Abstract
Unauthorized access to the bidding evaluation office and the departure of experts can significantly compromise the quality of on-site assessment work and introduce substantial integrity risks. To address these concerns, this paper presents the development of a hybrid neural network, integrating Yolov5s, Deepsort, and Dlib to ascertain the status of person within the bidding evaluation office. Our approach is bifurcated into two primary components. Firstly, Deepsort is integrated with Yolov5s to develop a model for the detection and tracking of personnel within the evaluation office. The model detects, counts, and tracks the flow of personnel on site and assesses the presence or absence of experts. Subsequently, Yolov5s, enhanced by the Swin Transformer architecture, refines the Dlib facial recognition model, augmenting its capacity to detect and swiftly identify micro-scale faces, thereby discerning potential intruders. The experimental results demonstrate that the model is capable of effectively detecting and tracking personnel on site, recognizing novel micro-scale targets, verifying individual identities, and evaluating the status of on-site personnel. Throughout the testing phase, when juxtaposed with conventional methodologies, our model has exhibited a marked enhancement in the accuracy of detecting unauthorized entry and the absence of designated experts, enabling real-time analysis of the evaluation office’s status.
Data availability
All relevant datasets and code used in this study will be made available upon request.
References
Oladimeji, O. Evaluation of unit rates bids of common building items. J. Eng. Proj. Prod. Manag. 11, 145–157. https://doi.org/10.2478/jeppm-2021-0015 (2021).
Huang, X., Zhou, X. Research on bidding evaluation of engineering projects based on fuzzy comprehensive evaluation method. In Proc. 2022 International Conference on Machine Learning and Knowledge Engineering, MLKE 2022 278-283. (Virtual, Guilin, China, 2022).
Liu, J. & Chen, X.-M. Bidding management of the ETFE cladding project of the national aquatic center for Beijing Olympics. Shenzhen Daxue Xuebao (Ligong Ban) J. Shenzhen Univ. Sci. Eng. 25, 39–42 (2008).
Zhu, W., Cheng, K., Guo, Y. & Chen, Y. Comprehensive evaluation of the tendency of vertical collusion in construction bidding based on deep neural network. Comput. Intell. Neurosci. https://doi.org/10.1155/2022/2897672 (2022).
He, X., Lin, Q., Liu, X., Yu, R., Zhou, Z., Xu, J., Chen, J., Wang, Z. A deep learning method for detecting phone call behaviors of bidding evaluation expert. In Proc. 2nd International Conference on Computer Science, Electronic Information Engineering and Intelligent Control Technology, CEI 2022, 699-704 (Virtual, Online, China, 2022).
Yang, X. et al. RatioVLP: Ambient light noise evaluation and suppression in the visible light positioning system. IEEE. Trans. Mob. Comput. 23, 5755–5769. https://doi.org/10.1109/TMC.2023.3312550 (2024).
Luo, R., Li, Y., Jin, Z. & Chen, B. An indoor positioning method integrating WiFi and wearable inertial navigation module. Yi Qi Yi Biao Xue Bao 43, 267–276. https://doi.org/10.19650/j.cnki.cjsi.J2108637 (2022).
Janczak, D. et al. Indoor positioning based on Bluetooth RSSI mean estimator for the evacuation supervision system application. IEEE. Access 12, 55843–55858. https://doi.org/10.1109/ACCESS.2024.3389986 (2024).
Janczak, D. et al. Accuracy analysis of the indoor location system based on Bluetooth Low-Energy RSSI measurements. Energies https://doi.org/10.3390/en15238832 (2022).
Yan, K., Zhou, X. K. & Yang, B. AI and IoT applications of smart buildings and smart environment design, construction and maintenance. Build Environ https://doi.org/10.1016/j.buildenv.109968 (2022).
Bi, J., Wang, H., Hua, M. & Yan, K. An interpretable feature selection method integrating ensemble models for chiller fault diagnosis. J. Build. Eng. 87, 13. https://doi.org/10.1016/j.jobe.2024.109029 (2024).
