{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T17:59:15Z","timestamp":1781632755554,"version":"3.54.5"},"reference-count":44,"publisher":"Public Library of Science (PLoS)","issue":"6","license":[{"start":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T00:00:00Z","timestamp":1781568000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Xinjiang Transportation Investment (Group) Co., Ltd.","award":["EKXFWCG2024040202"],"award-info":[{"award-number":["EKXFWCG2024040202"]}]},{"name":"Xinjiang Natural Science Foundation Project","award":["2024D01A53"],"award-info":[{"award-number":["2024D01A53"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>With the expansion of high-speed road mileage and the aging of road networks, maintenance workloads have increased dramatically. Accurately forecasting preventive maintenance costs is a practical approach to rationally control maintenance expenditure, enhance capital utilization efficiency, and ensure the long-term stable operation of the road network. However, the current predictive model for preventive maintenance costs fails to adequately account for variations in types of preventive maintenance measures, limiting their ability to capture the actual cost variation patterns under different engineering conditions. Consequently, there remains scope for improvement in prediction accuracy. In this study, we developed three meta-heuristic-optimized hybrid models, each tailored to a specific asphalt pavement preventive maintenance measure: 1) the fruit fly optimization algorithm (FOA)-enhanced XGBoost model for crack filling; 2) the hiking optimization algorithm (HOA)-enhanced RF model for surface sealing; 3) the particle swarm optimization (PSO)-enhanced BPNN model for overlay. A case study demonstrates that FOA-XGBoost (R\u00b2\u2009=\u20090.8622, MAE\u2009=\u20090.0552) improved XGBoost\u2019s R\u00b2 by 0.0526.<\/jats:p>\n                  <jats:p>In contrast, HOA-RF (MSE\u2009=\u20090.0032, RMSE\u2009=\u20090.0565) outperformed RF with lower error metrics. Furthermore, PSO-BPNN achieved the highest R\u00b2 (0.9277) and the lowest MAE (0.0419) compared to BPNN. All models maintained MAPE below 5%. To further support the reliability of the results, the Wilcoxon signed-rank test was conducted to assess the statistical significance of model performance differences. In addition, nested cross-validation and sensitivity analysis were performed to evaluate the robustness and stability of the proposed models. These findings indicate that the optimized hybrid model has demonstrated improvements in both predictive accuracy and stability. Consequently, the developed models may provide useful support for maintenance cost estimation and resource allocation in expressway maintenance management.<\/jats:p>","DOI":"10.1371\/journal.pone.0349595","type":"journal-article","created":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T17:35:26Z","timestamp":1781631326000},"page":"e0349595","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Machine learning approaches for predicting preventive maintenance costs of expressways in Xinjiang"],"prefix":"10.1371","volume":"21","author":[{"given":"Chunyan","family":"Jia","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianhui","family":"An","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shengqiang","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1835-8428","authenticated-orcid":true,"given":"Xiaomin","family":"Dai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,6,16]]},"reference":[{"issue":"16","key":"pone.0349595.ref001","doi-asserted-by":"crossref","first-page":"2304","DOI":"10.1111\/mice.13444","article-title":"An optimized and precise road crack segmentation network in complex scenarios","volume":"40","author":"G Wang","year":"2025","journal-title":"Computer-Aided Civil and Infrastructure Engineering"},{"key":"pone.0349595.ref002","doi-asserted-by":"crossref","first-page":"105853","DOI":"10.1016\/j.autcon.2024.105853","article-title":"Rutting extraction from vehicle-borne laser point clouds","volume":"168","author":"X Ma","year":"2024","journal-title":"Automation in Construction"},{"issue":"1","key":"pone.0349595.ref003","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1007\/s11204-025-10030-2","article-title":"Dynamic Response and Deformation Characteristics of Urban Loess Subgrade under Vehicle Loading","volume":"62","author":"Y