{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T15:07:30Z","timestamp":1787238450962,"version":"build-2736575974"},"reference-count":62,"publisher":"MDPI AG","issue":"16","license":[{"start":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T00:00:00Z","timestamp":1787184000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Cross-border trade security risks are often embedded in inconsistencies among trade documents, logistics trajectories, hardware sensor states, and financial settlement activities. Existing methods primarily rely on structured declaration fields, making it difficult to verify digital declarations against actual physical processes or to generate complete evidence suitable for regulatory review. To address these challenges, TradeSense-EQA is proposed as a cross-border trade security anomaly detection and evidence-grounded English question-answering framework. Multisource sensing information, including trade documents, GPS\/AIS trajectories, RFID records, electronic seal events, port weighing data, temperature and humidity measurements, vibration signals, container door states, and visual images, is jointly modeled within the framework. The reliability-aware representation module dynamically adjusts sensing-channel weights according to data missingness, sampling intervals, device health states, and communication quality. The trade-process-constrained module identifies anomalies across declaration, packing, transportation, transshipment, arrival, and customs clearance stages and generates process-consistent evidence chains. The evidence-grounded question-answering module answers English trade risk questions on the basis of verified documentary fields and sensor records, while confidence estimation and abstention mechanisms are incorporated to reduce factual hallucinations. Experimental results demonstrate that TradeSense-EQA achieved an Accuracy of 0.918, a Precision of 0.909, a Recall of 0.897, a Macro-F1 of 0.903, and a ROC-AUC of 0.958 on the cross-border trade anomaly detection task, outperforming baseline methods including XGBoost, LightGBM, TCN, Transformer, BERT, CLIP, and VisualBERT. On the English trade risk question-answering task, Exact Match, Token-level F1, BLEU, ROUGE-L, and BERTScore reached 0.782, 0.851, 0.668, 0.801, and 0.934, respectively. Ablation results further confirmed the effectiveness of hardware sensing input, reliability-aware weighting, declaration\u2013fact alignment, process-graph reasoning, and evidence-constrained generation. The proposed framework provides a reliable, interpretable, and auditable artificial intelligence-driven sensing solution for customs supervision, port security, international logistics review, and trade-background investigation.<\/jats:p>","DOI":"10.3390\/s26165272","type":"journal-article","created":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T09:48:31Z","timestamp":1787219311000},"page":"5272","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Artificial Intelligence-Driven Sensing of Cross-Border Trade Risks Through Declaration-to-Physical-Fact Alignment and Evidence-Grounded Question Answering"],"prefix":"10.3390","volume":"26","author":[{"given":"Meitong","family":"Chen","sequence":"first","affiliation":[{"name":"China Agricultural University, Beijing 100083, China"},{"name":"Peking University, Beijing 100871, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiayi","family":"Huang","sequence":"additional","affiliation":[{"name":"Peking University, Beijing 100871, China"},{"name":"Renmin University of China, Beijing 100872, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zilang","family":"Zhou","sequence":"additional","affiliation":[{"name":"China Agricultural University, Beijing 100083, China"},{"name":"Peking University, Beijing 100871, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhonghao","family":"Zhang","sequence":"additional","affiliation":[{"name":"China Agricultural University, Beijing 100083, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kele","family":"Lei","sequence":"additional","affiliation":[{"name":"Peking University, Beijing 100871, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongxin","family":"Tang","sequence":"additional","affiliation":[{"name":"China