From Federated Learning to Real-Time Pneumonia Prediction: Deploying an AdaptiveMesh-Based Global Model on Resource-Constrained Devices

Lamir Shkurti; Arsim Susuri; Vehebi Sofiu; Besnik Qehaja

doi:10.3991/ijim.v20i06.59653

Authors

Lamir Shkurti UBT Higher Education Institution, Prishtina, Kosovo https://orcid.org/0009-0002-1074-0398
Arsim Susuri University “Ukshin Hoti”, Prizren, Kosovo https://orcid.org/0000-0002-4434-5233
Vehebi Sofiu UBT Higher Education Institution, Prishtina, Kosovo
Besnik Qehaja UBT Higher Education Institution, Prishtina, Kosovo https://orcid.org/0000-0002-7775-0104

DOI:

https://doi.org/10.3991/ijim.v20i06.59653

Keywords:

adaptive federated learning, wireless mesh networks, edge AI deployment, medical image classification, , resource-constrained devices

Abstract

Federated learning (FL) enhances data privacy but faces significant deployment challenges on resource-constrained edge devices. Building on our previous development of the AdaptiveMesh algorithm, this study presents an end-to-end implementation of a resourceaware FL framework for pneumonia detection from chest X-ray images. The system is optimized for heterogeneous hardware and unstable network conditions. Validated on two independent datasets, the proposed global model achieved high diagnostic reliability, reaching up to 95% accuracy and critical recall performance for clinical use. A key contribution of this work is the practical transition from decentralized training to real-time prediction; we integrated the trained model into a lightweight Flask-based web application deployed on devices such as Raspberry Pi 4 and Intel Atom MiniPCs. Our results confirm that the AdaptiveMesh-based system provides a stable, privacy-preserving, and feasible solution for medical diagnostics in low-resource environments, bridging the gap between algorithmic optimization and real-world application.

References

[1] Shkurti, L., Selimi, M., Besimi, A.: Federatedmesh: Collaborative federated learn- ing for medical data sharing in mesh networks. In: Gao, H., Wang, X., Voros, N. (eds.) Collaborative Computing: Networking, Applications and Worksharing, pp. 154–169. Springer, Cham (2024)

[2] Shkurti, L., Selimi, M.: Baca: Bandwidth and cpu-aware adaptive federated learning for wireless environments. In: 2024 13th Mediterranean Conference on Embedded Computing (MECO), pp. 1–5 (2024). https://doi.org/10.1109/ MECO62516.2024.10577810

[3] Shkurti, L., Selimi, M.: Adaptivemesh: Adaptive federate learning for resource- constrained wireless environments. International Journal of Online and Biomedi- cal Engineering (iJOE) 20(14), 22–37 (2024) https://doi.org/10.3991/ijoe.v20i14.50559

[4] Shkurti, L., Selimi, M.: Enhancing adaptive behavior in federated learning: The adaptivemesh algorithm for interactive mobile and bandwidth-limited resource- constrained wireless environments. International Journal of Interactive Mobile Technologies (iJIM) 19(10), 32–55 (2025) https://doi.org/10.3991/ijim.v19i10.54067

[5] Tawsifur Rahman, A.K. Muhammad Chowdhury: COVID-19 Radio- graphy Database. https://www.kaggle.com/datasets/tawsifurrahman/covid19-radiography-database (2022)

[6] Cohen, J.P., Morrison, P., Dao, L.: COVID-19 image data collection. https:// github.com/ieee8023/covid-chestxray-dataset (2020)

[7] Chollet, F., et al.: Keras. https://keras.io, (2015)

[8] Tan, M., Le, Q.V.: Efficientnet: Rethinking model scaling for convolutional neural networks. In: International Conference on Machine Learning (ICML) (2020)

[9] Rana, N., Marwaha, H.: Pneumonia detection from x-ray images using federated learning–an unsupervised learning approach. Measurement: Sensors 37, 101410 (2025) https://doi.org/10.1016/j.measen.2024.101410

[10] Siddique, A.A., Talha, S.M.U., Aamir, M., Algarni, A.D., Soliman, N.F., El- Shafai, W.: Covid-19 classification from x-ray images: An approach to implement federated learning on decentralized dataset. Computers, Materials and Continua 75(2), 3883–3901 (2023) https://doi.org/10.32604/cmc.2023.037413

[11] Kumar, C.H., Jangam, E., Kumar, C.H., Philip Paul Arunodhayam, T.: Horizon- tal federated learning for advancing pneumonia detection with distributed medical imaging data. In: 2025 6th International Conference on Recent Advances in Infor- mation Technology (RAIT), pp. 1–8 (2025). https://doi.org/10.1109/RAIT65068. 2025.11088951