Liu","year":"2025","journal-title":"Soil Mech Found Eng"},{"issue":"9","key":"pone.0349595.ref004","doi-asserted-by":"crossref","first-page":"670","DOI":"10.1080\/15568318.2017.1302023","article-title":"Preventive maintenance of road pavement with microsurfacing\u2014an economic and sustainable strategy","volume":"11","author":"D Sim\u00f5es","year":"2017","journal-title":"International Journal of Sustainable Transportation"},{"issue":"3","key":"pone.0349595.ref005","doi-asserted-by":"crossref","first-page":"848","DOI":"10.1177\/03611981241283448","article-title":"Providing a Robust Optimization Model for the Preventive Maintenance of Asphalt Road Pavements","volume":"2679","author":"A Saadati","year":"2024","journal-title":"Transportation Research Record: Journal of the Transportation Research Board"},{"issue":"8017","key":"pone.0349595.ref006","doi-asserted-by":"crossref","first-page":"555","DOI":"10.1038\/d41586-024-01754-6","article-title":"Extending the Sustainable Development Goals to 2050 - a road map","volume":"630","author":"F Fuso Nerini","year":"2024","journal-title":"Nature"},{"key":"pone.0349595.ref007","doi-asserted-by":"crossref","first-page":"133534","DOI":"10.1016\/j.conbuildmat.2023.133534","article-title":"Prediction model of asphalt pavement functional and structural performance using PSO-BPNN algorithm","volume":"407","author":"M Xiao","year":"2023","journal-title":"Construction and Building Materials"},{"key":"pone.0349595.ref008","doi-asserted-by":"crossref","first-page":"420","DOI":"10.1016\/j.aej.2025.02.033","article-title":"Stochastic-based pavement performance and deterioration models: A review of techniques and applications","volume":"120","author":"CS Shahid","year":"2025","journal-title":"Alexandria Engineering Journal"},{"issue":"3","key":"pone.0349595.ref009","doi-asserted-by":"crossref","DOI":"10.29333\/jisem\/8427","article-title":"Estimated Maintenance Costs of Brazilian Highways Using Machine Learning Algorithms","volume":"5","author":"R Gaussmann","year":"2020","journal-title":"J INFORM SYSTEMS ENG"},{"issue":"1","key":"pone.0349595.ref010","article-title":"Estimation of Annual Routine Maintenance Cost for Highway Tunnels","volume":"2022","author":"X Wu","year":"2022","journal-title":"Advances in Civil Engineering"},{"issue":"2","key":"pone.0349595.ref011","doi-asserted-by":"crossref","first-page":"489","DOI":"10.1007\/s40030-025-00873-1","article-title":"Prediction of Pavement Maintenance Cost for Rural Roads at Network Level","volume":"106","author":"V Arun","year":"2025","journal-title":"J Inst Eng India Ser A"},{"key":"pone.0349595.ref012","doi-asserted-by":"crossref","first-page":"671","DOI":"10.1007\/978-981-16-6277-5_53","article-title":"Cost Prediction of Roads Construction Projects Using OLS Regression Method","volume-title":"Geotechnical Engineering and Sustainable Construction","author":"RH Rasheed","year":"2022"},{"issue":"11","key":"pone.0349595.ref013","doi-asserted-by":"crossref","DOI":"10.3390\/buildings13112827","article-title":"Estimating the renovation cost of water, sewage, and gas pipeline networks: multiple regression analysis to the appraisal of a reliable cost estimator for urban regeneration works","volume":"13","author":"G De Mare","year":"2023","journal-title":"Buildings"},{"issue":"2","key":"pone.0349595.ref014","article-title":"A Predictive Modeling Approach to Estimating Seismic Retrofit Costs","volume":"36","author":"JF Fung","year":"2020","journal-title":"Earthq Spectra"},{"key":"pone.0349595.ref015","article-title":"Application and prospect of machine learning techniques in cost estimation of building projects","author":"R Wang","year":"2024","journal-title":"Engineering, Construction and Architectural Management"},{"key":"pone.0349595.ref016","doi-asserted-by":"crossref","first-page":"119640","DOI":"10.1016\/j.eswa.2023.119640","article-title":"Financial applications of machine learning: A literature review","volume":"219","author":"N Nazareth","year":"2023","journal-title":"Expert Systems with Applications"},{"issue":"8","key":"pone.0349595.ref017","doi-asserted-by":"crossref","DOI":"10.2196\/37578","article-title":"Predicting Readmission Charges Billed by Hospitals: Machine Learning Approach","volume":"10","author":"D Gopukumar","year":"2022","journal-title":"JMIR Med Inform"},{"issue":"7","key":"pone.0349595.ref018","doi-asserted-by":"crossref","first-page":"3595","DOI":"10.3390\/app12073595","article-title":"A