ENHANCING DISASTER EARLY WARNING CAPABILITIES VIA EDGE-BASED MULTIMODAL VISION SYSTEMS: A CASE STUDY IN TUYEN QUANG

Các tác giả

  • PHAN VAN NAM
  • DO HUU SON

DOI:

https://doi.org/10.51453/3093-3706/2026/1475

Tóm tắt

Frequent extreme disasters in Tuyen Quang (e.g., 2025 Yen Son fires and Lo River floods) highlight the limitations of current systems: meteorological forecasts lack visual verification, and traditional cameras fail during bandwidth disruptions. To address this, we propose an independent edge-based early warning solution using small Vision-Language Models (sVLM) and grammar-based constrained decoding to analyze on-site imagery. Instead of free-form text, the model directly infers hazard levels into strict JSON schemas. Experiments on local hardware achieved 100% structural message integrity and 100% anomaly detection accuracy. The optimal model operates at 59.50 TPS with an end-to-end latency of just 0.1487 seconds, capping peak VRAM at 1.66 GB. By replacing continuous video streaming with verified JSON alerts, this method eliminates false alarms and optimizes bandwidth by 99.9880%, proving the viability of standalone smart monitoring stations for rapid evacuation during infrastructure blackouts.

Tải xuống

Dữ liệu tải xuống chưa có sẵn.

Tài liệu tham khảo

1 IPCC, “Climate Change 2023: Impacts, Adaptation and Vulnerability in Southeast Asia. Intergovernmental Panel on Climate Change.,” IPCC, 2023.

2. Nhan Dan Newspaper, “nhandan.vn,” 2025. [Online]. Available: https://nhandan.vn/tuyen-quang-da-dap-tat-hoan-toan-dam-chay-rung-tai-nui-nghiem-post866914.html.

3. Tuyen Quang Provincial People's Committee, “Summary report on natural disaster prevention and search and rescue in Tuyen Quang province in 2025”, Commanding Committee for Natural Disaster Prevention and Search and Rescue of Tuyen Quang province, 2025.

4. Thuy Duong, “Environment and Life e-Magazine,” 2025. [Online]. Available: https://moitruong.net.vn/tuyen-quang-muc-nuoc-song-lo-song-gam-dang-cao-anh-huong-den-nguoi-dan-86276.html.

5. Yuyi Mao, Changsheng You, Jun Zhang, Kaibin Huang, Khaled B. Letaief, “A Survey on Mobile Edge Computing: The Communication Perspective,” IEEE Communications Surveys & Tutorials, 2017.

6. Partha Pratim Ray, Mithun Mukherjee, Lei Shu, “Internet of Things for Disaster Management: State-of-the-Art and Prospects,” IEEE Access, 2017.

7. Dinh C. Nguyen, Ming Ding, Pubudu N. Pathirana, Aruna Seneviratne, Jun Li, Dusit Niyato, “6G Internet of Things: A Comprehensive Survey,” IEEE Internet of Things Journal, 2021.

8. Junaid Qadir, Anwaar Ali, Raihan ur Rasool, Andrej Zwitter, Arjuna Sathiaseelan & Jon Crowcroft, “Crisis analytics: big data-driven crisis response,” SPRINGER NATURE: Journal of International Humanitarian Action, 2016.

9. Elizabeth A. Basha, Sai Ravela, Daniela Rus, “Model-based monitoring for early warning flood detection,” Proceedings of the 6th ACM conference on Embedded network sensor systems, 2008.

10. Alkhatib, Ahmad, “A Review on Forest Fire Detection Techniques,” International Journal of Distributed Sensor Networks, 2014.

11. I.F. Akyildiz, W. Su, Y. Sankarasubramaniam, E. Cayirci, “Wireless sensor networks: a survey,” Computer Networks, 2002.

12. Jean-Baptiste Alayrac, Jeff Donahue, Pauline Luc, Antoine Miech, Iain Barr, Yana Hasson, Karel Lenc, Arthur Mensch, Katie Millican, Malcolm Reynolds, Roman Ring, Eliza Rutherford, Serkan Cabi, Tengda Han, Zhitao Gong, Sina Samangooei et al, “Flamingo: a Visual Language Model for Few-Shot Learning,” Proceedings of Neural Information Processing Systems (NeurIPS), 2022.

