Search Results (79)

Multi-modal object detection that fuses RGB (Red-Green-Blue) and infrared (IR) data has emerged as an effective approach for addressing challenging visual conditions such as low illumination, occlusion, and adverse weather. However, most existing multi-modal detectors prioritize accuracy while neglecting computational efficiency, making them unsuitable for deployment on resource-constrained edge devices. To address this limitation, we propose PONet, a lightweight and efficient multi-modal vehicle detection network tailored for real-time edge inference. PONet incorporates Polarized Self-Attention to improve feature adaptability and representation with minimal computational overhead. In addition, a novel fusion module is introduced to effectively integrate RGB and IR modalities while preserving efficiency. Experimental results on the VEDAI dataset demonstrate that PONet achieves a competitive detection accuracy of 82.2% mAP@0.5 while sustaining a throughput of 34 FPS on the OrangePi AIpro 20T device. With only 3.76 M parameters and 10.2 GFLOPs (Giga Floating Point Operations), PONet offers a practical solution for edge-oriented remote sensing applications requiring a balance between detection precision and computational cost. Full article

Aspect-based sentiment analysis (ABSA) aims at identifying the sentiment polarity for a particular aspect in a review. ABSA studies based on deep learning models have exploited the attention mechanism to detect aspect-related parts. Conventional softmax-based attention mechanisms generate dense distributions, which may limit performance in tasks that inherently require sparsity. Recent studies on sparse attention transformation functions have demonstrated their effectiveness over the conventional softmax function. However, these studies primarily focus on highly sparse tasks based on self-attention architectures, leaving their applicability to the ABSA domain unexplored. In addition, most ABSA research has focused on leveraging aspect terms despite the usefulness of aspect categories. To address these issues, we propose a sparse-attention-based residual joint network (SPA-RJ Net) for the aspect-category-based sentiment analysis (ACSA) task. SPA-RJ Net incorporates two aspect-guided sparse attentions—sparse aspect-category attention and sparse aspect-sentiment attention—that introduce sparsity in attention via a sparse distribution transformation function, enabling the model to selectively focus on aspect-related information. In addition, it employs a residual joint learning framework that connects the aspect category detection (ACD) task module and the ACSA task module via residual connections, enabling the ACSA module to receive explicit guidance on relevant aspect categories from the ACD module. Our experiment validates that SPA-RJ Net consistently outperforms existing models, demonstrating the effectiveness of sparse attention and residual joint learning for aspect category-based sentiment classification. Full article

In-band full-duplex (IBFD) technology has attracted significant attention for its potential to double the spectral efficiency by enabling a simultaneous transmission and reception over the same frequency channel. However, achieving high isolation between closely spaced transmit and receive paths remains a critical challenge. In this paper, a novel compact co-polarized monopole antenna with self-decoupling capability is proposed based on common-mode/differential-mode (CM/DM) theory. By innovatively folding the ends of the monopole elements, the antenna exploits the distinct behaviors under CM and DM excitations at a close spacing to achieve simultaneous impedance matching in both modes. This effectively enhances the isolation between antenna elements. The design enables self-interference suppression without requiring any additional decoupling structures, even under compact antenna and port spacing. Measurement results confirm that the proposed antenna achieves over 20 dB isolation within the 3.4–3.6 GHz operating band, with a compact spacing of 0.008 λ₀ (λ₀ corresponds to the wavelength at the center frequency). Full article

In recent years, UAV formations have garnered significant attention in fields such as reconnaissance, communications, and transportation. This paper aims to design an efficient passive localization method for UAV formations that satisfies system electromagnetic compatibility (EMC) requirements. A self-adjustment model characterized by internally active communication and externally silent operation for UAV formations is proposed, which optimizes the positions of the UAVs under test based on their current locations and standard reference positions while adhering to formation geometry constraints. By comprehensively considering constraints including the number of UAVs, formation geometry, and system EMC, this study evaluates electromagnetic radiation interference within the UAV formation system and derives an iterative adjustment scheme for formation positions. Finally, simulation experiments through specific case studies calculate polar radius deviations and polar angle deviations during the adjustment process. The results validate that the proposed method meets the requirements for both formation adjustment and EMC, thereby providing a more scientific basis for passive localization and position adjustment in UAV formations. Full article

