运用人工神经网络的防空系统威胁评估模型

Salih Taşdemir1*, Murat Atan2 1Department of Econometrics, Hacı Bayram Veli University, Türkiye2Department of Econometrics, Hacı Bayram Veli University, Türkiye *Corresponding author E-mail:salihtasdemir35@hotmail.com Received: Dec. 25, 2025Revised: Jan. 11, 2026Accepted: Jan. 13, 2026Online: Jan. 13, 2026 Abstract This study aims to automate threat assessment and target assignment processes inair defense systems using a dynamic, learning artificial intelligence-based model.Unlike threat assessment studies in the literature that use different criteria andmethods, this study integrates missing data completion, multi-criteria analysis, andartificial neural networks to dynamically update the threat score. Furthermore,unlike studies in the literature, the number of criteria used has been increased toenable the model to provide a broader perspective. Most studies are static and usea small number of criteria; this study presents a dynamic, multi-criteria model thatcan handle incomplete data. The developed Geometric Threat Score proposes an Keywords: Threat assessment; Artificial neural networks; Air defense systems; © The Author 2026.Published by ARDA. 1.Introduction Threat assessment and weapon assignment in air defense systems are among the most critical processes fordecision-makers in a combat environment [1]. These decisions are often made within limited time frames andre-quire considering multiple variables simultaneously. Therefore, artificial intelligence-based approaches aregaining importance to reduce human-related errors and create faster decision-making mechanisms. Traditionalmethods often struggle to dynamically adapt to evolving battlefield conditions and new threats [2]. This paper model's high performance with an R-value around 0.95 for regression across various data splits and a low meansquare error (MSE), highlighting its accuracy in predicting threat levels. It has been concluded that the AI-focused approach can significantly increase decision-making speed and accuracy, reduce human error, andprovide a scalable framework for automatic threat prioritization in network-centric air defense systems. Thisstudy takes into account more criteria in order to fill the gap in the literature. A comprehensive data set consisting 2.Literature Review It has been stated that the threat assessment concept and the weapon assignment model should be implemented, A review of the literature reveals that different numbers of different criteria are used and different threatassessment methods are employed. Studies in the literature have grouped threat assessment methods under four Rule-Based Fuzzy Logic: Also defined as gray relational analysis (GRA). It analyzes the relationship be-tweenthreats using gray system theory. As the number of criteria increases, so does the number of rules. Since toomany rules are required, evaluation can be performed with smaller-scale criteria. Expert opinions are re-quired Bayesian Networks and Stochastic Methods: They evaluate threats using probabilistic inference. They are usefulfor uncertain data, but require a large data set for training. It is very difficult to clearly determine the strikeeffectiveness of systems. A sufficient number of strikes and successful outcomes must be obtained. Generating Multi-Criteria Decision-Making Methods: When applying multi-criteria decision-making methods, in caseswhere weights are unknown in the literature, ranking superiority methods such as the Borda Method, CondorcetMethod, and Basic Lexicographic Method are available. Methods for determining the criterion weightsnecessary for calculation also play an important role. The most preferred methods for determining criterionweights are the Simple Cardinal Method,the Analytic Hierarchy Process (AHP), the Critic Method, and the Artificial Neural Networks: The model architecture section, consisting of input, output, and hidden layers, thetraining section comprising the dataset, preprocessing, optimization, and validation stages, and the mathematicalformulation. Criteria are used as input parameters. The number of layers is determined by the activation functionin the hidden layer. The desired result is specified in the output layer. It is necessary to know a sufficient numberof output results for the start. It is important that the data set consists of calculated, validated results. Studies in the literature according to the number of criteria and the method used are shown in the Table 1. Threat perception and reaction time may vary from person to person [1]. It has been noted that threatprioritization may differ depending on the individual or geographical conditions, and that reaction time mayvary [63]. This is due to factors such as the capacity, experience, knowledge base, length of hierarchical approvaltime, and delegation of authority of the individuals performing this task. It has been stated that a decision supportsystem is needed to reduce the initial uncertainty in threat assessm