This paper examines traditional machine learning algorithms, neural networks, and the benefits of utilizing ensemble models. Data preprocessing methods for improving the quality of classification models are considered. To balance the classes, Undersampling, Oversampling, and their combination (Over + Undersampling) algorithms are explored. A procedure for reducing feature correlation is proposed. Classification models based on meta-algorithms such as SVM, KNN Naive Bayes, Perceptron, Bagging, Random Forest, AdaBoost, and Gradient Boosting have been thoroughly investigated. The settings of the base classifiers and meta-algorithm parameters have been optimized. The best result was obtained by using an ensemble classifier based on the Random Forest algorithm. Thus, an intrusion detection method based on the preprocessing of highly correlated and imbalanced data has been proposed. The scientific novelty of the obtained results lies in the integrated use of the developed procedure for reducing feature correlation, the application of the SMOTEENN data balancing method, the selection of an appropriate classifier, and the fine tuning of its parameters. The integration of these procedures and methods resulted in a higher F1 score, reduced training time, and faster recognition speed for the model. This allows us to recommend this method for practical use to improve the quality of network intrusion detection.

Ensuring the resilient navigation of unmanned aerial vehicles (UAVs) under conditions of limited or unstable sensor information is one of the key challenges of modern autonomous mobility within smart infrastructure and sustainable development. This article proposes an intelligent autonomous UAV control method based on the integration of geometric trajectory modeling, neural network-based sensor data filtering, and reinforcement learning. The geometric model, constructed using path coordinates, allows the trajectory tracking problem to be formalized as an affine control system, which ensures motion stability even in cases of partial data loss. To process noisy or fragmented GPS and IMU signals, an LSTM-based recurrent neural network filter is implemented. This significantly reduces positioning errors and maintains trajectory stability under environmental disturbances. In addition, the navigation system includes a reinforcement learning module that performs real-time obstacle prediction, path correction, and speed adaptation. The method has been tested in a simulated environment with limited sensor availability, variable velocity profiles, and dynamic obstacles. The results confirm the functionality and effectiveness of the proposed navigation system under sensor-deficient conditions. The approach is applicable to environmental monitoring, autonomous delivery, precision agriculture, and emergency response missions within smart regions. Its implementation contributes to achieving the Sustainable Development Goals (SDG 9, SDG 11, and SDG 13) by enhancing autonomy, energy efficiency, and the safety of flight operations.