{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T15:31:39Z","timestamp":1767195099739,"version":"3.48.0"},"reference-count":43,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2025,12,29]],"date-time":"2025-12-29T00:00:00Z","timestamp":1766966400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["71561013"],"award-info":[{"award-number":["71561013"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Systems"],"abstract":"<jats:p>Urban welfare can deteriorate over a few weeks, yet most official indicators are only updated quarterly. This mismatch in time scales leaves city administrations effectively blind to the early stages of emerging crises, especially in areas where vulnerable residents generate few administrative or digital records. We cast urban socioeconomic monitoring as a systems problem: a six-dimensional welfare state on a spatial grid, observed through sparse delayed administrative data and noisy digital traces whose reliability declines with digital exclusion. On top of this latent state, we design a four-layer cyber\u2013physical\u2013social (CPSS) architecture centered on a stochastic state-space model with empirically guided couplings. This is supported by a semantic sensing layer where large language models (LLMs) convert daily geo-referenced public text into noisy welfare indicators. These signals are then fused with quarterly administrative records via an extended Kalman filter (EKF). Finally, a lightweight convex post-processing layer enforces fairness, differential privacy, and minimum representation as hard constraints. A key ingredient is a state-dependent noise model in which the LLM observation variance grows exponentially with digital exclusion. Under this model, we study finite-horizon observability and obtain an exclusion threshold beyond which several welfare dimensions become effectively unobservable over 30\u201360 day horizons; EKF error bounds scale with the same exponent, clarifying when semantic sensing is informative and when it is not. Finally, a 100,000-agent agent-based model of a synthetic city with daily shocks suggests that, relative to a quarterly-only baseline, the LLM-augmented fusion pipeline substantially reduces detection lags and multi-dimensional cascade failures while keeping estimation error bounded and satisfying the explicit fairness and privacy constraints.<\/jats:p>","DOI":"10.3390\/systems14010036","type":"journal-article","created":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T15:05:01Z","timestamp":1767193501000},"page":"36","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["LLM-Augmented Sensor Fusion for Urban Socioeconomic Monitoring: A Cyber\u2013Physical\u2013Social Systems Perspective"],"prefix":"10.3390","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5389-5280","authenticated-orcid":false,"given":"Hui","family":"Xie","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, Guangzhou Maritime University, Guangzhou 510725, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hui","family":"Cao","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Guangzhou Maritime University, Guangzhou 510725, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongkai","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Guangzhou Maritime University, Guangzhou 510725, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,12,29]]},"reference":[{"key":"ref_1","unstructured":"\u00c5str\u00f6m, K.J., and Murray, R.M. (2008). Feedback Systems: An Introduction for Scientists and Engineers, Princeton University Press."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1016\/j.poetic.2006.05.004","article-title":"Digital divide research, achievements and shortcomings","volume":"34","year":"2006","journal-title":"Poetics"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Sun, X., Zheng, X., Li, S., Zhang, J., and Shi, H. (2025). The Impact of Rural Energy Poverty on Primary Health Services Efficiency: The Case of China. Systems, 13.","DOI":"10.3390\/systems13080675"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Dobre, F., Sandu, A., T\u0103taru, G.-C., and Cotfas, L.-A. (2025). A Decade of Studies in Smart Cities and Urban Planning Through Big Data Analytics. Systems, 13.","DOI":"10.3390\/systems13090780"},{"key":"ref_5","unstructured":"Lee, E.A., and Seshia, S.A. (2017). Introduction to Embedded Systems\u2014A Cyber-Physical Systems Approach, MIT Press. [2nd ed.]."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"749","DOI":"10.2307\/1911028","article-title":"On the measurement of poverty","volume":"55","author":"Atkinson","year":"1987","journal-title":"Econometrica"},{"key":"ref_7","unstructured":"Sen, A. (1999). Development as Freedom, Oxford University Press."