{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T16:04:25Z","timestamp":1790093065361,"version":"4.0.1"},"reference-count":42,"publisher":"MDPI AG","issue":"19","license":[{"start":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T00:00:00Z","timestamp":1790035200000},"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>Banking data centers generate heterogeneous IT operational streams from servers, network devices, edge nodes, and business terminals. Existing detectors are vulnerable to asynchronous sampling and unreliable channels, while separate root-cause and language-model modules cannot preserve an end-to-end evidence trail. This study presents a cloud\u2013edge\u2013end framework that couples sensor-quality-aware temporal encoding, topology- and chronology-constrained event-graph reasoning, and evidence-constrained language generation. At the edge, dynamic reliability scores suppress missing, noisy, delayed, drifting, and frozen channels. At the cloud layer, the model ranks root causes and identifies propagation relations and onset times from device topology, logs, alarms, and maintenance records. The language model then generates traceable incident interpretations from the resulting evidence package and rejects claims when support is insufficient or conflicting. Experiments use IT operational data collected from the headquarters and disaster-recovery data centers of a commercial bank between 2024 and 2025; the dataset contains no customer financial or transaction records. The proposed method achieves 95.38% Accuracy, 95.06% Precision, 94.71% Recall, a 94.88% F1-score, and a 97.41% AUC for hardware anomaly detection. Root-cause localization accuracy, Top-3 Accuracy, event-relation F1-score, and temporal localization error are 91.84%, 97.26%, 90.73%, and 1.82 s, respectively. The complete model attains a 94.68% evidence support rate and a 4.26% unsupported statement rate. These results show that reliability is propagated from sensing through system-level diagnosis to evidence-grounded interpretation.<\/jats:p>","DOI":"10.3390\/s26196000","type":"journal-article","created":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T15:28:43Z","timestamp":1790090923000},"page":"6000","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Cloud\u2013Edge Collaborative Hardware Sensing with Dynamic Reliability Estimation and Evidence-Constrained Large Language Model Reasoning"],"prefix":"10.3390","volume":"26","author":[{"given":"Liyang","family":"Liu","sequence":"first","affiliation":[{"name":"Peking University, Beijing 100871, China"},{"name":"China Agricultural University, Beijing 100083, China"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"methodology","vocabulary":"credit"},{"role":"software","vocabulary":"credit"},{"role":"writing-original-draft","vocabulary":"credit"}]},{"given":"Ziyi","family":"Ren","sequence":"additional","affiliation":[{"name":"Peking University, Beijing 100871, China"},{"name":"China Agricultural University, Beijing 100083, China"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"methodology","vocabulary":"credit"},{"role":"software","vocabulary":"credit"},{"role":"writing-original-draft","vocabulary":"credit"}]},{"given":"Runxi","family":"Chen","sequence":"additional","affiliation":[{"name":"Peking University, Beijing 100871, China"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"methodology","vocabulary":"credit"},{"role":"software","vocabulary":"credit"},{"role":"writing-original-draft","vocabulary":"credit"}]},{"given":"Yan","family":"Li","sequence":"additional","affiliation":[{"name":"Peking University, Beijing 100871, China"},{"name":"China Agricultural University, Beijing 100083, China"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"validation","vocabulary":"credit"},{"role":"formal-analysis","vocabulary":"credit"},{"role":"investigation","vocabulary":"credit"},{"role":"writing-original-draft","vocabulary":"credit"}]},{"given":"Shuwen","family":"Yin","sequence":"additional","affiliation":[{"name":"Peking University, Beijing 100871, China"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"resources","vocabulary":"credit"},{"role":"data-curation","vocabulary":"credit"},{"role":"writing-original-draft","vocabulary":"credit"},{"role":"visualization","vocabulary":"credit"}]},{"given":"Jiahong","family":"Pu","sequence":"additional","affiliation":[{"name":"Peking University, Beijing 100871, China"},{"name":"China Agricultural University, Beijing 100083, China"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"validation","vocabulary":"credit"},{"role":"formal-analysis","vocabulary":"credit"},{"role":"investigation","vocabulary":"credit"},{"role":"writing-original-draft","vocabulary":"credit"}]},{"given":"Manzhou","family":"Li","sequence":"additional","affiliation":[{"name":"Peking University, Beijing 100871, China"},{"name":"China Agricultural University, Beijing 100083, China"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"supervision","vocabulary":"credit"},{"role":"project-administration","vocabulary":"credit"},{"role":"funding-acquisition","vocabulary":"credit"}]}],"member":"1968","published-online":{"date-parts":[[2026,9,22]]},"reference":[{"key":"ref_1","first-page":"1","article-title":"Edge computing and sensor-cloud: Overview, solutions, and directions","volume":"55","author":"Wang","year":"2023","journal-title":"ACM Comput. Surv."