Agricultural University, Beijing 100083, China"},{"name":"Peking University, Beijing 100871, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Manzhou","family":"Li","sequence":"additional","affiliation":[{"name":"China Agricultural University, Beijing 100083, China"},{"name":"Peking University, Beijing 100871, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,8,20]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Kawa, A., Abubakari, A., and Ofori, K.S. (2023). Cross-border E-commerce and supply chain management. The Palgrave Handbook of Supply Chain Management, Springer.","DOI":"10.1007\/978-3-030-89822-9_76-1"},{"key":"ref_2","unstructured":"Du, R., and Duval, Y. (2024). An Exploration of Paperless Trade Implementation in UN and Other International Conventions Involving Cross-Border Exchange of Trade-Related Data and Documents, UNESCAP. UNNExT working paper series no. 10."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1108\/IJLMA-09-2023-0209","article-title":"Legal analysis of the merits of electronic transferable records: Toward cross-border trade digitalization","volume":"67","author":"ALsheyab","year":"2025","journal-title":"Int. J. Law Manag."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"10436","DOI":"10.1109\/ACCESS.2026.3655398","article-title":"FraudFusion: A Multi-Modal Ensemble Framework for Anomaly-Based Fraud Detection in Retail POS Systems","volume":"14","author":"Mishra","year":"2026","journal-title":"IEEE Access"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Chin, Y.C., and Zhao, J. (2022). Governing cross-border data flows: International trade agreements and their limits. Laws, 11.","DOI":"10.3390\/laws11040063"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Boluchenko, V., Kudryavtsev, O., and Skiba, V. (2025). Digital Platform for Intelligent Tracking of International Road Transport Using Blockchain Technology and Electronic Navigation Seals. Proceedings of the International Conference on Intelligent Information Technologies for Industry, Springer.","DOI":"10.1007\/978-3-032-13615-2_19"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"35","DOI":"10.63278\/jicrcr.vi.3484","article-title":"AI-Enabled Trade Testing and Simulation Framework For Market Infrastructure Validation","volume":"8","author":"Chandana","year":"2025","journal-title":"J. Int. Crisis Risk Commun. Res."},{"key":"ref_8","first-page":"53","article-title":"Foreign Trade Risk Warning Model Based on Deep Learning and Association Rule Mining","volume":"167","author":"Li","year":"2025","journal-title":"Int. J. Marit. Eng."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"4645","DOI":"10.1108\/ECAM-03-2022-0209","article-title":"A data model for integrating BIM and blockchain to enable a single source of truth for the construction supply chain data delivery","volume":"30","author":"Hijazi","year":"2023","journal-title":"Eng. Constr. Archit. Manag."},{"key":"ref_10","first-page":"49","article-title":"Designing adaptive compliance frameworks using time series fraud detection models for dynamic regulatory and risk management environments","volume":"15","author":"Odunaike","year":"2025","journal-title":"Comput. Eng. Appl."},{"key":"ref_11","first-page":"47","article-title":"Machine Learning-Based Detection of Tax Anomalies in Cross-border E-commerce Transactions","volume":"3","author":"Fan","year":"2024","journal-title":"Acad. Nexus J."},{"key":"ref_12","unstructured":"Mahajan, K. (2025). Mitigating Hallucinations in LLMs for International Trade: Introducing the TradeGov Evaluation Dataset and TradeGuard Hallucination Mitigation Framework for Trade Q&A. Proceedings of the Bridge Between Artificial Intelligence and Law, Satyam Law International."},{"key":"ref_13","first-page":"3482","article-title":"Cross-border trade risk prediction model based on support vector machine","volume":"25","author":"Wei","year":"2025","journal-title":"J. Comput. Methods Sci. Eng."},{"key":"ref_14","first-page":"157","article-title":"Temporal graph neural networks for money laundering detection in cross-border transactions","volume":"3","author":"Wang","year":"2024","journal-title":"Acad. Nexus J."