{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T18:13:47Z","timestamp":1778177627504,"version":"3.51.4"},"reference-count":43,"publisher":"Public Library of Science (PLoS)","issue":"5","license":[{"start":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T00:00:00Z","timestamp":1778112000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"University in Jiangsu Natural Science General Projects of China","award":["22KJB220007"],"award-info":[{"award-number":["22KJB220007"]}]},{"name":"Doctoral Projects of Entrepreneurship and Innovation in Jiangsu Province of China","award":["JSSCBS20210868"],"award-info":[{"award-number":["JSSCBS20210868"]}]},{"name":"Doctoral Projects of Entrepreneurship and Innovation in Jiangsu Province of China","award":["JSSCBS20210864"],"award-info":[{"award-number":["JSSCBS20210864"]}]},{"name":"Wuxi Innovation and Entrepreneurship Fund \u201cTaihu Light\u201d Science and Technology (Fundamental Research) Project","award":["K20231002"],"award-info":[{"award-number":["K20231002"]}]},{"name":"Scientific Research Foundation of Wuxi University Research Start-up Fund for Introduced Talents","award":["2022r030"],"award-info":[{"award-number":["2022r030"]}]},{"name":"Scientific Research Foundation of Wuxi University Research Start-up Fund for Introduced Talents","award":["2023r030"],"award-info":[{"award-number":["2023r030"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"\n Rail freight volume trend prediction faces challenges due to data fuzziness, complexity and nonlinearity, and traditional deterministic prediction methods frequently fall short of practical application needs, particularly in addressing uncertainty. To overcome these limitations, we proposed a freight volume trend prediction model that integrated Fuzzy Information Granulation (FIG) with evolutionary optimization. The three-phase methodology establishes: (1)A FIG method was utilized to transform raw time-series into tri-granular representations (Low, R, Up) through fuzzy c-means clustering with temporal constraints, extracting feature information from the raw time-series data and encapsulating it into information granules (2) For complex predictions with small samples, we applied a Support Vector Machine (SVM) for granular modeling, combined with an Improved Particle Swarm Optimization (IPSO) algorithm featuring dynamic inertia weights and mutation operators to prevent premature convergence during training. (3) A hybrid FIG-IPSO-SVM architecture implementing granular-level regression with uncertainty quantification. Validation using 9-year operational records (2013\u20132022) from the Lanzhou Freight Center (n\u2009=\u2009114 monthly observations) in China reveals statistically significant enhancements: compared to the FIG-GS (grid search)-SVM and FIG-PSO (Particle Swarm Optimization)-SVM algorithms, the proposed IPSO-SVM algorithm achieved the smallest prediction error for each granulated set (Low, R, Up) and the smallest mean maxima of absolute percentage error (\n \n \n \n \n \n \n \n A<\/mml:mi>\n P<\/mml:mi>\n E<\/mml:mi>\n <\/mml:mrow>\n \n M<\/mml:mtext>\n <\/mml:mrow>\n <\/mml:msub>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:alternatives>\n <\/jats:inline-formula>\n ) for the prediction interval of freight volume, at 5.03%. Moreover,it yielded the tightest prediction interval, characterized by a relative width (\n R<\/jats:italic>\n \n w<\/jats:italic>\n <\/jats:sub>\n ) of just 8.53% and a corresponding interval width (\n W<\/jats:italic>\n ) of only 516,209 tons, surpassing all benchmark models.These findings validate that the FIG-IPSO-SVM framework substantially improves interval prediction precision and trend detection reliability, providing actionable intelligence for railway infrastructure planning and operational optimization.\n <\/jats:p>","DOI":"10.1371\/journal.pone.0348239","type":"journal-article","created":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T17:39:33Z","timestamp":1778175573000},"page":"e0348239","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Data-driven fuzzy information granulation for predicting freight volume trends"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-2863-5255","authenticated-orcid":true,"given":"Yunbo","family":"Gao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinyu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2920-3787","authenticated-orcid":true,"given":"Ming","family":"Niu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianguo","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liping","family":"Cai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"340","published-online":{"date-parts":[[2026,5,7]]},"reference":[{"issue":"3","key":"pone.0348239.ref001","doi-asserted-by":"crossref","first-page":"284","DOI":"10.1016\/j.icte.2022.02.001","article-title":"Utilizing