Dalarna University's logo and link to the university's website

du.sePublications
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • chicago-author-date
  • chicago-note-bibliography
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Towards Smart Maintenance: Machine-Learning Based Prediction of Retroreflectivity and Color of Road Traffic Signs
Dalarna University, School of Information and Engineering, Microdata Analysis.
2024 (English)Doctoral thesis, comprehensive summary (Other academic)
Description
Abstract [en]

Proper maintenance of road traffic signs is vital for safety, as their low visibility can cause accidents and fatalities. Many countries, including Sweden, lack a systematic approach for replacing signs due to the risky, costly, and complex methods needed to measure their color and retroreflectivity.

This thesis introduces a predictive maintenance method for road traffic signs to ensure their visibility day and night. The proposed data-driven models predict sign degradation, helping maintain optimal visibility, decreasing accidents, and enhancing safety, and environmental sustainability by reducing material consumption and waste reduction.

This thesis suggests using machine learning methods to predict the values of retroreflectivity (coefficient of retroreflection) and color (daylight chromaticity), and to estimate the status (rejected/accepted) and longevity according to color and retroreflectivity. Datasets collected in Sweden, Denmark, and Croatia were used in this research.

Regression and classification models, employing Random Forest (RF), Support Vector Machine (SVM), and Artificial Neural Networks (ANN) utilized to predict the degradation of road traffic signs. ANN showed the highest performance, 94% R2 for retroreflectivity predictions and up to 94% accuracy for color and retroreflectivity status. SVM and RF also achieved acceptable accuracies.

Statistical methods, including linear and logarithmic regression, were also applied to examine the impact of age on the retroreflectivity values and status, chromaticity, and color status of road traffic signs. Findings revealed age as a significant factor, with a generally linear relationship between chromaticity values and age, except for yellow signs which displayed non-linear patterns between 8 and 22 years. Logarithmic regression models achieved R2 values of 50% and 95%, which are more accurate than those from previous studies. These models reveal an annual decrease in retroreflectivity of 4-5% and a negative correlation with the sign's direction, indicating that signs facing south and west degrade faster due to more solar exposure.

Logistic regression and Kaplan-Meier survival analyses were used to assess road traffic signs' longevity. The longevity based on retroreflectivity and color durability varies depending on color, retroreflective sheeting classes, direction, and location.

In Sweden, the median lifespan of road traffic signs estimated based on retroreflectivity lasts up to 25 years for red, 20 for yellow, 20 for white, and 35 for blue sheeting. In Croatia, the lifespan is shorter, 12 years for red, 16 for yellow, and 17 for white, 20 for blue.

Considering color degradation, the median lifespan of yellow road traffic signs is 45 years, 35 years for white, and blue signs, while red signs have a shorter lifespan. However, the red signs deteriorate in color before retroreflectivity with a median lifespan of 16 years, whereas other signs maintain their color longer. This emphasizes the effect of factors like pigment choice and environmental conditions on the durability of road traffic signs.

Place, publisher, year, edition, pages
Borlänge: Dalarna University, 2024.
Series
Dalarna Doctoral Dissertations ; 32
Keywords [en]
Road traffic signs, Retroreflectivity, Chromaticity, Maintenance, Predictive models, classification, Survival analysis, Kaplan Estimator, Machine Learning
National Category
Computer Systems Infrastructure Engineering
Identifiers
URN: urn:nbn:se:du-48198ISBN: 978-91-88679-61-1 (print)OAI: oai:DiVA.org:du-48198DiVA, id: diva2:1843052
Public defence
2024-05-24, room Clas Ohlson and online, Campus Borlänge, 13:00 (English)
Opponent
Supervisors
Available from: 2024-04-22 Created: 2024-03-07 Last updated: 2024-04-22Bibliographically approved
List of papers
1. Factors Affecting Night-Time Visibility of Retroreflective Road Traffic Signs: A Review
Open this publication in new window or tab >>Factors Affecting Night-Time Visibility of Retroreflective Road Traffic Signs: A Review
2021 (English)In: International Journal for Traffic and Transport Engineering, ISSN 2217-5652, Vol. 11, no 1, p. 115-128, article id 10.7708/ijtte.2021.11(1).07Article in journal (Refereed) Published
Abstract [en]

Road traffic signs define a visual language that can be interpreted by drivers.They represent the current traffic situation on the road, show danger and difficulties aroundthe drivers, give them warnings, and help them with their navigation by providing usefulinformation that makes driving safe and convenient. The main part of the road traffic sign isthe retroreflective material which reflects the light from the vehicle headlights to the driver.Driving during night-time is a challenge, and the rertoreflective material on the sign boardhelps the drivers to perceive and interpret the information on the road traffic sign properly.The aim of this paper is to study the factors affecting the performance of driving during nighttimeand the role the retroreflective material that plays in this regard. The vehicle headlights,ambient conditions, and the type of retroreflection material affect the light reflected from theroad traffic signs. It is also found that the retroreflectivity depends on vehicle factors such asheadlights colour and angle of illumination. Other factors such as environmental factors andsign factors can also affect the retroreflectivity.

