21916

Simülasyon ortamlarında pekiştirmeli öğrenme yoluyla savunma sanayinde uç yapay zeka teknolojisi

Edge AI teknolojisi, günümüzde özellikle yapay zekâ ve büyük veri ile yaygın olarak kullanılan bulut teknolojilerinin avantajlarından yararlanırken güvenlik açıklarının önlenmesine de yardımcı olmaktadır. Sistemlerin buluta taşınması durumunda, hassas bilgilerin korunması ve yüksek bant genişliği gibi ihtiyaçlar ortaya çıkmaktadır. Bu alandaki ihtiyaçları karşılarken hassas verilerin güvenliği ve sistem trafiğinin azaltılması gibi konulara çözüm sunan Edge AI, dijital ikiz ve otonom sistem ile birlikte kullanıldığında özellikle askeri alandaki projelere yeni bir bakış açısı sunabilmektedir. Bu çalışmada edge AI teknolojisini simülasyon sistemlerinde kullanımı teknik olarak ele aldık. Bu teknolojinin kullanımı ile elde edilen sonuçları analiz ettik. Edge AI seviyelendirme sisteminde mevcut çalışmanın 2. seviyede olduğu tespit edilmiş, Edge AI kullanımı sayesinde %54 performans artışı elde edilmiştir. Ayrıca simülasyon sisteminde hedefi vurma isabet oranı da %34 oranında artırılmıştır.

Anahtar Kelimeler:

Havacılık simülasyonu, Yapay zekâ, Dijital ikiz, Uç yapay zeka, Uç hesaplama

Edge ai technology in the defense industry via reinforcement learning in simulation environments

Edge artificial intelligence (Edge AI) technology helps to avoid vulnerabilities while benefiting from the advantages of cloud technologies, which are widely used today, especially with artificial intelligence and big data. In the case of transferring systems to the cloud, and needs such as protection of sensitive information and high bandwidth emerges in cloud approaches. Edge AI, which provides solutions to issues such as the security of sensitive data and reducing system traffic, while meeting the needs in this field, can offer a new perspective, especially to projects in the military field, when used with digital twin and autonomous system technologies. In this study, we evaluated the “Forces in virtual environment machine learning (FIVE-ML)” simulation system technically in which we use edge AI technology, analyzed the results obtained with the use of this technology. It has been determined that the current work is at the 2nd level in Edge AI levelling system, also there is a 54% performance (in terms of time with accuracy) increase with edge AI. Besides, the accuracy of hitting the target in simulation system is also increased, with the rate of 34%.

Keywords:

Aerospace simulation, Artificial intelligence, Digital twin, Edge ai, Edge computing,