machine learning on freight transportation and logistics applications: A review","volume":"9","author":"K Tsolaki","year":"2023","journal-title":"ICT Express"},{"issue":"2","key":"pone.0348239.ref002","first-page":"91","article-title":"China\u2019s Belt and Road rail freight transport corridors\u2013the economic geography of underdevelopment","volume":"152","author":"T Kenderdine","year":"2021","journal-title":"DIE ERDE\u2013Journal of the Geographical Society of Berlin"},{"issue":"1","key":"pone.0348239.ref003","doi-asserted-by":"crossref","DOI":"10.1080\/23311975.2021.1932066","article-title":"Analyzing the Railway Network of the Belt and Road Initiative","volume":"8","author":"Y Uygun","year":"2021","journal-title":"Cogent Business & Management"},{"key":"pone.0348239.ref004","doi-asserted-by":"crossref","first-page":"103111","DOI":"10.1016\/j.trc.2021.103111","article-title":"Short-term prediction of outbound truck traffic from the exchange of information in logistics hubs: A case study for the port of Rotterdam","volume":"127","author":"A Nadi","year":"2021","journal-title":"Transportation Research Part C: Emerging Technologies"},{"key":"pone.0348239.ref005","doi-asserted-by":"crossref","first-page":"121900","DOI":"10.1016\/j.ins.2025.121900","article-title":"Enhanced decision-making for urban climate change transportation policies using q-rung orthopair fuzzy rough fairly information aggregation","volume":"702","author":"HMA Farid","year":"2025","journal-title":"Information Sciences"},{"key":"pone.0348239.ref006","doi-asserted-by":"crossref","first-page":"499","DOI":"10.1016\/j.amc.2019.05.043","article-title":"A novel hybrid approach to Baltic Dry Index forecasting based on a combined dynamic fluctuation network and artificial intelligence method","volume":"361","author":"X Zhang","year":"2019","journal-title":"Applied Mathematics and Computation"},{"key":"pone.0348239.ref007","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1155\/2022\/1568449","article-title":"Factors Affecting Evaluation of Railway Bulk Freight Rate: A Novel Cloud Theory-Based Approach","volume":"2022","author":"J Guo","year":"2022","journal-title":"Journal of Advanced Transportation"},{"key":"pone.0348239.ref008","doi-asserted-by":"crossref","first-page":"106687","DOI":"10.1016\/j.nedt.2025.106687","article-title":"Constructing educational content for neonatal palliative care: A Delphi method and needs analysis","volume":"150","author":"E Lee","year":"2025","journal-title":"Nurse Educ Today"},{"issue":"1","key":"pone.0348239.ref009","doi-asserted-by":"crossref","first-page":"695087","DOI":"10.1155\/2011\/695087","article-title":"A novel ranking method based on subjective probability theory for evolutionary multiobjective optimization","volume":"2011","author":"S Wei","year":"2011","journal-title":"Mathematical Problems in Engineering"},{"key":"pone.0348239.ref010","doi-asserted-by":"crossref","first-page":"101561","DOI":"10.1016\/j.cogpsych.2023.101561","article-title":"Analogical inferences mediated by relational categories","volume":"142","author":"RA Minervino","year":"2023","journal-title":"Cogn Psychol"},{"key":"pone.0348239.ref011","doi-asserted-by":"crossref","first-page":"210","DOI":"10.1016\/j.neucom.2015.01.046","article-title":"Prediction models based on multivariate statistical methods and their applications for predicting railway freight volume","volume":"158","author":"Y Yang","year":"2015","journal-title":"Neurocomputing"},{"issue":"3","key":"pone.0348239.ref012","doi-asserted-by":"crossref","first-page":"220","DOI":"10.1177\/1471082X19881840","article-title":"A mixture of linear-linear regression models for a linear-circular regression","volume":"21","author":"AE Sikaroudi","year":"2019","journal-title":"Statistical Modelling"},{"issue":"11","key":"pone.0348239.ref013","doi-asserted-by":"crossref","DOI":"10.3390\/agriculture14111980","article-title":"Road Freight Demand Forecasting Using National Accounts\u2019 Data\u2014The Case of Cereals","volume":"14","author":"T Karasu","year":"1980","journal-title":"Agriculture"},{"key":"pone.0348239.ref014","doi-asserted-by":"crossref","first-page":"032071","DOI":"10.1088\/1755-1315\/108\/3\/032071","article-title":"Fuzzy