A robust ensemble framework for helmet usage classification in real-world scenarios
and
*
Article Sidebar
Full Text: 
PDF
Main Article Content
Abstract
The application of machine learning models in the analysis of helmet-related images has yielded remarkable results in identifying and classifying helmet-wearing behaviours. Previous research has employed several pretrained models to predict proper or improper helmet use, achieving high accuracy on the Helmet Wearing Image Dataset (2024), a newly introduced dataset designed to enhance classification capabilities. This study aims to improve prediction performance on helmet datasets by leveraging state-of-the-art deep learning models and ensemble techniques. Using ResNet-50, MobileNetV2, and EfficientNet-B0 models, the proposed EnsemHelmet Framework uses a soft voting ensemble to optimise the classification results, achieving an outstanding accuracy of 99.24% on the experimental dataset. The results demonstrate the potential of ensemble learning to achieve high performance. This study not only improves the accuracy of the helmet-wearing recognition system but also highlights the effectiveness of ensemble techniques in optimizing performance on real-world datasets.
Article Details
Conflict of Interest
© 2026 The authors. This is an open access article distributed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License.
References
Adewopo, V. A., Elsayed, N., ElSayed, Z., Ozer, M., Abdelgawad, A., & Bayoumi, M. (2023). A review on action recognition for accident detection in smart city transportation systems. Journal of Electrical Systems and Information Technology, 10(1), 57. https://doi.org/10.1186/s43067-023-00124-y
He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 770–778). IEEE. https://doi.org/10.1109/CVPR.2016.90
Irfan, E., Jacob, C., & Resmi, R. (2024, May). Facial Recognition and CCTV Integration for Enhanced Security Using Deep Learning Techniques. In 2024 IEEE Recent Advances in Intelligent Computational Systems (RAICS) (pp. 1-5). IEEE. https://doi.org/10.1109/RAICS61201.2024.10689986
Masand, A., Chauhan, S., Jangid, M., Kumar, R., & Roy, S. (2021). Scrapnet: An efficient approach to trash classification. IEEE Access, 9, 130947–130958. https://doi.org/10.1109/ACCESS.2021.3111230
Nguyen, V. H., Bui, H. H. N., & Le, T. P. (2024, November). Assessing grain size variation across rice panicles using YOLOv8 and DeepLabv3 models. In Thai-Nghe, N., Do, T.N., & Benferhat, S. (Eds.), Intelligent Systems and Data Science. ISDS 2024 (pp. 15–29). Springer. https://doi.org/10.1007/978-981-97-9616-8_2
Patil, K., Jadhav, R., Suryawanshi, Y., Chumchu, P., Khare, G., & Shinde, T. (2024). HelmetML: A dataset of helmet images for machine learning applications. Data in Brief, 56, 110790. https://doi.org/10.1016/j.dib.2024.110790
Ren, Y., Cong, L. (2023). Traffic Image Classification Algorithm Based on Deep-Learning. In Atiquzzaman, M., Yen, N., & Xu, Z. (Eds.), Proceedings of the 4th International Conference on Big Data Analytics for Cyber-Physical System in Smart City - Volume 1. BDCPS 2022 (pp. 437–445). Springer. https://doi.org/10.1007/978-981-99-0880-6_48
Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., & Chen, L. C. (2018). MobileNetV2: Inverted residuals and linear bottlenecks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 4510–4520). IEEE. https://doi.org/10.1109/CVPR.2018.00474
Shourie, P. (2024). Optimizing traffic sign detection with MobileNetV2: A lightweight deep learning approach. In Proceedings of 2024 4th International Conference on Technological Advancements in Computational Sciences (ICTACS) (pp. 272–276). IEEE. https://doi.org/10.1109/ICTACS62700.2024.10840818
Singh, K., Patil, N., Mohite, S. G., Jadhav, S., Mohite, S., Gayakwad, M., & Joshi, R. (2024). Vehicle identification using RESNET-50: CNN approach. In Proceedings of 2024 IEEE International Conference on Blockchain and Distributed Systems Security (ICBDS) (pp. 1–6). IEEE. https://doi.org/10.1109/ICBDS61829.2024.10837029
Tan, M., & Le, Q. V. (2019). EfficientNet: Rethinking model scaling for convolutional neural networks. In Proceedings of the 36th International Conference on Machine Learning (ICML), (pp. 6105–6114). PMLR.
Tran, N., Nguyen, H., Ly, D., & Nguyen, H. D. (2024, November). Violence detection using skeleton data with graph convolutional networks. In Thai-Nghe, N., Do, T.N., & Benferhat, S. (Eds.), Intelligent Systems and Data Science. ISDS 2024 (pp. 86–97). Springer. https://doi.org/10.1007/978-981-97-9616-8_7
Truong, T. D., Huynh, P. H., Nguyen, V. H., & Do, T. N. (2024). Enhancing the efficiency of lung disease classification based on multi-modal fusion model. In Thai-Nghe, N., Do, TN., & Benferhat, S. (Eds.), Intelligent Systems and Data Science. ISDS 2024 (pp. 86–97). Springer. https://doi.org/10.1007/978-981-97-9616-8_5
Vo, A. H., Son, L. H., Vo, M. T., & Le, T. (2019). A novel framework for trash classification using deep transfer learning. IEEE Access, 7, 178631–178639. https://doi.org/10.1109/ACCESS.2019.2959033
Vo, M. T., Vo, A. H., & Le, T. (2022). A robust framework for shoulder implant X-ray image classification. Data Technologies and Applications, 56(3), 447–460. https://doi.org/10.1108/DTA-08-2021-0210
Zhang, W., Dang, L. M., Nguyen, L. Q., Alam, N., Bui, N. D., Park, H. Y., & Moon, H. (2024). Adapting the Segment Anything Model for plant recognition and automated phenotypic parameter measurement. Horticulturae, 10(4), 398. https://doi.org/10.3390/horticulturae10040398