Bi, J. H. W. et al. AI in HVAC fault detection and diagnosis: A systematic review. Energy Rev. https://doi.org/10.1016/j.enrev.2024.100071 (2024).
Wen, W., Xia, F., Xia, L., Ieee. Real-time personnel counting of indoor area division based on improved YOLOV4-Tiny. In Proc. 47th Annual Conference of the IEEE-Industrial-Electronics-Society (IECON), 13-16 (Electr Network, 2021).
Zhao, F., Li, Y., Liu, H., Zhang, J. & Zhu, Z. Lightweight anchor-free one-level feature indoor personnel detection method based on transformer. Eng. Appl. Artif. Intell. 2024, 133. https://doi.org/10.1016/j.engappai.108176 (2024).
Li, Y. et al. Adaptive kernel learning Kalman filtering with application to model-free maneuvering target tracking. IEEE. Access 10, 78088–78101. https://doi.org/10.1109/ACCESS.2022.3193101 (2022).
Lukasik, G., Rogers, J., Kota, K.R., Wilkerson, J.W., Lacy, T.E., Kulatilaka, W.D. Application of digital particle tracking and schlieren imaging to study debris cloud and shockwave formation during hypervelocity impacts. In Proc. AIAA science and technology forum and exposition, AIAA SciTech Forum 2021, January 11, 2021 - January 15 2021, Virtual, 1-11 (2021).
Li, T. Research on sports video tracking technology based on mean shift algorithm and color histogram algorithm. In Proc. 3rd IEEE International Conference on Intelligent Technologies, CONIT 2023, June 23, 2023 - June 25 (Hubli, India, 2023).
Fernandez, M.M., Delrieux, C., Munoz, J.A.F. Automated personnel digital twinning in industrial workplaces. In Proc. 2022 IEEE International Conference on Electrical, Computer, and Energy Technologies, ICECET 2022, July 20, 2022 - July 22 (Prague, Czech republic, 2022).
Zha, W. et al. Research on the recognition and tracking of group-housed pigs’ posture based on edge computing. Sensors 23, 8952 (2023).
Wang, C. X. & Wang, H. R. Cascaded feature fusion with multi-level self-attention mechanism for object detection. Pattern Recognit. 138, 10. https://doi.org/10.1016/j.patcog.109377 (2023).
Tu, S. et al. Behavior recognition and tracking method of group housed pigs based on improved DeepSORT algorithm. Nongye Jixie Xuebao 53, 345–352. https://doi.org/10.6041/j.issn.1000-1298.08.037 (2022).
Cheng, H., Quanli, Z., Fangyu, Xiong., & Jiazhong, X. Space dynamic target tracking method based on five frame difference and Deepsort. Sci. Sci. (2023).
Al-Atroshi, S. J. A. & Ali, A. M. Improving facial expression recognition using HOG with SVM and modified datasets classified by Alexnet. Trait. Signal. 40, 1611–1619. https://doi.org/10.18280/ts.400429 (2023).
Goel, R., Mehmood, I. & Ugail, H. A study of deep learning-based face recognition models for sibling identification. Sensors 21, 5068 (2021).
Majeed, F., Shafique, U., Safran, M., Alfarhood, S. & Ashraf, I. Detection of drowsiness among drivers using novel deep convolutional neural network model. Sensors 23, 8741 (2023).
Wu, Q., Li, Y., Huang, W., Chen, Q. & Wu, Y. C3TB-YOLOv5: Integrated YOLOv5 with transformer for object detection in high-resolution remote sensing images. Int. J. Remote Sens. 45, 2622–2650. https://doi.org/10.1080/01431161.2024.2329528 (2024).