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s10708-013-9516-8","article-title":"The real-time city? Big data and smart urbanism","volume":"79","author":"Kitchin","year":"2014","journal-title":"GeoJournal"},{"key":"ref_9","first-page":"88","article-title":"Simulation analysis of mustard combine harvester extraction device based on ADAMS","volume":"6","author":"Zhou","year":"2025","journal-title":"J. Intell. Agric. Mech."},{"key":"ref_10","unstructured":"Park, J.S., O\u2019Brien, J.C., Cai, C.J., Morris, M.R., Liang, P., and Bernstein, M.S. (November, January 29). Generative Agents: Interactive Simulacra of Human Behavior. Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology (UIST \u201923), San Francisco, CA, USA."},{"key":"ref_11","first-page":"76","article-title":"Large Models for Machine Monitoring and Fault Diagnostics: Opportunities, Challenges, and Future Direction","volume":"4","author":"Chen","year":"2025","journal-title":"J. Dyn. Monit. Diagn."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Lu, Q., and Li, M. (2025). Fault Prediction Method Towards Rolling Element Bearing Based on Digital Twin and Deep Transfer Learning. Appl. Sci., 15.","DOI":"10.3390\/app152312509"},{"key":"ref_13","unstructured":"Bommasani, R., Hudson, D.A., Adeli, E., Altman, R., Arora, S., von Arx, S., Bernstein, M.S., Bohg, J., Bosselut, A., and Brunskill, E. (2021). On the Opportunities and Risks of Foundation Models. arXiv."},{"key":"ref_14","unstructured":"Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J.D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., and Askell, A. (2020, January 6\u201312). Language Models are Few-Shot Learners. Proceedings of the 34th Conference on Neural Information Processing Systems (NeurIPS 2020), Vancouver, BC, Canada."},{"key":"ref_15","unstructured":"Wei, J., Tay, Y., Bommasani, R., Raffel, C., Zoph, B., Borgeaud, S., Yogatama, D., Bosma, M., Zhou, D., and Metzler, D. (2022). Emergent Abilities of Large Language Models. arXiv."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1162\/coli_a_00502","article-title":"Can Large Language Models Transform Computational Social Science?","volume":"50","author":"Ziems","year":"2024","journal-title":"Comput. Linguist."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1108","DOI":"10.1126\/science.adi1778","article-title":"AI and the transformation of social science research","volume":"380","author":"Grossmann","year":"2023","journal-title":"Science"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"337","DOI":"10.1017\/pan.2023.2","article-title":"Out of One, Many: Using Language Models to Simulate Human Samples","volume":"31","author":"Argyle","year":"2023","journal-title":"Political Anal."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"pgae245","DOI":"10.1093\/pnasnexus\/pgae245","article-title":"Perils and Opportunities in Using Large Language Models in Psychological Research","volume":"3","author":"Abdurahman","year":"2024","journal-title":"PNAS Nexus"},{"key":"ref_20","unstructured":"Liang, P., Bommasani, R., Lee, T., Tsipras, D., Soylu, D., Yasunaga, M., Zhang, M., Narayanan, D., Reich, J., and Ganguli, D. (2022). Holistic Evaluation of Language Models. arXiv."},{"key":"ref_21","unstructured":"(2023). GPT-4 Technical Report. arXiv."},{"key":"ref_22","unstructured":"Bubeck, S., Chandrasekaran, V., Eldan, R., Gehrke, J., Horvitz, E., Kamar, E., Lee, P., Lee, Y.T., Li, Y., and Lundberg, S. (2023). Sparks of Artificial General Intelligence: Early experiments with GPT-4. arXiv."},{"key":"ref_23","unstructured":"Bai, Y., Kadavath, S., Kundu, S., Askell, A., Kernion, J., Jones, A., Chen, A., Goldie, A., Mirhoseini, A., and McKinnon, C. (2022). Constitutional AI: Harmlessness from AI Feedback. arXiv."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Bender, E.M., Gebru, T., McMillan-Major, A., and Shmitchell, S. (2021, January 3\u201310). On the Dangers of Stochastic Parrots: Can Language Models Be Too Big?. Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency (FAccT \u201921), Virtual Event, Canada.","DOI":"10.1145\/3442188.3445922"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3571730","article-title":"Survey of Hallucination in Natural Language Generation","volume":"55","author":"Ji","year":"2023","journal-title":"ACM Comput. Surv."},{"key":"ref_26","unstructured":"Gal, Y., and Ghahramani, Z. (2016, January 19\u201324). Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning. Proceedings of the 33rd International Conference on Machine Learning (ICML), New York, NY, USA."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Pan, X., Zhang, M., Ji, S., and Yang, M. (2020, January 18\u201321). Privacy Risks of General-Purpose Language Models. Proceedings of the 2020 IEEE Symposium on Security and Privacy (SP), San Francisco, CA, USA.","DOI":"10.1109\/SP40000.2020.00095"},{"key":"ref_28","unstructured":"Santurkar, S., Durmus, E., Ladhak, F., Lee, C., Liang, P., and Hashimoto, T. (2023, January 23\u201329). Whose Opinions Do Language Models Reflect?. Proceedings of the 40th International Conference on Machine Learning (ICML), Honolulu, HI, USA."