Askeri Taktik Ağlarda Derin Makine Öğreniminin Etkisi

Yıl 2024, Cilt: 20 Sayı: 2, 303 - 326, 01.11.2024

Fuat Özçakmak

https://doi.org/10.17134/khosbd.1355231

Öz

Askeri operasyonlar, her zaman strateji ve taktiklerin etkili bir şekilde kullanılmasını gerektirmektedir. Bu gerekliliğin şekil verdiği teknolojik ilerlemeler, günümüzde askeri güçlerin daha verimli ve etkili kullanılmasını sağlamaktadır. Derin makine öğrenimi gibi yapay zekâ yöntemleri, askeri taktiklerin geliştirilmesi ve uygulanmasında önemli bir rol oynamıştır. Bu taktiklerden biri de Askeri Taktik Ağların tüm harp alanında kullanılması sayesinde yaşanmaktadır. Ancak harp alanında Askeri Taktik Ağlar tarafından üretilen büyük verinin korelasyon yapılarak karar destek sistemlerine anlık bilgi olarak aktarılabilmesi ve doğru kararları zamanında verebilmesi zor bir süreç olup, normal insan zekâsı ile yapılamayacağı aşikârdır. Bu noktada Yapay zekâ uygulamalarından biri olan Derin Makine Öğrenimini askeri taktik ağlar ile bütünleştirmek, daha hızlı ve isabetli tahminler sağlayabilir, kısıtlamaları hafifletebilir, askerler üzerindeki aşırı bilgi yüklemesini azaltabilir ve ağ savunma stratejilerini iyileştirebilir. Bu makalede, Askeri Taktik Ağların Derin Makine Öğrenimi ile bütünleştirilmesi durumunda harp sahasındaki askeri operasyonların anlamlı bir oranda değişip değişmeyeceği incelenmiştir. Konu hakkında yapılan literatür incelemesi çerçevesinde elde edilen veriler ile halen kullanılmakta olan askeri taktik ağ konseptleri ve geliştirilmekte olan yapay zekâ uygulamaları ele alınarak, Derin Makine Öğreniminin askeri taktik ağlardaki etkisi, potansiyel uygulamaları ve faydaları incelenmiş ayrıca askeri taktiklerin geliştirilmesinde ve optimize edilmesinde olası kullanım sahaları tespit edilmeye çalışılmıştır. Çalışmadan elde edilen bulgulardan hareketle, bu makalede varılan sonuçların, askeri taktik ağların teknoloji gelişim tahminlerine kaynak olarak kullanılabileceği ve askeri stratejilerin geliştirilmesine katkı sağlayabileceği değerlendirilmektedir.

Anahtar Kelimeler

Derin Makine Öğrenimi (DML), Askeri Taktik Ağlar (ATA), Yapay Zekâ, Askeri İletişim, Derin Sinir Ağları.