Comparative Study of a Fully-Connected Artificial Neural Network and a Convolutional Neural Network in Predicting Bridge Maintenance Costs","volume":"12","author":"C Wang","year":"2022","journal-title":"Applied Sciences"},{"key":"pone.0349595.ref019","doi-asserted-by":"crossref","first-page":"217848","DOI":"10.1109\/ACCESS.2020.3042329","article-title":"Expressway project cost estimation with a convolutional neural network model","volume":"8","author":"X Xue","year":"2020","journal-title":"IEEE Access"},{"key":"pone.0349595.ref020","first-page":"1","article-title":"Prediction of bronchopneumonia inpatients\u2019 total hospitalization expenses based on BP neural network and support vector machine models","volume":"2022","author":"C Wu","year":"2022","journal-title":"Computational and Mathematical Methods in Medicine"},{"issue":"11","key":"pone.0349595.ref021","doi-asserted-by":"crossref","first-page":"6651","DOI":"10.3390\/su14116651","article-title":"Extreme Gradient Boosting-Based Machine Learning Approach for Green Building Cost Prediction","volume":"14","author":"O Alshboul","year":"2022","journal-title":"Sustainability"},{"issue":"2","key":"pone.0349595.ref022","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1016\/j.icte.2025.02.008","article-title":"A review on multi-fidelity hyperparameter optimization in machine learning","volume":"11","author":"J Won","year":"2025","journal-title":"ICT Express"},{"key":"pone.0349595.ref023","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1016\/j.neucom.2020.07.061","article-title":"On hyperparameter optimization of machine learning algorithms: Theory and practice","volume":"415","author":"L Yang","year":"2020","journal-title":"Neurocomputing"},{"issue":"8","key":"pone.0349595.ref024","doi-asserted-by":"crossref","first-page":"8043","DOI":"10.1007\/s10462-022-10359-2","article-title":"A survey on multi-objective hyperparameter optimization algorithms for machine learning","volume":"56","author":"A Morales-Hern\u00e1ndez","year":"2022","journal-title":"Artif Intell Rev"},{"key":"pone.0349595.ref025","doi-asserted-by":"crossref","first-page":"100294","DOI":"10.1016\/j.dajour.2023.100294","article-title":"A comparative analysis of global optimization algorithms for surface electromyographic signal onset detection","volume":"8","author":"S Alam","year":"2023","journal-title":"Decision Analytics Journal"},{"issue":"23","key":"pone.0349595.ref026","doi-asserted-by":"crossref","first-page":"3688","DOI":"10.3390\/math12233688","article-title":"Conceptual Framework for Adaptive Bacterial Memetic Algorithm Parameterization in Storage Location Assignment Problem","volume":"12","author":"K Udvardy","year":"2024","journal-title":"Mathematics"},{"issue":"3","key":"pone.0349595.ref027","doi-asserted-by":"crossref","first-page":"4989","DOI":"10.32604\/cmc.2022.023884","article-title":"Optimized Ensemble Algorithm for Predicting Metamaterial Antenna Parameters","volume":"71","author":"E-S M. El-kenawy","year":"2022","journal-title":"Computers, Materials & Continua"},{"key":"pone.0349595.ref028","doi-asserted-by":"crossref","first-page":"94094","DOI":"10.1109\/ACCESS.2023.3310429","article-title":"BAOA: Binary Arithmetic Optimization Algorithm With K-Nearest Neighbor Classifier for Feature Selection","volume":"11","author":"N Khodadadi","year":"2023","journal-title":"IEEE Access"},{"issue":"1","key":"pone.0349595.ref029","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1038\/s41598-023-45806-9","article-title":"Prediction model of spontaneous combustion risk of extraction borehole based on PSO-BPNN and its application","volume":"14","author":"W Wang","year":"2024","journal-title":"Sci Rep"},{"key":"pone.0349595.ref030","doi-asserted-by":"crossref","first-page":"106827","DOI":"10.1016\/j.cor.2024.106827","article-title":"Machine Learning based Algorithm Selection and Genetic Algorithms for serial-batch scheduling","volume":"173","author":"A Uzunoglu","year":"2025","journal-title":"Computers & Operations Research"},{"key":"pone.0349595.ref031","doi-asserted-by":"crossref","first-page":"603","DOI":"10.1016\/j.aej.2023.12.015","article-title":"Research on prediction model of iron ore powder sintering foundation characteristics based on FOA-Catboost algorithm","volume":"86","author":"Y Li","year":"2024","journal-title":"Alexandria