Road surface classification using accelerometer and speed data: evaluation of a convolutional neural network model

Sabapathy, Ashwin; Biswas, Avik

doi:10.1007/s00521-023-08479-z

Cited by 4 publications

(1 citation statement)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposed method exceeded neural feedforward networks and support vector machines (SVM), achieving a precision of 98.5%. To classify roads into the categories of good, fair, and poor, Sabapathy et al 22 evaluated the ordinal logistic model, the SVM model, the ANN model, and the CNN model using accelerometer and speed data collected from OBD-II. The CNN model's overall accuracy on the validation dataset was 65.6%, but it outperformed others.…”

Section: Related Workmentioning

confidence: 99%

Evaluation of data representation techniques for vibration based road surface condition classification

Raslan,

Alrahmawy,

Mohammed

et al. 2024

Sci Rep

View full text Add to dashboard Cite

The accurate classification of road surface conditions plays a vital role in ensuring road safety and effective maintenance. Vibration-based techniques have shown promise in this domain, leveraging the unique vibration signatures generated by vehicles to identify different road conditions. In this study, we focus on utilizing vehicle-mounted vibration sensors to collect road surface vibrations and comparing various data representation techniques for classifying road surface conditions into four classes: normal road surface, potholes, bad road surface, and speedbumps. Our experimental results reveal that the combination of multiple data representation techniques results in higher performance, with an average accuracy of 93.4%. This suggests that the integration of deep neural networks and signal processing techniques can produce a high-level representation better suited for challenging multivariate time series classification issues.

show abstract

Section: Related Workmentioning

confidence: 99%

Evaluation of data representation techniques for vibration based road surface condition classification

Raslan,

Alrahmawy,

Mohammed

et al. 2024

Sci Rep

View full text Add to dashboard Cite

show abstract

Adaptable Accelerometer Signal Processing Pipelines for Smartphone based Evenness Estimation

Münke,

Schenk,

Murr

et al. 2024

J Sign Process Syst

View full text Add to dashboard Cite

Evenness is an essential indicator of road quality. Accelerometer sensors in smartphones offer an accessible and cost-efficient solution for monitoring road evenness. However, the accelerometer signal from smartphones is influenced by various internal and external factors beyond the road’s actual evenness. External factors, in particular, can introduce systematic bias due to differences in vehicle suspension or smartphone mounting methods. In this study, we investigate specific external factors affecting windshield-mounted smartphones and propose a method to automatically adapt accelerometer processing pipelines, improving robustness against such external influences.

show abstract

Recent Advancements in Deep Learning Techniques for Road Condition Monitoring: A Comprehensive Review

Manoni,

Orcioni,

Conti

2024

IEEE Access

View full text Add to dashboard Cite

Road surface classification using accelerometer and speed data: evaluation of a convolutional neural network model

Cited by 4 publications

References 15 publications

Evaluation of data representation techniques for vibration based road surface condition classification

Evaluation of data representation techniques for vibration based road surface condition classification

Adaptable Accelerometer Signal Processing Pipelines for Smartphone based Evenness Estimation

Recent Advancements in Deep Learning Techniques for Road Condition Monitoring: A Comprehensive Review

Contact Info

Product

Resources

About