Liquid hydrogen is regarded as a key energy source and propellant for lunar bases due to its high energy density and abundance of polar water ice resources. However, its low boiling point and high latent heat of vaporization pose severe challenges for storage and management under the extreme lunar environment characterized by wide temperature variations, low pressure, and low gravity. This paper reviews the strategies for siting and deployment of liquid hydrogen storage systems on the Moon and the technical challenges posed by the lunar environment, with particular attention for thermal management technologies. Passive technologies include advanced insulation materials, thermal shielding, gas-cooled shielding layers, ortho-para hydrogen conversion, and passive venting, which optimize insulation performance and structural design to effectively reduce evaporation losses and maintain storage stability. Active technologies, such as cryogenic fluid mixing, thermodynamic venting, and refrigeration systems, dynamically regulate heat transfer and pressure variations within storage tanks, further enhancing storage efficiency and system reliability. In addition, this paper explores boil-off hydrogen recovery and reutilization strategies for liquid hydrogen, including hydrogen reliquefaction, mechanical, and non-mechanical compression. By recycling vaporized hydrogen, these strategies reduce resource waste and support the sustainable development of energy systems for lunar bases. In conclusion, this paper systematically evaluates passive and active thermal management technologies as well as vapor recovery strategies along with their technical adaptability, and then proposes feasible storage designs for the lunar environment. These efforts provide critical theoretical foundations and technical references for achieving safe and efficient storage of liquid hydrogen and energy self-sufficiency in lunar bases. Full article

In this study, we present a groundbreaking approach to aspect-based sentiment analysis (ABSA) using transformer-based models. ABSA is essential for understanding the intricate nuances of sentiment expressed in text, particularly across diverse linguistic and cultural contexts. Focusing on movie reviews in Hausa, a language under-represented in sentiment analysis research, we propose HauBERT, a bidirectional transformer-based approach tailored for aspect and polarity classification, by fine-tuning a pre-trained mBERT model. Our work addresses the scarcity of resources for sentiment analysis in under-represented languages by creating a comprehensive Hausa ABSA dataset. Leveraging this dataset, we preprocess the text using state-of-the-art techniques for feature extraction, enhancing the model’s ability to capture nuanced aspects of sentiment. Furthermore, we manually annotate aspect-level feature ontology words and sentiment polarity assignments within the reviewed text, enriching the dataset with valuable semantic information. Our proposed transformer-based model utilizes self-attention mechanisms to capture long-range dependencies and contextual information, enabling it to effectively analyze sentiment in Hausa movie reviews. The proposed model achieves significant accuracy in aspect term extraction and sentiment polarity classification, with scores of 99% and 92% respectively, outperforming traditional machine models. This demonstrates the transformer’s ability to capture complex linguistic patterns and nuances of sentiment. Our study advances ABSA research and contributes to a more inclusive sentiment analysis landscape by providing resources and models tailored for under-represented languages. Full article

Automated damage segmentation for concrete bridges is a fundamental task in infrastructure maintenance, yet existing systems often depend heavily on large annotated datasets, which are costly and time-consuming to produce. This paper presents an innovative framework for concrete bridge damage segmentation, leveraging the Segment Anything Model (SAM) to reduce the reliance on extensive annotated data while enhancing segmentation accuracy and efficiency. Firstly, a SAM-guided mask generation network is introduced, which utilizes the SAM’s segmentation capabilities to generate supplementary supervision labels for damage segmentation. Then, a novel point-prompting strategy, incorporating saliency information, is proposed to refine SAM’s prompts, ensuring accurate mask generation for complex damage patterns. Next, a trainable semantic segmentation network is designed, integrating MambaVision and ResNet as dual backbones to capture multi-level features from concrete bridge damages. To fuse these features effectively, a Hierarchical Attention Fusion (HAF) mechanism is introduced. Finally, a Polarized Self-Attention (PSA) decoder is employed to improve segmentation precision. Experiments on a dataset of 10,000 concrete bridge images with box-level annotations achieved state-of-the-art performance, with an MIoU of 60.13%, PA of 74.02%, and MDice of 75.40%, outperforming existing segmentation models. In summary, this study improves the accuracy of concrete bridge damage segmentation through a series of innovative methods and strategies, and the concrete bridge damage segmentation algorithm opens up new horizons and directions. Full article

In foggy environments, infrared images suffer from reduced contrast, degraded details, and blurred objects, which impair detection accuracy and real-time performance. To tackle these issues, we propose IDDNet, a lightweight infrared object detection network that integrates multi-scale fusion dehazing. IDDNet includes a multi-scale fusion dehazing (MSFD) module, which uses multi-scale feature fusion to eliminate haze interference while preserving key object details. A dedicated dehazing loss function, DhLoss, further improves the dehazing effect. In addition to MSFD, IDDNet incorporates three main components: (1) bidirectional polarized self-attention, (2) a weighted bidirectional feature pyramid network, and (3) multi-scale object detection layers. This architecture ensures high detection accuracy and computational efficiency. A two-stage training strategy optimizes the model’s performance, enhancing its accuracy and robustness in foggy environments. Extensive experiments on public datasets demonstrate that IDDNet achieves 89.4% precision and 83.9% AP, showing its superior accuracy, processing speed, generalization, and robust detection performance. Full article

