This work reports a study into the possibility of using the GoogleNet neural network in the optoelectronic channel of the Data Fusion system. The search for the most accurate algorithms for detecting and recognizing unmanned aerial vehicles (UAVs) in Data Fusion systems has been carried out. The data processing scheme was selected (merging SVF state vectors and merging MF measurements), as well as the sensors and recognition models on each channel of the system. The Data Fusion model based on the Kalman Filter was chosen, integrating radar and optoelectronic channels. Mini-radars LPI-FMCW were used as a radar channel. Evaluation of the effectiveness of the selected Data Fusion channel model in UAV detection is based on the recognition accuracy. The main study is aimed at determining the possibility of using the GoogleNet neural network in the optoelectronic channel for UAV recognition under conditions of different range classes. The neural network for the recognition of drones was developed using transfer training technology. For training, validation, and testing of the GoogleNet neural network, a database has been built, and a special application has been developed in the MATLAB environment. The capabilities of the developed neural network were studied for 5 variants of the distance to the object. The detection objects were the Inspire 2, DJI Phantom 4 Pro, DJI F450, DU 1911 UAVs, not included in the training database. The UAV recognition accuracy by the neural network was 98.13 % at a distance of up to 5 m, 94.65 % at a distance of up to 20 m, 92.47 % at a distance of up to 20 m, 90.28 % at a distance of up to 100 m, and 88.76 % at a distance of up to 200 m. The average speed of UAV recognition by this method was 0.81 s.

The rapid spread of unmanned aerial vehicles (UAVs) has created new challenges for airspace security, as drones are increasingly used for surveillance, smuggling, and potentially for attacks near critical infrastructure. A key difficulty lies in reliably distinguishing UAVs from visually similar birds in electro-optical surveillance channels, where complex backgrounds and visual noise often increase false alarms. To address this, we investigated recent YOLO architectures and developed an enhanced model named YOLOv12-ADBC, incorporating an adaptive hierarchical feature integration mechanism to strengthen multi-scale spatial fusion. This architectural refinement improves sensitivity to subtle inter-class differences between drones and birds. A dedicated dataset of 7291 images was used to train and evaluate five YOLO versions (v8–v12), together with the proposed YOLOv12-ADBC. Comparative experiments demonstrated that YOLOv12-ADBC achieved the best overall performance, with precision = 0.892, recall = 0.864, mAP50 = 0.881, mAP50–95 = 0.633, and per-class accuracy reaching 96.4% for drones and 80% for birds. In inference tests on three video sequences simulating realistic monitoring conditions, YOLOv12-ADBC consistently outperformed baselines, achieving a detection accuracy of 92.1–95.5% and confidence levels up to 88.6%, while maintaining real-time processing at 118–135 frames per second (FPS). These results demonstrate that YOLOv12-ADBC not only surpasses previous YOLO models but also offers strong potential as the optical module in multi-sensor fusion frameworks. Its integration with radar, RF, and acoustic channels is expected to further enhance system-level robustness, providing a practical pathway toward reliable UAV detection in modern airspace protection systems.

The integration of Artificial Intelligence (AI) with Wireless Sensor Networks (WSNs) has substantially advanced the capabilities of these systems to collect, process, and respond to large volumes of sensor data. Machine learning (ML) algorithms, a key component of AI, enable WSNs to detect patterns, trends, and anomalies, thereby enhancing their adaptability and performance in dynamic environments. One particularly impactful application is in aging-in-place systems, where elderly individuals can be continuously monitored for vital signs and daily activities, maintaining independence while benefiting from timely health and safety interventions. As the global elderly population grows, there is a pressing need for intelligent monitoring solutions to support independent living. This review aims to consolidate and critically evaluate existing ML algorithms and sensor technologies used in WSNs for aging-in-place applications. It introduces a structured taxonomy of ML approaches—including supervised, unsupervised, hybrid, and reinforcement learning—and presents a comparative analysis of wearable and environmental sensors. Unlike prior reviews, this work integrates technical performance evaluation with application-specific relevance, offering a unified view of algorithmic capabilities, sensor trade-offs, and practical deployment challenges. Based on a systematic selection process, 124 peer-reviewed articles were analyzed. The review also identifies open research challenges, highlights limitations of current solutions, and proposes targeted future directions to guide the development of adaptive, reliable, and user-centered aging-in-place systems.

The state of the art in deepfake technology demonstrates rapid technological evolution. Machine learning algorithms are becoming increasingly talented at generating synthetic yet realistic media, raising ethical, social security, and political concerns. Concurrently, the increasing frequency of supply chain attacks and Advanced Persistent Threats (APTs) poses an evolving threat to the security of critical infrastructure, drawing the attention of state-level actors. Our research on AI-generated threats explores the fabrication of images that depict non-existent events, demonstrating the ability to create false radar images. Specifically, counterfeit Inverse Synthetic Aperture Radar (ISAR) images, created using Generative Adversarial Networks (GANs), closely resemble real targets and present a significant threat to maritime operations when exploited in supply chain attacks or by APTs. Radar systems are one of the main elements of ship navigational chains that provide vital information on the surrounding area in terms of distance and speed. Real data analysis in this paper has been conducted on an ISAR database extracted from the NATO SET-196 trials, demonstrating the capability of GANs to create convincing fake ISAR images. Such experiments raise awareness of the vulnerabilities of imaging radar systems to novel, AI-generated cyberattacks.