Sensor networks in IoT play a crucial role in harsh and complex environments, such as pipeline monitoring and irregular terrains. Traditional geographic OR (GOR) schemes that rely on Euclidean distance for packet forwarding are often unsuitable for irregular network topologies, frequently resulting in incorrect forwarding directions and routing holes. To address the limitations, this paper proposes a Manifold Learning-based Geographic Opportunistic Routing (MLGOR) scheme for 3D strip sensor networks. Inspired by the Isomap algorithm, MLGOR first maps the irregular 3D network onto a regular 2D strip network, enabling the construction of effective forwarding candidates using Euclidean distance and thus mitigating topological issues. A novel forwarding node selection scheme is then introduced that combines both node and network-based metrics. This hybrid approach calculates forwarding priorities and leverages connectivity to minimize duplicate transmissions, supplemented by a time-based coordination mechanism. The applicability of MLGOR is discussed, and simulation results demonstrate its energy efficiency in low-reliability and irregular 3D network environments, thereby extending network lifetime.

Accurate inversion of low altitude atmospheric temperature and humidity is crucial for weather forecasting and climate monitoring. This letter introduces the MR-TH method, a deep learning approach that uses convolutional neural networks and Transformer architecture to invert low altitude three-dimensional atmospheric temperature and humidity distribution from airborne microwave radiometer data. By capturing nonlinear relationships and spatial correlations, MR-TH improves the inversion accuracy of traditional methods. This network is trained and validated using onboard flight data, reanalysis products, and radiosonde measurements. The results indicate that the mean square error (MSE) of temperature inversion for MR-TH is 0.3-1.5 K and the humidity MSE is 0.2-2.0 g/kg, with an accuracy improvement of over 15% compared to the BP neural network method within the range of 1-5 km altitude. MR-TH also shows a high correlation (>90%) with radiosonde data. MR-TH provides a feasible solution for improving the accuracy of atmospheric parameter inversion from airborne microwave radiometer observation data.

The Aperture Synthetic Radiometer (ASR) system consists of an antenna array along with subsequent receiving channels and data processing modules, and it has been widely applied in Earth observation fields. The arrangement of the antenna array directly affects the system’s sampling coverage in the spatial frequency, which in turn determines its imaging quality. Therefore, we propose a cooperative optimization method for antenna arrays based on deep reinforcement learning, aiming to improve the sampling coverage of the ASR system, thereby enhancing its imaging performance. Experimental results show that the final stable coverage value of the proposed method is 10.545%, representing a 41.2% improvement over the lowest value. Furthermore, it outperforms other comparative methods in both coverage performance and reconstructed image quality, demonstrating its effectiveness in optimizing antenna array layout and enhancing the imaging quality of the system.

In 1-D mirrored aperture synthesis (MAS), the antenna array arrangement and metal reflector are crucial in determining the rank of the transformation matrix. Accurate cosine visibility is achievable only when the transformation matrix is full rank. However, the anti-phase characteristic of the metal reflector introduces non-zero elements of “-1” into the matrix, leading to rank deficiency. This letter proposes a method of using artificial magnetic conductor (AMC) with in-phase reflection property instead of metal reflector to ensure that the transformation matrix only contains non-zero elements “1”. Based on this property, the rank of both linear and nonlinear arrays is verified. The results indicate that AMC can effectively enhance the rank of the transformation matrix, potentially achieving full rank. Additionally, further verification is performed on the reconstruction of trapezoidal extended source scene using two types of arrays. The results demonstrate that AMC-based 1-D MAS can achieve a low root-mean-square error (RMSE), significantly improving the quality of the reconstructed images.

Accurately measuring and inverting air parameters, such as air temperature and humidity, is crucial for weather forecasting, climate research, and environmental monitoring. In this letter, we propose an inversion method based on the transformer model to accurately estimate the spatial distribution of air temperature and humidity. Compared with traditional methods, the transformer model demonstrates superior ability in capturing nonlinear relationships and spatial dependencies in observational data, thereby improving inversion accuracy. Experiments conducted on real observational data have shown that compared to traditional techniques, the proposed method achieves a reduction of over 4.8% in the root mean square error (RMSE) of air temperature and over 14.2% in humidity estimation, demonstrating its high accuracy and reliability in inverting air temperature and humidity. This method provides a new approach for advancing air parameter inversion technology.

