Skip to main content
SpringerLink
Log in

Emergency events detection based on integration of federated learning and active learning

  • Original Research
  • Published:
International Journal of Information Technology Aims and scope Submit manuscript

Abstract

Social media networks now make it easy to access, in real-time, massive amounts of information from all over the world. They are often the primary source of information for billions of people. In addition to other uses, social media platforms can be valuable to provide real-time information about emergency events and can help detect emergency situations. This can provide affected individuals with crucial information about imminent dangers, prompting them to take appropriate action and significantly influencing their decisions. The continuous flow of data generated during these emergencies requires efficient training and modeling. Deep learning can simplify this process and make it less reliant on feature extraction strategies. However, implementing deep learning-based solutions can be expensive and time-consuming due to the vast amounts of data involved. To address these limitations, in this paper, we employed and analyzed the effectiveness of utilizing Active Learning techniques along with Federated Learning for emergency events using a dataset garnered from the social media. After collecting images, we used a Federated Learning paradigm to split the data amongst different clients and used vision transformers as local models for each client. Furthermore, we used an ensemble approach to integrate the results from these strengthened local and global models in a novel way, demonstrating that the proposed setup yields an accuracy of 99%. The Logloss score reached 0.043, indicating the outstanding performance of our approach.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14

Similar content being viewed by others

References

  1. Abhinav A, Shiva K, Zekun X, Oluwaseyi F, Nathanael T (2021) Label inference attacks from log-loss scores. In: International conference on machine learning, PMLR, pp 120–129

  2. Ahmed L, Ahmad K, Said N, Qolomany B, Qadir J, Al-Fuqaha A (2020) Active learning based federated learning for waste and natural disaster image classification. IEEE Access 8:208518–208531

    Article  Google Scholar 

  3. Alfalqi K, Bellaiche M (2022) An emergency event detection ensemble model based on big data. Big Data Cogn Comput 6(2):42

    Article  Google Scholar 

  4. Bommel JR (2021) Active learning during federated learning for object detection. B.S. thesis, University of Twente

  5. Bügel U, Zielinski A (2013) Multilingual analysis of twitter news in support of mass emergency events. Int J Inf Syst Crisis Response Manag (IJISCRAM) 5(1):77–85

    Article  Google Scholar 

  6. Cao J, Yuan X-L, Cui Y, Fan J-C, Chen C-L (2022) A VPN-encrypted traffic identification method based on ensemble learning. Appl Sci 12(13):6434

    Article  Google Scholar 

  7. Chaudhary MT, Piracha A (2021) Natural disasters-origins, impacts, management. Encyclopedia 1(4):1101–1131

    Article  Google Scholar 

  8. Da Y, Ji Z, Zhou Y (2022) Building damage assessment based on Siamese hierarchical transformer framework. Mathematics 10(11):1898

    Article  Google Scholar 

  9. Grandini M, Bagli E, Visani G (2022) Metrics for multi-class classification: an overview. arxiv preprint. 2020: 1–17

  10. Guo Y, Wang C, Yu SX, McKenna F, Law KH (2022) Adaln: a vision transformer for multidomain learning and predisaster building information extraction from images. J Comput Civ Eng 36(5):04022024

    Article  Google Scholar 

  11. Han K, Wang Y, Chen H, Chen X, Guo J, Liu Z, Tang Y, Xiao A, Xu C, Xu Y et al (2022) A survey on vision transformer. IEEE Trans Pattern Anal Mach Intell

  12. Health Services Provider (2020) Emergency and disaster-management. https://healthstandards.org/standard/emergency-and-disaster-management/

  13. Horváth J, Baireddy S, Hao H, Montserrat DM, Delp EJ (2021) Manipulation detection in satellite images using vision transformer. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 1032–1041

  14. Hossain HMS, Al Khan MA, Hafiz R Nirmalya (2017) Active learning enabled activity recognition. Pervasive Mob Comput 38:312–330

    Article  Google Scholar 

  15. Hossin M, Sulaiman MN (2015) A review on evaluation metrics for data classification evaluations. Int J Data Min Knowl Manag Process 5(2):1

    Article  Google Scholar 

  16. Kaur N, Lee C-C, Mostafavi A, Mahdavi-Amiri A (2023) Large-scale building damage assessment using a novel hierarchical transformer architecture on satellite images. Comput Aided Civ Infrastruct Eng

  17. Khalifa NE, Loey M, Mirjalili S (2021) A comprehensive survey of recent trends in deep learning for digital images augmentation. Artif Intell Rev 55:2351–2377

    Article  Google Scholar 

  18. Khanday AMUD, Rabani ST, Khan QR, Rouf N, Din MMU (2020) Machine learning based approaches for detecting COVID-19 using clinical text data. Int J Inf Technol 12:731–739

