A 5G metasurface (MS) transmitarray (TA) feed by compact-antenna array with the performance of high gain and side-lobe level (SLL) reduction is presented. The proposed MS has two identical metallic layers etched on both sides of the dielectric substrate and four fixed vias connecting two metallic layers that works at 28 GHz to increase the transmission phase shift range. The proposed planar TA consisting of unit cells with different dimensional information can simulate the function as an optical lens according to the Fermat’s principle, so the quasi-spherical wave emitted by the compact Potter horn antenna at the virtual focal point will transform to the quasi-plane wave by the phase-adjustments. Then, the particle swarm optimization (PSO) is introduced to optimize the phase distribution on the TA to decrease the SLL further. It is found that the optimized TA could achieve 27 dB gain at 28 GHz, 11.8% 3 dB gain bandwidth, −30 dB SLL, and aperture efficiency of 23% at the operating bandwidth of 27.5–29.5 GHz, which performs better than the nonoptimized one. The advanced particularities of this optimized TA including low cost, low profile, and easy to configure make it great potential in paving the way to 5G communication and radar system.

Low-altitude unmanned aerial vehicles (UAVs) and unmanned ground vehicles (UGVs), which boast high-resolution imaging and agile maneuvering capabilities, are widely utilized in military scenarios and generate a vast amount of image data that can be leveraged for textual intelligence generation to support military decision making. Military image captioning (MilitIC), as a visual-language learning task, provides innovative solutions for military image understanding and intelligence generation. However, the scarcity of military image datasets hinders the advancement of MilitIC methods, especially those based on deep learning. To overcome this limitation, we introduce an open-access benchmark dataset, which was termed the Military Objects in Real Combat (MOCO) dataset. It features real combat images captured from the perspective of low-altitude UAVs or UGVs, along with a comprehensive set of captions. Furthermore, we propose a novel encoder–augmentation–decoder image-captioning architecture with a map augmentation embedding (MAE) mechanism, MAE-MilitIC, which leverages both image and text modalities as a guiding prefix for caption generation and bridges the semantic gap between visual and textual data. The MAE mechanism maps both image and text embeddings onto a semantic subspace constructed by relevant military prompts, and augments the military semantics of the image embeddings with attribute-explicit text embeddings. Finally, we demonstrate through extensive experiments that MAE-MilitIC surpasses existing models in performance on two challenging datasets, which provides strong support for intelligence warfare based on military UAVs and UGVs.

In recent years, extreme learning machine (ELM) and its improved algorithms have been successfully applied to various classification and regression tasks. In these algorithms, MSE criterion is commonly used to control training error. However, MSE criterion is not suitable to deal with outliers, which can exist in general regression or classification tasks. In this paper, a novel extreme learning machine under minimum information divergence criterion (ELM-MinID) is proposed to deal with the training set with noises. In minimum information divergence criterion, the Gaussian kernel function and Euclidean information divergence are utilized to substitute the mean square error (MSE) criterion to enhance the anti-noise ability of ELM. Experimental results on two synthetic datasets and eleven benchmark datasets show that this method is superior to traditional ELMs.