Weak feature enhancement is an important and intractable issue in machine vision fields. In this paper, an effective complex-scene inverse synthetic aperture radar (ISAR) image feature enhancement method is proposed based on spatial neighborhood sparse constraint hybrid clustering oversegmentation (SNSC-HCOS). A hybrid superpixel concept is first developed considering the consistency of pixel labels and the discrimination of perturbations. The scattering characteristic similarity, spatial proximity, neighborhood information, sparsity bias, and overall image features are simultaneously explored. The SNSC-HCOS algorithm is designed based on the hybrid superpixel concept, data reconstruction, and fuzzy c-means (FCM) clustering. Both sparsity constraints and local spatial information constraints are embedded into the oversegmentation framework, improving the perturbation defense capability and clustering robustness. To correct misclassified pixel membership and improve system efficiency, median membership filtering and area merging strategies are further applied. Extensive qualitative and quantitative experiments are conducted on a real-scene dataset, demonstrating that SNSC-HCOS greatly outperforms the outstanding comparison systems. The proposed system has good segmentation performance, can generate more pure superpixels with regular shapes and uniform sizes, and has perturbation defense and feature enhancement capabilities.

This study presents a knowledge graph construction scheme leveraging large language models (LLMs) for task-oriented semantic communication systems. The proposed methodology systematically addresses four critical stages: corpus collection, entity extraction and relationship analysis, knowledge base generation, and dynamic updating mechanisms. It is worth noting that prompt engineering is combined with few-shot learning to enhance reliability and accuracy in this methodology. Experimental demonstration showed that this methodology had superior entity extraction performance, achieving 89.7% precision and 92.3% recall rate. This scheme overcomes the demand for domain knowledge and the labor cost of traditional knowledge base construction schemes. It greatly improves the construction efficiency of knowledge graphs. This paper provides an efficient and reliable task knowledge base construction scheme for task-oriented semantic communication, which is expected to promote its wider application.

With the tight couplings between the power grid and communication networks, smart grid is vulnerable to cyber-physical attacks, which can inject imperceptive perturbations to cause cascading failures. Nevertheless, as a dynamic and evolving process, it remains challenging to precisely lock the susceptible components that initiate a cascading event. To address this issue, we formulate a bi-level optimization problem in the context of cyber-physical attacks to model the attacker-operator adversarial game and generate an optimal attack strategy for electricity vulnerability assessments. Specifically, we merge the electrical overloading, topological proximity and outage correlations to construct a dense overload subgraph, which is critical for cascading propagation, by making use of fractional program to capture the density of subgraph with maximum average degree. We then compute exact solutions by adopting multiple linearization techniques to convert this bi-level fractional program into a mixed-integer linear program. Numerical studies in IEEE different-scale power systems verify the effectiveness of our model in understanding the cascading risk for a smart grid.

With the development of artificial intelligence and computer hardware, semantic communication has been attracting great interest. As an emerging communication paradigm, semantic communication can reduce the requirement for channel bandwidth by extracting semantic information. This is an effective method that can be applied to image acquisition of unmanned aerial vehicles, which can transmit high-data-volume images within the constraints of limited available bandwidth. However, the existing semantic communication schemes fail to adequately incorporate the guidance of task requirements into the semantic communication process and are difficult to adapt to the dynamic changes of tasks. A task-oriented image semantic communication scheme driven by knowledge base is proposed, aiming at achieving high compression ratio and high quality image reconstruction, and effectively solving the bandwidth limitation. This scheme segments the input image into several semantic information unit under the guidance of task requirements by Yolo-World and Segment Anything Model. The assigned bandwidth for each unit is according to the task relevance scores, which enables high-quality transmission of task-related information with lower communication overheads. An improved metric weighted learned perceptual image patch similarity (LPIPS) is proposed to evaluate the transmission accuracy of the novel scheme. Experimental results show that our scheme achieves a notable performance improvement on weighted LPIPS while the same compression ratio compared with traditional image compression schemes. Our scheme has a higher target capture ratio than traditional image compression schemes under the task of target detection.