    Google Scholar 

  19. Kim YJ, Hong CS (2019) Blockchain-based node-aware dynamic weighting methods for improving federated learning performance. In: 2019 20th Asia-Pacific network operations and management symposium (APNOMS), IEEE, pp 1–4

  20. Li X, Qu Z, Tang B, Lu Z (2021) Stragglers are not disaster: a hybrid federated learning algorithm with delayed gradients. arXiv preprint arXiv:2102.06329

  21. Mandavilli VS, Madamala N (2018) Detection of natural disaster affected areas using R. Int J Inf Technol 10:123–131

    Google Scholar 

  22. Martínez-Rojas M, Pardo-Ferreira MDC, Rubio-Romero JC (2018) Twitter as a tool for the management and analysis of emergency situations: a systematic literature review. Int J Inf Manag 43:196–208

    Article  Google Scholar 

  23. McMahan B, Ramage D (2017) Federated learning: collaborative machine learning without centralized training data. https://www.ai.googleblog.com/2017/04/federated-learning-collaborative.html

  24. Miguel J, Caballé S, Xhafa F, Prieto J (2015) A massive data processing approach for effective trustworthiness in online learning groups. Concur Comput Pract Exp 27(8):1988–2003

    Article  Google Scholar 

  25. Mittal V, Jahanian M, Ramakrishnan KK (2021) Flare: federated active learning assisted by naming for responding to emergencies. In: 2021 IEEE 29th international conference on network protocols (ICNP), IEEE, pp 1–2

  26. Priyanshu A, Sinha M, Mehta S (2021) Continual distributed learning for crisis management. arXiv preprint arXiv:2104.12876

  27. Ragini JR, Anand PMR, Bhaskar V (2018) Big data analytics for disaster response and recovery through sentiment analysis. Int J Inf Manag 42:13–24

    Article  Google Scholar 

  28. Said N, Ahmad K, Conci N, Al-Fuqaha A (2021) Active learning for event detection in support of disaster analysis applications. Signal Image Video Process 15(6):1081–1088

    Article  Google Scholar 

  29. Shastri S, Singh K, Kumar S, Kour P, Mansotra V (2021) Deep-LSTM ensemble framework to forecast covid-19: an insight to the global pandemic. Int J Inf Technol 13:1291–1301

    Google Scholar 

  30. Simeon AI, Edim EA, Eteng IE, Ukegbu CC (2021) Design of a flood magnitude prediction model using algorithmic and mathematical approaches. Int J Inf Technol 13(4):1569–1579

    Google Scholar 

  31. Simon T, Goldberg A, Adini B (2015) Socializing in emergencies-a review of the use of social media in emergency situations. Int J Inf Manag 35(5):609–619

    Article  Google Scholar 

  32. Walambe R, Marathe A, Kotecha K (2021) Multiscale object detection from drone imagery using ensemble transfer learning. Drones 5(3):66

    Article  Google Scholar 

  33. Wang L, Yang Y, Li R (2021) Buildformer: automatic building extraction with vision transformer. arXiv preprint arXiv:2111.15637

  34. Wang Z, Brenning A (2021) Active-learning approaches for landslide mapping using support vector machines. Remote Sens 13(13):2588

    Article  Google Scholar 

  35. Xia Z, Li Z, Bai Y, Yu J, Adriano B (2022) Self-supervised learning for building damage assessment from large-scale XBD satellite imagery benchmark datasets. arXiv preprint arXiv:2205.15688

  36. Xu Z, Liu Y, Yen NY, Mei L, Luo X, Wei X, Hu C (2016) Crowdsourcing based description of urban emergency events using social media big data. IEEE Trans Cloud Comput 8(2):387–397

    Article  Google Scholar 

  37. Xiang Yu, Wang J, Hong Q-Q, Teku R, Wang S-H, Zhang Y-D (2022) Transfer learning for medical images analyses: a survey. Neurocomputing 489:230–254

    Article  Google Scholar 

  38. Zhan X, Wang Q, Huang K-H, Xiong H, Dou D, Chan AB (2022) A comparative survey of deep active learning. arXiv preprint arXiv:2203.13450

  39. Zhang C, Yu X, Bai H, Yu B, Li W, Gao Y (2021) A survey on federated learning. Knowl Based Syst 216:106775

    Article  Google Scholar 

  40. Zhang Z, He N, Li D, Gao H, Gao T, Zhou C (2022) Federated transfer learning for disaster classification in social computing networks. J Saf Sci Resil 3(1):15–23

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Computer and Software Engineering Department, Ecole Polytechnique, Montreal, Canada

    Khalid Alfalqi & Martine Bellaiche

Authors
  1. Khalid Alfalqi
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Martine Bellaiche
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Martine Bellaiche.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Alfalqi, K., Bellaiche, M. Emergency events detection based on integration of federated learning and active learning. Int. j. inf. tecnol. 15, 2863–2876 (2023). https://doi.org/10.1007/s41870-023-01307-6

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s41870-023-01307-6

Keywords

Search

Navigation