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"29162","DOI":"10.1109\/ACCESS.2025.3539569","article-title":"A transformer-based multimodal object detection system for real-world applications","volume":"13","author":"Ikram","year":"2025","journal-title":"IEEE Access"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"e70017","DOI":"10.1002\/widm.70017","article-title":"Review on Information Fusion-Based Data Mining for Improving Complex Anomaly Detection","volume":"15","author":"Moldovan","year":"2025","journal-title":"Wiley Interdiscip. Rev. Data Min. Knowl. Discov."},{"key":"ref_17","first-page":"3","article-title":"Anomaly detection methods to improve supply chain data quality and operations","volume":"6","author":"Glaser","year":"2022","journal-title":"SMU Data Sci. Rev."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Xu, Z., and Li, Y. (2025). A User-Centered System for Reliable Cross-Border Trade Fraud Detection. Proceedings of the 2025 IEEE International Conference on E-Business Engineering (ICEBE), IEEE.","DOI":"10.1109\/ICEBE68123.2025.00035"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Chen, Y., Huang, C., Gao, S., Lyu, Y., Chen, X., Liu, S., Bao, D., and Lv, C. (2025). A multimodal deep learning approach for legal English learning in intelligent educational systems. Sensors, 25.","DOI":"10.3390\/s25113397"},{"key":"ref_20","unstructured":"Chowdhury, M.A.A. (2025, March 02). The Impact of Trade Agreements on International Business Expansion, Trade and Investment in the European Union. Available online: https:\/\/urn.fi\/URN:NBN:fi-fe2025052654494."},{"key":"ref_21","unstructured":"Demirta\u015f, \u0130.N. (2025, March 02). Event Extraction from Turkish Trade Registry Gazette. Available online: http:\/\/hdl.handle.net\/11527\/25116."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"1","DOI":"10.63125\/agnvxs76","article-title":"A quantitative analysis of ai-driven trade-finance risk assessment models for strengthening us import\u2013export operations","volume":"6","author":"Kamal","year":"2026","journal-title":"Int. J. Bus. Econ. Insights"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"24","DOI":"10.26599\/IJCS.2022.9100032","article-title":"A correlation analysis based risk warning service for cross-border trading","volume":"7","author":"Zhang","year":"2023","journal-title":"Int. J. Crowd Sci."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Poudel, S. (2025, March 02). Small-Cap Stock Trading Strategies for Retail Traders: A Data-Driven, Statistically Validated, and Reproducible Study of Strategy Design, Risk Management, and Technical-Pattern-Based Signals. Available online: https:\/\/ssrn.com\/abstract=5921742.","DOI":"10.2139\/ssrn.5921742"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Borch, C. (2026). Trading Beyond Understanding: Machine Learning, Risk, and Markets, Stanford University Press.","DOI":"10.1515\/9781503645530"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"199105","DOI":"10.1109\/ACCESS.2025.3631446","article-title":"Research on Comparative Modeling of Free Trade Agreement Clauses with Deep Semantic Integration","volume":"13","author":"Zhang","year":"2025","journal-title":"IEEE Access"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"e3259","DOI":"10.7717\/peerj-cs.3259","article-title":"Ten quick tips for improving estimated time of arrival predictions using machine learning in logistics and transportation systems","volume":"11","author":"Wani","year":"2025","journal-title":"PeerJ Comput. Sci."},{"key":"ref_28","first-page":"1","article-title":"Graph Neural Networks, Analytics, and AI for Fraudulent-Seller Detection: Methods, Evaluation, and Impact on Future Trends","volume":"3","author":"Adams","year":"2024","journal-title":"Front. Robot. Artif. Intell. J."},{"key":"ref_29","unstructured":"Hoffstr\u00f6m, M. (2025, December 02). Strategic Pathways to T + 1 and Beyond: Global Lessons, European Readiness, and the Future of Real-Time Settlement. Available online: https:\/\/urn.fi\/URN:NBN:fi:amk-2025102826551."