Place, publisher, year, edition, pages
Serbia: , 2021
Keywords
road traffic sign, retroreflective material, night-time visibility.
National Category
Infrastructure Engineering
Identifiers
urn:nbn:se:du-35835 (URN)10.7708/ijtte.2021.11(1).07 (DOI)
Funder
Swedish Transport Administration
Available from: 2021-01-22 Created: 2021-01-22 Last updated: 2024-04-22Bibliographically approved
2. Using Supervised Machine Learning to Predict the Status of Road Signs
Open this publication in new window or tab >>Using Supervised Machine Learning to Predict the Status of Road Signs
2022 (English)In: Transportation Research Procedia, E-ISSN 2352-1465, Vol. 62, p. 221-228Article in journal (Refereed) Published
Abstract [en]

There is no data collected and saved about road signs in Sweden and the status for these signs is unknown. Furthermore, the status of the sign colors, the quality of the sign, the type of the retroreflection material, and age of the road signs are unknown. Therefore, the status of a road sign (approved or not), which depends on these parameters, is unknown.The aim of this study is to predict the status of the road signs mounted on the Swedish roads by using supervised machine learning. This study investigates the effect of using principal component analysis (PCA) and data scaling on the accuracy of the prediction. The data were prepared before using then scaled using two methods which are the normalization and the standardization.The three algorithms that tested in this study are Random Forest, Artificial Neural Network (ANN), and Support Vector Machines (SVM). They are invoked to predict the status of the road signs. The algorithms exhibited overall high predicting accuracy (98%), high precision (98%), high recall (98%), and high F1 scores (98%).Random forest showed the best performance with 4 PC components on the normalized data with a highest accuracy of 98%.Using PCA showed different impacts on the performance of different techniques. In the case of ANN, invoking PCA improves the accuracy, while for SVM the accuracy decreases when PCA is used. On other hand, PCA has no effect on the accuracy of the random forest model when scaling is invoked.The effect of the data scaling using normalization and standardization is also investigated in this study, and it is noticed that scaling of the data increases the accuracy of the prediction for all the three models (ANN, SVM and Random Forest). Furthermore, better accuracy is achieved when the standardization is invoked compared with normalization.

Place, publisher, year, edition, pages
Elsevier, 2022
Keywords
Road signs, supervised machine learning, principal component analysis, prediction
National Category
Computer Sciences Signal Processing
Identifiers
urn:nbn:se:du-38670 (URN)10.1016/j.trpro.2022.02.028 (DOI)2-s2.0-85127476053 (Scopus ID)
Conference
24th EURO Working Group on Transportation Meeting, EWGT 2021, virtual event, 8-10 September 2021, organized by the University of Aveiro, Portugal
Available from: 2021-10-28 Created: 2021-10-28 Last updated: 2024-04-22Bibliographically approved
3. An Analysis of the Factors Influencing the Retroreflectivity Performance of In-Service Road Traffic Signs
Open this publication in new window or tab >>An Analysis of the Factors Influencing the Retroreflectivity Performance of In-Service Road Traffic Signs
2022 (English)In: Applied Sciences, E-ISSN 2076-3417, Vol. 12, no 5, article id 2413Article in journal (Refereed) Published
Abstract [en]

The road traffic signs in Sweden have no inventory system and it is unknown when a sign has reached the end of its service life and needs to be replaced. As a result, the road authorities do not have a systematic maintenance program for road traffic signs, and many signs which are not in compliance with the minimum retroreflectivity performance requirements are still found on the roads. Therefore, it is very important to find an inexpensive, safe, easy, and highly accurate method to judge the retroreflectivity performance of road signs. This will enable maintenance staff to determine the retroreflectivity of road signs without requiring measuring instruments for retroreflectivity or colors performance. As a first step toward the above goal, this paper aims to identify factors affecting the retroreflectivity of road signs. Two different datasets were used, namely, the VTI dataset from Sweden and NMF dataset from Denmark. After testing different models, two logarithmic regression models were found to be the best-fitting models, with R2 values of 0.50 and 0.95 for the VTI and NMF datasets, respectively. The first model identified the age, direction, GPS positions, color, and class of road signs as significant predictors, while the second model used age, color, and the class of road signs. © 2022 by the authors. Licensee MDPI, Basel, Switzerland.

