The opaque nature of black-box deep learning (DL) models poses significant challenges for intrusion detection systems (IDSs) in Internet of Things (IoT) networks, where transparency, trust, and operational reliability are critical. Although explainable artificial intelligence (XAI) has been increasingly adopted to enhance interpretability, its impact on detection performance and computational efficiency in resource-constrained IoT environments remains insufficiently understood. This systematic review investigates the performance of an explainable deep learning-based IDS for IoT networks by analyzing trade-offs among detection accuracy, computational overhead, and explanation quality. Following the PRISMA methodology, 129 peer-reviewed studies published between 2018 and 2025 are systematically analyzed to address key research questions related to XAI technique trade-offs, deep learning architecture performance, post-deployment XAI evaluation practices, and deployment bottlenecks. The findings reveal a pronounced imbalance in existing approaches, where high detection accuracy is often achieved at the expense of computational efficiency and rigorous explainability evaluation, limiting practical deployment on IoT edge devices. To address these gaps, this review proposes two conceptual contributions: (i) an XAI evaluation framework that standardizes post-deployment evaluation categories for explainability, and (ii) the Unified Explainable IDS Evaluation Framework (UXIEF), which models the fundamental trilemma between detection performance, resource efficiency, and explanation quality in IoT IDSs. By systematically highlighting performance–efficiency gaps, methodological shortcomings, and practical deployment challenges, this review provides a structured foundation and actionable insights for the development of trustworthy, efficient, and deployable explainable IDS solutions in IoT ecosystems.
Membrane diffraction imaging is one of the most widely used imaging technologies today, which offers the advantages such as lightweight design, large aperture, foldability, and low cost. However, the system imaging quality degrades because of the multiple order diffraction generated by the diffractive elements in practical applications. To eliminate the effects of multiple diffraction orders from the diffractive elements and optimize imaging quality, the system images are post processed. Iterative optimization algorithms are commonly used for image post processing. Particle swarm optimization is a commonly used iterative optimization algorithm, which is often used to search for optimal solutions within the solution space. The particle swarm optimization algorithm has the features of few parameters, simple behavior, and fast iteration speed, which can rapidly and effectively optimize imaging. This paper optimizes the simulated imaging of a diffraction imaging system based on Fresnel zone plates by adopting the particle swarm optimization algorithm. Optimize the system image based on known point spread functions and the system image. System imaging is optimized under the premise of known point spread functions and system imaging. The iteration speed is enhanced, reducing the number of iterations by approximately 99.6 compared to the random parallel gradient descent algorithm. Simultaneously, contrast is improved by about 5.4 , while gradient optimization effectiveness increases by approximately 25.4 after optimization by the particle swarm algorithm. Finally, the derived restoration model was applied to other images, achieving overall improvements in all evaluation metrics.
Silicon carbide (SiC) three-phase converters are widely adopted in parallel power distribution systems for their high efficiency, yet their performance is challenged by high switching frequency and communication constraints. For the parallel inverter system, problems such as uneven power distribution and circulating current may occur. Therefore, the droop control method was proposed. The droop control method is limited in precise power sharing and circulating current mitigation. To address these issues in the communication-free parallel inverter system, a hybrid droop-enhanced virtual impedance method is proposed. The methodology integrates droop characteristics with frequency-selective virtual impedance compensation, enabling concurrent optimization of power sharing and circulating current suppression. Through simulation, the droop control method and the improved droop control method were compared and analyzed. Finally, the effectiveness of the improved droop control method was verified through experiments.
11 July 2026 in Journal of Mechanical Science and Technology
The issues about security and privacy caused by the misuse of unmanned aerial vehicles (UAVs) have attracted increasing attention. Rapid and accurate UAV detection in complex scenarios has become critical for anti-UAV missions. This paper proposes an enhanced model for UAV detection in complex conditions based on YOLO11, aiming to achieve accurate and efficient detection under challenging conditions. Firstly, a small-object detection head is introduced. The large-object detection head is removed. This design improves sensitivity to tiny targets. It also reduces model parameters and increases inference speed. Then, a feature fusion strategy based on FPN is employed to prevent the loss of low-level features that may occur during multi-scale fusion. In addition, the WIoU v3 loss function is incorporated to mitigate oscillations that arise during the regression of small targets. Finally, a feature enhancement module termed C3k2-NAM is proposed. It integrates a normalization-based attention mechanism into the C3k2 block. This design improves the discriminative capability of features for UAV targets. At the same time, it suppresses background interference in complex conditions. The proposed method achieves a comparable inference speed to the baseline model on the DUT Anti-UAV dataset. Precision, recall, mAP0.5, and mAP@0.5 :0.95 increase by 10%, 11%, 8.3%, and 24.3%, respectively. These results demonstrate significant overall performance gains. The improvement in mAP@0.5 :0.95 is particularly notable. Furthermore, the proposed method enables more accurate UAV detection under stricter IoU thresholds in complex environments.