Drones have long been explored by commercial and military users for supply. While several systems offering small payloads in drone delivery have seen operational use, large-scale supply drones have yet to be adopted. A range of setbacks cause this, including technological and operational challenges that hinder their adoption. Here, we evaluate these challenges from a conceptual modelling perspective and forecast their applicability once these barriers are overcome. This study uses technology trend modelling and bibliometric activity mapping methodologies to predict the applicability of specific technologies that are currently identified as operational challenges. Specifically for supply drones, we model trends in technological improvements of battery technology and aircraft control, and project its focus on landing zone autonomy and powertrain. The prediction also focuses on the current state of hybrid power and higher levels of automation required for landing zone operations. These models are validated through several published case studies of small delivery drones and then applied to assess the feasibility and constraints of larger supply drones. A case study involving the conceptual design of a supply drone large enough to move a shipping container is presented to illustrate the critical technologies required to transition large supply drones from concept to operational reality. Key technologies required for large-scale supply drones have yet to build up a critical mass of research activity, particularly on landing zone autonomy and powertrain. Moreover, additional constraints beyond technological and operational challenges could include limitations in autonomy, certification hurdles, regulatory complexity, and the need for greater social trust and acceptance.

The rapid evolution of Artificial Intelligence (AI) has significantly transformed the capabilities, performance, and autonomy of modern mechatronic systems. As industries transition toward intelligent and interconnected manufacturing environments, AI has emerged as a powerful enabler of real-time decision-making, adaptive control, predictive maintenance, and autonomous operation. This review provides a comprehensive analysis of AI integration within mechatronic systems, examining its influence on system performance, autonomy, and manufacturing efficiency. Key AI techniques including machine learning, deep learning, reinforcement learning, evolutionary optimization, and computer vision are evaluated in terms of their applications in control, sensing, diagnostics, and robotics. The paper also highlights advancements in AI-driven motion control, autonomous navigation, sensor fusion, and smart factory operations. Critical challenges such as data requirements, computational constraints, system interoperability, and safety concerns are discussed to identify research gaps. Finally, emerging trends and future directions, such as edge AI, digital twins, explainable AI, and fully autonomous mechatronic cells, are explored. This review consolidates current knowledge and provides insights to guide researchers and practitioners in developing next-generation intelligent mechatronic systems capable of supporting the demands of Industry 4.0 and beyond.

Anonymous communication networks such as the Invisible Internet Project (I2P) are essential for safeguarding privacy and ensuring freedom of expression, necessitating robust performance and security evaluation in controlled environments. Network testbeds offer a reliable alternative to real-world testing. This paper proposes a dynamic modeling framework based on Graph Attention Network (GAT). We introduce a Region-Centric Initialization (RCI) strategy to establish an initial observation anchor, followed by a GAT-based Locality-Aware (GAT-LA) sampling mechanism that treats representative node selection as a dynamic learning task. Experimental results demonstrate that the GAT-LA mechanism significantly outperforms static methods in maintaining long-term similarity to real-world I2P performance metrics. The integrated stability penalty mechanism effectively suppresses excessive topological fluctuations, ensuring temporal smoothness across evolutionary cycles. Furthermore, the RCI strategy provides high engineering flexibility by supporting both automated scoring and target-oriented manual configuration. This paper presents a scalable methodology for dynamic network simulation with enhanced statistical alignment, providing a practical reference for security research within resource-constrained anonymous network ranges or testbeds.

Fast and reliable fault detection is critical in photovoltaic (PV) systems to improve reliability and energy yield and reduce maintenance costs, ensuring safe and efficient operation under varying operating conditions. Although recent data-driven PV fault detection techniques (FDTs) in literature have demonstrated high diagnostic accuracies, they often suffer from practical limitations, offline operation, lack of fault localization and/or inability to concurrently identify faults. To address these challenges, a unified framework is proposed that simultaneously integrates real-time operation, fault classification and localization, and concurrent-fault identification in a single compact diagnostic approach. This is realized by developing a parallel feedforward neural network (FFNN) architecture whose performance is enhanced by a residual model-based structure, resulting in a more interpretable, scalable, reliable and accurate scheme. In addition, Grey Wolf Optimizer–Support Vector Machine (GWO–SVM) feature selection is incorporated to select the most influential diagnostic features, thus reducing data redundancy, enhancing diagnostic accuracy, and shortening training time. The proposed approach was tested to diagnose five types of PV faults (open circuit, short circuit, partial shading, degradation, and simultaneous faults), as well as classify their intensity and location. Simulation results show that the proposed FFNNs consistently outperform conventional Support Vector Machines (SVMs) in classification accuracy, with accuracies exceeding 98% and 99% for fault classification and localization, respectively, and above 95% for noisy data. Moreover, GWO-SVM proved to offer more stable feature subsets compared to Particle Swarm Optimization–SVM (PSO–SVM) in the considered feature selection structure. Simulation results validated the effectiveness of the proposed unified multiclassification fault diagnosis approach, even under system uncertainties, making it suited for real-world PV systems.

