{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T14:22:47Z","timestamp":1753885367132,"version":"3.41.2"},"reference-count":43,"publisher":"World Scientific Pub Co Pte Ltd","issue":"03n04","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Adv. Data Sci. Adapt. Data Anal."],"published-print":{"date-parts":[[2022,7]]},"abstract":"<jats:p> This study proposes a data fusion and deep learning (DL) framework that learns high-level traffic features from network-level images to predict large-scale, multi-route, speed and volume of connected vehicles (CVs). We present a scalable and parallel method of processing statewide CVs\u2019 trajectory data that leads to real-time insights on the micro-scale in time and space (two-dimensional (2D) arrays) on graphics processing unit (GPUs) using the Nvidia rapids framework and dask parallel cluster, which provided a 50\u00d7 speed-up in the data extraction, transform and load (ETL). A UNet model is then applied to perform feature extraction and multi-route speed and volume channels over a multi-step prediction horizon. The accuracy and robustness of the proposed model are evaluated by taking different road types, times of day and image snippets and comparing the model to benchmarks: Convolutional Long\u2013Short-Term Memory (ConvLSTM) and a historical average (HA). The results show that the proposed model outperforms benchmarks with an average improvement of 15% over ConvLSTM and 65% over the HA. Comparing the image snippets from each prediction model to the actual image shows that image textures were highly similar in UNet to the benchmark models used. UNet\u2019s dominance in performing image predictions was also evident in multi-step forecasting, where the increase in errors was relatively minimal over longer prediction horizons. <\/jats:p>","DOI":"10.1142\/s2424922x22500103","type":"journal-article","created":{"date-parts":[[2022,7,16]],"date-time":"2022-07-16T03:56:46Z","timestamp":1657943806000},"source":"Crossref","is-referenced-by-count":5,"title":["Multi-Purpose, Multi-Step Deep Learning Framework for Network-Level Traffic Flow Prediction"],"prefix":"10.1142","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4265-071X","authenticated-orcid":false,"given":"Maged","family":"Shoman","sequence":"first","affiliation":[{"name":"Department of Civil and Environmental Engineering, University of Missouri, W1024 Lafferre Hall, Columbia MO 65211, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mark","family":"Amo-Boateng","sequence":"additional","affiliation":[{"name":"Department of Civil and Environmental Engineering, University of Missouri, W1024 Lafferre Hall, Columbia MO 65211, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yaw","family":"Adu-Gyamfi","sequence":"additional","affiliation":[{"name":"Department of Civil and Environmental Engineering, University of Missouri, W1024 Lafferre Hall, Columbia MO 65211, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"219","published-online":{"date-parts":[[2022,9,23]]},"reference":[{"key":"S2424922X22500103BIB001","doi-asserted-by":"publisher","DOI":"10.1155\/2015\/432389"},{"key":"S2424922X22500103BIB002","doi-asserted-by":"publisher","DOI":"10.1016\/j.physa.2020.125574"},{"key":"S2424922X22500103BIB005","first-page":"890","volume-title":"2018 Proceedings of the AAAI Conference on Artificial Intelligence","author":"Diao Z.","year":"2019"},{"key":"S2424922X22500103BIB006","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2010.06.001"},{"key":"S2424922X22500103BIB007","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2014.02.016"},{"key":"S2424922X22500103BIB008","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/317"},{"key":"S2424922X22500103BIB009","doi-asserted-by":"publisher","DOI":"10.1109\/MDM.2019.00-52"},{"key":"S2424922X22500103BIB010","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013656"},{"key":"S2424922X22500103BIB011","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301922"},{"key":"S2424922X22500103BIB012","first-page":"1","volume":"22","author":"Guo K.","year":"2020","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"S2424922X22500103BIB013","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2019.00116"},{"key":"S2424922X22500103BIB014","first-page":"233","volume-title":"Proceedings of the Twenty-First ACM SIGMOD-SIGACT-SIGART Symposium on Principles of Database Systems","author":"Lenzerini