{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/97803"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/97803","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Prediction of arrival times of freight traffic on us railroads using support vector regression","abstract":"Variability of the travel times on the United States freight rail network is high due to large network demand relative to infrastructure capacity especially when traffic is heterogeneous. Variable runtimes pose significant operational challenges if the nature of runtime variability is not predictable. To address this issue, this article proposes a data-driven approach to predict estimated times of arrival (ETAs) of individual freight trains, based on the properties of the train, the properties of the network, and the properties of potentially conflicting traffic on the network. The ETA problem is posed as a machine learning regression problem and solved using a support vector regression machine trained and cross validated on over two years of historical data for a 140 mile stretch of track located primarily in Tennessee, USA. The article presents the data used in this problem and details on feature engineering and construction for predictions made across the full route. It also highlights findings on the dominant sources of runtime variability and the most predictive factors for ETA, identified by applying the data framework. ETA improvement results exceeded 20% over baseline methods for predictions made at some locations and averaged over 15% across the study area. Ideas for further ETA improvement using the prediction algorithms are also discussed.","abstract_html":"Variability of the travel times on the United States freight rail network is high due to large network demand relative to infrastructure capacity especially when traffic is heterogeneous. Variable runtimes pose significant operational challenges if the nature of runtime variability is not predictable. To address this issue, this article proposes a data-driven approach to predict estimated times of arrival (ETAs) of individual freight trains, based on the properties of the train, the properties of the network, and the properties of potentially conflicting traffic on the network. The ETA problem is posed as a machine learning regression problem and solved using a support vector regression machine trained and cross validated on over two years of historical data for a 140 mile stretch of track located primarily in Tennessee, USA. The article presents the data used in this problem and details on feature engineering and construction for predictions made across the full route. It also highlights findings on the dominant sources of runtime variability and the most predictive factors for ETA, identified by applying the data framework. ETA improvement results exceeded 20% over baseline methods for predictions made at some locations and averaged over 15% across the study area. Ideas for further ETA improvement using the prediction algorithms are also discussed.","abstract_has_math":false,"creators":["Barbour, William Walker"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Civil Engineering","degree_department":null,"school":null,"contributors":["Work, Daniel B."],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2017,"date_issued":"2017-08-10T20:33:32Z","date_published":"2017-08-10T20:33:32Z","updated_at":"2026-07-22T22:24:34Z","subjects":["Machine learning","Railroad","Prediction","Support vector machine","Arrival time","Data mining","Feature engineering"],"languages":["en"],"rights":["Copyright 2017 William W. Barbour"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/97803","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Work, Daniel B."]},{"key":"dc:creator","label":"Author","values":["Barbour, William Walker"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2017-08-10T20:33:32Z","2019-08-11T09:15:17Z","2017-04-28","2017-05"]},{"key":"dc:type","label":"Dc Type","values":["text"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Civil Engineering"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["M.S."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Illinois at Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Machine learning","Railroad","Prediction","Support vector machine","Arrival time","Data mining","Feature engineering"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2017 William W. Barbour"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/97803"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Variability of the travel times on the United States freight rail network is high due to large network demand relative to infrastructure capacity especially when traffic is heterogeneous. Variable runtimes pose significant operational challenges if the nature of runtime variability is not predictable. To address this issue, this article proposes a data-driven approach to predict estimated times of arrival (ETAs) of individual freight trains, based on the properties of the