Development of serviceability prediction model for county paved roads

Aleadelat, Waleed; Saha, Promothes; Ksaibati, Khaled

doi:10.1080/10298436.2016.1176167

Cited by 16 publications

(5 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other researchers developed sensor-based models using various sensors to predict the presence of defects on road surfaces. Aleadelat et al [16] used smartphone accelerometers to determine International Roughness Index (IRI) and achieved an adjusted R 2 of 0.8. Souza et al [17] used sensor data collected from smartphone accelerometers and complexity invariant distance to develop an ML model.…”

Section: Literature Reviewmentioning

confidence: 99%

Pavement Distress Identification Based on Computer Vision and Controller Area Network (CAN) Sensor Models

et al. 2023

View full text Add to dashboard Cite

Recent technological developments have attracted the use of machine learning technologies and sensors in various pavement maintenance and rehabilitation studies. To avoid excessive road damages, which cause high road maintenance costs, reduced mobility, vehicle damages, and safety concerns, the periodic maintenance of roads is necessary. As part of maintenance works, road pavement conditions should be monitored continuously. This monitoring is possible using modern distress detection methods that are simple to use, comparatively cheap, less labor-intensive, faster, safer, and able to provide data on a real-time basis. This paper proposed and developed two models: computer vision and sensor-based. The computer vision model was developed using the You Only Look Once (YOLOv5) algorithm for detecting and classifying pavement distresses into nine classes. The sensor-based model combined eight Controller Area Network (CAN) bus sensors available in most new vehicles to predict pavement distress. This research employed an extreme gradient boosting model (XGBoost) to train the sensor-based model. The results showed that the model achieved 98.42% and 97.99% area under the curve (AUC) metrics for training and validation datasets, respectively. The computer vision model attained an accuracy of 81.28% and an F1-score of 76.40%, which agree with past studies. The results indicated that both computer vision and sensor-based models proved highly efficient in predicting pavement distress and can be used to complement each other. Overall, computer vision and sensor-based tools provide cheap and practical road condition monitoring compared to traditional manual instruments.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Pavement Distress Identification Based on Computer Vision and Controller Area Network (CAN) Sensor Models

et al. 2023

View full text Add to dashboard Cite

show abstract

“…While Roadroid underestimated IRI values, there was a linear correlation between IRI measurements obtained from both methods. Aleadelat et al [18] utilized smartphone accelerometers to obtain acceleration data and applied basic signal processing and pattern recognition techniques to establish a correlation between the measured data and the IRI). This validates the use of variance in acceleration measurements obtained from smartphone sensors for determining IRI.…”

Section: Related Workmentioning

confidence: 99%

Design and Implementation of a Vibration-Based Real-Time Internet of Things Framework for Road Condition Monitoring

AbdelRaheem,

Hassan,

Alyousify

et al. 2023

IEEE Open J. Veh. Technol.

View full text Add to dashboard Cite

This paper presents a study on the design and implementation of a real-time Internet of Things (IoT) framework for monitoring road conditions. The proposed system incorporates an accelerometer sensor attached to the rear axle of a vehicle to capture vertical acceleration signals resulting from the interaction between the vehicle suspension system and the road surface. These acceleration signals are utilized to determine vertical displacements, which are then used to calculate the International Roughness Index (IRI) as an indicator of road quality. The system comprises a hardware node for acquiring acceleration signals and a remote monitoring system for calculating and visually representing the IRI on a road map. Our results demonstrate that the proposed system is effective in automatically assessing road conditions, with an error in the calculated IRI of less than 3.5%INDEX TERMS Internet of Things (IoT), road condition assessment, cellular internet, IRI.

show abstract

“…The PSI of the selected road segments was obtained using the county roads serviceability prediction model (Equation 2). This model is exclusive to the county roads in Wyoming and it is developed by WYT 2 /LTAP as part of the county roads PMS building process (26). where IRI is in inches per mile and rut is the depth in inches.…”

Section: Data Collectionmentioning

confidence: 99%

Estimation of Pavement Serviceability Index Through Android-Based Smartphone Application for Local Roads

Aleadelat

Ksaibati

2017

Transportation Research Record: Journal of the Transportation R

Self Cite

View full text Add to dashboard Cite

The Wyoming Technology Transfer Center is in the process of developing a pavement management system (PMS) for county paved roads in Wyoming. This PMS uses the present serviceability index (PSI) as a main pavement performance parameter. This PMS depends on pavement condition index, international roughness index, and pavement rutting as explanatory variables to estimate PSI. This study researched new explanatory variables measured by using smartphones’ sensors to estimate PSI. It was found that the variance of the signals (time series acceleration data) acquired by smartphones’ accelerometers could work as a very good explanatory variable to estimate PSI. Two models were developed with high significance ( R2 higher than .9) to predict PSI using the variance of smartphone signals. The initial validation results suggested that using these models could predict, with high certainty, the actual PSI values. The difference between the predicted and the actual PSI values was not statistically different. The study was performed on 20 roadway segments extracted from the Wyoming county roads’ PMS database. In addition, the selected segments had various lengths and geometric features reflecting various roadway segments under any PMS. The proposed methodology is intended to lower the cost of measuring county roads’ pavement conditions by estimating PSI directly without the reliance on the direct measurement of pavement condition parameters.

show abstract

Development of serviceability prediction model for county paved roads

Cited by 16 publications

References 3 publications

Pavement Distress Identification Based on Computer Vision and Controller Area Network (CAN) Sensor Models

Pavement Distress Identification Based on Computer Vision and Controller Area Network (CAN) Sensor Models

Design and Implementation of a Vibration-Based Real-Time Internet of Things Framework for Road Condition Monitoring

Estimation of Pavement Serviceability Index Through Android-Based Smartphone Application for Local Roads

Contact Info

Product

Resources

About