Keywords
Linear regression, Retroreflective sheeting material, Road traffic sign
National Category
Computer Systems Signal Processing Infrastructure Engineering
Identifiers
urn:nbn:se:du-39844 (URN)10.3390/app12052413 (DOI)000926968600001 ()2-s2.0-85125768375 (Scopus ID)
Available from: 2022-03-14 Created: 2022-03-14 Last updated: 2024-04-22Bibliographically approved
4. Assessing the color status and daylight chromaticity of road signs through machine learning approaches
Open this publication in new window or tab >>Assessing the color status and daylight chromaticity of road signs through machine learning approaches
2023 (English)In: IATSS Research, ISSN 0386-1112, Vol. 47, no 3, p. 305-317Article in journal (Refereed) Published
Abstract [en]

The color of road signs is a critical aspect of road safety, as it helps drivers quickly and accurately identify and respond to these signs. Properly colored road signs improve visibility during the day and make it easier for drivers to make informed decisions while driving. In order to ensure the safety and efficiency of road traffic, it is essential to maintain the appropriate color level of road signs. The objective of this study was to analyze the color status and daylight chromaticity of in-use road signs using supervised machine learning models, and to explore the correlation between road sign's age and daylight chromaticity. Three algorithms were employed: Random Forest (RF), Support Vector Machine (SVM), and Artificial Neural Network (ANN). The data used in this study was collected from road signs that were in-use on roads in Sweden. The study employed classification models to assess the color status (accepted or rejected) of the road signs based on minimum acceptable color levels according to standards, and regression models to predict the daylight chromaticity values. The correlation between road sign's age and daylight chromaticity was explored through regression analysis. Daylight chromaticity describes the color quality of road signs in daylight, that is expressed in terms of X and Y chromaticity coordinates. The study revealed a linear relationship between the road sign's age and daylight chromaticity for blue, green, red, and white sheeting, but not for yellow. The lifespan of red signs was estimated to be around 12 years, much shorter than the estimated lifespans of yellow, green, blue, and white sheeting, which are 35, 42, 45, and 75 years, respectively. The supervised machine learning models successfully assessed the color status of the road signs and predicted the daylight chromaticity values using the three algorithms. The results of this study showed that the ANN classification and ANN regression models achieved high accuracy of 81% and R2 of 97%, respectively. The RF and SVM models also performed well, with accuracy values of 74% and 79% and R2 ranging from 59% to 92%. The findings demonstrate the potential of machine learning to effectively predict the status and daylight chromaticity of road signs and their impact on road safety in the Swedish context. © 2023 International Association of Traffic and Safety Sciences

Keywords
Classification, Daylight chromaticity, Machine learning algorithms, Prediction, Regression, Road signs, Accident prevention, Color, Forecasting, Forestry, Learning algorithms, Learning systems, Motor transportation, Regression analysis, Roads and streets, Support vector machines, Color levels, Machine learning models, Random forests, Regression modelling, Road safety, Supervised machine learning, Neural networks
National Category
Transport Systems and Logistics Computer and Information Sciences
Identifiers
urn:nbn:se:du-46627 (URN)10.1016/j.iatssr.2023.06.003 (DOI)001048708900001 ()2-s2.0-85164276006 (Scopus ID)
Available from: 2023-08-04 Created: 2023-08-04 Last updated: 2024-04-22Bibliographically approved
5. Predictive models for road traffic sign: Retroreflectivity status, retroreflectivity coefficient, and lifespan
Open this publication in new window or tab >>Predictive models for road traffic sign: Retroreflectivity status, retroreflectivity coefficient, and lifespan
2024 (English)In: International Journal of Transportation Science and Technology, ISSN 2046-0430Article in journal (Refereed) In press
Abstract [en]

