 117, P. 2, 2025

Pages 72 -86

Zarichnyi, A., & Usychenko, O. (2025). SMARTPHONE-BASED MONITORING OF ROAD PAVEMENT CONDITION. Automobile Roads and Road Construction, (117.2), 72-86. https://doi.org/10.33744/0365-8171-2025-117.2-072-086

SMARTPHONE-BASED MONITORING OF ROAD PAVEMENT CONDITION

Anton Zarichnyi Olena Usychenko

The article substantiates the relevance of creating innovative approaches to monitoring the condition of road pavement in Ukraine, where a significant part of the road network is in poor condition, while traditional diagnostic methods are characterized by high costs and limited scalability. The aim of the research is to develop a concept of a smartphone-based monitoring system that utilizes built-in sensors (accelerometer, gyroscope, GPS) to collect and analyze telemetry data in real time. The study reviews modern methods of pavement evaluation, outlines the technical aspects of sensor data collection, filtering, and processing, and identifies key metrics such as Root Mean Square Acceleration, peak values, and spectral features of the signal. A prototype Android application was developed to record sensor data in CSV format, which was further processed in Python using libraries such as pandas, numpy, scipy, matplotlib, and folium. The results demonstrated the sensitivity of the system to differences in road quality: for smooth segments, RMSA values ranged from 0.3 to 1.5 m/s², while for damaged areas they exceeded 4 m/s². Visualization on interactive maps confirmed the practical applicability of the method for identifying defects such as potholes, cracks, and manholes. The novelty of the research lies in combining sensor monitoring methods with crowdsourcing concepts, which enables large-scale data collection without the need for expensive equipment. The practical value is defined by the economic feasibility of using smartphones as measuring devices and the possibility of integration into urban transport and smart city platforms. Future research directions include improving data normalization algorithms, considering vehicle type and speed, and applying machine learning models (XGBoost, RandomForest, CNN) for defect classification

road pavement, smartphone, sensors, accelerometer, RMSA, monitoring, vibration analysis, machine learning
  1. Asian Development Bank. (2025). Guidebook on machine learning techniques for road quality monitoring. Retrieved from https://www.adb.org/publications/guidebook-machine-learning-road-quality.
  2. Burningham, S., & Stankevich, N. (2005). Why road maintenance is important and how to get it done (Transport Notes No. 4). Washington, DC: World Bank.
  3. Cadamuro, G., Muhebwa, A., & Taneja, J. (2018). Assigning a grade: Accurate measurement of road quality using satellite imagery. arXiv. doi: 10.48550/arXiv.1812.01699.
  4. Oshri, B., Hu, W., Yang, P., & Jean, N. (2018). Infrastructure quality assessment in Africa using satellite imagery and deep learning. arXiv. doi: 10.48550/arXiv.1806.00894.
  5. Gebreegziabher, B.A. (2021). Mapping road pavement quality from optical satellite imagery using machine learning. (Master's thesis, University of Twente, Enschede, Netherlands).
  6. Roadroid. (n.d.). Retrieved from https://www.roadroid.com.
  7. RoadBotics. (n.d.). Retrieved from https://www.roadbotics.com.
  8. Sayers, M.W., & Karamihas, S.M. (1998). The little book of profiling: Basic information about measuring and interpreting road profiles. Ann Arbor, MI: University of Michigan Transportation Research Institute.
  9. Ghate, A.T., & Qamar, F. (2020). Pavement condition monitoring using smartphone sensors: A review. Journal of Traffic and Transportation Engineering (English Edition), 7(2), 237-251.
  10. Zhang, L., & Li, Q. (2019). A smartphone-based road roughness detection algorithm using wavelet packet transform. Sensors, 19(17), article number 3822.
  11. Chien, S., Ding, Y., & Wei, C. (2002). Dynamic bus arrival time prediction with artificial neural networks. Journal of Transportation Engineering, 128(5), 429-438.
  12. SciPy Community. (n.d.). Retrieved from https://docs.scipy.org/doc/scipy/reference/generated/scipy.signal.find_peaks.html.
  13. Mednis, A., Strazdins, G., Zviedris, R., Kanonirs, G., & Selavo, L. (2011). Real-time pothole detection using Android smartphones with accelerometers. In 2011 International conference on distributed computing in sensor systems and workshops (DCOSS) (pp. 1-6).
  14. Douangphachanh, V., & Oneyama, H. (2014). A study on the use of smartphones for road roughness condition estimation. Journal of the Eastern Asia Society for Transportation Studies, 11, 1718-1732.
  15. Eriksson, J., Girod, L., Hull, B., Newton, R., Madden, S., & Balakrishnan, H. (2008). The pothole patrol: Using a mobile sensor network for road surface monitoring. In Proceedings of the 6th international conference on mobile systems, applications, and services (MobiSys '08) (pp. 29-39).
  16. Wahab, A., & Hussain, K. (2018). Road anomaly detection using smartphone sensors: A survey. Journal of Network and Computer Applications, 109, 1-11.
  17. Python Visualization Team. (n.d.). Folium: Python data, leaflet.js maps. Retrieved from https://python-visualization.github.io/folium

https://doi.org/10.33744/0365-8171-2025-117.2-072-086