PDF

___

360 Research Reports. (2019). Global Edge AI Software Market Growth (Status and Outlook) 2019-2024. https://www.360researchreports.com/global-edge-ai-software-market-14355998
Ahmed, E., Rehmani, M. H., & Bonnet, P. (2017). Editorial to a Special Section on Information Fusion in Internet of Things. Information Systems, 69, 194. https://doi.org/10.1016/j.is.2017.06.004
Anciaux, N., Bonnet, P., Bouganim, L., Nguyen, B., Pucheral, P., Sandu Popa, I., & Scerri, G. (2019). Personal Data Management Systems: The security and functionality standpoint. Information Systems, 80, 13–35. https://doi.org/10.1016/j.is.2018.09.002
Arisoy, E. B., Ren, G., Ulu, E., Ulu, N. G., & Musuvathy, S. (2016). A data-driven approach to predict hand positions for two-hand grasps of industrial objects. Proceedings of the ASME Design Engineering Technical Conference, 1A-2016(August). https://doi.org/10.1115/DETC2016-60095
Atos. (2020, November 23). Atos named by Gartner as an Edge AI Technology Innovator for 2020 - Atos. Atos. https://atos.net/en/2020/press-release_2020_11_23/atos-gartner-edge
Bernard Marr. (2017, March). What Is Digital Twin Technology - And Why Is It So Important? Forbes. https://www.forbes.com/sites/bernardmarr/2017/03/06/what-is-digital-twin-technology-and-why-is-it-so-important/?sh=66775e592e2a
Chang, W. J., Chen, L. B., & Su, K. Y. (2019). Deepcrash: A Deep Learning-Based Internet of Vehicles System for Head-on and Single-Vehicle Accident Detection with Emergency Notification. IEEE Access, 7, 148163–148175. https://doi.org/10.1109/ACCESS.2019.2946468
Dursun, M., & Çuhasdar, İ. (2018). Video Streaming with Raspberry Pi 3, Picamera and https Implementation for Unmanned Aerial Vehicle (UAV) Data Link. Bilişim Teknolojileri Dergisi, 23–28. https://doi.org/10.17671/gazibtd.307294
Eurotech. (2021). Edge AI: Enabling Deep Learning and Machine Learning with High Performance Edge Computers. Eurotech. https://www.eurotech.com/en/page/edge-ai
Grand View Research. (2021, May). Edge Computing Market Size, Share & Trends Analysis Report By Component (Hardware, Software, Services, Edge-managed Platforms), By Application, By Industry Vertical, By Region, And Segment Forecasts, 2021 - 2028. Grandviewresearch. https://www.grandviewresearch.com/industry-analysis/edge-computing-market
Hung, N. Q. V., Weidlich, M., Tam, N. T., Miklós, Z., Aberer, K., Gal, A., & Stantic, B. (2019). Handling probabilistic integrity constraints in pay-as-you-go reconciliation of data models. Information Systems, 83, 166–180. https://doi.org/10.1016/j.is.2019.04.002
Karaarslan, A. (2019). Bilgisayar Sistemlerinde SEPIC Dönüştürücü Uygulaması ve Benzetim Çalışması. Bilişim Teknolojileri Dergisi, 111–117. https://doi.org/10.17671/gazibtd.540127
Koohestani, A., Abdar, M., Khosravi, A., Nahavandi, S., & Koohestani, M. (2019). Integration of Ensemble and Evolutionary Machine Learning Algorithms for Monitoring Diver Behavior Using Physiological Signals. IEEE Access, 7, 98971–98992. https://doi.org/10.1109/ACCESS.2019.2926444
Lechtenbörger, J., & Vossen, G. (2003). Multidimensional normal forms for data warehouse design. Information Systems, 28(5), 415–434. https://doi.org/10.1016/S0306-4379(02)00024-8
Lee, Y. L., Tsung, P. K., & Wu, M. (2018). Techology trend of edge AI. 2018 International Symposium on VLSI Design, Automation and Test, VLSI-DAT 2018, 1–2. https://doi.org/10.1109/VLSI-DAT.2018.8373244
Navrat, P., Manolopoulos, Y., & Vossen, G. (2004). Special issue on ADBIS 2002: Advances in databases and information systems. Information Systems, 29(6), 437–438. https://doi.org/10.1016/j.is.2003.10.003
Nguyen, N. D., Nguyen, T., & Nahavandi, S. (2017). System Design Perspective for Human-Level Agents Using Deep Reinforcement Learning: A Survey. IEEE Access, 5, 27091–27102. https://doi.org/10.1109/ACCESS.2017.2777827
Nguyen, T. (2023). Emerging Technologies on the 2023 Gartner Impact Radar. Gartner. https://www.gartner.com/en/articles/4-emerging-technologies-you-need-to-know-about
Nvidia. (2021). AIMobile Edge AI Solution Powered by NVIDIA. Nvidia. https://www.aimobile.com.tw/EdgeAI_Products.html
Orrin, S., & Chehreh, C. (2020, October 20). How Edge Computing and Hybrid Cloud Are Shifting the IT Paradigm - Nextgov. Nextgov. https://www.nextgov.com/ideas/2020/11/how-edge-computing-and-hybrid-cloud-are-shifting-it-paradigm/170238/
Paajanen, S. (2020, April 28). What is Edge Analytics? Advian. https://www.advian.fi/en/blog/what-is-edge-analytics
Satyanarayanan, M., & Davies, N. (2019). Augmenting Cognition Through Edge Computing. Computer, 52(7), 37–46. https://doi.org/10.1109/MC.2019.2911878
Senderovich, A., Weidlich, M., & Gal, A. (2019). Context-aware temporal network representation of event logs: Model and methods for process performance analysis. Information Systems, 84, 240–254. https://doi.org/10.1016/j.is.2019.04.004
Tao, F., Qi, Q., Liu, A., & Kusiak, A. (2018). Data-driven smart manufacturing. Journal of Manufacturing Systems, 48(January), 157–169. https://doi.org/10.1016/j.jmsy.2018.01.006
Van Den Bussche, J., Vansummeren, S., & Vossen, G. (2005). Towards practical meta-querying. Information Systems, 30(4), 317–332. https://doi.org/10.1016/j.is.2004.04.001
Wang, P., Ye, F., Chen, X., & Qian, Y. (2018). Datanet: Deep learning based encrypted network traffic classification in SDN home gateway. IEEE Access, 6, 55380–55391. https://doi.org/10.1109/ACCESS.2018.2872430
Watkinson, N., Zaitsev, F., Shivam, A., Demirev, M., Heddes, M., Givargis, T., Nicolau, A., & Veidenbaum, A. (2021). EdgeAvatar: An Edge Computing System for Building Virtual Beings. Electronics, 10(3), 229. https://doi.org/10.3390/ELECTRONICS10030229
Xilinx. (2021). Edge AI. Xilinx. https://www.xilinx.com/applications/industrial/analytics-machine-learning.html
Yılmaz, S. (2022). Development stages of a semi-autonomous underwater vehicle experiment platform. International Journal of Advanced Robotic Systems, 19(3), 1–21. https://doi.org/10.1177/17298806221103710
Zhou, Z., Chen, X., Li, E., Zeng, L., Luo, K., & Zhang, J. (2019). Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing. Proceedings of the IEEE. https://doi.org/10.1109/JPROC.2019.2918951