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"511","DOI":"10.1109\/SR.2025.3601092","article-title":"Toward Reliable and Intelligent Sensor Systems: A Comprehensive Study of Fault Diagnosis and Mitigation","volume":"2","author":"Belgacem","year":"2025","journal-title":"IEEE Sens. Rev."},{"key":"ref_3","first-page":"16","article-title":"The role of machine learning in network anomaly detection for cybersecurity","volume":"6","author":"Yaseen","year":"2023","journal-title":"Sage Sci. Rev. Appl. Mach. Learn."},{"key":"ref_4","unstructured":"Shanker, A., and Ahmad, N. (2026, August 12). Optimizing Network Performance with Load Balancing Techniques in Heterogeneous Environments. Available online: https:\/\/www.researchgate.net\/publication\/385378473_Optimizing_Network_Performance_with_Load_Balancing_Techniques_in_Heterogeneous_Environments?channel=doi&linkId=672225ca77f274616d5224ed&showFulltext=true."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"849","DOI":"10.1109\/TIV.2022.3188662","article-title":"Prediction-Uncertainty-Aware Decision-Making for Autonomous Vehicles","volume":"7","author":"Tang","year":"2022","journal-title":"IEEE Trans. Intell. Veh."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Zeng, Z., Lin, C., Peng, W., and Xu, M. (2026). The evolving paradigm of reliability engineering for complex systems: A review from an uncertainty control perspective. Aerospace, 13.","DOI":"10.3390\/aerospace13020183"},{"key":"ref_7","first-page":"3507848","article-title":"A systematic review of multi-sensor information fusion for equipment fault diagnosis","volume":"74","author":"Lin","year":"2025","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_8","first-page":"2029","article-title":"An insight survey on sensor errors and fault detection techniques in smart spaces","volume":"138","author":"Sharma","year":"2024","journal-title":"Comput. Model. Eng. Sci."},{"key":"ref_9","first-page":"1","article-title":"Explainability for large language models: A survey","volume":"15","author":"Zhao","year":"2024","journal-title":"ACM Trans. Intell. Syst. Technol."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"441","DOI":"10.1002\/prs.12579","article-title":"How audits fail according to accident investigations: A counterfactual logic analysis","volume":"43","author":"Hutchinson","year":"2024","journal-title":"Process Saf. Prog."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Du, M., Yue, X., Chow, S.S.M., Wang, T., Huang, C., and Sun, H. (2023). DP-Forward: Fine-tuning and Inference on Language Models with Differential Privacy in Forward Pass. Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications Security (CCS), ACM.","DOI":"10.1145\/3576915.3616592"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Chen, T., Bao, H., Huang, S., Dong, L., Jiao, B., Jiang, D., Zhou, H., Li, J., and Wei, F. (2022). THE-X: Privacy-Preserving Transformer Inference with Homomorphic Encryption. arXiv.","DOI":"10.18653\/v1\/2022.findings-acl.277"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Zeng, W., Li, M., Yang, H., Lu, W.-J., Wang, R., and Huang, R. (2023, January 10\u201316). CoPriv: Network\/Protocol Co-Optimization for Communication-Efficient Private Inference. Proceedings of the Advances in Neural Information Processing Systems (NeurIPS), New Orleans, LA, USA.","DOI":"10.52202\/075280-3451"},{"key":"ref_14","unstructured":"Fan, T., Kang, Y., Ma, G., Chen, W., Wei, W., Fan, L., and Yang, Q. (2023). FATE-LLM: An Industrial Grade Federated Learning Framework for Large Language Models. arXiv."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Li, Q., and Zhang, Y. (2024, January 5\u20137). Confidential Federated Learning for Heterogeneous Platforms against Client-Side Privacy Leakages. Proceedings of the ACM Turing Award Celebration Conference\u2014China 2024, Changsha, China.","DOI":"10.1145\/3674399.3674484"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Deng, J., Wang, Y., Li, J., Wang, C., Shang, C., Liu, H., Rajasekaran, S., and Ding, C. (2021, January 7\u201311). TAG: Gradient Attack on Transformer-based Language Models. Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2021, Punta Cana, Dominican Republic.","DOI":"10.18653\/v1\/2021.findings-emnlp.305"},{"key":"ref_17","unstructured":"Sensoy, M., Kaplan, L., and Kandemir, M. (2018, January 3\u20138). Evidential Deep Learning to Quantify Classification Uncertainty. Proceedings of the Advances in Neural Information Processing Systems, Montr\u00e9al, QC, Canada."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"3396","DOI":"10.1109\/TMM.2026.3651098","article-title":"Generalized Trusted Multi-view Classification Framework with Hierarchical Opinion Aggregation","volume":"28","author":"Shi","year":"2026","journal-title":"IEEE Trans. Multimed."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"103143","DOI":"10.1016\/j.inffus.2025.103143","article-title":"RSEA-MVGNN: Multi-view Graph Neural Network with Reliable Structural Enhancement and Aggregation","volume":"121","author":"Chen","year":"2025","journal-title":"Inf. Fusion"},{"key":"ref_20","first-page":"25814","article-title":"Trusted Multi-view Learning for Long-tailed Classification","volume":"40","author":"Tang","year":"2026","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Niklaus, J., Matoshi, V., Rani, P., Galassi, A., St\u00fcrmer, M., and Chalkidis, I. (2023, January 6\u201310). LEXTREME: A Multi-Lingual and Multi-Task Benchmark for the Legal Domain. Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2023, Singapore.","DOI":"10.18653\/v1\/2023.findings-emnlp.200"},{"key":"ref_22","unstructured":"Hendrycks, D., Burns, C., Chen, A., and Ball, S. (2021). CUAD: An Expert-Annotated NLP Dataset for Legal Contract Review. arXiv."},{"key":"ref_23","unstructured":"Wu, S., Irsoy, O., Lu, S., Dabravolski, V., Dredze, M., Gehrmann, S., Kambadur, P., Rosenberg, D., and Mann, G. (2023). BloombergGPT: A Large Language Model for Finance. arXiv."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Modi, A., Kalamkar, P., Karn, S., Tiwari, A., Joshi, A., Tanikella, S.K., Guha, S.K., Malhan, S., and Raghavan, V. (2023, January 13\u201314). SemEval-2023 Task 6: LegalEval\u2014Understanding Legal Texts. Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023), Toronto, ON, Canada.","DOI":"10.18653\/v1\/2023.semeval-1.318"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Luo, C.F., Bhambhoria, R., Dahan, S., and Zhu, X. (2023, January 9\u201314). Prototype-Based Interpretability for Legal Citation Prediction. Proceedings of the Findings of the Association for Computational Linguistics: ACL 2023, Toronto, ON, Canada.","DOI":"10.18653\/v1\/2023.findings-acl.301"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Li, Q., Ren, J., Zhang, Y., Song, C., Liao, Y., and Zhang, Y. (2023). Privacy-Preserving DNN Training with Prefetched Meta-Keys on Heterogeneous Neural Network Accelerators. Proceedings of the 2023 60th ACM\/IEEE Design Automation Conference (DAC), IEEE.","DOI":"10.1109\/DAC56929.2023.10247964"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Santosh, T.Y.S.S., Baumgartner, N., St\u00fcrmer, M., Grabmair, M., and Niklaus, J. (2024). Towards Explainability and Fairness in Swiss Judgement Prediction: Benchmarking on a Multilingual Dataset. arXiv.","DOI":"10.63317\/3popcyrfhvqb"},{"key":"ref_28","unstructured":"Ponemon Institute and IBM Security (2024). Cost of a Data Breach Report 2024, IBM Security. Technical Report."},{"key":"ref_29","unstructured":"Percia David, D., Mermoud, A., and Gillard, S. (2021). Cyber-Security Investment in the Context of Disruptive Technologies: Extension of the Gordon\u2013Loeb Model. arXiv."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Callegaro, G., Fontana, C., Hillairet, C., and Ongarato, B. (2026). A Stochastic Gordon\u2013Loeb Model for Optimal Cybersecurity Investment under Clustered Attacks. Ann. Actuar. Sci., 1\u201329.","DOI":"10.1017\/S1748499526100359"},{"key":"ref_31","unstructured":"Ebel, A., and Mitra, D. (2022). Economics and Optimal Investment Policies of Attackers and Defenders in Cybersecurity. arXiv."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Amaral, O., Abualhaija, S., Torre, D., Sabetzadeh, M., and Briand, L.C. (2021). AI-enabled Automation for Completeness Checking of Privacy Policies. arXiv.","DOI":"10.1109\/TSE.2021.3124332"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Liu, J., Tong, Y., Huang, H., Zheng, B., Hu, Y., Wu, P., Xiao, C., Onizuka, M., Yang, M., and Zheng, S. (2025). Legal Fact Prediction: The Missing Piece in Legal Judgment Prediction. arXiv.","DOI":"10.18653\/v1\/2025.emnlp-main.322"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Chen, T., and Guestrin, C. (2016, January 13\u201317). Xgboost: A scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA.","DOI":"10.1145\/2939672.2939785"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"key":"ref_37","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_38","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., and Polosukhin, I. (2017, January 4\u20139). Attention is all you need. Proceedings of the Advances in Neural Information Processing Systems, Long Beach, CA, USA."},{"key":"ref_39","unstructured":"Nie, Y., Nguyen, N.H., Sinthong, P., and Kalagnanam, J. (2022). A time series is worth 64 words: Long-term forecasting with transformers. arXiv."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Snoek, C.G., Worring, M., and Smeulders, A.W. (2005, January 6\u201311). Early versus late fusion in semantic video analysis. Proceedings of the 13th Annual ACM International Conference on Multimedia, Singapore, Sinapore.","DOI":"10.1145\/1101149.1101236"},{"key":"ref_41","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_42","doi-asserted-by":"crossref","first-page":"729","DOI":"10.1109\/IJCNN.2005.1555942","article-title":"A new model for learning in graph domains","volume":"Volume 2","author":"Gori","year":"2005","journal-title":"Proceedings of the 2005 IEEE International Joint Conference on Neural Networks"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/19\/6000\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T15:29:36Z","timestamp":1790090976000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/19\/6000"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,22]]},"references-count":42,"journal-issue":{"issue":"19","published-online":{"date-parts":[[2026,10]]}},"alternative-id":["s26196000"],"URL":"https:\/\/doi.org\/10.3390\/s26196000","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,22]]}}}