An LSTM-GNN-Based Early Warning System for Laboratory Biosafety Using BIM and IoT-Driven Multi-Source Data Fusion
Abstract
To address the challenges of traditional laboratory biosafety monitoring (e.g., data lag, single-dimensionality, rigid early warning), this paper designs an integrated system combining "BIM + IoT + LSTM-GNN Intelligent Algorithm" with a four-layer "Perception-Transmission-Platform-Application" architecture. Hardware includes the SHT35 temperature and humidity sensor (±0.1°C/±2% RH), BV6000 pathogen sensor (0.01 CFU/mL lower limit), and UWB positioning tags (0.3–1m accuracy). Software adopts a MySQL+Redis database, and a dynamic early warning algorithm integrating an improved attention mechanism, LSTM (for temporal feature extraction), and GNN (for spatial correlation mining) is proposed. Experiments were conducted on 15,000 datasets (covering 10 scenarios) with three control systems: traditional threshold system, single LSTM system, and IoT static monitoring system. Key results include: (1) Temperature-humidity error rates: 0.5% (normal scenarios), 0.7% (mild abnormal), 0.8% (severe abnormal); (2) Response time: 0.3s for 10,000 datasets; (3) Early warning accuracy: 98.5% (false positive rate 1.2%, false negative rate 0.3%); (4) 72-hour data transmission success rate: 99.9%. SPSS significance analysis (p<0.01) confirms the system outperforms control solutions, fully meeting laboratories’ dynamic safety management needs.
Full Text:
PDFReferences
Sari, I. P., Khairani, L., & Ginting, R. (2023). Enhancing Disaster Resilience: Evaluating the Implementation of an Early Warning System through Tabletop Exercises. PERSPEKTIF, 12(4), 1253-1260. DOI: 10.31289/perspektif.v12i4.10341
Hossain, M. M., Ahmed, S., Anam, S. A., Baxramovna, I. A., Meem, T. I., Sobuz, M. H. R., & Haq, I. (2025). A BIM-based smart safety monitoring system using a mobile app is a case study in an ongoing construction site. Construction Innovation, 25(2), 552-576.https://doi.org/10.1108/CI-11-2022-0296
Judijanto, L., Hindarto, D., Wahjono, S. I., & Djunarto, A. (2023). Edge of enterprise architecture in addressing cybersecurity threats and business risks. International Journal Software Engineering and Computer Science (IJSECS), 3(3), 386-396. https://doi.org/10.35870/ijsecs.v3i3.1816.
Žvirblis, T., Pikšrys, A., Bzinkowski, D., Rucki, M., Kilikevičius, A., & Kurasova, O. (2024). Data Augmentation for Classification of Multi-Domain Tension Signals. Informatica, 35(4), 883-908. doi:10.15388/24-INFOR578
Lyu, N., Jin, Y., Xiong, R., Miao, S., & Gao, J. (2021). Real-time overcharge warning and early thermal runaway prediction of Li-ion battery by online impedance measurement. IEEE transactions on industrial electronics, 69(2), 1929-1936.doi: 10.1109/TIE.2021.3062267
Rezaee, K., Rezakhani, S. M., Khosravi, M. R., & Moghimi, M. K. (2024). A survey on deep learning-based real-time crowd anomaly detection for secure distributed video surveillance. Personal and Ubiquitous Computing, 28(1), 135-151. https://doi.org/10.1007/s00779-021-01586-5
Van Poppel, H., Hogenhout, R., Albers, P., van den Bergh, R. C., Barentsz, J. O., & Roobol, M. J. (2021). A European model for an organised risk-stratified early detection programme for prostate cancer. European urology oncology, 4(5), 731-739. https://doi.org/10.1016/j.euo.2021.06.006
Möller, T., da Silva Burke, T. S., Xu, X., Della Ragione, G., Bilotta, E., & Abadie, C. N. (2023). Distributed fibre optic sensing for sinkhole early warning: experimental study. Géotechnique, 73(8), 701-715. https://doi.org/10.1680/jgeot.21.00154
Casagli, N., Intrieri, E., Tofani, V., Gigli, G., & Raspini, F. (2023). Landslide detection, monitoring and prediction with remote-sensing techniques. Nature Reviews Earth & Environment, 4(1), 51-64. https://doi.org/10.1038/s43017-022-00373-x
Ju, Z., Zhang, H., Li, X., Chen, X., Han, J., & Yang, M. (2022). A survey on attack detection and resilience for connected and automated vehicles: From vehicle dynamics and control perspective. IEEE Transactions on Intelligent Vehicles, 7(4), 815-837. DOI: 10.1109/TIV.2022.3186897
Yi, Z., Chen, Z., Yin, K., Wang, L., & Wang, K. (2023). Sensing as the key to the safety and sustainability of new energy storage devices. Protection and Control of Modern Power Systems, 8(2), 1-22. DOI: 10.1186/s41601-023-00300-2
Wang, Y., Su, Z., Guo, S., Dai, M., Luan, T. H., & Liu, Y. (2023). A survey on digital twins: Architecture, enabling technologies, security and privacy, and future prospects. IEEE Internet of Things Journal, 10(17), 14965-14987. DOI: 10.1109/JIOT.2023.3263909
Jiang, W., Ding, L., & Zhou, C. (2021). Cyber physical system for safety management in smart construction site. Engineering, Construction and Architectural Management, 28(3), 788-808. https://doi.org/10.1108/ECAM-10-2019-0578
Debroy, P., Smarandache, F., Majumder, P., Majumdar, P., & Seban, L. (2025). OPA-IF-Neutrosophic-TOPSIS Strategy under SVNS Environment Approach and Its Application to Select the Most Effective Control Strategy for Aquaponic System. Informatica, 36(1), 1-32. doi:10.15388/24-INFOR583
Hatefi, M. A. (2025). New Aggregation Multiple Attribute Methods Based on Indifference Threshold and Yearning Threshold Concepts. Informatica, 36(2), 337-367. doi:10.15388/24-INFOR580
Zhang, Y. M., Wang, H., Bai, Y., Mao, J. X., & Xu, Y. C. (2022). Bayesian dynamic regression for reconstructing missing data in structural health monitoring. Structural Health Monitoring, 21(5), 2097-2115. https://doi.org/10.1177/14759217211053779
Liu, R. W., Liang, M., Nie, J., Lim, W. Y. B., Zhang, Y., & Guizani, M. (2022). Deep learning-powered vessel trajectory prediction for improving smart traffic services in maritime Internet of Things. IEEE Transactions on Network Science and Engineering, 9(5), 3080-3094. DOI: 10.1109/TNSE.2022.3140529
Wang, X., Bouzembrak, Y., Lansink, A. O., & Van Der Fels‐Klerx, H. J. (2022). Application of machine learning to the monitoring and prediction of food safety: A review. Comprehensive reviews in food science and food safety, 21(1), 416-434. https://doi.org/10.1111/1541-4337.12868
Imran, C. A. B., Shakir, M. K., Umer, M., & Imran, Z. (2023). ASSESSING ROAD SAFETY AT INTERSECTIONS USING COMPUTER VISION AND CRASH DATA ANALYTICS. Spectrum of Engineering Sciences, 1(2), 62-69. https://doi.org/10.5281/zenodo.15876666
Raghuwanshi, P. (2024). Ai-driven identity and financial fraud detection for national security. Journal of Artificial Intelligence General Science (JAIGS) ISSN: 3006-4023, 7(01), 38-51. https://doi.org/10.60087/jaigs.v7i01.294
DOI: https://doi.org/10.31449/inf.v49i32.11449
This work is licensed under a Creative Commons Attribution 3.0 License.