In modern conditions, the problem of mine detection remains one of the most urgent due to the serious threat to the life and health of people in contaminated areas. This paper presents an approach to mine detection using a hybrid neural network CNN+BiLSTM+Attention, which analyzes B-scan signals received from ground-penetrating radar systems. To improve the quality of training with a limited amount of data, image augmentation was used, which includes shifting, reflecting, scaling, and adding noise. The initial layers of the architecture use convolutional operations to extract local spatial features, after which a bidirectional recurrent layer BiLSTM is used, which allows the model to learn dependencies within each B-scan, taking into account the context in both directions. An attention mechanism is additionally integrated to focus on the most informative fragments of the signal. The final layers of the model are dense layers with a sigmoid activation function for mine detection. The results of the computer experiment demonstrated the high efficiency of the model: the classification accuracy exceeds 99%, and the values of Precision, Recall, F1-score and AUC indicate the reliability of the approach. Visualization of the results (loss and accuracy graphs, confusion matrix, metric histogram) confirms stable learning without overtraining. The proposed architecture is promising for application in remote mine monitoring tasks and can be used as a basis for further research in the field of military security.
- Abhishek Rangole, De, S., Nilesh Kuchekar, & Bazil, A. (2024). A Comprehensive Review of Ground Penetrating Radar: Techniques, Applications and Future Directions. 12(3), 30–53. doi: 10.5281/zenodo.13842586
- Adhikari, S., Noh, D., Kim, M., Ahn, D., Jang, Y., Oh, E., & Lee, D. (2024). Vapor phase detection of explosives by surface enhanced Raman scattering under ambient conditions with metal nanogap structures. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 311, 123996. doi: 10.1016/j.saa.2024.123996
- Gurkan S., Karapinar M., & Dogan, S. (2017). Classification of explosives materials detected by magnetic anomaly method. 347–350. doi: 10.1109/iceee2.2017.7935848
- Landmine and Cluster Munition Monitor. (2024). Retrieved from https://www.the-monitor.org
- Madavha L., Laseinde, T., Ilesanmi Daniyan, & Khumbulani Mpofu. (2020). Functional design and performance evaluation of a metal handheld detector for land mines detection. Procedia CIRP, 91, 696–703. doi: 10.1016/j.procir.2020.04.134
- Lytvyn V., Peleshchak, I., Vysotska, V., Motyka, V., & Peleshchak, R. (2022). Passive Method for Mine Detection and Classification Using Magnetic Fields and Convolutional Neural Networks. 2022 I EEE 16th International Conference on Advanced Trends in Radioelectronics, Telecommunications and Computer Engineering (TCSET), 1–6. doi: 10.1109/tcset64720.2024.10755852
- Markoulidakis, I., Rallis, I., Georgoulas, I., Kopsiaftis, G., Doulamis, A., & Doulamis, N. (2021). Multiclass Confusion Matrix Reduction Method and Its Application on Net Promoter Score Classification Problem. Technologies, 9(4), 81. doi: 10.3390/technologies9040081
- Peleshchak, R., Vasyl Lytvyn, Oleksandr Mediakov, & Peleshchak, I. (2023). Morphology of Convolutional Neural Network with Diagonalized Pooling. Communications in Computer and Information Science, 161–172. doi: 10.1007/978-3-031-27034-5_11
- Pol, A. A. (2020). Machine Learning Anomaly Detection Applications to Compact Muon Solenoid Data Quality Monitoring. Hal.science. Retrieved from https://theses.hal.science/tel-02924477
- Study on evaluating airborne GPR’s potential for UXO and Landmine Detection in a Controlled Environment. (2023). Retrieved from https://www.sphengineering.com/news/study-on-evaluating-airborne-gprs-potential-for- uxo-and-landmine-detection-in-a-controlled-environment
- Yilmaz, C., Sonmez, Y., Kahraman, H. T., Salih Soyler, & Ugur Guvenc. (2016). Developing of decision support system for land mine classification by meta-heuristic classifier. 1–5. doi: 10.1109/inista.2016.7571867
- Yilmaz, C., Kahraman, H. T., & Soyler, S. (2018). Passive Mine Detection and Classification Method Based on Hybrid Model. IEEE Access, 6, 47870–47888. doi: 10.1109/access.2018.2866538