Autonomous navigation in mobile robots operating in dynamic and partially known environments demands the coordinated integration of perception, decision-making, and control while ensuring stability, safety, and energy efficiency. This paper presents an integrated navigation framework for differential-drive mobile robots that combines deep learning-based visual perception, reinforcement learning (RL) for high-level decision-making, and a Lyapunov-based trajectory reference generator for low-level motion execution. A convolutional neural network processes RGB-D images to classify obstacle configurations in real time, enabling navigation without prior map information. Based on this perception layer, an RL policy generates adaptive navigation subgoals in response to environmental changes. To ensure stable motion execution, a Lyapunov-based control strategy is formulated at the kinematic level to generate smooth velocity references, which are subsequently tracked by embedded PID controllers, explicitly decoupling learning-based decision-making from stability-critical control tasks. The local stability of the trajectory-tracking error is analyzed using a quadratic Lyapunov candidate function, ensuring asymptotic convergence under ideal kinematic assumptions. Experimental results demonstrate that while higher control gains provide faster convergence in simulation, an intermediate gain value (K = 0.5I) achieves a favorable trade-off between responsiveness and robustness in real-world conditions, mitigating oscillations caused by actuator dynamics, delays, and sensor noise. Validation across multiple navigation scenarios shows average tracking errors below 1.2 cm, obstacle detection accuracies above 95% for human obstacles, and a significant reduction in energy consumption compared to classical A* planners, highlighting the effectiveness of integrating learning-based navigation with analytically grounded control.

Image deraining is a crucial preprocessing task for enhancing the robustness of high-level vision systems under adverse weather conditions. However, most of the existing methods are limited to a single RGB color space, and it is difficult to effectively separate high-frequency rain streaks from low-frequency backgrounds, resulting in color distortion and detail loss in the restored image. Therefore, a rain removal network that combines dual-color space and frequency domain priors is proposed. Specifically, the devised network employs a dual-branch Transformer architecture to extract color and structural features from the RGB and YCbCr color spaces, respectively. Meanwhile, a Hybrid Attention Feedforward Block (HAFB) is constructed. HAFB achieves feature enhancement and regional focus through a progressive perception selection mechanism and a multi-scale feature extraction architecture, thereby effectively separating rain streaks from the background. Furthermore, a Wavelet-Gated Cross-Attention module is designed, including a Wavelet-Enhanced Attention Block (WEAB) and a Dual Cross-Attention module (DCA). This design enhances the complementary fusion of structural information and color features through frequency-domain guidance and bidirectional semantic interaction. Finally, experimental results on multiple datasets (i.e., Rain100L, Rain100H, Rain800, Rain12, and SPA-Data) demonstrate that the proposed method outperforms other approaches.

The past years have seen a progressive process of urbanization and upgrading, along with the intelligentialization and popularity of supply-demand sides through advanced information and communication technologies [...]