Current 3D detection methods, whether single-modal or multimodal, face notable limitations. Single-modal detectors, using either camera or LiDAR, struggle with spatial accuracy and object differentiation due to insufficient depth information or difficulty distinguishing semantically similar objects. Existing multimodal fusion techniques, while improving performance, often suffer from high computational costs, false positives, and complex architectures, especially when utilizing anchor-based pipelines. To address these challenges, we propose an efficient pointwise fusion method that directly extracts point features from enhanced RGB images and fuses them with corresponding point cloud features, preserving essential spatial and semantic information. This fused data is then processed through a three-dimensional neural network, significantly improving inference speed and detection performance. Our framework is designed for multi-class 3D object detection, leveraging the complementary strengths of LiDAR and camera data without the need for multiple backbones or complex synchronization steps. Extensive experiments on the KITTI benchmark demonstrate that the proposed method outperforms state-of-the-art LiDAR-camera fusion techniques, achieving 92.5% AP for 3D detection and 95.41% AP for BEV detection, making it particularly suitable for autonomous driving systems. These results highlight the effectiveness of the proposed fusion strategy in balancing accuracy, computational efficiency, and robustness in complex 3D environments.

Subsurface object detection and segmentation, which has been widely conducted in the ground-penetrating radar (GPR) image field, is of real significance but technically challenging. Although deep learning-based methods have been implemented to segment GPR target signatures, they still rely on complex network architectures such as region proposal networks, which are tedious and time-consuming and not suitable for on-site engineering. To address this challenge, we propose a novel supervised learning-driven model for GPR targe signature segmentation based on cycle-consistence generative adversarial networks (CycleGAN), called S-CycleGAN. Significantly distinguished from the original unsupervised CycleGAN, S-CycleGAN can achieve supervised learning while preserving the attributes and loss function of the previous model. Furthermore, the proposed model can learn a function that maps the GPR B-scan data to the segmented hyperbolic targets. Moreover, a new loss combination strategy including the perceptual loss is developed to improve the segmentation performance. This strategy can highlight and segment GPR target by comparing the perceptual features of a segmented output against those of the labelled images in same established feature space. Therefore, the proposed method transfers our visual perception knowledge to the target instance segmentation task and is able to preserve key information. Experiment results indicate a 97.88% F1-score and a 97.15% MIoU, and the modified loss function accelerates convergence speed and reduces computational costs.

Accurate 3-D object detection is vital in autonomous driving. Traditional LiDAR models struggle with sparse point clouds. We propose a novel approach integrating LiDAR and camera data to maximize sensor strengths while overcoming individual limitations for enhanced 3-D object detection. Our research introduces the channelwise and spatially guided multimodal feature fusion network (CSMNET) for 3-D object detection. First, our method enhances LiDAR data by projecting it onto a 2-D plane, enabling the extraction of class-specific features from a probability map. Second, we design class-based farthest point sampling (C-FPS), which boosts the selection of foreground points by utilizing point weights based on geometric or probability features while ensuring diversity among the selected points. Third, we developed a parallel attention (PAT)-based multimodal fusion mechanism achieving higher resolution compared to raw LiDAR points. This fusion mechanism integrates two attention mechanisms: channel attention for LiDAR data and spatial attention for camera data. These mechanisms enhance the utilization of semantic features in a region of interest (ROI) to obtain more representative point features, leading to a more effective fusion of information from both LiDAR and camera sources. Specifically, CSMNET achieves an average precision (AP) in bird’s eye view (BEV) detection of 90.16% (easy), 85.18% (moderate), and 80.51% (hard), with a mean AP (mAP) of 85.12%. In 3-D detection, CSMNET attains 82.05% (easy), 72.64% (moderate), and 67.10% (hard) with an mAP of 73.75%. For 2-D detection, the scores are 95.47% (easy), 93.25% (moderate), and 86.68% (hard), yielding an mAP of 91.72% for the KITTI dataset.