Wu, F., Zhou, Z., He, X., Wang, Z., Li, J., Ruan, Y., Lei, H. A composite image recognition based approach for spontaneous combustion point detection and positioning in coal piles. In Proc. 2021 3rd international conference on robotics, intelligent control and artificial intelligence, ICRICA 2021, December 3, 2021 - December 5, 2021, Virtual, Online (2022).
Zhu, X., Lyu, S., Wang, X., Zhao, Q. TPH-YOLOv5: Improved YOLOv5 based on transformer prediction head for object detection on drone-captured scenarios. In Proc. IEEE International Conference on Computer Vision (2021).
Haiying, L., Xuehu, D., Haitong, L., Jason., Haonan, Chen., & Lingyun, Bi. Improved GBS YOLOv5 algorithm based onYOLOv5 applied to UAV intelligent traffic. Sci. Sci. (2023).
Chun, S., HongMing, L., &Yu, Y. Research on improved algorithm for helmet detection based onYOLOv5. Sci. Sci. (2023).
Cao, X., Zhang, Y., Lang, S. & Gong, Y. Swin-Transformer-Based YOLOv5 for small-object detection in remote sensing images. Sensors https://doi.org/10.3390/s23073634 (2023).
Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., Guo, B. Swin transformer: Hierarchical vision transformer using shifted windows. Microsoft at ICCV 2021. Comput. Sci. (2021).
Shao, X. et al. Underground personnel detection and tracking based on improved YOLOv5s and DeepSORT. Meitan Kexue Jishu/Coal Sci. Technol. (Peking) 51, 291–301. https://doi.org/10.13199/j.cnki.cst.2022-1933 (2023).
Liu, Z., Gao, X., Wan, Y., Wang, J. & Lyu, H. An improved YOLOv5 method for small object detection in UAV capture scenes. IEEE Access 11, 14365–14374. https://doi.org/10.1109/ACCESS.2023.3241005 (2023).
Acknowledgements
This work was supported by The National Key Research and Development Program of China (No. 2020YFC1512202), in part by the Key Research and Development Program of Zhejiang Province (No. 2021C01065).
Author information
Authors and Affiliations
Contributions
All the authors contributed extensively to the manuscript. Z.Z.: (1) development or design of methodology; creation of models. (2) Verification, whether as a part of the activity or separate, of the overall replication/ reproducibility of results/experiments and other research outputs. (3) Programming; computer programming; computer code implementation and algorithm support; Testing of existing code components. (4) Analyze synthetic research data, and analyze and discuss the feasibility of experimental design. (5) The first draft of the paper was written. Z.W.: (1) development or design of methodology; creation of models. (2) Verification, whether as a part of the activity or separate, of the overall replication/ reproducibility of results/experiments and other research outputs. (3) Programming; computer programming; computer code implementation and algorithm support; Testing of existing code components. Y.M.: (1) Analyze synthetic research data, and analyze and discuss the feasibility of experimental design. (2) Verification, whether as a part of the activity or separate, of the overall replication/ reproducibility of results/experiments and other research outputs. R.Y.: revised and suggested the manuscript, and helped with the formatting review and editing of the manuscript. X.H.: Programming; computer programming; computer code implementation and algorithm support; Testing of existing code components. D.L.: (1) Analyze and discuss the feasibility of experimental design. (2) Programming; computer programming. All authors have read and agreed to the published version of the manuscript.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Consent to publish
We hereby confirm that we have obtained the consent and signed permission documents from individuals with clearly identifiable facial features appearing in Figure 6, Figure 7, Figure 8 and Figure 10 of this manuscript for publication. For other individuals depicted in the article, we have taken the necessary steps to obscure their faces. In addition, all individuals have been informed of the nature of the publication and have granted their permission for the images to be used in this publication.
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
Zhou, Z., Wang, Z., Meng, Y. et al. Hybrid neural network for personnel recognition and tracking in remote bidding evaluation monitoring. Sci Rep (2026). https://doi.org/10.1038/s41598-026-42936-8
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41598-026-42936-8