The cotter pin is a critical component in power transmission lines, as it prevents the loosening or detachment of nuts at essential locations. Therefore, detecting defects in cotter pins is vital for monitoring and diagnosing faults in power transmission systems. Due to environmental factors and human errors, cotter pins are susceptible to loosening and becoming missing. In split pin detection, the primary challenges lie in the small size of the target features and the fine-grained issue of “small inter-class differences and large intra-class variations”. This paper aims to enhance the detection performance of the model for fine-grained small targets by adding a detection head specifically designed for small objects and embedding an attention mechanism. This paper addresses the detection of looseness and missing defects in cotter pins by proposing a target detection model called PMW-YOLOv8 (P-C2f + MCA + WIOU) based on the YOLOv8 framework. The model introduces a specialized small-target detection head (160 × 160), which forms a four-scale pyramid (P2–P5) through cross-layer aggregation, effectively utilizing shallow features. Additionally, it incorporates a multidimensional collaborative attention (MCA) module to enhance the features transmitted to the detection head. To further address the fine-grained feature extraction problem, a polarization self-attention mechanism is integrated into C2f, leading to the proposed P-C2f module. Finally, the WIOU loss function is applied to the model to mitigate the impact of sample quality fluctuations on training. Experiments were conducted on a cotter pin defect dataset to validate the model’s effectiveness, achieving a detection accuracy of 66.3%, an improvement of 3% over YOLOv8. The experimental results demonstrate that our model exhibits strong robustness and generalization, enabling it to extract more profound and comprehensive features. Full article

Aluminum–air batteries have attracted more attention in recent years due to the theoretical possibility of replacing lithium batteries. Al6061/0.5wt.%TiB₂ is considered a suitable anode material due to decreased hydrogenation corrosion. In this work, laser power was optimized via a selective laser melting process to increase the electrochemical and discharge performance of an Al composite anode. Relative density was studied in this work, and the formation mechanism caused by molten pool morphology was also researched using finite element analysis and experiments. The self-corrosion rate, open-circuit potential, polarization curve, EIS curve, and constant-current discharge performance were all studied in the following section, and the relationship between anode quality and laser power was discussed accordingly. The testing results revealed that when laser power reached 340 W, the Al6061/0.5wt.%TiB₂ composite anode reached a relative optimal condition as defects reduced to a minimum value at this point, which resulted in overall anode performance increasing in the electrochemical and discharge test. Full article

Aspect-based sentiment analysis (ABSA) through joint task learning aims to simultaneously identify aspect terms and predict their sentiment polarities. However, existing methods face two major challenges: (1) Most existing studies focus on the sentiment polarity classification task, ignoring the critical role of aspect term extraction, leading to insufficient performance in capturing aspect-related information; (2) existing methods typically model the two tasks independently, failing to effectively share underlying features and semantic information, which weakens the synergy between the tasks and limits the overall performance of the model. In order to resolve these issues, this research suggests a unified framework model through joint task learning, named MTL-GCN, to simultaneously perform aspect term extraction and sentiment polarity classification. The proposed model utilizes dependency trees combined with self-attention mechanisms to generate new weight matrices, emphasizing the locational information of aspect terms, and optimizes the graph convolutional network (GCN) to extract aspect terms more efficiently. Furthermore, the model employs the multi-head attention (MHA) mechanism to process input data and uses its output as the input to the GCN. Next, GCN models the graph structure of the input data, capturing the relationships between nodes and global structural information, fully integrating global contextual semantic information, and generating deep-level contextual feature representations. Finally, the extracted aspect-related features are fused with global features and applied to the sentiment classification task. The proposed unified framework achieves state-of-the-art performance, as evidenced by experimental results on four benchmark datasets. MTL-GCN outperforms baseline models in terms of F1_ATE, accuracy, and F1_SC metrics, as demonstrated by experimental results on four benchmark datasets. Additionally, comparative and ablation studies further validate the rationale and effectiveness of the model design. Full article