Kaynakça

• [1] M. Atalay ve E. Çelik, “Büyük Veri Analizinde Yapay Zekâ ve Makine Öğrenmesi Uygulamaları- Artificial Intelligence and Machine Learning Applications in Big Data Analysis,” Mehmet Akif Ersoy Üniversitesi Sosyal Bilimler Enstitüsü Dergisi, cilt 9, no. 22, pp. 155-172, 2017. DOI: 10.20875/makusobed. 309727.
• [2] S. Patel, “A Comprehensive Analysis of Convolutional Neural Network Models,” International Journal of Advanced Science and Technology, cilt 29, no. 4, pp. 771-777, 2020., DOI: 10.1109/ICUE49301.2020.9307089
• [3] A. Testolin, W. Y. Zou ve J. L. McClelland, “Numerosity discrimination in deep neural networks: Initial competence, developmental refinement and experience statistics,” Developmental Science, cilt 23, no. 5, 24 January 2020. DOI: 10.1111/desc.12940
• [4] K. Goztepe, V. Dizdaroğlu ve Ş. Sağıroğlu, “New directions in military and security studies: artificial intelligence and military decision making process,” International Journal of Information Security Science, cilt 4, no. 2, pp. 69- 80, 2015.
• [5] N. Barışçı ve S. Sarıkaya, “Real-Time Multiple Objects Detection Using Yolo and Retinanet From Video and Camera,” UppsalaSWEDEN, 2019. DOI:10.56979/601/2023
• [6] A. Yazici, Koyuncu Murat, S. A. Sert ve T. Yilmaz, “A Fusion-Based Framework for Wireless Multimedia Sensor Networks in Surveillance Applications,” IEEE Access, cilt 7, pp. 88418-88434, 2019. DOI: 10.1109/ACCESS. 2019.2926206
• [7] A. Stoica, D. Militaru, D. Moldoveanu ve A. Popa, “TACTICAL DATA LINK – FROM LINK 1 TO LINK 22,” Sci. Bull. Mircea cel Batran Naval Acad, cilt 19, no. 2, pp. 316-322, 2016. DOI: 10.21279/1454-864x-16-i2-046.
• [8] J. Schubert, J. Brynielsson, M. Nilsson ve P. Svenmarck, “Artificial Intelligence for Decision Support in Command and Control Systems,” 23rd International Command and Control Research & Technology Symposium “Multi-Domain C2”, 2018.
• [9] N. Suri, G. Benincasa, R. Lenzi, M. Tortonesi, C. Stefanelli ve L. Sadler, “Exploring value-of-information-based approaches to support effective communications in tactical networks,” IEEE Communications Magazine, cilt 53, no. 10, pp. 39-45, 2015. DOI: 10.1109/ MCOM.2015.7295461
• [10] I. Ahmad, K. Shah ve S. Ullah, “Military Applications using Wireless Sensor Networks: A survey,” International Journal of Engineering Science and Computing, cilt 6, no. 6, pp. 7039- 7043, June 2016.
• [11] L. Chen, S. Li, Q. Bai, J. Yang, J. Sanlong ve Miao Yanming, “Review of Image Classification Algorithms Based on Convolutional Neural Networks,” Remote Sensing, cilt 13, no. 22, p. 4712, 2012. DOI: 10.3390/rs13224712.
• [12] J. Saxe ve K. Berlin, “Deep neural network based malware detection using two dimensional binary program features,” 10th International Conference on Malicious and Unwanted Software (MALWARE), Fajardo, PR, USA, 2015. DOI:10.1109/MALWARE.2015.7413680.
• [13] J. Romeo, “The coming of age of artificial intelligence,” 20 April 2023. https://www.militaryaerospace.com/computers/a rticle/14290944/artificial-intelligence-machinelearning. (01.06.2023).
• [14] E. Granger, J. F. Connolly ve R. Sabourin, “A Comparison of Fuzzy ARTMAP and Gaussian ARTMAP Neural Networks for Incremental Learning,” IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence), Hong Kong, China, 2008. DOI: 10.1109/IJCNN.2008.4634267.
• [15] M. Coşkun, A. Uçar, Ö. Yıldırım ve Y. Demir, “Face recognition based on convolutional neural network,” Face recognition based on convolutional neural network, Kremenchuk, Ukraine, 2017. DOI: 10.1109/MEES.2017.8248937.
• [16] S. Lawrence, L. Giles, A. C. Tsoi ve A. D. Back, “Face recognition: a convolutional neuralnetwork approach,” IEEE Transactions on Neural Networks, cilt 8, no. 1, pp. 98-113, January 1997. DOI: 10.1109/72.554195.
• [17] P. Kamencay, M. Benco, T. Mizdos ve R. Radil, “A New Method for Face Recognition Using Convolutional Neural Network,” Advances In Electrical And Electronic Engineering, cilt 15, no. 4, pp. 663-672, 2017. DOI:10.15598/aeee.v15i4.2389.
• [18] J. Redmon, S. Divvala, R. Girshick ve A. Farhadi, “You Only Look Once: Unified, RealTime Object Detection,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016. DOI:10.1109/CVPR.2016.91.