13. Yuqing Tian, Zhaoyang Zhang,, “An Edge-Cloud Collaboration Framework for Generative AI Service Provision with Synergetic Big Cloud Model and Small Edge Models,” ARXIV, 2024.

14. Haotian Liu, Chunyuan Li, Qingyang Wu, Yong Jae Lee, “Visual Instruction Tuning,” NeurIPS, 2023.

15. Jinze Bai, Shuai Bai, Shusheng Yang, Shijie Wang, Sinan Tan, Peng Wang, Junyang Lin, Chang Zhou, Jingren Zhou, “Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond,” Computer Vision and Pattern Recognition, 2023.

16. Xiangxiang Chu, Limeng Qiao, Xinyang Lin, Shuang Xu, Yang Yang, Yiming Hu, Fei Wei, Xinyu Zhang, Bo Zhang, Xiaolin Wei, Chunhua Shen, “MobileVLM : A Fast, Strong and Open Vision Language Assistant for Mobile Devices,” Arxiv, 2023.

17. Cuenca, P., Wolf, T., & Tunstall, L, “SmolVLM: Small yet powerful vision-language model for edge devices. Hugging Face Technical Report.,” Hugging Face Technical Report, 2024.

18. Khang T. Doan, Bao G. Huynh, Dung T. Hoang, Thuc D. Pham, Nhat H. Pham, Quan T.M. Nguyen, Bang Q. Vo, Suong N. Hoang, “Vintern-1B: An Efficient Multimodal Large Language Model for Vietnamese,” Proceedings of the 18th IEEE International Conference on Computing and Communication Technologies (RIVF), 2024.

19. Ziwei Ji, Nayeon Lee, Rita Frieske, Tiezheng Yu, Dan Su, Yan Xu, Etsuko Ishii, Yejin Bang, Delong Chen, Wenliang Dai, Ho Shu Chan, Andrea Madotto, Pascale Fung, “Survey of Hallucination in Natural Language Generation,” ACM Computing Surveys, 2022.

20. Torsten Scholak, Nathan Schucher, Dzmitry Bahdanau, “PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models,” EMNLP, 2021.

21. Brandon T. Willard, Rémi Louf, “Efficient Guided Generation for Large Language Models,” Arxiv: Computation and Language, 2023.

22. Luca Beurer-Kellner, Marc Fischer, Martin Vechev, “Prompting Is Programming: A Query Language for Large Language Models,” PLDI'23: 44th ACM SIGPLAN International Conference on Programming Language Design and Implementation, p. 2022, 2022.

23. Weisong Shi, Jie Cao, Quan Zhang, Youhuizi Li, Lanyu Xu, “Edge Computing: Vision and Challenges,” IEEE Internet of Things Journal, 2016.

24. Jiasi Chen, Xukan Ran, “Deep Learning With Edge Computing: A Review,” Proceedings of the IEEE, 2019.

25. Munish Bhatia, Tariq Ahamed Ahanger, “Internet of things‐fog computing‐based framework for smart disaster management,” Transactions on Emerging Telecommunications Technologies, 2020.

26. Shri Janani Muruganantham, N. Ramasubramanian, B. Shameedha Begum, “Resilient Edge-IoT Architectures by Optimizing Energy, Security and Adaptability : A Review,” 2025 IEEE 9th International Conference on Information and Communication Technology (CICT), 2025.

27. Kechar Bouabdellah, Houache Noureddine, Sekhri Larbi, “Using Wireless Sensor Networks for Reliable Forest Fires Detection☆,” Procedia Computer Science, 2013.

28. Ramesh, Maneesha Vinodini, “Design, development, and deployment of a wireless sensor network for detection of landslides,” Ad Hoc Networks, 2014.

29. Khan Muhammad, Jamil Ahmad, Sung Wook Baik, “Early fire detection using convolutional neural networks during surveillance for effective disaster management,” Neurocomputing, 2018.

30. Saima Majid, Fayadh Alenezi, Sarfaraz Masood, Musheer Ahmad, Emine Selda Gündüz, Kemal Polat, “Attention based CNN model for fire detection and localization in real-world images,” Applied Soft Computing, 2022.

31. Shukang Yin, Chaoyou Fu, Sirui Zhao, Ke Li, Xing Sun, Tong Xu, Enhong Chen, “A Survey on Multimodal Large Language Models,” Arxiv, 2024.

