Abstract
Mobility robots for elderly care not only satisfy the basic needs of disabled seniors but also help ensure their safety. Safety monitoring is particularly critical when disabled seniors remain alone indoors. This research focuses on detecting flame and smoke targets in indoor environments, enabling faster decision-making during fires, facilitating timely evacuation for disabled seniors, and thereby providing improved protection. This study aims to enhance detection accuracy and algorithm performance by introducing the improved YOLO11-BSCS model. The Biformer two-layer routing attention mechanism is incorporated into the Backbone and Neck of YOLO11s, replacing the original C2SPA module with C2SPA_Biformer to enable dynamic, query-aware sparse attention, reduce the number of model parameters, and improve the detection of dynamic targets. The SCConv convolution replaces the C3k2 convolution module in the original model with the C3k2_SCConv module, reducing spatial and channel redundancy during the fusion of image features extracted by the model and increasing detection speed. The loss function of the model was optimized by replacing CIoU-Loss with the SIoU-Loss module. This modification improves both convergence speed and detection accuracy. Through 600 rounds of experimental testing on 5,000 data samples, supplemented by three independent training runs using random seeds (107,325,592) for evaluation, YOLO11-BSCS achieved 94.612% accuracy, 89.678% recall, and 90.319% average precision—representing improvements of 4.934, 7.452, and 5.184%, respectively, over YOLO11s. Comparative analysis with widely used models indicates that YOLO11-BSCS provides strong generalizability, precise localization, robust detection, and overall superior performance. The necessity of each model enhancement was validated through ablation experiments, confirming that all modifications contributed meaningfully to performance improvements. These findings provide a valuable reference for addressing similar challenges in object detection.
Data availability
Data will be made available on request.
References
Wang, L., Liang, J. & Wang, B. Population aging and sustainable economic development: An analysis based on the role of green finance. Financ Res. Lett. 70, 106239. https://doi.org/10.1016/j.frl.2024.106239 (2024).
Kyrychenko, A., Khanyukova, I., Moroz, O., Sirenko, O. & Kuryata, O. Disability trends among elderly Ukrainians in war conditions: a 10-year retrospective study. Aging Clin. Exp. Res. 36, 211. https://doi.org/10.1007/s40520-024-02863-y (2024).
Perello, N. et al. An adaptable dead fuel moisture model for various fuel types and temporal scales tailored for wildfire danger assessment. Environ. Model. Softw. 183, 106254. https://doi.org/10.1016/j.envsoft.2024.106254 (2025).
Zhao, Q. & Liu, Y. Design of apple recognition model based on improved deep learning object detection framework Faster-RCNN. Adv. Contin Discrete Model. 2024, 49. https://doi.org/10.1186/s13662-024-03835-2 (2024).
Yu, C. et al. YOLO-MRS: An efficient deep learning-based maritime object detection method for unmanned surface vehicles. Appl. Ocean. Res. 153, 104240. https://doi.org/10.1016/j.apor.2024.104240 (2024).
Akhtar, M. M. et al. AOHDL: Adversarial optimized hybrid deep learning design for preventing attack in radar target detection. Remote Sens. 16, 3109. https://doi.org/10.3390/rs16163109 (2024).
Guo, S. et al. SDS-YOLOv8n: A lightweight detection method for flames and smoke. J. Phys. Conf. Ser. 2858, 012020. https://doi.org/10.1088/1742-6596/2858/1/012020 (2024).
Gao, Y., Yang, Q., Meng, H. & Gao, D. Application of a real-time flame smoke detection algorithm based on improved YOLOv7. J. Intell. Fuzzy Syst. 46, 851–861. https://doi.org/10.3233/JIFS-232650 (2024).
Yang, Y., Hu, S., Ke, Y. & Zhou, R. Flame smoke detection algorithm based on YOLOv5 in petrochemical plant. Int. J. Intell. Comput. Cybern. 16, 502–519. https://doi.org/10.1108/IJICC-11-2022-0291 (2023).
Hosseini, A., Hashemzadeh, M. & Farajzadeh, N. UFS-Net: A unified flame and smoke detection method for early detection of fire in video surveillance applications using CNNs. J. Comput. Sci. 61, 101638. https://doi.org/10.1016/j.jocs.2022.101638 (2022).
Chua, L. O. CNN: A vision of complexity. Int. J. Bifurc Chaos. 7, 2219–2425. https://doi.org/10.1142/S0218127497001618 (1997).