• [19] Z. Feng, X. Zhu, L. Xu ve Y. Liu, “Research on Human Target Detection and Tracking Based on Artificial Intelligence Vision,” IEEE AsiaPacific Conference on Image Processing, Electronics and Computers (IPEC), Dalian, China, 2021. DOI:10.1109/IPEC51340.2021. 9421306.
• [20] A. Rohan, M. Rabah ve S.-H. Kim, “Convolutional Neural Network-Based RealTime Object Detection and Tracking for Parrot AR Drone 2,” IEEE Access, pp. 69575-69584, 2019. DOI:10.1109/ACCESS.2019.2919332.
• [21] Y. Chen, X. Yang, B. Zhong, S. Pan, D. Chen ve H. Zhang, “CNNTracker: Online discriminative object tracking via deep convolutional neural network,” Applied Soft Computing, cilt 38, pp. 1088-1098, 2016. DOI: 10.1016/j.asoc.2015.06.048.
• [22] Y. Wang, X. Luo, L. Ding, S. Fu ve X. Wei, “Detection based visual tracking with convolutional neural network,” KnowledgeBased Systems, cilt 175, pp. 62-71, 2019. DOI: 10.1016/j.knosys.2019.03.01. [23] M. A. Demirtaş, “Derin Öğrenme Yöntemleri ile 3B Nokta Bulutlarının Semantik Segmentasyonuna Genel bir Bakış,” Duzce University Journal of Science and Technology, cilt 11, no. 1, pp. 342-357, 2023. DOI: 10.29130/dubited.1004211.
• [24] O. Güler ve İ. Yücedağ, “Derin Öğrenme İle El Hareketi Tanıma Üzerine Yapılan Çalışmaların İncelenmesi” 21. Akademik Bilişim konferansı., 2019.
• [25] L. Zhang, Z. Sheng, Y. Li, Q. Sun, Y. Zhao ve D. Feng, “Image object detection and semantic segmentation based on convolutional neural network,” Neural Comput & Applic, p. 1949– 1958, 2020. DOI:10.1007/s00521-019-04491-4.
• [26] M. Ren, W. Zeng, B. Yang ve R. Urtasun, “Learning to Reweight Examples for Robust Deep Learning,” 35th International Conference on Machine Learning, Stockholm, Sweden, 2018.
• [27] B. R. Kiran, I. Sobh, V. Talpaert, P. Mannion, A. A. A. Sallab, S. Yogamani ve P. Pérez, “Deep Reinforcement Learning for Autonomous Driving: A Survey,” EEE Transactions on Intelligent Transportation Systems, cilt 23, no. 6, pp. 4909-4926, Haziran 2022. DOI: 10.1109/TITS.2021.3054625.
• [28] X. Zhou, W. Gong, W. Fu ve F. Du, “Application of deep learning in object detection,” 16th International Conference on Computer and Information Science (ICIS), Wuhan, China, 2017. DOI:10.1109/ICIS.2017. 7960069.
• [29] M. Bistron ve Z. Piotrowski, “Artificial Intelligence Applications in Military Systems and Their Influence on Sense of Security of Citizens,” Electronics, cilt 10, no. 7, p. 871, 2021. DOI:10.3390/electronics10070871.
• [30] S. Joshi, A. Thakar ve C. Patel, “Applications of Machine Learning and Deep Learning in Securing Internet of Battlefield Things: A Futuristic Perspective,” 10th International Conference on Computing for Sustainable Global Development (INDIACom), Delhi, India, 2023.
• [31] P. F. Lamas, L. C. Ribas, A. M. Mendez ve J. C. Albar, “Evolving Military Bradband Wireless Communication Systems: WiMAX, LTE and WLAN,” International Conferance on Military Communications and Information Systems (ICMCIS), Brüksel, Belçika, 2016. DOI: 10.1002/9781119892199.ch20 [32] M. N. Sadiku, O. I. Fagbohungbe ve S. M. Musa, “Artificial intelligence in cyber security,” International Journal of Engineering Research and Advanced Technology, cilt 6, no. 5, pp. 1-7, 2020. DOI:10.1088/1742-6596/1964/4/042072
• [33] M. M. Yamin, M. Ullah ve B. Katt, “Weaponized AI for cyber attacks,” Journal of Information Security and Applications, cilt 57, 2021. DOI:10.1016/j.jisa.2020.102722
• [34] A. Gökdemir ve A. Çalhan, “Deep learning and machine learning based anomaly detection in internet of things environments,” Journal of the Faculty of Engineering and Architecture of Gazi University, cilt 37, no. 4, pp. 1945-1956, 2022. DOI: 10.17341/gazimmfd.962375
• [35] D. Tsadikovich, E. Levner ve H. Tell, “AIBased Integrated Scheduling of Production and Transportation Operations within Military Supply Chains,” Advances in Artificial Intelligence: 9th Mexican International Conference on Artificial Intelligence, MICAI, Berlin, 2010. DOI: 10.1007/978-3-642-16761- 4_19. [36] N. Abell, “7 Key Military Applications of Machine Learning,” 2 October 2020. https://medium.com/@nqabell89/7-key-military-applications-of-machine-learning-9818dfa2ea86. (08.08.2023).