We propose a competitive binary multi-objective grey wolf optimizer (CBMOGWO) to reduce the heavy computational burden of conventional multi-objective antenna topology optimization problems. This method introduces a population competition mechanism to reduce the burden of electromagnetic (EM) simulation and achieve appropriate fitness values. Furthermore, we introduce a function of cosine oscillation to improve the linear convergence factor of the original binary multi-objective grey wolf optimizer (BMOGWO) to achieve a good balance between exploration and exploitation. Then, the optimization performance of CBMOGWO is verified on 12 standard multi-objective test problems (MOTPs) and four multi-objective knapsack problems (MOKPs) by comparison with the original BMOGWO and the traditional binary multi-objective particle swarm optimization (BMOPSO). Finally, the effectiveness of our method in reducing the computational cost is validated by an example of a compact high-isolation dual-band multiple-input multiple-output (MIMO) antenna with high-dimensional mixed design variables and multiple objectives. The experimental results show that CBMOGWO reduces nearly half of the computational cost compared with traditional methods, which indicates that our method is highly efficient for complex antenna topology optimization problems. It provides new ideas for exploring new and unexpected antenna structures based on multi-objective evolutionary algorithms (MOEAs) in a flexible and efficient manner.

A new efficient optimization method, called binary multi-objective grey wolf optimizer based on competition and teaching (BMOGWO-CT) mechanisms, is proposed for computationally complex engineering applications. The proposed algorithm first divides the population into four parts belonging to three levels through the competition mechanism, thereby reducing the population number during the following procedure of position updating. Then, the teaching mechanism supervises different parts to update their positions according to their priorities within the whole population therefore further reducing the computational cost for solving the problems. To check the effectiveness of the method, the BMOGWO-CT is tested on ten benchmark test functions and compared to other population-based optimization methods, indicating BMOGWO-CT is more effective and efficient. Furthermore, the novel optimization method is extended to a computationally time-consuming engineering problem- multi-objective optimization of antenna topology. This example verifies the effectiveness of our proposed method in engineering applications.

Vulnerable code clones in the operating system (OS) threaten the safety of smart industrial environment, and most vulnerable OS code clone detection approaches neglect correlations between functions that limits the detection effectiveness. In this article, we propose a two-phase framework to find vulnerable OS code clones by learning on correlations between functions. On the training phase, functions as the training set are extracted from the latest code repository and function features are derived by their AST structure. Then, external and internal correlations are explored by graph modeling of functions. Finally, the graph convolutional network for code clone detection (GCN-CC) is trained using function features and correlations. On the detection phase, functions in the to-be-detected OS code repository are extracted and the vulnerable OS code clones are detected by the trained GCN-CC. We conduct experiments on five real OS code repositories, and experimental results show that our framework outperforms the state-of-the-art approaches.

The calibration of aperture synthesis radiometers (ASRs) by the standard method of noise injection would seriously increase hardware requirements and system complexity. To reduce the network of noise injection, redundant space calibration (RSC) method has been considered. However the number of error phases is larger than the number of independent equations. In this paper, an external calibration method with 120-degree antenna array rotation for geostationary ASR with staggered Y-shaped array is proposed. More redundant baselines are produced by rotation. The equations by rotation and by RSC are combined for solving the phase errors. Basic procedure on this method and preliminary simulation are introduced. As another advantage, if twice 120-degree rotation is taken, one of the antenna arms can be removed from staggered Y-shaped arrays with the missing baselines supplied by the rotations. In this way, the number of antenna elements can be reduced by 1/3.

The on-board calibration of aperture synthesis radiometers (ASRs) with large arrays by the standard method of noise injection would seriously increase hardware requirements and system complexity. To avoid the use of noise injection, an external phase calibration method with antenna array rotation is proposed in this letter, which uses the observation scene as reference without needing for an external calibrator. The relationship of the visibility samples before and after the rotation is established and used to solve for the instrumental phase errors. The proposed method has been proved to be valid by simulations as well as some preliminary experimental results. It is applicable to geostationary ASRs with rotating array such as the geostationary atmospheric sounder.

Mirrored interferometric aperture synthesis (IAS) (MIAS) is a novel interferometry which has the potential to reduce system complexity compared with that of conventional IAS. Array configuration design plays a major role in imaging. As the concept of MIAS was proposed just a few years ago, the problem of array configuration design has not been solved yet. In this letter, the principles of array configuration design of 1-D MIAS are proposed, and the corresponding optimization model is established and refined. The optimal array configurations are presented through simulated annealing method and show that 1-D MIAS can achieve almost twice as much of spatial resolution as 1-D IAS with the same array size.