Zhu, L., Wang, X., Ke, Z., Zhang, W. & Lau, R. W. H. Biformer: Vision transformer with bi-level routing attention. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 10323–10333. https://doi.org/10.1109/CVPR52729.2023.00995 (2023).
Li, J., Wen, Y. & He, L. Scconv: Spatial and channel reconstruction convolution for feature redundancy. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 6153–6162. https://doi.org/10.1109/CVPR52729.2023.00596 (2023).
Wu, Y. & He, K. Group normalization. In: Proceedings of the European Conference on Vomputer Vision (ECCV). 3–19. https://doi.org/10.1007/978-3-030-01261-8_1 (2018).
Pan, J. et al. ASAPP-ASR: Multistream CNN and self-attentive SRU for SOTA speech recognition. https://doi.org/10.48550/arXiv.2005.10469 (2020).
Chen, C-F., Oh, J., Fan, Q. & Pistoia, M. SC-Conv: Sparse-complementary convolution for efficient model utilization on CNNs. In: 2018 IEEE International Symposium on Multimedia (ISM). 97–100. https://doi.org/10.1109/ISM.2018.00024 (IEEE, 2018).
Wang, Y. & Wang, S. Skin lesion segmentation with attention-based SC-Conv U-Net and feature map distortion. Signal. Image Video Process. 16, 1471–1479. https://doi.org/10.1007/s11760-021-02100-3 (2022).
Wang, W. et al. Scd-Net: An efficient detection network for pcb defects based on spatial and channel reconstruction convolution and deformable convolutions. Available at SSRN: https://doi.org/10.2139/ssrn.4897923.
Harris, I., Jones, P. D., Osborn, T. J. & Lister, D. H. Updated high-resolution grids of monthly climatic observations–the CRU TS3. 10 Dataset. Int. J. Climatol. 34, 623–642. https://doi.org/10.1002/joc.3711 (2014).
Gevorgyan, Z. SIoU loss: More powerful learning for bounding box regression. https://doi.org/10.48550/arXiv.2205.12740 (2022).
Du, S., Zhang, B. & Zhang, P. Scale-sensitive IOU loss: An improved regression loss function in remote sensing object detection. IEEE Access. 9, 141258–141272. https://doi.org/10.1109/ACCESS.2021.3119562 (2021).
Do, M. T. et al. An effective method for detecting personal protective equipment at real construction sites using the improved YOLOv5s with SIoU loss function. In: 2023 RIVF International Conference on Computing and Communication Technologies (RIVF). 430–434. https://doi.org/10.1109/RIVF60135.2023.10471799 (IEEE, 2023).
Xiang, Q., Wang, X., Lei, L. & Song, Y. Dynamic bound adaptive gradient methods with belief in observed gradients. Pattern Recognit. 168, 111819. https://doi.org/10.1016/j.patcog.2025.111819 (2025).
Xiang, Q. et al. Quadruplet depth-wise separable fusion convolution neural network for ballistic target recognition with limited samples. Expert Syst. Appl. 235, 121182. https://doi.org/10.1016/j.eswa.2023.121182 (2024).
Acknowledgements
The authors would like to express their gratitude to the Jilin Province Science and Technology Development Program (20240401082YY), the Jilin Province International Joint Research Center for Intelligent Equipment (20240501008GH) and the College Students’ Innovation and Entrepreneurship Training Program(202510201013) for their financial support, guidance, and recognition of the research direction. We would also like to extend our sincere thanks to all professors and students for their support and assistance.
Funding
This work was supported in part by the Jilin province science and technology development plan item (20240401082YY), the Jilin International Joint Research Center for Intelligent Instruments and Equipment (20240501008GH), and the College Students’ Innovation and Entrepreneurship Training Program (202510201013).
Author information
Authors and Affiliations
Contributions
All authors participated in the conception and design of the study. Material preparation, data collection, and analysis were performed by Yao Wang, Yanzhen Wang, and Zhimin Wei. The initial draft was written by Yao Wang. Xiaolong Zhou was responsible for training the model, while Yao Wang oversaw model optimization. Linlin Cao and Haoyu Zhang conducted training after model optimization. Jianyong Li analyzed and summarized the experimental results. All authors provided feedback on earlier versions of the manuscript. The final version was reviewed and approved by all authors.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
About this article
Cite this article
Wang, Y., Wang, Y., Wei, Z. et al. YOLO11-BSCS: an enhanced attention-optimized framework for real-time indoor flame and smoke detection in elderly care mobile robots. Sci Rep (2026). https://doi.org/10.1038/s41598-026-45957-5
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41598-026-45957-5
