{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T14:58:18Z","timestamp":1773932298375,"version":"3.50.1"},"reference-count":28,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T00:00:00Z","timestamp":1773878400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["BDCC"],"abstract":"<jats:p>Spontaneous combustion in goaf areas poses a significant threat to coal mine safety. Traditional safety management systems, reliant on passive response and single-indicator thresholds, often suffer from delayed warnings and lack cognitive decision support. To address this challenge, this study proposes a big-data-driven cognitive computing framework for dynamic risk prediction of goaf spontaneous combustion, based on a \u201cCloud-Edge-End\u201d collaborative architecture. The method leverages multi-sensor big data streams (CO, C2H4, O2, etc.) and deploys a lightweight Radial Basis Function (RBF) neural network on underground edge computing nodes (STM32) for real-time analytics. The model demonstrates excellent predictive performance on imbalanced datasets, with a PR-AUC of 0.910 and a recall of 99.7%. The edge-deployed RBF model achieves a single-pass inference time of only 0.62 ms, enabling real-time cognitive risk mapping. Field application at Z Coal Mine validated the system\u2019s effectiveness, providing an average pre-warning time of 48.5 h, achieving zero spontaneous combustion accidents, and reducing the Total Recordable Injury Rate (TRIR) by 15.2%. This work illustrates how edge-based cognitive computing can transform safety management from passive response to proactive prevention, offering a scalable and interpretable framework for intelligent mine safety.<\/jats:p>","DOI":"10.3390\/bdcc10030091","type":"journal-article","created":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T11:50:36Z","timestamp":1773921036000},"page":"91","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Data-Driven Cognitive Early Warning for Goaf Spontaneous Combustion: An Edge-Deployed RBF Network with Real-Time Multisensor Analytics"],"prefix":"10.3390","volume":"10","author":[{"given":"Gang","family":"Cheng","sequence":"first","affiliation":[{"name":"Key Laboratory of Green and Efficient Mining and Ecological Restoration in High-Altitude Arid Regions of Xinjiang, Urumqi 830047, China"},{"name":"School of Geology and Mining Engineering, Xinjiang University, Urumqi 830047, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1097-5930","authenticated-orcid":false,"given":"Hailin","family":"Pei","sequence":"additional","affiliation":[{"name":"School of Geology and Mining Engineering, Xinjiang University, Urumqi 830047, China"}]},{"given":"Xiaokang","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Intelligent Manufacturing Modern Industry, Xinjiang University, Urumqi 830047, China"}]},{"given":"Xiaorong","family":"Pang","sequence":"additional","affiliation":[{"name":"School of Geology and Mining Engineering, Xinjiang University, Urumqi 830047, China"}]},{"given":"Renzheng","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Business, Xinjiang University, Urumqi 830047, China"}]}],"member":"1968","published-online":{"date-parts":[[2026,3,19]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Ouyang, Z., Xu, Q., Zhang, T., Yi, H., Zhang, N., Xiao, M., and Ju, C. (2025). Coupling Analysis of Disaster-Causing Factors in Coal Mines and Dual Prevention Mechanism Based on the KeyBERT Model and Accident-Causation Theory Model. Front. Earth Sci., 13.","DOI":"10.3389\/feart.2025.1586785"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1016\/j.psep.2020.02.021","article-title":"LSTM Based Encoder-Decoder for Short-Term Predictions of Gas Concentration Using Multi-Sensor Fusion","volume":"137","author":"Lyu","year":"2020","journal-title":"Process Saf. Environ. Prot."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1461","DOI":"10.1126\/science.adi5639","article-title":"Mechanism for Feature Learning in Neural Networks and Backpropagation-Free Machine Learning Models","volume":"383","author":"Radhakrishnan","year":"2024","journal-title":"Science"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"969","DOI":"10.1007\/s00521-015-2113-7","article-title":"An Overview on Semi-Supervised Support Vector Machine","volume":"28","author":"Ding","year":"2017","journal-title":"Neural Comput. Appl."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Wang, W., Liang, R., Qi, Y., Cui, X., Liu, J., and Xue, K. (2023). Study on the Prediction Model of Coal Spontaneous Combustion Limit Parameters and Its Application. Fire, 6.","DOI":"10.3390\/fire6100381"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"132306","DOI":"10.1016\/j.physd.2019.132306","article-title":"Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) Network","volume":"404","author":"Sherstinsky","year":"2020","journal-title":"Physica D"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"575","DOI":"10.1016\/j.psep.2021.09.034","article-title":"Risk Assessment of Dynamic Disasters in Deep Coal Mines Based on Multi-Source, Multi-Parameter Indexes, and Engineering Application","volume":"155","author":"Du","year":"2021","journal-title":"Process Saf. Environ. Prot."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"64154","DOI":"10.1007\/s11356-023-26958-7","article-title":"Dynamic Assessment and System Dynamics Simulation of Safety Risk in Whole Life Cycle of Coal Mine","volume":"30","author":"Zhu","year":"2023","journal-title":"Environ. Sci. Pollut. Res."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"106727","DOI":"10.1016\/j.ssci.2024.106727","article-title":"Research on Data-Driven Coal Mine Environmental Safety Risk Assessment System","volume":"183","author":"Lu","year":"2025","journal-title":"Saf. Sci."