M.","year":"2015"},{"volume-title":"2018 International Conference on Learning Representations","year":"2018","author":"Li Y.","key":"S2424922X22500103BIB015"},{"key":"S2424922X22500103BIB016","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330847"},{"key":"S2424922X22500103BIB017","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.11.032"},{"key":"S2424922X22500103BIB018","first-page":"865","volume":"16","author":"Lv Y.","year":"2015","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"S2424922X22500103BIB019","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2015.03.014"},{"key":"S2424922X22500103BIB020","doi-asserted-by":"publisher","DOI":"10.1145\/2346496.2346502"},{"key":"S2424922X22500103BIB021","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2012.52"},{"key":"S2424922X22500103BIB022","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2013.44"},{"key":"S2424922X22500103BIB023","doi-asserted-by":"publisher","DOI":"10.5038\/2375-0901.7.1.1"},{"issue":"6","key":"S2424922X22500103BIB024","first-page":"433","volume":"13","author":"Phusittrakool A.","year":"2015","journal-title":"Walailak J. Sci. Technol. (WJST)"},{"key":"S2424922X22500103BIB027","first-page":"64","volume-title":"Proceedings of the 2015 IEEE 22nd International Conference on High Performance Computing Workshops (HiPCW)","author":"Shekhar S.","year":"2015"},{"key":"S2424922X22500103BIB028","doi-asserted-by":"publisher","DOI":"10.1109\/SMARTCOMP.2016.7501714"},{"issue":"5","key":"S2424922X22500103BIB029","first-page":"2348","volume-title":"IEEE Transactions on Knowledge and Data Engineering","volume":"34","author":"Sun J.","year":"2020"},{"key":"S2424922X22500103BIB030","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11877"},{"key":"S2424922X22500103BIB031","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2018.03.001"},{"key":"S2424922X22500103BIB032","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/264"},{"key":"S2424922X22500103BIB033","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2020.01.002"},{"key":"S2424922X22500103BIB034","first-page":"5668","volume-title":"The Thirty-Third AAAI Conference on Artificial Intelligence (AAAI-19)","author":"Yao H.","year":"2019"},{"key":"S2424922X22500103BIB035","first-page":"1","volume-title":"2020 International Joint Conference on Neural Networks (IJCNN)","author":"Ye J.","year":"2018"},{"key":"S2424922X22500103BIB036","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.11.038"},{"key":"S2424922X22500103BIB037","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2011.01.003"},{"key":"S2424922X22500103BIB038","doi-asserted-by":"publisher","DOI":"10.3390\/s17071501"},{"key":"S2424922X22500103BIB039","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/505"},{"key":"S2424922X22500103BIB040","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2910560"},{"key":"S2424922X22500103BIB041","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.106592"},{"key":"S2424922X22500103BIB042","first-page":"339","author":"Zhang J.","year":"2018","journal-title":"UAI"},{"key":"S2424922X22500103BIB043","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2953888"},{"key":"S2424922X22500103BIB044","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2019.8852211"},{"key":"S2424922X22500103BIB045","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2019.05.039"},{"key":"S2424922X22500103BIB046","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2935152"},{"key":"S2424922X22500103BIB047","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5477"}],"container-title":["Advances in Data Science and Adaptive Analysis"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.worldscientific.com\/doi\/pdf\/10.1142\/S2424922X22500103","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,15]],"date-time":"2022-11-15T10:14:32Z","timestamp":1668507272000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.worldscientific.com\/doi\/10.1142\/S2424922X22500103"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7]]},"references-count":43,"journal-issue":{"issue":"03n04","published-print":{"date-parts":[[2022,7]]}},"alternative-id":["10.1142\/S2424922X22500103"],"URL":"https:\/\/doi.org\/10.1142\/s2424922x22500103","relation":{},"ISSN":["2424-922X","2424-9238"],"issn-type":[{"type":"print","value":"2424-922X"},{"type":"electronic","value":"2424-9238"}],"subject":[],"published":{"date-parts":[[2022,7]]},"article-number":"2250010"}}