{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T20:14:50Z","timestamp":1773951290284,"version":"3.50.1"},"reference-count":70,"publisher":"Association for Computing Machinery (ACM)","issue":"2","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Intell. Syst. Technol."],"published-print":{"date-parts":[[2026,4,30]]},"abstract":"<jats:p>\n                    Predicting vehicle traffic optimizes transportation management and urban planning. In this article, we combine real-time data from vehicle-detection Internet of Things (IoT) devices with external variables from Google Trends. Integrating such heterogeneous, complex data streams is challenging for traditional machine learning models that struggle to capture the dynamics of traffic patterns, which are influenced by multiple interdependent factors. To effectively model these complex, interdependent factors, we introduce the Granger-Causal Transformer (GCT), a transformer-based architecture for traffic prediction that integrates an LSTM network with a modified multi-head attention mechanism. This mechanism extends Granger causality to the spatio-temporal domain to analyze all causality relations between features consistently, while capturing long-range dependencies and temporal patterns. Before applying GCT, we generate lagged versions of the Google Trends time series to capture lead and lag effects. Tourists usually make searches about their destination weeks before traveling, so peaks in search interest occur earlier than peaks in weekly traffic volume. Using lags aligns the predictors with weekly traffic volume and allows the model to use past searches to predict future traffic. We semantically validate the Google Trends terms by comparing each term with a reference string describing the study area, using a language model aligned with the data\u2019s linguistic context. We then apply a dual filtering process comprising Granger noncausality and correlation tests to minimize noise and redundancy. We evaluate our proposed methodology against classical statistical models, deep learning models, large foundation models, and transformers across two case studies. The results demonstrate consistently superior performance and generalizability, with GCT achieving\n                    <jats:inline-formula content-type=\"math\/tex\">\n                      <jats:tex-math notation=\"LaTeX\" version=\"MathJax\">\\(R^{2}\\)<\/jats:tex-math>\n                    <\/jats:inline-formula>\n                    improvements between 47% and 68% compared to the best-performing baselines across both settings, alongside substantial reductions in MAE and MSE.\n                  <\/jats:p>","DOI":"10.1145\/3787462","type":"journal-article","created":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T14:06:46Z","timestamp":1771855606000},"page":"1-25","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["GCT: A Granger-Causal Transformer for Multivariate Traffic Analysis in Smart Villages"],"prefix":"10.1145","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-8995-869X","authenticated-orcid":false,"given":"Alberto","family":"Dur\u00e1n-L\u00f3pez","sequence":"first","affiliation":[{"name":"Research Centre for Information and Communication Technologies (CITIC-UGR), University of Granada, Granada, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0207-2908","authenticated-orcid":false,"given":"Daniel","family":"Bola\u00f1os-Martinez","sequence":"additional","affiliation":[{"name":"Research Centre for Information and Communication Technologies (CITIC-UGR), University of Granada, Granada, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7439-6077","authenticated-orcid":false,"given":"Suparna","family":"De","sequence":"additional","affiliation":[{"name":"School of Computer Science and Electronic Engineering, University of Surrey, Guildford, United Kingdom of Great Britain and Northern Ireland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2028-4755","authenticated-orcid":false,"given":"Maria","family":"Bermudez-Edo","sequence":"additional","affiliation":[{"name":"Research Centre for Information and Communication Technologies (CITIC-UGR), University of Granada, Granada, Spain and IATUR, Granada, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,3,19]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1002\/cyto.a.20896"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.suscom.2023.100868"},{"key":"e_1_3_2_4_2","unstructured":"Abdul Fatir Ansari Lorenzo Stella Caner Turkmen Xiyuan Zhang Pedro Mercado Huibin Shen Oleksandr Shchur Syama Sundar Rangapuram Sebastian Pineda Arango Shubham Kapoor et al. 2024. Chronos: Learning the language of time series. arXiv:2403.07815. Retrieved from https:\/\/arxiv.org\/abs\/2403.07815"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jocs.2023.101984"},{"key":"e_1_3_2_6_2","unstructured":"Jimmy Lei Ba Jamie Ryan Kiros and Geoffrey E. Hinton. 