A dual-frequency aperiodic planar scanning array with diversified radiation elements is proposed. The proposed element consists of an elliptic patch and two parasitic rectangular patches, which can work both at 5.28−5.33 GHz with difference radiation beam and 5.78−5.83 GHz with sum radiation beam. A four equivalent magnetic currents model has been established to explain the radiation principle of the proposed element. Compared to the beamwidth of the sum beam, the 3 dB beamwidth of the difference beam is broadened about 30% and the radiation gain of the sum beam is obviously improved about 48%. A 64-element aperiodic array with diversified radiation elements is constructed. The array can scan at a wide angle of ±70° with no grating lobes at difference radiation mode and can scan in the range of ±60° with high gain at sum radiation mode.

As is well known, mutual coupling between array elements has a significant negative impact on direction of arrival (DOA) estimation. To achieve DOA estimation under unknown mutual coupling, this paper proposes a low computational complexity Newton-like method. Firstly, a block sparse model based on the signal subspace is established, and the Lagrangian function is established according to the block sparse model. Secondly, since the Hessian matrix of the Lagrangian function cannot always ensure positive definiteness and the computational complexity of the inverse matrix of the Hessian matrix is enormous, the Newton method is no longer applicable. Therefore, this paper proposes a Newton-like method to achieve DOA estimation under mutual coupling and reduce the computational complexity by matrix inversion lemma. Finally, compared with existing methods of DOA estimation under array mutual coupling, the simulation results validate the effectiveness of the proposed method.

The rapid proliferation of unmanned aerial vehicles (UAVs) has increasingly posed significant challenges for airspace security, particularly under long-range and visually degraded conditions. Effective UAV recognition is thus critical, yet current methodologies typically depend on single-sensor inputs, such as infrared (IR) imaging and radio frequency (RF) analysis, which suffer inherent limitations in complex environments. Although multimodal sensing has been explored in UAV detection, the joint exploitation of IR imagery and RF signals for UAV type recognition remains largely underexplored. The structural heterogeneity between IR and RF features presents challenges for joint representation and decision-making, which remains underexplored in previous work. To address this gap, this paper proposes RF-IRSynNet, a multimodal UAV classification framework that integrates IR imagery and in-flight RF emissions to enhance recognition performance. In RF-IRSynNet, IR images are processed using YOLOv11 to detect UAV candidates and extract structured semantic features. Meanwhile, RF signals are modeled using reservoir computing, which efficiently encodes temporal and spectral dynamics via feature sequences. These modalities are fused through an adaptive confidence-weighted soft-voting strategy, dynamically balancing their contributions based on specific tasks. Experimental results demonstrate that RF-IRSynNet outperforms both unimodal baselines and existing multimodal approaches, achieving robust classification at long ranges. The framework maintains high accuracy even with reduced training data, indicating high efficiency for real-world UAV monitoring.

The physical architecture of optical convolution restricts its capacity to capture multi-scale features from targets, thus impeding the precision of network recognition. In this work, we propose a multi-scale optical convolutional neural network (MS-OCNN), which uses convolution kernels with different resolutions in the convolution layer to extract different scale features, along with attention mechanism and residual structure to analyze features. By separating the training and inference platforms of the network, we facilitate the electronic training of model parameters on a computer and the optical deployment on a system equipped with a spatial light modulator, enabling efficient target classification. The proposed MS-OCNN exhibits 1% to 3% improvement in classification performance on the modified national institute of standards and technology (MNIST) and Fashion-MNIST datasets compared to single-scale optical inference models. Online experimental systems in real-world scenarios have validated the target recognition capabilities of this method, which yielded classification accuracies of 97% and 87% on the MNIST and Fashion-MNIST datasets, respectively. This work enhances the feature acquisition capabilities of optical convolutional networks, elevates network recognition accuracy, and significantly propels the application of optical computing in domains such as guidance systems, autonomous driving, and robotics.

To address the energy consumption issues caused by task lengths in task scheduling on heterogeneous multi-core systems, this paper proposes an adaptive parameterized improved simulated annealing algorithm based on the directed acyclic graph task model. The algorithm employs feedback from acceptance rates to dynamically adjust the temperature and neighborhood size of the simulated annealing process. Additionally, it introduces a security mechanism to enhance convergence speed and global search capabilities. Compared against classical simulated annealing and standard heuristic algorithms, the proposed algorithm achieves reductions exceeding 54% in convergence generations, 50% in task slots, and 10% in scheduling time, providing a direction for low-power task scheduling.