• [37] M. Woschank, E. Rauch ve H. Zsifkovits, “A Review of Further Directions for Artificial Intelligence, Machine Learning, and Deep Learning in Smart Logistics,” Sustainability, cilt 12, no. 9, p. 3760, 2020. DOI:10.3390/su12093760.
• [38] S. C. Shu ve T. H. Xing, “Application of AI in Modern Logistics Systems,” 11th International Conference on Information Technology in Medicine and Education (ITME), Wuyishan, Fujian, China, 2021. DOI:10.1109/ITME53901.2021.00015.
• [39] C. Crosby, “Operationalizing Artificial Intelligence for Algorithmic Warfare,” JulyAugust 2020. https://www.armyupress.army.mil/Journals/Milit ary-Review/English-Edition-Archives/JulyAugust-2020/Crosby-Operationalizing-AI/. (09.08.2023).
• [40] S. Fei-fei, Z. Zhi-Min, W. Yue-liang, X. Yang, Z. Fan ve N. Huan-sheng, “Application progress of artificial intelligence in military confrontation.” Chinese journal of engineering, cilt 42, no. 9, pp. 1106-1118, 2020. DOI: 10.13374/j.issn2095-9389.2019.11.19.001.
• [41] B. L. Yoon, "Artificial neural network technology," ACM SIGSMALL/PC Notes, vol. 15, no. 3, pp. 3-16, Agust 1989.
• [42] S. Yuan ve X. Wu, “Deep learning for insider threat detection: Review, challenges and opportunities,” Computers & Security, cilt 104, 2021. DOI: 10.1016/j.cose.2021.102221.
• [43] S. Panesar, C. Yvonne, D. Chander, J. Morey, J. Fernandez-Miranda ve M. Kliot, “Artificial Intelligence and the Future of Surgical Robotics,” Annals of surgery, cilt 270, no. 2, pp. 223-226, 2019. DOI:10.1097/SLA. 0000000000003262.
• [44] Y. Zhang, Z. Dai, L. Zhang, Z. Wang, L. Chen ve Y. Zhou, “Application of Artificial Intelligence in Military: From Projects View,” 6th International Conference on Big Data and Information Analytics (BigDIA), Shenzhen, China, 2020. DOI:10.1109/BigDIA51454.2020. 00026.
• [45] S. Bhavya and A. S. Pillai, "Prediction Models in Healthcare Using Deep Learning," in Proceedings of the 11th International Conference on Soft Computing and Pattern Recognition (SoCPaR 2019), 2020. DOI: 10.1007/978-3-030- 49345-5_21.
• [46] O. S. Pianykh, S. Guitron, D. Parke, C. Zhang, P. Pandharipande, J. Brink ve D. Rosenthal, “Improving healthcare operations management with machine learning,” Nature Machine Intelligence, cilt 5, no. 2, pp. 266-273, 18 May 2020. DOI:10.1038/s42256-020-0176-3.
• [47] V. P. Gurupur, S. A. Kulkarni, X. Liu, U. Desai ve A. Nasir, “Analysing the power of deep learning techniques over the traditional methods using medicare utilisation and provider data,” Journal of Experimental & Theoretical Artificial Intelligence, cilt 31, no. 1, pp. 99-115, 2018. DOI:10.1080/0952813X.2018.1518999
• [48] A. J. Fawkes, “Developments in Artificial Intelligence: Opportunities and Challenges for Military Modeling and Simulation.” 017 NATO M&S Symposium, 2017.
• [49] C. Tsatsoulis, “A Review Of Artificial Intelligence In Simulation,” ACM SIGART Bulletin, cilt 2, no. 1, p. 115–121, 1991. DOI: 10.1145/122388.106234
• [50] J. L. Burbank, P. F. Chimento, B. K. Haberman ve W. T. Kasch, “Key Challenges of Military Tactical Networking and the Elusive Promise of MANET Technology,” IEEE Communications Magazine, cilt 44, no. 11, pp. 39-45, November 2006. DOI: 10.1109/COMM.2006.24815.
• [51] M. A. Ali, Q. Guan, R. Umer, W. J. Cantwell ve T. Zhang, “Deep learning based semantic segmentation of µCT images for creating digital material twins of fibrous reinforcements,” Composites Part A: Applied Science and Manufacturing, cilt 139, December 2020. DOI: 10.1016/j.compositesa.2020.106131.
• [52] M. Bistron ve Z. Piotrowski, “Artificial Intelligence Applications in Military Systems and Their Influence on Sense of Security of Citizens,” Electronics, cilt 10, no. 7, pp. 127-145, 2021. DOI:10.3390/electronics10070871.
• [53] A. Kim, Y. Yang, S. Lessmann, T. Ma, M. - C. Sung ve J. E. Johnson, “Can deep learning predict risky retail investors? A case study in financial risk behavior forecasting,” European Journal of Operational Research, cilt 283, no. 1, pp. 217-234, 16 May 2020. DOI:10.1002/isaf. 1532.