2016. Layer normalization. arXiv:1607.06450. Retrieved from https:\/\/arxiv.org\/abs\/1607.06450"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.tourman.2014.07.014"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","unstructured":"Daniel Berrar. 2019. Cross-validation. Encyclopedia of Bioinformatics and Computational Biology 1 (2019) 542\u2013545. DOI: 10.1016\/B978-0-12-809633-8.20349-X","DOI":"10.1016\/B978-0-12-809633-8.20349-X"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.dib.2024.110084"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.126245"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00181-018-1446-3"},{"key":"e_1_3_2_12_2","unstructured":"Jos\u00e9 Ca\u00f1ete Gabriel Chaperon Rodrigo Fuentes Jou-Hui Ho Hojin Kang and Jorge P\u00e9rez. 2023. Spanish pre-trained BERT model and evaluation data. arXiv:2308.02976. Retrieved from https:\/\/arxiv.org\/abs\/2308.02976"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2024.108791"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.7717\/peerj-cs.623"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1111\/j.1475-4932.2012.00809.x"},{"issue":"1","key":"e_1_3_2_16_2","first-page":"106","article-title":"Predicting tourism demands by google trends: A hidden Markov models based study","volume":"10","author":"Claude Uwimana","year":"2020","unstructured":"Uwimana Claude. 2020. Predicting tourism demands by google trends: A hidden Markov models based study. Journal of System and Management Sciences 10, 1 (2020), 106\u2013120.","journal-title":"Journal of System and Management Sciences"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2020.102674"},{"key":"e_1_3_2_18_2","first-page":"10148","volume-title":"Proceedings of the 41st International Conference on Machine Learning","volume":"235","author":"Das Abhimanyu","year":"2024","unstructured":"Abhimanyu Das, Weihao Kong, Rajat Sen, and Yichen Zhou. 2024. A decoder-only foundation model for time-series forecasting. In Proceedings of the 41st International Conference on Machine Learning, Vol. 235, PMLR, 10148\u201310167."},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2022.3155656"},{"key":"e_1_3_2_20_2","unstructured":"Jacob Devlin. 2018. BERT: Pre-training of deep bidirectional transformers for language understanding. arXiv:1810.04805. Retrieved from https:\/\/arxiv.org\/abs\/1810.04805"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/jiot.2025.3599235"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.simpa.2024.100636"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2024.104945"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2024.109463"},{"key":"e_1_3_2_25_2","unstructured":"Azul Garza Cristian Challu and Max Mergenthaler-Canseco. 2023. TimeGPT-1. arXiv:2310.03589. Retrieved from https:\/\/arxiv.org\/abs\/2310.03589"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.2307\/1912791"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.3389\/fnetp.2022.893743"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.tre.2025.104426"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3097141"},{"key":"e_1_3_2_30_2","volume-title":"Forecasting: Principles and Practice","author":"Hyndman R. J.","year":"2018","unstructured":"R. J. Hyndman. 2018. Forecasting: Principles and Practice (2nd ed.). OTexts.","edition":"2"},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.aap.2017.12.016"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.3390\/su151914522"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3484461"},{"key":"e_1_3_2_34_2","doi-asserted-by":"crossref","unstructured":"T. Kudo. 2018. SentencePiece: A simple and language independent subword tokenizer and detokenizer for neural text processing. arXiv:1808.06226. Retrieved from https:\/\/arxiv.org\/abs1808.06226","DOI":"10.18653\/v1\/D18-2012"},{"issue":"4","key":"e_1_3_2_35_2","first-page":"408","article-title":"Time series traffic flow prediction with hyper-parameter optimized ARIMA models for intelligent transportation system","volume":"81","author":"Kumar Praveen B.","year":"2022","unstructured":"Praveen B. Kumar and K. Hariharan. 2022. Time series traffic flow prediction with hyper-parameter optimized ARIMA models for intelligent transportation system. Journal of Scientific & Industrial Research 81, 4 (2022), 408\u2013415.","journal-title":"Journal of Scientific & Industrial Research"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2020.03.240"},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.gem-1.8"},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/tcsii.2022.3160266"},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.54254\/2755-2721\/75\/20240544"},{"key":"e_1_3_2_40_2","unstructured":"Zhouhan Lin Minwei Feng Cicero Nogueira dos Santos Mo Yu Bing Xiang Bowen Zhou and Yoshua Bengio. 