[12] Hoang, T.-H., Fuhrman, J., Klarqvist, M., Li, M., Chaturvedi, P., Li, Z., Kim, K., Ryu, M., Chard, R., Huerta, E.A., Giger, M., Madduri, R.: Enabling end-to- end secure federated learning in biomedical research on heterogeneous computing environments with appflx. Computational and Structural Biotechnology Journal 28, 29–39 (2025) https://doi.org/10.1016/j.csbj.2024.12.001

[13] Roy, A., Mahanta, D.R., Mahanta, L.B.: A semi-synchronous federated learn- ing framework with chaos-based encryption for enhanced security in medical image sharing. Results in Engineering 25, 103886 (2025) https://doi.org/10.1016/ j.rineng.2024.103886

[14] S´ainz-Pardo D´ıaz, J., L´opez Garc´ıa: Study of the performance and scalability of federated learning for medical imaging with intermittent clients. Neurocomputing 518, 142–154 (2023) https://doi.org/10.1016/j.neucom.2022.11.011

[15] Nawrin Tabassum, Mustofa Ahmed, Nushrat Jahan Shorna, MD Mejbah Ur Rahman Sowad, and H M Zabir Haque, “Depression Detection Through Smartphone Sensing: A Federated Learning Approach”, Int. J. Interact. Mob. Technol., vol. 17, no. 01, pp. pp. 40–56, Jan. 2023.

[16] B. Ankayarkanni, Niroj Kumar Pani, M. Anand, V. Malathy, and Bhupati, “P2FLF: Privacy-Preserving Federated Learning Framework Based on Mobile Fog Computing”, Int. J. Interact. Mob. Technol., vol. 17, no. 17, pp. pp. 72–81, Sep. 2023.

[17] Sun, W., Wu, D., Shen, J., Luo, Y., Wang, H., Min, L., Luo, C.: A deep learning method for pneumoconiosis staging on chest x-ray under label noise. IEEE Access 13, 134031–134040 (2025) https://doi.org/10.1109/ACCESS.2025.3590783

[18] Patel, A.N., Murugan, R., Srivastava, G., Maddikunta, P.K.R., Yenduri, G., Gadekallu, T.R., Chengoden, R.: An explainable transfer learning framework for multi-classification of lung diseases in chest x-rays. Alexandria Engineering Journal 98, 328–343 (2024) https://doi.org/10.1016/j.aej.2024.04.072

[19] Hu, T., Khishe, M., Mohammadi, M., Parvizi, G.-R., Taher Karim, S.H., Rashid, T.A.: Real-time covid-19 diagnosis from x-ray images using deep cnn and extreme learning machines stabilized by chimp optimization algorithm. Biomedical Signal Processing and Control 68, 102764 (2021) https://doi.org/10.1016/j.bspc.2021.102764

[20] Qayyum, A., Ahmad, K., Ahsan, M.A., Al-Fuqaha, A., Qadir, J.: Collaborative federated learning for healthcare: Multi-modal covid-19 diagnosis at the edge. IEEE Open Journal of the Computer Society 3, 172–184 (2022) https://doi.org/ 10.1109/OJCS.2022.3206407

[21] Kareem, A., Liu, H., Velisavljevic, V.: A federated learning framework for pneu- monia image detection using distributed data. Healthcare Analytics 4, 100204 (2023) https://doi.org/10.1016/j.health.2023.100204

[22] Mohammed, M.A., Lakhan, A., Abdulkareem, K.H., Deveci, M., Dutta, A.K., Memon, S., Marhoon, H.A., Martinek, R.: Federated-reinforcement learning- assisted iot consumers system for kidney disease images. IEEE Transactions on Consumer Electronics 70(4), 7163–7173 (2024) https://doi.org/10.1109/TCE.2024.3384455

[23] Kermany, D.S., Goldbaum, M., Cai, W., Valentim, C.C.S., Liang, H., Baxter, S.L., McKeown, A., Yang, G., Wu, X., Yan, F., Dong, J., Prasadha, M.K., Pei, J., Ting, M.Y.L., Zhu, J., Li, C., Hewett, S., Dong, J., Ziyar, I., Shi, A., Zhang, R., Zheng, L., Hou, R., Shi, W., Fu, X., Duan, Y., Huu, V.A.N., Wen, C., Zhang, E.D., Zhang, C.L., Li, O., Wang, X., Singer, M.A., Sun, X., Xu, J., Tafreshi, A., Lewis, M.A., Xia, H., Zhang, K.: Identifying medical diagnoses and treatable diseases by image-based deep learning. Cell 172(5), 1122–11319 (2018) https://doi.org/10.1016/j.cell.2018.02.010