Cross-domain feature fusion offers an approach to weak target recognition in complex sea environments. This paper proposes a distance metric learning-based method for weak target classification. The method first extracts three time-domain features and three frequency-domain features from radar echo signals. Then, the features are partitioned and mapped to low-dimensional subspaces using linear projection matrices. The squared Euclidean distance is used as a metric function to measure the similarity between samples, and supervised optimization is performed by introducing information from similar and dissimilar sample pairs. Next, the projection matrices of each group are jointly updated iteratively using the gradient descent method to achieve supervised feature fusion. Finally, the fused feature is input into an ensemble one-class support vector machine (EOCSVM) for classification. Verified by IPIX measured data, the proposed method can effectively improve the separability of targets and sea clutter and improve the classification ability of sea clutter and weak targets under short-time observation. The proposed method enhances the features correlation from different domains through metric learning and EOCSVM, which can effectively alleviate the sample imbalance problem between sea clutter and targets.

Aiming at the issues where traditional direction-of-arrival (DOA) estimation algorithms experience substantial performance degradation in low signal-to-noise ratio environments, and deep learning-based DOA estimation methods rely on massive training data with prolonged model training cycles, this paper proposes two efficient and high-precision DOA estimation methods based on ensemble learning. By formulating DOA estimation as a multi-label classification problem and leveraging the classification chain paradigm, data-driven models, classification chain-random forest (CC-RF) and classification chain-eXtreme gradient boosting (CC-XGBoost), are constructed, which are capable of handling multi-label classification tasks. To verify the effectiveness of the proposed methods, a multi-dimensional comparative experiment is designed to benchmark their performance against the traditional multiple signal classification (MUSIC) algorithm and a convolutional neural network (CNN) model. Experimental results indicate that in both single-source and multi-source scenarios, the proposed CC-RF algorithm exhibits excellent performance, achieving DOA estimation accuracy comparable to the MUSIC algorithm; in multi-source estimation scenarios, both proposed models demonstrate strong noise adaptability. Compared with the traditional MUSIC and CNN algorithms, the estimation error of the CC-XGBoost and CC-RF models is reduced by up to nearly 30 times while maintaining low time complexity, with the single estimation time reduced by approximately 90% compared to traditional methods. This study provides a technical pathway for DOA estimation in complex environments and holds significant application value in fields such as radar detection and wireless communication.

In this paper, the system we consider has multiple inventory warehouses and multiple pieces of equipment with multiple repairable components, where the joint planning of spare components and maintenance workers with lateral and cross-echelon transshipment is studied. Firstly, the characteristics of inventory system is analyzed, and the scheduled relationship of maintenance resources is carded. Based on this, a total system cost model is proposed, incorporating holding, ordering, and maintenance costs under an average waiting time constraint. A hyper-heuristic algorithm is then introduced to efficiently solve larger-scale problems with improved computational speed, and is applied to derive an optimized inventory allocation plan for maintenance resources. Finally, a maintenance system is analyzed, comprising four local warehouses, three central warehouses, and one plant that serves five machine groups. Each group contains four machines, each warehouse supports one or two machines, and every machine includes five independently failing key components. By analyzing the effect on reducing total cost, improving maintenance demand satisfaction rate, the effectiveness of the proposed optimization approach is verified.

The calibration of parameters for onboard stereo cameras is crucial for achieving efficient visual-assisted driving. However, in practical scenarios, low-resolution images often result in inaccuracies in feature point extraction, thereby affecting the accuracy of camera parameter calibration. To address this issue, this paper proposes a self-calibration method for stereo cameras based on joint de-noising, de-mosaic, de-ringing, and super-resolution network (JDDDSN) super-resolution reconstruction. By reconstructing images into higher-resolution images with richer details, feature points are extracted for extrinsic calibration of stereo cameras. For real-world driving scenarios, the reconstructed images achieve noise and ringing artifact reduction while obtaining clearer high-resolution images. This study further investigates the impact of the super-resolution reconstruction network on target area calibration at various distances. Additionally, it highlights the significant role of super-resolution in enhancing stereo camera calibration accuracy by removing dynamic points and focusing on static regions. Through a series of experiments, this paper validates the effectiveness and practicality of the JDDDSN super-resolution reconstruction network in improving stereo camera calibration accuracy, demonstrating its application value in the field of stereoscopic vision.

The evaluation of the equipment contribution rate to system-of-systems (CRSoS) is crucial for optimizing the armament system-of-systems structure and enhancing combat effectiveness. The traditional relative contribution rate method poses limitations by focusing on individual equipment evaluation without considering the interrelations between equipment. In response to the issue, this study proposes a framework based on operation loop and improved Shapley value (OLISV) for analysis to ananlyze the equipment CRSoS. Specifically, a multi-layer network model is first constructed based on complex heterogeneous network and operation loop theory. Next, information entropy and evidence theory are used for the edges of the functional node layer, while improving the parallel node structure within the network. Subsequently, an improved Shapley value contribution rate method based on non-efficiency influencing factors is proposed. Finally, the rationality and effectiveness of the OLISV are illustrated through a case study.