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Shao, J. (2025). Adaptive Multi-Modal Risk Assessment for Agricultural Product Processing and Trade. Proceedings of the 2025 International Conference on Communication, Computer, and Information Technology (IC3IT), IEEE.","DOI":"10.1109\/IC3IT66137.2025.11341074"},{"key":"ref_31","unstructured":"Buban, S., Nagallo, J., and Reyes, C.V. (2023). Results from the Follow-up ASEAN Seamless Trade Facilitation Indicators (ASTFI II)\u2013Philippines. Follow-Up ASEAN Seamless Trade Facilitation Indicators, ERIA."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"125","DOI":"10.1111\/1468-2230.70008","article-title":"Is the Electronic Trade Documents Act 2023 Sufficient to Promote the Uptake of Paperless Trading Systems?","volume":"89","author":"Ioannou","year":"2026","journal-title":"Mod. Law Rev."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Farina, G., Kocian, A., Brunori, G., Chessa, S., Lai, M.B., Nardi, D., Schifanella, C., Bonura, S., Masi, N., and Comella, S. (2025). Interoperable Traceability in Agrifood Supply Chains: Enhancing Transport Systems Through IoT Sensor Data, Blockchain, and DataSpace. Sensors, 25.","DOI":"10.3390\/s25113419"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"1531","DOI":"10.1007\/s12063-024-00519-8","article-title":"Analysing cross-border logistics operations for performance improvement: Development and validation of a reference model","volume":"17","author":"Bandaranayake","year":"2024","journal-title":"Oper. Manag. Res."},{"key":"ref_35","unstructured":"Savolainen, P. (2025, April 05). Vessel Sensor Performance Analysis. Available online: https:\/\/urn.fi\/URN:NBN:fi:amk-202504106081."},{"key":"ref_36","unstructured":"Thiagarajan, H. (2022). Supporting Model Based Safety and Security Assessment of High Assurance Systems, Kansas State University."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"127221","DOI":"10.1109\/ACCESS.2025.3589063","article-title":"A multi-modal approach using a hybrid vision transformer and temporal fusion transformer model for stock price movement classification","volume":"13","author":"Friday","year":"2025","journal-title":"IEEE Access"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Wang, Q., and Wang, T. (2026). Machine learning-driven sensor fusion for precision agriculture: Current applications and future perspectives. Sens. Rev., 1\u201326.","DOI":"10.1108\/SR-08-2025-0613"},{"key":"ref_39","unstructured":"Obayemi, A. (2025). Fine-Grained E-Commerce Product Classification Using Image and Text Modalities. [Ph.D. Thesis, University of Brighton]."},{"key":"ref_40","unstructured":"Wright, Z.A. (2025). Essays on Drivers of Compliance and Quality Performance: Perspectives Across Human and Technology Monitoring Environments. [Ph.D. Thesis, The Ohio State University]."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Kalari, S., Sunkara, M.K., So\u00f3s, D., Ashok, V., and Mukkamala, R. (2025). ReViewQwen: An Explainable Vision-Language Model for Discrepancy Detection in Multimodal E-Commerce Reviews. Proceedings of the 2025 International Conference on Content-Based Multimedia Indexing (CBMI), IEEE.","DOI":"10.1109\/CBMI66578.2025.11339346"},{"key":"ref_42","unstructured":"Azimi, S. (2025). Anomalies and Root Cause Analysis in Machine Learning Model Quality. [Ph.D. Thesis, Free University of Bozen-Bolzano]."},{"key":"ref_43","unstructured":"Nourbakhsh, A. (2025). Towards Grounded Multimodal Enterprise Document Understanding. [Ph.D. Thesis, Carnegie Mellon University]."},{"key":"ref_44","unstructured":"Usmanova, A., Huang, J., Banerjee, D., and Usbeck, R. (2024). Reporting and analysing the environmental impact of language models on the example of commonsense question answering with external knowledge. arXiv."},{"key":"ref_45","unstructured":"Islam, M.M., Gladstone, A., Islam, R., and Iqbal, T. (2024, January 7\u201311). Eqa-mx: Embodied question answering using multimodal expression. Proceedings of the International Conference on Learning Representations, Vienna, Austria."},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Alam, M.Z., Zaman, K.A.U., and Miraz, M.H. (2025). AstuteRAG-FQA: Task-Aware Retrieval-Augmented Generation Framework for Proprietary Data Challenges in Financial Question Answering. arXiv.","DOI":"10.33166\/AETiC.2025.05.002"},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Lee, S.H., Choi, S.W., and Lee, E.B. (2023). A question-answering model based on knowledge graphs for the general provisions of equipment purchase orders for steel plants maintenance. Electronics, 12.","DOI":"10.3390\/electronics12112504"},{"key":"ref_48","unstructured":"Elewah, A. (2025, March 02). SensorsConnect: World Wide Web for Internet of Things. Available online: https:\/\/hdl.handle.net\/10155\/1917."