Research on deep learning (DL)-based channel estimation for massive multiple-input multiple-output (MIMO) communication systems has attracted considerable interest in recent years. In this paper, we propose a DL-assisted channel estimation algorithm that transforms the original channel estimation problem into an image denoising problem, contrasting it with traditional experience-based channel estimation methods. We establish a new polarized self-attention-aided channel estimation neural network (PACE-Net) to achieve efficient channel estimation. This approach addresses the limitations of the conventional methods, particularly their low accuracy and high computational complexity. In addition, we construct a channel dataset to facilitate the training and testing of PACE-Net. The simulation results show that the proposed DL-assisted channel estimation algorithm has better normalization mean square error (NMSE) performance compared with the traditional algorithms and other DL-assisted algorithms. Furthermore, the computational complexity of the proposed DL-assisted algorithm is significantly lower than that of the traditional minimum mean square error (MMSE) channel estimation algorithm. Full article

In the process of steel strip production, the accuracy of defect detection remains a challenge due to the diversity of defect types, complex backgrounds, and noise interference. To improve the effectiveness of surface defect detection in steel strips, we propose an enhanced detection model known as YOLOv8-BSPB. First, we propose a novel pooling layer module, SCRD, which replaces max pooling with average pooling. This module introduces the receptive field block (RFB) and deformable convolutional network version 4 (DCNv4) to obtain learnable offsets, allowing convolutional kernels to flexibly move and deform on the input feature map, thus, more effectively extracting multi-scale features. Second, we integrate a polarized self-attention (PSA) mechanism to improve the model’s feature representation and enhance its ability to focus on relevant information. Additionally, we incorporate the BAM attention mechanism after the C2f module to strengthen the model’s feature selection capabilities. A bidirectional feature pyramid network is introduced at the neck of the model to improve feature transmission efficiency. Finally, the WIoU loss function is employed to accelerate the model’s convergence speed and enhance regression accuracy. Experimental results on the NEU-DET dataset demonstrate that the improved model achieves a classification accuracy of 81.3%, an increase of 4.9% over the baseline, with a mean average precision of 86.9%. The model has a parameter count of 5.5 M and operates at 103.1 FPS. To validate the model’s effectiveness, we conducted tests on the Kaggle steel strip dataset and our custom dataset, where the average accuracy improved by 2.3% and 5.5%, respectively. The experimental results indicate that the model meets the requirements for real-time, lightweight, and portable deployment. Full article

In their shapes, molecules of some bipolar metabolites resemble the so-called bola, a hunting weapon of the South American inhabitants, consisting of two heavy balls connected to each other by a long flexible cord. Herein, we discuss the structures and properties of these natural products (bola-like compounds or bolaamphiphiles), containing two polar terminal fragments and a non-polar chain (or chains) between them, from archaea, bacteria, and marine invertebrates. Additional modifications of core compounds of this class, for example, interchain and intrachain cyclization, hydroxylation, methylation, etc., expand the number of known metabolites of this type, providing their great structural variety. Isolation of such complex compounds individually is problematic, since they usually exist as mixtures of regioisomers and stereoisomers, that are very difficult to be separated. The main approaches to the study of their structures combine various methods of HPLC/MS or GC/MS, 2D-NMR experiments and organic synthesis. The recent identification of new enzymes, taking part in their biosynthesis and metabolism, made it possible to understand molecular aspects of their origination and some features of evolution during geological times. The promising properties of these metabolites, such as their ability to self-assemble and stabilize biological or artificial membranes, and biological activities, attract additional attention to them. Full article

Underwater object detection is highly complex and requires a high speed and accuracy. In this paper, an underwater target detection model based on YOLOv8 (SPSM-YOLOv8) is proposed. It solves the problems of high computational complexities, slow detection speeds and low accuracies. Firstly, the SPDConv module is utilized in the backbone network to replace the standard convolutional module for feature extraction. This enhances computational efficiency and reduces redundant computations. Secondly, the PSA (Polarized Self-Attention) mechanism is added to filter and enhance the polarization of features in the channel and spatial dimensions to improve the accuracy of pixel-level prediction. The SCDown (spatial–channel decoupled downsampling) downsampling mechanism is then introduced to reduce the computational cost by decoupling the space and channel operations while retaining the information in the downsampling process. Finally, MPDIoU (Minimum Point Distance-based IoU) is used to replace the CIoU (Complete-IOU) loss function to accelerate the convergence speed of the bounding box and improve the bounding box regression accuracy. The experimental results show that compared with the YOLOv8n baseline model, the SPSM-YOLOv8 (SPDConv-PSA-SCDown-MPDIoU-YOLOv8) detection accuracy reaches 87.3% on the ROUD dataset and 76.4% on the UPRC2020 dataset, and the number of parameters and amount of computation decrease by 4.3% and 4.9%, respectively. The detection frame rate reaches 189 frames per second on the ROUD dataset, thus meeting the high accuracy requirements for underwater object detection algorithms and facilitating lightweight and fast edge deployment. Full article