To address the challenges of high model complexity and low accuracy in detecting small targets in insulator defect detection using UAV aerial imagery, we propose a lightweight algorithm, PAL-YOLOv8. Firstly, the baseline model, YOLOv8n, is enhanced by incorporating the PKI Block from PKINet to improve the C2f module, effectively reducing the model complexity and enhancing feature extraction capabilities. Secondly, Adown from YOLOv9 is employed in the backbone and neck for downsampling, which retains more feature information while reducing the feature map size, thus improving the detection accuracy. Additionally, Focaler-SIoU is used as the bounding-box regression loss function to improve model performance by focusing on different regression samples. Finally, pruning is applied to the improved model to further reduce its size. The experimental results show that PAL-YOLOv8 achieves an mAP50 of 95.0%, which represents increases of 5.5% and 2.6% over YOLOv8n and YOLOv9t, respectively. Furthermore, GFLOPs is only 3.9, the model size is just 2.7 MB, and the parameter count is only 1.24 × 10⁶.

The three greatest theories in science and engineering developed in the 1940s are cybernetics, information theory, and systems theory. Cybernetics is the science of communication and control in humans, machines, organizations, and societies across the reductive hierarchy of neural, cognitive, functional, and logical levels. A contemporary form of cybernetics, known as cognitive informatics (CI), is a transdisciplinary inquiry of cognitive and information sciences that investigates into the internal information processing mechanisms and processes of the brain and natural intelligence and their engineering applications via an interdisciplinary approach. This special issue on cybernetics and CI focuses on the theme of "convergence of CI and cybernetics" which investigates the shared foundations of cybernetics and CI and their impacts on cybernetic and cognitive systems. This editorial demonstrates that the investigation into CI and cybernetics may encouragingly result in fundamental discoveries toward the development of next-generation intelligent systems and cognitive computing technologies.

As one of the five major transportation systems, pipeline plays an important role in the energy transportation systems. In large-scale pipeline transportation systems, security issues such as leaks and explosions are prevalent, thus early detection of leaks is important to reduce security hazards in pipeline systems. Time series-based studies are widely used for leak detection in large-scale pipeline transportation systems, but single time-domain information, which ignores the spatial distribution of pressure sensors and does not consider periodic features, may not be sufficient for the detection accuracy of complex systems. To address it, a leak detection method based on frequency spatial-temporal convolution network (FSTCN) is proposed in this paper. Next, a spatial-encoder module for leak detection is proposed, which considers the spatial correlation of pressure sensors in pipeline systems. Second, a frequency-enhanced attention layer is proposed, which enables the feature extraction module to capture the periodic features of the pressure data. Meanwhile, a network self-updating mechanism is proposed which considers the changes in detection accuracy and data distribution to adapt to the continuously changing conditions of the pipeline systems. Finally, experiments are used to validate the proposed method, and nine time series classification models are chosen for comparison. The comprehensive results demonstrate that the effectiveness and superiority of the proposed leak detection method for large-scale pipeline systems.

To address the challenges of ambiguous smoke morphology, a high proportion of small flame targets, and cluttered backgrounds in forest fire environments, a forest fire smoke detection algorithm, referred to as DFS-D-FINE, is proposed based on the light-weight next-generation real-time object detector D-FINE-N, aiming to improve the de-tection performance of flame and smoke targets in complex forest environments. First, a DB_C2f module is designed to improve the backbone network, thereby enhancing the model’s ability to extract fine-grained and ambiguous features. Then, a hybrid encoder with a feature focusing and diffusion mechanism is introduced to enhance semantic correlations and information interaction among multi-scale features. Finally, an SCMetaFormer encoder block is designed to further enhance the extraction of critical features. Experimental results on the M4SFWD dataset demonstrate that DFS-D-FINE outperforms the baseline model, achieving improvements of 2.7% in AP and 2.1% in AP50, respectively, while the parameter count is only 6.24 × 10⁶ and the GFLOPs is only 11.8. Moreover, experiments on the FireSmokeNEWdataset and mytest-hrswj datasets demonstrate that the proposed method exhibits good generali-zation capability.