},{"key":"ref_49","unstructured":"Ogbeide, H. (2023). An Exploratory Examination of Anti-Money Laundering Risk Assessment, University of Northumbria at Newcastle (United Kingdom)."},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Tasioulis, T., Bagkis, E., Kassandros, T., and Karatzas, K. (2025). The quest for the best explanation: Comparing models and XAI methods in air quality modeling tasks. Appl. Sci., 15.","DOI":"10.3390\/app15137390"},{"key":"ref_51","unstructured":"Nejadghorban, H. (2024). A Causal Analysis of the European Union Emissions Trading System. [Ph.D. Thesis, University of Essex (United Kingdom)]."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"100686","DOI":"10.1016\/j.dajour.2026.100686","article-title":"An analytical framework for causal decision-making in international trade","volume":"18","year":"2026","journal-title":"Decis. Anal. J."},{"key":"ref_53","unstructured":"(2021). Information Technology\u2014Radio Frequency Identification for Item management. Part 63: Parameters for Air Interface Communications at 860 MHz to 960 MHz Type C (Standard No. ISO\/IEC 18000-63:2021)."},{"key":"ref_54","doi-asserted-by":"crossref","unstructured":"Chen, T., and Guestrin, C. (2016). Xgboost: A scalable tree boosting system. Proceedings of the 22nd ACM Sigkdd International Conference on Knowledge Discovery and Data Mining, ACM.","DOI":"10.1145\/2939672.2939785"},{"key":"ref_55","unstructured":"Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., and Liu, T.Y. (2017). Lightgbm: A highly efficient gradient boosting decision tree. Advances in Neural Information Processing Systems, Curran Associates, Inc."},{"key":"ref_56","doi-asserted-by":"crossref","unstructured":"Lea, C., Flynn, M.D., Vidal, R., Reiter, A., and Hager, G.D. (2017, January 21\u201326). Temporal convolutional networks for action segmentation and detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.113"},{"key":"ref_57","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., and Polosukhin, I. (2017). Attention is all you need. Advances in Neural Information Processing Systems, Curran Associates, Inc."},{"key":"ref_58","unstructured":"Devlin, J., Chang, M.W., Lee, K., and Toutanova, K. (2019). Bert: Pre-training of deep bidirectional transformers for language understanding. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), Association for Computational Linguistics."},{"key":"ref_59","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., and Clark, J. (March, January 26). Learning transferable visual models from natural language supervision. Proceedings of the International Conference on Machine Learning, Shenzhen, China."},{"key":"ref_60","unstructured":"Li, L.H., Yatskar, M., Yin, D., Hsieh, C.J., and Chang, K.W. (2019). Visualbert: A simple and performant baseline for vision and language. arXiv."},{"key":"ref_61","unstructured":"Tsai, Y.H.H., Bai, S., Liang, P.P., Kolter, J.Z., Morency, L.P., and Salakhutdinov, R. (August, January 28). Multimodal transformer for unaligned multimodal language sequences. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, Florence, Italy."},{"key":"ref_62","unstructured":"Jaegle, A., Borgeaud, S., Alayrac, J.B., Doersch, C., Ionescu, C., Ding, D., Koppula, S., Zoran, D., Brock, A., and Shelhamer, E. (2021). Perceiver io: A general architecture for structured inputs & outputs. arXiv."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/16\/5272\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T09:51:09Z","timestamp":1787219469000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/16\/5272"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,20]]},"references-count":62,"journal-issue":{"issue":"16","published-online":{"date-parts":[[2026,8]]}},"alternative-id":["s26165272"],"URL":"https:\/\/doi.org\/10.3390\/s26165272","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,20]]}}}