Deep Learning Based Security Support System For The Prevention Of Dynamite-Backed Terrorist Activities

Year 2021, Issue: 22, 81 - 85, 31.01.2021

Volkan Kaya Ahmet Baran Servet Tuncer

https://doi.org/10.31590/ejosat.845467

Cited By: 2

Abstract

In today's society, one of the most important factors that threaten people is terrorism. In a society, terrorism affects the quality of life by disrupting the order of people. On the other hand, states are constantly developing different methods to fight terrorism. One of these methods is the use of deep learning, a subfield of machine learning, to fight terrorism. Deep learning has gained considerable popularity in the field of machine learning in recent years. In this study, a new model was proposed the basically VGG-16 architecture based on deep learning to recognize and prevent terrorist activities. With the proposed model, when dynamite was detected on human or train tracks in the images taken from the camera images used in security controls, a system that alerts the security guards in order to quickly identify the situation and take the appropriate measures. The data set used in the study was created by editing images of dynamite downloaded from the internet environment. In order to evaluate the performance of the proposed model, dynamite images found on human or train tracks were tested and dynamite images were determined with a success accuracy of 98.4% and a loss rate of 0.024.

Keywords

Dynamite detection, Deep learning, Convolutional neural network

Dinamit Destekli Terör Faaliyetlerinin Önlenmesi İçin Derin Öğrenme Temelli Güvenlik Destek Sistemi

Abstract

Günümüz toplumunda, insanları tehdit eden en önemli etmenlerden birisi terörizmdir. Terörizm bir toplumda, insanların düzen durumlarını bozarak, yaşam kalitesini etkilemektedir. Devletler ise terörle mücadele etmek için sürekli farklı yöntemler geliştirmektedir. Bu yöntemlerden birisi de terörle mücadele için makine öğrenmesinin bir alt alanı olan derin öğrenmenin kullanılmasıdır. Derin öğrenme, makine öğrenmesi alanında son yıllarda oldukça popülerlik kazanmıştır. Bu çalışmada, terör faaliyetlerini fark etmek ve önlemek için derin öğrenmeye dayalı VGG-16 mimarisi temel alınarak yeni bir model önerilmektedir. Önerilen model ile güvenlik kontrollerinde kullanılan kamera görüntülerinden alınan görüntülerde, insan ya da tren rayları üzerinde dinamit tespit edildiğinde, durumu hızla belirlemek ve uygun önlemleri almak için güvenlik görevlilerini uyaran bir sistem gerçekleştirilmiştir. Çalışmada kullanılan veri seti, internet ortamından indirilen dinamit resimleri düzenlenerek oluşturulmuştur. Önerilen modelin performansını değerlendirmek için, insan ya da tren rayları üzerinde bulunan dinamit resimleri test edilerek, %98,4’lük başarı doğruluğu ve 0,024 kayıp oranıyla dinamit görüntüleri tespit edilmektedir.

Keywords

Dinamit tespit, Derin öğrenme, Evrişimsel sinir ağı

References

• Yuan, J., & Guo, C. (2018, June). A deep learning method for detection of dangerous equipment. In 2018 Eighth International Conference on Information Science and Technology (ICIST) (pp. 159-164). IEEE.
• Ionescu, B., Ghenescu, M., Răstoceanu, F., Roman, R., & Buric, M. (2020). Artificial Intelligence Fights Crime and Terrorism at a New Level. IEEE MultiMedia, 27(2), 55-61.
• Makarenko, T. (2004). The crime-terror continuum: tracing the interplay between transnational organised crime and terrorism. Global crime, 6(1), 129-145.
• Krieger, T., & Meierrieks, D. (2011). What causes terrorism?. Public Choice, 147(1-2), 3-27.
• Ouassini, N., & Verma, A. (2018). Socio-economic inequality or demographic conditions: a micro-level analysis of terrorism in Jharkhand. Journal of Victimology and Victim Justice, 1(1), 63-84.
• Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A. A., Veness, J., Bellemare, M. G., ... & Petersen, S. (2015). Human-level control through deep reinforcement learning. nature, 518(7540), 529-533.
• Lake, B. M., Salakhutdinov, R., & Tenenbaum, J. B. (2015). Human-level concept learning through probabilistic program induction. Science, 350(6266), 1332-1338.
• Karatas, G., Demir, O., & Sahingoz, O. K. (2018, December). Deep learning in intrusion detection systems. In 2018 International Congress on Big Data, Deep Learning and Fighting Cyber Terrorism (IBIGDELFT) (pp. 113-116). IEEE.
• Alhamdani, R., Abdullah, M., & Sattar, I. (2018). Recommender system for global terrorist database based on deep learning. International Journal of Machine Learning and Computing, 8(6).
• Saeed, Y., Ahmed, K., Zareei, M., Zeb, A., Vargas-Rosales, C., & Awan, K. M. (2019). In-vehicle cognitive route decision using fuzzy modeling and artificial neural network. IEEE Access, 7, 20262-20272.
• Huamaní, E. L., Alicia, A. M., & Roman-Gonzalez, A. (2020). Machine Learning Techniques to Visualize and Predict Terrorist Attacks Worldwide using the Global Terrorism Database. Machine Learning, 11(4).
• Ali Shah, S. A., Uddin, I., Aziz, F., Ahmad, S., Al-Khasawneh, M. A., & Sharaf, M. (2020). An enhanced deep neural network for predicting workplace absenteeism. Complexity, 2020.
• Sai, B. K., & Sasikala, T. (2019, November). Object Detection and Count of Objects in Image using Tensor Flow Object Detection API. In 2019 International Conference on Smart Systems and Inventive Technology (ICSSIT) (pp. 542-546). IEEE.
• Bakker, R., Hill Jr, D. W., & Moore, W. H. (2014). Modeling terror attacks: A cross-national, out-of-sample study. Understanding Terrorism (Contributions to Conflict Management, Peace Economics and Development, Volume 22) Emerald Group Publishing Limited, 22, 51-68.
• Uddin, M. I., Zada, N., Aziz, F., Saeed, Y., Zeb, A., Ali Shah, S. A., ... & Mahmoud, M. (2020). Prediction of Future Terrorist Activities Using Deep Neural Networks. Complexity, 2020.
• Toure, I., & Gangopadhyay, A. (2016, May). Real time big data analytics for predicting terrorist incidents. In 2016 IEEE Symposium on Technologies for Homeland Security (HST) (pp. 1-6). IEEE.
• Verma, C., Malhotra, S., & Verma, V. (2018). Predictive modeling of terrorist attacks using machine learning. International Journal of Pure and Applied Mathematics, 119, 06.
• Yang, S., Sun, J., Duan, Y., Li, X., & Zhang, B. (2020, January). Dangerous object detection by deep learning of convolutional neural network. In Second Target Recognition and Artificial Intelligence Summit Forum (Vol. 11427, p. 1142722). International Society for Optics and Photonics.
• Zou, L., Yusuke, T., & Hitoshi, I. (2018, December). Dangerous objects detection of X-ray images using convolution neural network. In International Conference on Security with Intelligent Computing and Big-data Services (pp. 714-728). Springer, Cham.
• Chang, Y., Du, Z., & Sun, J. (2019, August). Dangerous behaviors detection based on deep learning. In Proceedings of the 2nd International Conference on Artificial Intelligence and Pattern Recognition (pp. 24-27).
• Kibria, S. B., & Hasan, M. S. (2017, December). An analysis of feature extraction and classification algorithms for dangerous object detection. In 2017 2nd International Conference on Electrical & Electronic Engineering (ICEEE) (pp. 1-4). IEEE.
• Istock, https://www.istockphoto.com, Erişim Tarihi Eylül, 20, 2020.
• Liu, Z., Luo, P., Wang, X., & Tang, X. (2015). Deep learning face attributes in the wild. In Proceedings of the IEEE international conference on computer vision (pp. 3730-3738).