Authors

Bennett, E. O.

Department of Computer Science, Rivers State University, Port Harcourt, Nigeria

Obomanu Queenlucky Chizorom

Department of Computer Science, Rivers State University, Port Harcourt, Nigeria

Igiri, C. G.

Department of Computer Science, Rivers State University, Port Harcourt, Nigeria

Abstract

This study addresses the critical challenges of computational expense, scalability, and generalization in real-time object classification for autonomous systems. The paperpresents a novel data mining model, integrating a Domain Adversarial Neural Network (DANN) with a pre-trained ResNet18 backbone, leveraging transfer learning to enhance adaptability and efficiency. The system employs Automatic Mixed Precision (AMP) for training optimization and NVIDIA TensorRT for deployment, achieving a balance between high accuracy and low latency. Evaluated on a dataset comprising four object classes (Stop Sign, Pedestrian, Vehicle, Bicycle), the model attained an average precision of 81.7% and recall of 79.4%, with an inference time of 15.3ms per image, confirming its suitability for real-time applications. The DANN architecture effectively learned domain-invariant features, addressing generalization issues in unseen environments. This research provides a practical framework for scalable and efficient object classification, offering significant implications for autonomous vehicles, surveillance, and robotics.

Keywords

Object Classification Domain Adversarial Neural Network Autonomous Systems

Citation of this Article

Bennett, E. O., Obomanu Queenlucky Chizorom, & Igiri, C. G.. (2025). Data Mining Model for Object Classification. Journal of Artificial Intelligence and Emerging Technologies (JAIET). 2(12), 1-6. Article DOI: https://doi.org/10.47001/JAIET/2025.212001

Licence Copyright (c) 2026 Journal of Artificial Intelligence and Emerging Technologies. This work is licensed under a Creative Commons Attribution Non Commercial 4.0 International Licence.

References

  1. Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). ImageNet classification with deep convolutional neural networks. In Advances in Neural Information Processing Systems 25 (pp. 1097–1105).
  2. Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv. https://arxiv.org/abs/1409.1556
  3. Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., and Rabinovich, A. (2015).Going deeper with convolutions. In Proc. IEEE Conference on Computer Vision and Pattern Recognition (pp. 1–9).
  4. He, K., Zhang, X., Ren, S., and Sun, J. (2016). Deep residual learning for image recognition. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (pp. 770–778).
  5. Howard, A. G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., abd Adam, H. (2017). MobileNets: Efficient convolutional neural networks for mobile vision applications. arXiv. https://arxiv.org/abs/1704.04861
  6. Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., & Chen, L.-C. (2018). MobileNetV2: Inverted residuals and linear bottlenecks. In 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 4510–4520). IEEE. https://doi.org/10.1109/CVPR.2018.00474
  7. Tan, M., & Le, Q. V. (2019). EfficientNet: Rethinking model scaling for convolutional neural networks. In Proceedings of the 36th International Conference on Machine Learning (pp. 6105–6114).
  8. Pan, S. J., & Yang, Q. (2010). A survey on transfer learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345–1359.
  9. Hinton, G. E., Vinyals, O., & Dean, J. (2015). Distilling the knowledge in a neural network. arXiv. https://arxiv.org/abs/1503.02531
  10. Ganin, Y., Ustinova, E., Ajakan, H., Sullivan, J., Motiian, S., Lempitsky, V., and Hoffman, J. (2016). Domain-adversarial training of neural networks. The Journal of Machine Learning Research, 17(1), 2096–2130.
  11. Li, Y., Tian, Y., Gong, M., Liu, Y., Tenenbaum, J. B., & Torralba, A. (2018). Deep feature disentanglement and reconstruction. arXiv. https://arxiv.org/abs/1804.11376
  12. Han, S., Mao, H., and Dally, W. J.(2016). Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding. arXiv. https://arxiv.org/abs/1510.00149
  13. Zhang, Z., Luo, P., Huang, T., and Tang, X.(2017). Light CNN: A compact convolutional neural network for face recognition. arXiv. https://arxiv.org/abs/1708.06072
  14. Wu, Q., Xu, D., Sun, J., Guo, B., Zhang, X., Wang, Q., and Chen, S., “Quantization and Pruning for Accelerating Deep Neural Networks,” IEEE Access, vol. 8, pp. 19572–19586, 2020.
  15. Chen, X., Li, C., Zhou, J., Wu, J., Zhang, Y., and Gong, X. (2021). “AutoML for Deep Learning: A Survey,” ACM Trans. Intell. Syst. Technol., vol. 12, no. 4, pp. 1–25.