Regression Prediction and Application Based on Multi-Dimensional Factors of Freight Volume","volume":"108","author":"M Xiao","year":"2018","journal-title":"IOP Conf Ser: Earth Environ Sci"},{"issue":"5","key":"pone.0348239.ref015","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"},{"issue":"13","key":"pone.0348239.ref016","doi-asserted-by":"crossref","first-page":"5948","DOI":"10.3390\/app14135948","article-title":"Multi-Factor Highway Freight Volume Prediction Based on Backpropagation Neural Network","volume":"14","author":"Y Zhang","year":"2024","journal-title":"Applied Sciences"},{"issue":"8","key":"pone.0348239.ref017","doi-asserted-by":"crossref","first-page":"851","DOI":"10.1049\/iet-its.2017.0369","article-title":"Railway freight volume forecast using an ensemble model with optimised deep belief network","volume":"12","author":"F Feng","year":"2018","journal-title":"IET Intelligent Trans Sys"},{"issue":"15","key":"pone.0348239.ref018","doi-asserted-by":"crossref","first-page":"17475","DOI":"10.1007\/s11227-023-05333-w","article-title":"The short-term prediction of daily traffic volume for rural roads using shallow and deep learning networks: ANN and LSTM","volume":"79","author":"M Mohammadzadeh","year":"2023","journal-title":"J Supercomput"},{"issue":"7","key":"pone.0348239.ref019","doi-asserted-by":"crossref","first-page":"3337","DOI":"10.3390\/app12073337","article-title":"Image Classification of Parcel Boxes under the Underground Logistics System Using CNN MobileNet","volume":"12","author":"M Kim","year":"2022","journal-title":"Applied Sciences"},{"issue":"1","key":"pone.0348239.ref020","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3532611","article-title":"Dynamic Graph Convolutional Recurrent Network for Traffic Prediction: Benchmark and Solution","volume":"17","author":"F Li","year":"2023","journal-title":"ACM Trans Knowl Discov Data"},{"issue":"9","key":"pone.0348239.ref021","doi-asserted-by":"crossref","first-page":"11873","DOI":"10.1007\/s11227-022-04343-4","article-title":"A new form of deep learning in smart logistics with IoT environment","volume":"78","author":"F Jiang","year":"2022","journal-title":"J Supercomput"},{"issue":"10","key":"pone.0348239.ref022","doi-asserted-by":"crossref","first-page":"2049","DOI":"10.1016\/j.ins.2007.01.009","article-title":"Hybridizing mixtures of experts with support vector machines: Investigation into nonlinear dynamic systems identification","volume":"177","author":"CA Lima","year":"2007","journal-title":"Information Sciences"},{"issue":"000","key":"pone.0348239.ref023","first-page":"6","article-title":"Forecast of Freight Volume in Xi\u2019an Based on Gray GM (1, 1) Model and Markov Forecasting Model","volume":"2021","author":"F Yang","year":"2021","journal-title":"JOURNAL OF MECHANICS"},{"issue":"12","key":"pone.0348239.ref024","doi-asserted-by":"crossref","first-page":"9652","DOI":"10.3390\/su15129652","article-title":"Railway Freight Demand Forecasting Based on Multiple Factors: Grey Relational Analysis and Deep Autoencoder Neural Networks","volume":"15","author":"C Liu","year":"2023","journal-title":"Sustainability"},{"key":"pone.0348239.ref025","doi-asserted-by":"crossref","first-page":"104870","DOI":"10.1016\/j.trc.2024.104870","article-title":"Bi-objective robust nonlinear decision approach for en-route bus speed control considering implementation errors and traffic uncertainties","volume":"169","author":"P Liu","year":"2024","journal-title":"Transportation Research Part C: Emerging Technologies"},{"issue":"3","key":"pone.0348239.ref026","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1023\/A:1022627411411","article-title":"Support-vector networks","volume":"20","author":"C Cortes","year":"1995","journal-title":"Mach Learn"},{"key":"pone.0348239.ref027","doi-asserted-by":"crossref","first-page":"352","DOI":"10.1016\/j.trc.2019.12.022","article-title":"Hybrid machine learning algorithm and statistical time series model for network-wide traffic forecast","volume":"111","author":"T Ma","year":"2020","journal-title":"Transportation Research Part C: Emerging Technologies"},{"key":"pone.0348239.ref028","doi-asserted-by":"crossref","first-page":"9551","DOI":"10.1109\/ACCESS.2019.2963540","article-title":"Research on Regional Logistics Demand Forecast Based on Improved Support Vector Machine: A Case Study of Qingdao City under the New Free Trade Zone Strategy","volume":"8","author":"N Yu","year":"2020","journal-title":"IEEE