No systematic review has previously examined the application of large language models (LLMs) for generating impressions from radiology report findings. This study systematically reviews the performance of LLMs on this task and their associated evaluation methodologies. A search of seven electronic databases on 7 August 2025 identified 15 eligible papers (average quality score: 71.4%). These articles evaluated 35 LLMs, including 21 base models. The reported performance ranges were as follows: Recall-Oriented Understudy for Gisting Evaluation (ROUGE)-1, 35.9% (Generative Pre-Trained Transformer (GPT)-4) to 69.7% (Baichuan2-13B); ROUGE-2, 13.4% (Large Language Model Meta AI (Llama)) to 52.4% (Baichuan2-13B); and ROUGE-L, 16.5% (Chat General Language Model–Medical (ChatGLM-Med)) to 63.8% (finetuned Text-to-Text Transfer Transformer (T5)). The finetuned T5 consistently demonstrated high performance, based on Bidirectional Encoder Representations from Transformers Score (BERTScore): 89.2%; BiLingual Evaluation Understudy (BLEU)-1: 65.2%; BLEU-2: 57.9%; BLEU-3: 52.5%; BLEU-4: 48.3%; Metric for Evaluation of Translation with Explicit ORdering (METEOR): 38.1%; ROUGE-1: 59.9%; ROUGE-2: 50.9%; ROUGE-L: 63.8%; and subjective metrics (clinical usability: 4.5/5.0; completeness: 4.3/5.0; conciseness: 4.3/5.0; fluency: 4.4/5.0). These results, based on 132,043 computed tomography, echocardiography, magnetic resonance imaging, and X-ray reports, indicate its strong clinical potential for assisting radiologists in impression generation through supervised finetuning rather than prompting techniques used in closed-source LLMs.

Whole-body vibration (WBV) remains a critical factor influencing ride comfort, driver performance and occupational health in vehicle applications. Despite the widespread use of standardized indicators, assessing WBV exposure and its perceptual implications remains challenging due to the complex interaction between road excitation, vehicle dynamics, seat transmissibility and human biodynamic response. This review provides a comprehensive synthesis of contemporary methods for WBV assessment, emphasizing their theoretical foundations, practical implementation and inherent limitations. The paper examines classical evaluation metrics, including frequency-weighted root mean square acceleration and vibration dose value, alongside complementary approaches such as overall vibration total value, absorbed power and motion sickness indicators. Biodynamic modeling strategies for the human–seat–vehicle system are critically reviewed, highlighting trade-offs between model simplicity and physiological realism. Particular attention is given to road surface representation and excitation modeling, discussing the implications of ISO 8608-based stochastic profiles versus measured, time-domain inputs on WBV assessment outcomes. Simulation frameworks, experimental platforms and driving simulators are reviewed as complementary tools for evaluating vibration exposure and validating predictive models. Emerging methods, including time–frequency analysis and data-driven approaches, are discussed with a focus on interpretability, validation and integration with established standards such as ISO 2631. The review consolidates recent advances in integrated evaluation approaches, including the role of driving simulators and simulation-, hardware- and driver-in-the-loop (SiL/HiL/DiL) frameworks as enabling tools for repeatable testing, objective–subjective comfort correlation and early-stage vibration-control development. By critically examining both established and emerging methodologies, this review aims to support informed selection and interpretation of WBV assessment tools in vehicle design and evaluation. The findings underscore the need for integrated, transparent and application-oriented approaches to advance vibration comfort assessment and guide future research and standardization efforts.

Obstructive sleep apnea (OSA) is a common sleep disorder that impacts patient health and imposes a burden on families and healthcare systems. The diagnosis of OSA is usually performed through overnight polysomnography (PSG) in a hospital setting. In recent years, OSA detection using a single-lead electrocardiogram (ECG) has been explored. The advantage of this method is that patients can be measured in home environments. Thus, the aim of this study was to predict occurrences of sleep apnea with parameters extracted from previous single-lead ECG measurements. The parameters were the R-R interval (RRI) and R-wave amplitude (RwA). The dataset was the single-lead ECG Apnea-ECG Database, and a stacking hybrid architecture (SHA) including three gated recurrent neural network architectures (GRNNAs) and logistic regression was proposed to improve the accuracy of OSA detection. Three GRNNAs used three different recurrent neural networks: Bidirectional Long Short-Term Memory (BiLSTM), Gated Recurrent Unit (GRU), and Bidirectional GRU (BiGRU). The challenge of this method was in exploring how many minutes of previous RRI and RwA measurements (n minutes) have the best performance in predicting occurrences of sleep apnea in the future (h minutes). The results showed that the SHA under an n of 20 min had the best performance in predicting occurrences of sleep apnea in the following 10 min: the SHA achieved a precision of 95.79%, sensitivity of 94.74%, specificity of 97.48%, F1-score of 95.26%, and accuracy of 96.45%. The proposed SHA was successful in predicting future sleep apnea occurrence with a single-lead ECG. Thus, this approach could be used in the development of wearable sleep monitors for the management of sleep apnea.