Analysis of Road Damages for Micro Mobility Vehicles Via Synthetic Data: Three-Axis Accelerometer-Based Machine Learning DOI Creative Commons
Ömer Kaya

Brilliant Engineering, Journal Year: 2025, Volume and Issue: 6(1), P. 1 - 8

Published: Jan. 1, 2025

The effect of road damages on the surface driver safety and comfort depends damping mechanism vehicle. Since micro mobility vehicles have small wheels, damage affects them with varying severity. This study aims to determine based response bicycles, e-bikes, e-scooters surface. In order achieve this goal, firstly synthetic data approach is adopted. There are 10 000 samples in set it was produced Google Colab Python. These simulate collected a three-axis accelerometer. for distributions represent real world, flat roads (undamaged), cracks potholes determined as 7 000, 2 1 samples, respectively. prevent distribution from being biased eliminate overfitting problem, unbalanced class sensor noise simulated. Random Forest algorithm used classification damages. accuracy rate 95%. addition, K-Means clustering helps analyze how each vehicle type responds Silhouette Score 0.543, which shows intertwined clusters separate they other. results confirm that proposed integrates well real-world data. To validate model performance, researchers should collect accelerometer alongside simulated

Language: Английский

Two-camera vision technique for measuring pothole area and depth DOI
Sung-Sik Park, Nhut-Nhut Nguyen

Measurement, Journal Year: 2025, Volume and Issue: unknown, P. 116809 - 116809

Published: Jan. 1, 2025

Language: Английский

Citations

0
EPDD-YOLO: An efficient benchmark for pavement damage detection based on Mamba-YOLO DOI

Shipeng Luo,

Yuxin Zhang, Zeyu Zhang

et al.

Measurement, Journal Year: 2025, Volume and Issue: unknown, P. 117638 - 117638

Published: April 1, 2025

Language: Английский

Citations

0
Analysis of Road Damages for Micro Mobility Vehicles Via Synthetic Data: Three-Axis Accelerometer-Based Machine Learning DOI Creative Commons
Ömer Kaya

Brilliant Engineering, Journal Year: 2025, Volume and Issue: 6(1), P. 1 - 8

Published: Jan. 1, 2025

The effect of road damages on the surface driver safety and comfort depends damping mechanism vehicle. Since micro mobility vehicles have small wheels, damage affects them with varying severity. This study aims to determine based response bicycles, e-bikes, e-scooters surface. In order achieve this goal, firstly synthetic data approach is adopted. There are 10 000 samples in set it was produced Google Colab Python. These simulate collected a three-axis accelerometer. for distributions represent real world, flat roads (undamaged), cracks potholes determined as 7 000, 2 1 samples, respectively. prevent distribution from being biased eliminate overfitting problem, unbalanced class sensor noise simulated. Random Forest algorithm used classification damages. accuracy rate 95%. addition, K-Means clustering helps analyze how each vehicle type responds Silhouette Score 0.543, which shows intertwined clusters separate they other. results confirm that proposed integrates well real-world data. To validate model performance, researchers should collect accelerometer alongside simulated

Language: Английский

Citations

0