Engineering Journal"},{"issue":"1","key":"pone.0349595.ref032","doi-asserted-by":"crossref","first-page":"13324","DOI":"10.1038\/s41598-025-97271-1","article-title":"A multi-objective optimization framework for EV-integrated distribution grids using the hiking optimization algorithm","volume":"15","author":"M Samiei Moghaddam","year":"2025","journal-title":"Sci Rep"},{"issue":"2","key":"pone.0349595.ref033","doi-asserted-by":"crossref","DOI":"10.1214\/aos\/1016218223","article-title":"Additive logistic regression: a statistical view of boosting (With discussion and a rejoinder by the authors)","volume":"28","author":"J Friedman","year":"2000","journal-title":"Ann Statist"},{"issue":"6","key":"pone.0349595.ref034","doi-asserted-by":"crossref","first-page":"2131","DOI":"10.1109\/TCBB.2019.2911071","article-title":"XGBoost Model for Chronic Kidney Disease Diagnosis","volume":"17","author":"A Ogunleye","year":"2020","journal-title":"IEEE\/ACM Trans Comput Biol Bioinform"},{"key":"pone.0349595.ref035","doi-asserted-by":"crossref","unstructured":"Chen T, Guestrin C. XGBoost a scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2016. 785\u201394. https:\/\/doi.org\/10.1145\/2939672.2939785","DOI":"10.1145\/2939672.2939785"},{"issue":"1","key":"pone.0349595.ref036","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random Forests","volume":"45","author":"L Breiman","year":"2001","journal-title":"Machine Learning"},{"issue":"11","key":"pone.0349595.ref037","doi-asserted-by":"crossref","first-page":"216","DOI":"10.1177\/03611981241240766","volume":"2678","author":"F Chung","year":"2024","journal-title":"Transportation Research Record: Journal of the Transportation Research Board"},{"issue":"10","key":"pone.0349595.ref038","doi-asserted-by":"crossref","first-page":"2677","DOI":"10.1080\/14680629.2025.2454376","article-title":"Machine learning for predicting pavement roughness and optimising maintenance","volume":"26","author":"M Ghodratabadi","year":"2025","journal-title":"Road Materials and Pavement Design"},{"issue":"5","key":"pone.0349595.ref039","doi-asserted-by":"crossref","first-page":"359","DOI":"10.1016\/0893-6080(89)90020-8","article-title":"Multilayer feedforward networks are universal approximators","volume":"2","author":"K Hornik","year":"1989","journal-title":"Neural Networks"},{"key":"pone.0349595.ref040","doi-asserted-by":"crossref","first-page":"69","DOI":"10.1016\/j.knosys.2011.07.001","article-title":"A new Fruit Fly Optimization Algorithm: Taking the financial distress model as an example","volume":"26","author":"W-T Pan","year":"2012","journal-title":"Knowledge-Based Systems"},{"issue":"2","key":"pone.0349595.ref041","first-page":"1439","article-title":"Thrust force requirement prediction using HOA\u2010XGBoost for TBM tunneling in squeezing ground","volume":"8","author":"R Chen","year":"2025","journal-title":"Civil Engineering and Practice"},{"key":"pone.0349595.ref042","doi-asserted-by":"crossref","unstructured":"Kennedy J, Eberhart R. Particle swarm optimization. In: Proceedings of ICNN\u201995 - International Conference on Neural Networks. 1942\u20138. https:\/\/doi.org\/10.1109\/icnn.1995.488968","DOI":"10.1109\/ICNN.1995.488968"},{"issue":"3","key":"pone.0349595.ref043","doi-asserted-by":"crossref","first-page":"321","DOI":"10.3390\/biomimetics8030321","article-title":"A Novel Bio-Inspired Optimization Algorithm Design for Wind Power Engineering Applications Time-Series Forecasting","volume":"8","author":"FK Karim","year":"2023","journal-title":"Biomimetics (Basel)"},{"key":"pone.0349595.ref044","doi-asserted-by":"crossref","first-page":"100516","DOI":"10.1016\/j.mlwa.2023.100516","article-title":"Machine learning for an explainable cost prediction of medical insurance","volume":"15","author":"U Orji","year":"2024","journal-title":"Machine Learning with Applications"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0349595","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T17:35:41Z","timestamp":1781631341000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0349595"}},"subtitle":[],"editor":[{"given":"Shaheer","family":"Ansari","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,6,16]]},"references-count":44,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2026,6,16]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0349595","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,16]]}}}