This study addresses the critical safety issue of declining retroreflectivity values of road traffic signs, which can lead to unsafe driving conditions, especially at night. The paper aims to predict the retroreflectivity coefficient values of these signs and to classify their status as acceptable or rejected (in need of replacement) using machine learning models. Moreover, logistic regression and survival analysis are used to predict the median lifespans of road traffic signs across various geographical locations, focusing on signs in Croatia and Sweden as case studies. The results indicate high accuracy in the predictive models, with classification accuracy at 94% and an R2 value of 94% for regression analysis. A significant finding is that a considerable number of signs maintain acceptable retroreflectivity levels within their warranty period, suggesting the feasibility of extending maintenance checks and warranty periods to 15 years which is longer than the current standard of 10 years. Additionally, the study reveals notable variations in the median lifespans of signs based on color and location. Blue signs in Croatia and Sweden exhibit the longest median lifespans (28 to 35 years), whereas white signs in Sweden and red signs in Croatia show the shortest (16 and 10 years, respectively). The high accuracy of logistic regression models (72–90%) for lifespan prediction confirms the effectiveness of this approach. These findings provide valuable insights for road authorities regarding the maintenance and management of road traffic signs, enhancing road safety standards. © 2024 Tongji University and Tongji University Press

Place, publisher, year, edition, pages
KeAi Communications Co., 2024
Keywords
Daylight Chromaticity, Machine learning algorithms, Prediction, Retroreflectivity, Road signs, Highway administration, Highway planning, Learning algorithms, Logistic regression, Machine learning, Motor transportation, Roads and streets, Traffic signs, Croatia, High-accuracy, Lifespans, Predictive models, Road traffic, Warranty period, Forecasting
National Category
Infrastructure Engineering Computer Systems
Identifiers
urn:nbn:se:du-48218 (URN)10.1016/j.ijtst.2024.02.008 (DOI)2-s2.0-85186242464 (Scopus ID)
Available from: 2024-03-12 Created: 2024-03-12 Last updated: 2024-04-22
6. Predicting the service life of road signs based on their retroreflectivity and color using Logistic Regression
Open this publication in new window or tab >>Predicting the service life of road signs based on their retroreflectivity and color using Logistic Regression
2023 (English)In: Transportation Research Procedia, ISSN 2352-1465, Vol. 73, p. 77-84Article in journal (Refereed) Published
Abstract [en]

AbstractRoad signs play a vital role in providing drivers with crucial information for safe driving in both day and nighttime. The color of road signs enhances visibility during daylight hours, while retroreflectivity is essential for improving visibility during nighttime conditions. Road authorities, responsible for maintaining road signs, primarily consider the levels of retroreflectivity when deciding to replace them, ensuring optimal visibility for drivers. This study focuses on examining the degradation of road signs based on retroreflectivity and color to ensure safe driving through adequate visibility in both day and nighttime conditions. The study underscores the significance of regulating the deterioration of road sign colors to enhance visibility and legibility, while minimizing maintenance and replacement costs. The primary objective of this paper is to predict the age (service life) of road signs by considering both retroreflectivity and color status and using logistic regression. The results indicate that the age of road signs can be influenced by either retroreflectivity or color. For instance, approximately 50% of red road signs are projected to lose their color after 16 years, while their retroreflectivity remains acceptable. Similarly, around 50% of yellow and white road signs experience retroreflectivity degradation after 20 and 16 years, respectively, while their color remains acceptable. Finally, blue road signs demonstrate acceptable retroreflectivity and color levels even after 35 years.

Keywords
Retroreflectivity; Road signs; Age predicting; Logistic Regression
National Category
Infrastructure Engineering Computer and Information Sciences Signal Processing
Identifiers
urn:nbn:se:du-47866 (URN)10.1016/j.trpro.2023.11.894 (DOI)2-s2.0-85184960441 (Scopus ID)
Conference
The Science and Development of Transport - Znanost i razvitak prometa – ZIRP 2023
Funder
Swedish Transport Administration
Available from: 2024-01-17 Created: 2024-01-17 Last updated: 2024-04-22Bibliographically approved

Open Access in DiVA

fulltext(1441 kB)43 downloads
File information
File name FULLTEXT01.pdfFile size 1441 kBChecksum SHA-512
b83c54ab372167ca53e89f4998e9d2213a0c2f36abc4ea1f105a51cfb0474d55ecd255c42632991ff1a1e7f4e3ff07182b8a15f7548bd2b362d675e8b9899e02
Type fulltextMimetype application/pdf

Authority records

Saleh, Roxan

Search in DiVA

By author/editor
Saleh, Roxan
By organisation
Microdata Analysis
Computer SystemsInfrastructure Engineering

Search outside of DiVA

GoogleGoogle Scholar
Total: 43 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

isbn
urn-nbn

Altmetric score

isbn
urn-nbn
Total: 788 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • chicago-author-date
  • chicago-note-bibliography
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf