Justification of the Architecture a Promising Automated System for Monitoring Radiation, Chemical and Biological Environment Using Artificial Intelligence

The most progressive direction for identifying and assessing the chemical warfare situation is the introduction of technologies based on artificial intelligence. The goal of the work is to develop the architecture of a promising system for monitoring the radiation, chemical and biological situation using artificial intelligence. Research information base. Publications on the use of mathematical models in artificial intelligence (AI), available via the Internet. The research method is analytical, from general to specific. We considered the features of using artificial intelligence in automated control systems. Results and discussion. Confrontations with Ukraine and NATO are multivariate and spatial in nature, and require constant monitoring in the face of a lack of specific information about attacks being prepared and already carried out. The use of AI technologies will allow us to go beyond simply displaying the current situation, providing tools for predicting the development of events. The proposed architecture of a promising system involves the creation of a single database filled with verified information from open sources. The developed structure of the web application, which is an interactive interface for analyzing and responding to changes in the chemical warfare situation, will allow flexible switching between information layers and obtaining data in real time. Conclusion. The use of neural network technologies by NBC protection troops will make it possible to search according to specified parameters and conduct retrospective data analysis, which will significantly simplify monitoring of NBC threats for the troops and population of the Russian Federation.

1. Kallenborn Z, Bleek PC. Swarming destruction: drone swarms and chemical, biological, radiological, and nuclear weapons. The Nonproliferation Review. 2018;25(5–6):523–43. https://doi.org/10.1080/10736700.2018.1546902

2. Borgonovi F, Calvino F, Criscuolo C, Nania J, Nitschke J, O’Kane L, et al. Emerging trends in AI skill demand across 14 OECD countries. OECD Artificial Intelligence Papers. 2023; No. 2, OECD Publ, Paris. https://doi.org/10.1787/7c691b9a-en

3. Filippucci F, Gal P, Jona-Lasinio C, Leandro A, Nicoletti G. The impact of Artificial Intelligence on productivity, distribution and growth: Key mechanisms, initial evidence and policy challenges, OECD Artificial Intelligence Papers, 2024; No. 15, OECD Publ, Paris. https://doi.org/10.1787/8d900037-en

4. Guo X, Liu X, Zhu E, Yin J. Deep Clustering with Convolutional Autoencoders. In: Liu D, Xie S, Li Y, Zhao D, El-Alfy ES, Eds. Neural Information Processing. Vol. 10635. Cham: Springer; 2017. P. 373–82. https://doi.org/10.1007/978-3-319-70096-0_39

5. Vasudevan SK, Pulari SR, Vasudevan S. CNN – Convolutional Neural Networks: A Complete Understanding. In: Deep Learning. Chapman and Hall/CRC; 2021. P. 81–120. http://doi.org/10.1201/9781003185635-5.

6. Chuan Z, du y. Early Identification Methods for Emerging Technologies Based on Weak Signals. 2022. http://doi.org/10.21203/rs.3.rs-2291140/v1

7. Ghayoumi M. Deep Convolutional Generative Adversarial Networks (DCGANs). In: Generative Adversarial Networks in Practice. New York: Chapman and Hall/CRC; 2023. P. 220–57. http://doi.org/10.1201/9781003281344-8

8. Layton J, Hu F. Attacks on Deep Reinforcement Learning Systems: A Tutorial. In: AI, Machine Learning and Deep Learning. CRC Press; 2023. P. 79–82. http://doi.org/10.1201/9781003187158-6

9. Бурков А. Машинное обучение без лишних слов. СПб.: Питер; 2020. 192 c. Burkov A. Machine learning without further ado. St. Petersburg: Peter; 2020. 192 p (in Russian).

10. Suh C. Machine Learning Applications. Convex Optimization for Machine Learning. Ch. 3. Boston – Delft; 2022. P. 185–328. http://doi.org/10.1561/9781638280538.ch3

11. Thomas P. Trappenberg. Machine learning with sklearn. Fundamentals of Machine Learning. 2019. Р. 38–65. http://doi.org/10.1093/oso/9780198828044.003.0003

12. Girasa R. Applications of AI and Projections of AI Impact. Artificial Intelligence as a Disruptive Technology. Palgrave Macmillan, Cham.; 2020. P. 23–67. http://doi.org/10.1007/978-3-030-35975-1_2

13. Kondaurov RYu, Gangan DA. The Development Trend in Advanced Armaments and Means of Radiation, Chemical and Biological Protection with Artificial Intelligence Elements within the System of Control Automation. Military Thought. 2022;(7):79–85 (in Russian).

14. Segev E. How to conduct semantic network analysis. Semantic Network Analysis in Social Sciences. 2021. P. 16–31. http://doi.org/10.4324/9781003120100-1

15. Poola L, Aparna P. ‘A Mixed Parallel and Pipelined Efficient Architecture for Intra Prediction Scheme in HEVC’. IETE Technical Review. 20224;39(2):244–56. https://doi.org/10.1080/02564602.2020.1841686

16. Li Z. Pipeline Spatial Data Model. Pipeline Spatial Data Modeling and Pipeline WebGIS. 2020. P. 29–102. http://doi.org/10.1007/978-3-030-24240-4_3

17. Li Z, Yang L. Pipeline Real-Time Data, Pipeline SCADA and OPC. Pipeline Real-time Data Integration and Pipeline Network Virtual Reality System. 2021. P. 7–20. http://doi.org/10.1007/978-3-030-62110-0_2

18. Timm S, Yuan W, Benjamin D. Scale Tests of the New DUNE Data Pipeline. Scale Tests of the New DUNE Data Pipeline. 2023. http://doi.org/10.2172/1988450

19. Meedeniya D. Enhancement of Deep Learning Architectures. Deep Learning. 2023. P. 112–46. http://doi.org/10.1201/9781003390824-6

20. Hemanand D, Bhavani NPG, Ayub S, Ahmad MW, Narayanan S, Haldorai A. Multilayer vectorization to develop a deeper image feature learning model. Automatika. 2023;64(2):355–64. https://doi.org/10.1080/00051144.2022.2157946

21. Calvino F, Criscuolo C, Dernis H, Samek L. What technologies are at the core of AI?: An exploration based on patent data, OECD Artificial Intelligence Papers. 2023. No. 6. OECD Publ, Paris. https://doi.org/10.1787/32406765-en/