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"e2305016120","DOI":"10.1073\/pnas.2305016120","article-title":"ChatGPT Outperforms Crowd Workers for Text-Annotation Tasks","volume":"120","author":"Gilardi","year":"2023","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"102274","DOI":"10.1016\/j.lindif.2023.102274","article-title":"ChatGPT for Good? On Opportunities and Challenges of Large Language Models for Education","volume":"103","author":"Kasneci","year":"2023","journal-title":"Learn. Individ. Differ."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1214\/19-AAP1485","article-title":"Generalized Couplings and Ergodic Rates for SPDEs and Other Markov Models","volume":"30","author":"Butkovsky","year":"2020","journal-title":"Ann. Appl. Probab."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"e2305860120","DOI":"10.1073\/pnas.2305860120","article-title":"A Comprehensive Demographic Profile of the US Evicted Population","volume":"120","author":"Graetz","year":"2023","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1146\/annurev-soc-121919-054857","article-title":"What Do Platforms Do? Understanding the Gig Economy","volume":"46","author":"Vallas","year":"2020","journal-title":"Annu. Rev. Sociol."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"136","DOI":"10.1016\/j.arcontrol.2008.08.003","article-title":"Towards Applied Nonlinear Adaptive Control","volume":"32","author":"Astolfi","year":"2008","journal-title":"Annu. Rev. Control"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"104727","DOI":"10.1016\/j.robot.2024.104727","article-title":"Learning-based methods for adaptive informative path planning","volume":"179","author":"Ott","year":"2024","journal-title":"Robot. Auton. Syst."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"1532","DOI":"10.1109\/TSP.2022.3158588","article-title":"KalmanNet: Neural Network Aided Kalman Filtering for Partially Known Dynamics","volume":"70","author":"Revach","year":"2022","journal-title":"IEEE Trans. Signal Process."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"1275","DOI":"10.1109\/TAC.2014.2370472","article-title":"On Set-Valued Kalman Filtering and Its Application to Event-Based State Estimation","volume":"60","author":"Shi","year":"2014","journal-title":"IEEE Trans. Autom. Control"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1561\/2200000016","article-title":"Distributed Optimization and Statistical Learning via the Alternating Direction Method of Multipliers","volume":"3","author":"Boyd","year":"2011","journal-title":"Found. Trends Mach. Learn."},{"key":"ref_39","first-page":"1","article-title":"Artificial intelligence for safety-critical systems in industrial and transportation domains: A survey","volume":"56","author":"Abella","year":"2024","journal-title":"ACM Comput. Surv."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1561\/2200000086","article-title":"Model-based Reinforcement Learning: A Survey","volume":"16","author":"Moerland","year":"2023","journal-title":"Found. Trends Mach. Learn."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"1327","DOI":"10.1007\/s00170-021-07682-3","article-title":"Review on Model Predictive Control: An Engineering Perspective","volume":"117","author":"Schwenzer","year":"2021","journal-title":"Int. J. Adv. Manuf. Technol."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"789","DOI":"10.1016\/S0005-1098(99)00214-9","article-title":"Constrained model predictive control: Stability and optimality","volume":"36","author":"Mayne","year":"2000","journal-title":"Automatica"},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Alshiekh, M., Bloem, R., Ehlers, R., K\"onighofer, B., Niekum, S., and Topcu, U. (2018, January 2\u20137). Safe Reinforcement Learning via Shielding. Proceedings of the 32nd AAAI Conference on Artificial Intelligence (AAAI), New Orleans, LA, USA.","DOI":"10.1609\/aaai.v32i1.11797"}],"container-title":["Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2079-8954\/14\/1\/36\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T15:26:44Z","timestamp":1767194804000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2079-8954\/14\/1\/36"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,29]]},"references-count":43,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,1]]}},"alternative-id":["systems14010036"],"URL":"https:\/\/doi.org\/10.3390\/systems14010036","relation":{},"ISSN":["2079-8954"],"issn-type":[{"type":"electronic","value":"2079-8954"}],"subject":[],"published":{"date-parts":[[2025,12,29]]}}}