EUVIMEDEUVIMED entdecken
Crossref

ARCHITECTURE OF A MACHINE LEARNING MODEL FOR ROAD SURFACE CONDITION ASSESSMENT BASED ON SENSOR DATA

Volodymyr Havran, Volodymyr Tkachenko

Computer Design Systems. Theory and Practice · 2026 · 8 (1) · 29-38

DOI: 10.23939/cds2026.01.029 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computer Design Systems. Theory and Practice, online erschienen am 30.04.2026. Verfasst von Volodymyr Havran und 1 weiteren Autor:innen. Die Arbeit nennt 16 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The article clearly describes the architecture of a machine learning model for assessing road surface conditions based on sensor data. The relevance of the study is driven by the need for automated road surface analysis in situations with limited or missed labeled data, high noise levels in sensor signals, and requirements for real-time data processing. The task of online estimation of road defect intensity based on time-series data obtained from motion sensors is considered. The proposed approach involves forming an ordinal assessment of road surface condition that reflects the relative intensity of events without using classical multiclass classification. The paper provides a detailed description of the model structure, feature engineering principles, adaptation mechanisms, and the logic for updating assessments as new data arrives. An experimental study of the effectiveness of the proposed architecture was conducted, including analysis of the dynamics of the assessments, their robustness to noise, and the model’s ability to adapt to different road condition scenarios. The obtained results demonstrate the feasibility of using the proposed approach for road surface monitoring and condition assessment tasks based on sensor information.

Zitieren

APA

Havran, V., & Tkachenko, V. (2026). ARCHITECTURE OF A MACHINE LEARNING MODEL FOR ROAD SURFACE CONDITION ASSESSMENT BASED ON SENSOR DATA. Computer Design Systems. Theory and Practice, 8(1), 29-38. https://doi.org/10.23939/cds2026.01.029

Vancouver

Havran V, Tkachenko V. ARCHITECTURE OF A MACHINE LEARNING MODEL FOR ROAD SURFACE CONDITION ASSESSMENT BASED ON SENSOR DATA. Computer Design Systems. Theory and Practice. 2026;8(1):29-38. doi:10.23939/cds2026.01.029

BibTeX
@article{Havran2026,
  author = {Havran, Volodymyr and Tkachenko, Volodymyr},
  title = {ARCHITECTURE OF A MACHINE LEARNING MODEL FOR ROAD SURFACE CONDITION ASSESSMENT BASED ON SENSOR DATA},
  journal = {Computer Design Systems. Theory and Practice},
  year = {2026},
  volume = {8},
  number = {1},
  pages = {29--38},
  doi = {10.23939/cds2026.01.029}
}
Kostenlos starten →