2017. A structured self-attentive sentence embedding. arXiv:1703.03130. Retrieved from https:\/\/arxiv.org\/abs\/1703.03130"},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1145\/3643890"},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1504\/IJES.2020.105287"},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jairtraman.2021.102083"},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.matpr.2021.04.249"},{"key":"e_1_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3287980"},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1002\/jtr.2137"},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.3390\/econometrics12020013"},{"key":"e_1_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1155\/2020\/5960171"},{"key":"e_1_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3233801"},{"key":"e_1_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.52783\/dxjb.v35.113"},{"key":"e_1_3_2_51_2","unstructured":"Kashif Rasul Arjun Ashok Andrew Robert Williams Arian Khorasani George Adamopoulos Rishika Bhagwatkar Marin Bilo\u0161 Hena Ghonia Nadhir Hassen Anderson Schneider et al. 2023. Lag-Llama: Towards foundation models for time series forecasting. R0-FoMo: Robustness of few-shot and zero-shot learning in large foundation models. arXiv:2310.08278v3. Retrieved from https:\/\/arxiv.org\/abs\/2310.08278v3"},{"key":"e_1_3_2_52_2","doi-asserted-by":"crossref","unstructured":"N. Reimers. 2019. Sentence-BERT: Sentence embeddings using Siamese BERT-networks. arXiv:1908.10084. Retrieved from https:\/\/arxiv.org\/abs\/1908.10084","DOI":"10.18653\/v1\/D19-1410"},{"key":"e_1_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.117275"},{"key":"e_1_3_2_54_2","first-page":"338","volume-title":"Interspeech","volume":"2014","author":"Sak Hasim","year":"2014","unstructured":"Hasim Sak, Andrew W. Senior, Fran\u00e7oise Beaufays, et al. 2014. Long short-term memory recurrent neural network architectures for large scale acoustic modeling. In Interspeech, Vol. 2014, 338\u2013342."},{"key":"e_1_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-022-00607-1"},{"key":"e_1_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.1080\/23249935.2020.1764662"},{"key":"e_1_3_2_57_2","doi-asserted-by":"publisher","DOI":"10.5555\/2627435.2670313"},{"key":"e_1_3_2_58_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-41902-y"},{"key":"e_1_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1109\/CyberC49757.2020.00055"},{"key":"e_1_3_2_60_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3065601"},{"key":"e_1_3_2_61_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2023.119557"},{"key":"e_1_3_2_62_2","article-title":"Attention is all you need","volume":"30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in Neural Information Processing Systems, Vol. 30.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_63_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-024-05279-3"},{"key":"e_1_3_2_64_2","unstructured":"Gerald Woo Chenghao Liu Akshat Kumar Caiming Xiong Silvio Savarese and Doyen Sahoo. 2024. Unified training of universal time series forecasting transformers. In Proceedings of the 41st International Conference on Machine Learning (ICML \u201924). ACM 53140\u201353164."},{"key":"e_1_3_2_65_2","doi-asserted-by":"publisher","DOI":"10.4236\/eng.2020.123016"},{"key":"e_1_3_2_66_2","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC55140.2022.9922445"},{"key":"e_1_3_2_67_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2020.102938"},{"key":"e_1_3_2_68_2","doi-asserted-by":"publisher","DOI":"10.1145\/3409382"},{"key":"e_1_3_2_69_2","doi-asserted-by":"publisher","DOI":"10.1162\/neco_a_01199"},{"key":"e_1_3_2_70_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3245085"},{"key":"e_1_3_2_71_2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3231959"}],"container-title":["ACM Transactions on Intelligent Systems and Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3787462","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T16:30:33Z","timestamp":1773937833000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3787462"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,19]]},"references-count":70,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,4,30]]}},"alternative-id":["10.1145\/3787462"],"URL":"https:\/\/doi.org\/10.1145\/3787462","relation":{},"ISSN":["2157-6904","2157-6912"],"issn-type":[{"value":"2157-6904","type":"print"},{"value":"2157-6912","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,19]]},"assertion":[{"value":"2025-02-14","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-12-25","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-03-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}