train, the properties of the network, and the properties of potentially conflicting traffic on the network. The ETA problem is posed as a machine learning regression problem and solved using a support vector regression machine trained and cross validated on over two years of historical data for a 140 mile stretch of track located primarily in Tennessee, USA. The article presents the data used in this problem and details on feature engineering and construction for predictions made across the full route. It also highlights findings on the dominant sources of runtime variability and the most predictive factors for ETA, identified by applying the data framework. ETA improvement results exceeded 20% over baseline methods for predictions made at some locations and averaged over 15% across the study area. Ideas for further ETA improvement using the prediction algorithms are also discussed.","Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2019-05-01","The student, William Barbour, accepted the attached license on 2017-04-28 at 09:36.","The student, William Barbour, submitted this Thesis for approval on 2017-04-28 at 09:44.","This Thesis was approved for publication on 2017-04-28 at 10:34.","DSpace SAF Submission Ingestion Package generated from Vireo submission #11130 on 2017-08-10 at 15:07:20","Made available in DSpace on 2017-08-10T20:33:32Z (GMT). No. of bitstreams: 2 BARBOUR-THESIS-2017.pdf: 1267536 bytes, checksum: 4b9f21fce228b6102308d9a5b2b1a2bf (MD5) LICENSE.txt: 4212 bytes, checksum: e1f4d4730001ca14bd32518931df7851 (MD5) Previous issue date: 2017-04-28","Embargo set by: Colleen Fallaw for item 102856 Lift date: 2019-08-10T21:27:21Z Reason: Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD system","U of I Only Restriction Lifted for Item 102856 on 2019-08-11T09:15:17Z."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Prediction of arrival times of freight traffic on us railroads using support vector regression"]}]}],"canonical_facts":{"dc:contributor":["Work, Daniel B."],"dc:creator":["Barbour, William Walker"],"dc:date":["2017-08-10T20:33:32Z","2019-08-11T09:15:17Z","2017-04-28","2017-05"],"dc:description":["Variability of the travel times on the United States freight rail network is high due to large network demand relative to infrastructure capacity especially when traffic is heterogeneous. Variable runtimes pose significant operational challenges if the nature of runtime variability is not predictable. To address this issue, this article proposes a data-driven approach to predict estimated times of arrival (ETAs) of individual freight trains, based on the properties of the train, the properties of the network, and the properties of potentially conflicting traffic on the network. The ETA problem is posed as a machine learning regression problem and solved using a support vector regression machine trained and cross validated on over two years of historical data for a 140 mile stretch of track located primarily in Tennessee, USA. The article presents the data used in this problem and details on feature engineering and construction for predictions made across the full route. It also highlights findings on the dominant sources of runtime variability and the most predictive factors for ETA, identified by applying the data framework. ETA improvement results exceeded 20% over baseline methods for predictions made at some locations and averaged over 15% across the study area. Ideas for further ETA improvement using the prediction algorithms are also discussed.","Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2019-05-01","The student, William Barbour, accepted the attached license on 2017-04-28 at 09:36.","The student, William Barbour, submitted this Thesis for approval on 2017-04-28 at 09:44.","This Thesis was approved for publication on 2017-04-28 at 10:34.","DSpace SAF Submission Ingestion Package generated from Vireo submission #11130 on 2017-08-10 at 15:07:20","Made available in DSpace on 2017-08-10T20:33:32Z (GMT). No. of bitstreams: 2 BARBOUR-THESIS-2017.pdf: 1267536 bytes, checksum: 4b9f21fce228b6102308d9a5b2b1a2bf (MD5) LICENSE.txt: 4212 bytes, checksum: e1f4d4730001ca14bd32518931df7851 (MD5) Previous issue date: 2017-04-28","Embargo set by: Colleen Fallaw for item 102856 Lift date: 2019-08-10T21:27:21Z Reason: Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD system","U of I Only Restriction Lifted for Item 102856 on 2019-08-11T09:15:17Z."],"dc:format":["application/pdf"],"dc:identifier":["http://hdl.handle.net/2142/97803"],"dc:language":["en"],"dc:rights":["Copyright 2017 William W. Barbour"],"dc:subject":["Machine learning","Railroad","Prediction","Support vector machine","Arrival time","Data mining","Feature engineering"],"dc:title":["Prediction of arrival times of freight traffic on us railroads using support vector regression"],"dc:type":["text"],"thesis:degree_discipline":["Civil Engineering"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["M.S."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:24:34Z"}