Access"},{"issue":"4","key":"pone.0348239.ref029","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0285131","article-title":"Global-local least-squares support vector machine (GLocal-LS-SVM)","volume":"18","author":"A Youssef Ali Amer","year":"2023","journal-title":"PLoS One"},{"issue":"4","key":"pone.0348239.ref030","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1080\/19427867.2020.1728037","article-title":"Calibrating microscopic traffic simulators using machine learning and particle swarm optimization","volume":"13","author":"Y Liu","year":"2020","journal-title":"Transportation Letters"},{"key":"pone.0348239.ref031","doi-asserted-by":"crossref","first-page":"103488","DOI":"10.1016\/j.trc.2021.103488","article-title":"Robust optimal control of connected and automated vehicle platoons through improved particle swarm optimization","volume":"135","author":"G Ma","year":"2022","journal-title":"Transportation Research Part C: Emerging Technologies"},{"issue":"1","key":"pone.0348239.ref032","article-title":"A novel hybrid PSO based on levy flight and wavelet mutation for global optimization","volume":"18","author":"Y Gao","year":"2023","journal-title":"PLoS One"},{"issue":"2","key":"pone.0348239.ref033","article-title":"Interval price prediction of livestock product based on fuzzy mathematics and improved LSTM","volume":"20","author":"W Ma","year":"2025","journal-title":"PLoS One"},{"key":"pone.0348239.ref034","doi-asserted-by":"crossref","unstructured":"Kiersztyn A, Karczmarek P, Kiersztyn K, Pedrycz W. The Concept of Detecting and Classifying Anomalies in Large Data Sets on a Basis of Information Granules. In: 2020 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), 2020. 1\u20137. https:\/\/doi.org\/10.1109\/fuzz48607.2020.9177668","DOI":"10.1109\/FUZZ48607.2020.9177668"},{"key":"pone.0348239.ref035","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":"1","key":"pone.0348239.ref036","doi-asserted-by":"crossref","first-page":"1","DOI":"10.3390\/logistics4010001","article-title":"Travel Time Prediction in a Multimodal Freight Transport Relation Using Machine Learning Algorithms","volume":"4","author":"N Servos","year":"2019","journal-title":"Logistics"},{"key":"pone.0348239.ref037","volume-title":"Advances in kernel methods: support vector learning","author":"B Sch\u00f6lkopf","year":"1999"},{"key":"pone.0348239.ref038","doi-asserted-by":"crossref","first-page":"103875","DOI":"10.1016\/j.trc.2022.103875","article-title":"Predicting public transit arrival: A nonlinear approach","volume":"144","author":"A Achar","year":"2022","journal-title":"Transportation Research Part C: Emerging Technologies"},{"issue":"3","key":"pone.0348239.ref039","doi-asserted-by":"crossref","first-page":"7229","DOI":"10.15376\/biores.14.3.7229-7246","article-title":"Bi-directional prediction of wood fiber production using the combination of improved particle swarm optimization and support vector machine","volume":"14","author":"Y Gao","year":"2019","journal-title":"BioRes"},{"issue":"2","key":"pone.0348239.ref040","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0274054","article-title":"A color image contrast enhancement method based on improved PSO","volume":"18","author":"X Zhang","year":"2023","journal-title":"PLoS One"},{"issue":"8","key":"pone.0348239.ref041","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0271924","article-title":"Path planning for autonomous mobile robots using multi-objective evolutionary particle swarm optimization","volume":"17","author":"I Thammachantuek","year":"2022","journal-title":"PLoS One"},{"issue":"3","key":"pone.0348239.ref042","doi-asserted-by":"crossref","DOI":"10.1145\/1961189.1961199","article-title":"LIBSVM: A Library for Support Vector Machines","volume":"2","author":"CC Chang","year":"2011","journal-title":"ACM Transactions on Intelligent Systems and Technology"},{"key":"pone.0348239.ref043","volume-title":"MATLAB Neural Network 43 Case Studies","author":"XC Wang","year":"2013"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0348239","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T17:39:42Z","timestamp":1778175582000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0348239"}},"subtitle":[],"editor":[{"given":"Antonio Javier","family":"Nakhal Akel","sequence":"first","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2026,5,7]]},"references-count":43,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2026,5,7]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0348239","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,7]]}}}