32. Olakunle Elijah, Tharek Abdul Rahman, Igbafe Orikumhi, Chee Yen Leow, MHD Nour Hindia, “An Overview of Internet of Things (IoT) and Data Analytics in Agriculture: Benefits and Challenges,” IEEE Internet of Things Journal, 2018.

33. Vestias, Mario P., “A Survey of Convolutional Neural Networks on Edge with Reconfigurable Computing,” MDPI, 2019.

34. Ramon Sanchez-Iborra, Jesus Sanchez-Gomez, Juan Ballesta-Vinas, Maria-Dolores Cano, Antonio F. Skarmeta, “Performance Evaluation of LoRa Considering Scenario Conditions,” MDPI, 2018.

35. Kais Mekki, Eddy Bajic, Frederic Chaxel, Fernand Meyer, “A comparative study of LPWAN technologies for large-scale IoT deployment,” ICT Express, 2019.

36. Datatracker, “https://datatracker.ietf.org/,” 2017. [Online]. Available:

https://datatracker.ietf.org/doc/html/rfc8259.

37. Naik, Nitin, “Choice of effective messaging protocols for IoT systems: MQTT, CoAP, AMQP and HTTP,” 2017 IEEE International Systems Engineering Symposium (ISSE), 2017.

38. Elias Frantar, Saleh Ashkboos, Torsten Hoefler, Dan Alistarh, “GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers,” Arxiv: Machine Learning, 2023.

39. Ji Lin, Jiaming Tang, Haotian Tang, Shang Yang, Wei-Ming Chen, Wei-Chen Wang, Guangxuan Xiao, Xingyu Dang, Chuang Gan, Song Han, “AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration,” Proceedings of Machine Learning and Systems, 2023.

40. Reiner Pope, Sholto Douglas, Aakanksha Chowdhery, Jacob Devlin, James Bradbury, Anselm Levskaya, Jonathan Heek, Kefan Xiao, Shivani Agrawal, Jeff Dean, “Efficiently Scaling Transformer Inference,” Proceedings of Machine Learning and Systems, 2023.

41. Chaoyou Fu, Yuhan Dai, Yongdong Luo, Lei Li, Shuhuai Ren, Renrui Zhang, Zihan Wang, Chenyu Zhou, Yunhang Shen, Mengdan Zhang, Peixian Chen, Yanwei Li, Shaohui Lin, Sirui Zhao, Ke Li, Tong Xu, Xiawu Zheng, Enhong Chen, Caifeng Shan, Ran He, Xing Sun, “Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis,” Computer Vision and Pattern Recognition, 2024.

42. Xiang Yue, Yuansheng Ni, Kai Zhang, Tianyu Zheng, Ruoqi Liu, Ge Zhang, Samuel Stevens, Dongfu Jiang, Weiming Ren, Yuxuan Sun, Cong Wei, Botao Yu, Ruibin Yuan, Renliang Sun, Ming Yin, Boyuan Zheng, Zhenzhu Yang, Yibo Liu, Wenhao Huang, Huan Sun et al, “MMMU: A massive multi-discipline multimodal understanding and reasoning benchmark for expert AGI.,” CVPR 2024 Oral, 2024.

43. Alireza Shamsoshoara, Fatemeh Afghah, Abolfazl Razi, Liming Zheng, Peter Fule, Erik Blasch, “The FLAME dataset: Aerial Imagery Pile burn detection using drones (UAVs),” IEEE, 2020.

44. Khanh Hoa Television, “ktvkhanhhoa,” 2025. [Online]. Available:

https://www.tiktok.com/@ktvkhanhhoa/video/7579831016852884737?_r=1&_t=ZS-96WwvpbwjSr.

Tải xuống

Đã Xuất bản

2026-07-06

Cách trích dẫn

PHAN VAN NAM, & DO HUU SON. (2026). ENHANCING DISASTER EARLY WARNING CAPABILITIES VIA EDGE-BASED MULTIMODAL VISION SYSTEMS: A CASE STUDY IN TUYEN QUANG. SCIENTIFIC JOURNAL OF TAN TRAO UNIVERSITY, 12(2). https://doi.org/10.51453/3093-3706/2026/1475