},{"key":"ref_10","first-page":"138","article-title":"Automatic Reasoning Technology for Coal Mine Industrial Data AI Models","volume":"50","author":"Zhang","year":"2024","journal-title":"Ind. Mine Autom."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"2863","DOI":"10.1007\/s11053-025-10508-8","article-title":"Coal Spontaneous Combustion Early Warning Methods Based on Slope Grey Relation Analysis","volume":"34","author":"Huo","year":"2025","journal-title":"Nat. Resour. Res."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"102458","DOI":"10.1016\/j.jnca.2019.102458","article-title":"An Intelligent, Time-Optimized Monitoring Scheme for Edge Nodes","volume":"148","author":"Anagnostopoulos","year":"2019","journal-title":"J. Netw. Comput. Appl."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1545","DOI":"10.1007\/s11276-021-02858-x","article-title":"A Novel Edge Computing Architecture for Intelligent Coal Mining System","volume":"29","author":"Bing","year":"2023","journal-title":"Wirel. Netw."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"22056","DOI":"10.1038\/s41598-025-04652-7","article-title":"Optimizing Lightweight Neural Networks for Efficient Mobile Edge Computing","volume":"15","author":"Liu","year":"2025","journal-title":"Sci. Rep."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"445","DOI":"10.1109\/TCC.2021.3097879","article-title":"Latency-Aware Strategies for Deploying Data Stream Processing Applications on Large Cloud-Edge Infrastructure","volume":"11","author":"Lefevre","year":"2023","journal-title":"IEEE Trans. Cloud Comput."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Ul Mehmood, M., Ulasyar, A., Khattak, A., Imran, K., Zad, H.S., and Nisar, S. (2020). Cloud Based IoT Solution for Fault Detection and Localization in Power Distribution Systems. Energies, 13.","DOI":"10.3390\/en13112686"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1815","DOI":"10.1007\/s10618-014-0395-5","article-title":"Properties of the Sample Estimators Used for Statistical Normalization of Feature Vectors","volume":"29","author":"Prostov","year":"2015","journal-title":"Data Min. Knowl. Discov."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Merenda, M., Porcaro, C., and Iero, D. (2020). Edge Machine Learning for AI-Enabled IoT Devices: A Review. Sensors, 20.","DOI":"10.3390\/s20092533"},{"key":"ref_19","first-page":"139","article-title":"An Improved K-Means Clustering Algorithm for K-Value Selection","volume":"55","author":"Wang","year":"2019","journal-title":"Comput. Eng. Appl."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"569","DOI":"10.1007\/s10208-014-9192-1","article-title":"Random Design Analysis of Ridge Regression","volume":"14","author":"Hsu","year":"2014","journal-title":"Found. Comput. Math."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"101641","DOI":"10.1016\/j.is.2020.101641","article-title":"On the Appropriateness of Platt Scaling in Classifier Calibration","volume":"95","author":"Boeken","year":"2021","journal-title":"Inf. Syst."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1186\/s13040-021-00244-z","article-title":"The Matthews Correlation Coefficient (MCC) Is More Reliable than Balanced Accuracy, Bookmaker Informedness, and Markedness in Two-Class Confusion Matrix Evaluation","volume":"14","author":"Chicco","year":"2021","journal-title":"BioData Min."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"2789","DOI":"10.1162\/NECO_a_00336","article-title":"An Extension of the Receiver Operating Characteristic Curve and AUC-Optimal Classification","volume":"24","author":"Takenouchi","year":"2012","journal-title":"Neural Comput."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"1389","DOI":"10.1002\/qj.4266","article-title":"A Scoring Framework for Tiered Warnings and Multicategorical Forecasts Based on Fixed Risk Measures","volume":"148","author":"Taggart","year":"2022","journal-title":"Q. J. R. Meteorol. Soc."},{"key":"ref_25","unstructured":"(2019). General Technical Conditions of Coal Mine Spontaneous Ignition Beam Monitoring System (Standard No. MT\/T 757-2019)."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"27165","DOI":"10.1021\/acsomega.5c02444","article-title":"CFD Simulation Study on Nitrogen Injection to Suppress Coal Spontaneous Combustion in Goaf under Downward-Ventilation Conditions","volume":"10","author":"Wang","year":"2025","journal-title":"ACS Omega"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Khun-anod, K., Watanabe, T., and Tsuchiya, S. (2025). Understanding the Relationship Between Safety Satisfaction and Total Recordable Incident Rate (TRIR), and Their Relevant Processes Through Self-Determination Theory. Buildings, 15.","DOI":"10.3390\/buildings15081274"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"131350","DOI":"10.1016\/j.energy.2024.131350","article-title":"Numerical Simulation Study on Chemical Ignition Process of Underground Coal Gasification","volume":"298","author":"Zhang","year":"2024","journal-title":"Energy"}],"container-title":["Big Data and Cognitive Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2504-2289\/10\/3\/91\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T12:28:23Z","timestamp":1773923303000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2504-2289\/10\/3\/91"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,19]]},"references-count":28,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,3]]}},"alternative-id":["bdcc10030091"],"URL":"https:\/\/doi.org\/10.3390\/bdcc10030091","relation":{},"ISSN":["2504-2289"],"issn-type":[{"value":"2504-2289","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,19]]}}}