Search Results (128)

Synthetic Aperture Radar (SAR) enables the acquisition of high-resolution imagery even under severe meteorological and illumination conditions. Its utility is evident across a spectrum of applications, particularly in automatic target recognition (ATR). Since SAR samples are often scarce in practical ATR applications, there is an urgent need to develop sample-efficient augmentation techniques to augment the SAR images. However, most of the existing generative approaches require an excessive amount of training samples for effective modeling of the SAR imaging characteristics. Additionally, they show limitations in augmenting the interesting target samples while maintaining image recognizability. In this study, we introduce an innovative single-sample image generation approach tailored to SAR data augmentation. To closely approximate the target distribution across both the spatial layout and local texture, a multi-level Generative Adversarial Network (GAN) architecture is constructed. It comprises three distinct GANs that independently model the structural, semantic, and texture patterns. Furthermore, we introduce multiple constraints including prior-regularized noise sampling and perceptual loss optimization to enhance the fidelity and stability of the generation process. Comparative evaluations against the state-of-the-art generative methods demonstrate the superior performance of the proposed method in terms of generation diversity, recognizability, and stability. In particular, its advantages over the baseline method are up to 0.2 and 0.22 in the SIFID and SSIM, respectively. It also exhibits stronger robustness in the generation of images across varying spatial sizes. Full article

The prediction of bike-sharing demand plays a pivotal role in the optimization of intelligent transportation systems, particularly amidst the COVID-19 pandemic, which has significantly altered travel behaviors and demand dynamics. In this study, we examine various spatiotemporal influencing factors associated with bike-sharing and propose the Local-Global Dynamic Multi-Graph Convolutional Network (LGDMGCN) model, driven by multi-source data, for multi-step prediction of station-level bike-sharing demand. In the temporal dimension, we dynamically model temporal dependencies by incorporating multiple sources of time semantic features such as confirmed COVID-19 cases, weather conditions, and holidays. Additionally, we integrate a time attention mechanism to better capture variations over time. In the spatial dimension, we consider factors related to the addition or removal of stations and utilize spatial semantic features, such as urban points of interest and station locations, to construct dynamic multi-graphs. The model utilizes a local-global structure to capture spatial dependencies among individual bike-sharing stations and all stations collectively. Experimental results, obtained through comparisons with baseline models on the same dataset and conducting ablation studies, demonstrate the feasibility and effectiveness of the proposed model in predicting bike-sharing demand. Full article

In response to the low accuracy and slow detection speed of chili recognition in natural environments, this study proposes a chili pepper object detection method based on the improved YOLOv8n. Evaluations were conducted among YOLOv5n, YOLOv6n, YOLOv7-tiny, YOLOv8n, YOLOv9, and YOLOv10 to select the optimal model. YOLOv8n was chosen as the baseline and improved as follows: (1) Replacing the YOLOv8 backbone with the improved HGNetV2 model to reduce floating-point operations and computational load during convolution. (2) Integrating the SEAM (spatially enhanced attention module) into the YOLOv8 detection head to enhance feature extraction capability under chili fruit occlusion. (3) Optimizing feature fusion using the dilated reparam block module in certain C2f (CSP bottleneck with two convolutions). (4) Substituting the traditional upsample operator with the CARAFE(content-aware reassembly of features) upsampling operator to further enhance network feature fusion capability and improve detection performance. On a custom-built chili dataset, the F_0.5-score, mAP_0.5, and mAP_0.5:0.95 metrics improved by 1.98, 2, and 5.2 percentage points, respectively, over the original model, achieving 96.47%, 96.3%, and 79.4%. The improved model reduced parameter count and GFLOPs by 29.5% and 28.4% respectively, with a final model size of 4.6 MB. Thus, this method effectively enhances chili target detection, providing a technical foundation for intelligent chili harvesting processes. Full article

Traditional measurement methods often rely on manual operations, which are not only inefficient but also cause stress to cattle, affecting animal welfare. Currently, non-contact cattle dimension measurement usually involves the use of multi-view images combined with point cloud or 3D reconstruction technologies, which are costly and less flexible in actual farming environments. To address this, this study proposes an automated cattle dimension measurement method based on an improved keypoint detection model combined with unilateral depth imaging. Firstly, YOLOv8-Pose is selected as the keypoint detection model and SimSPPF replaces the original SPPF to optimize spatial pyramid pooling, reducing computational complexity. The CARAFE architecture, which enhances upsampling content-aware capabilities, is introduced at the neck. The improved YOLOv8-pose achieves a mAP of 94.4%, a 2% increase over the baseline model. Then, cattle keypoints are captured on RGB images and mapped to depth images, where keypoints are optimized using conditional filtering on the depth image. Finally, cattle dimension parameters are calculated using the cattle keypoints combined with Euclidean distance, the Moving Least Squares (MLS) method, Radial Basis Functions (RBFs), and Cubic B-Spline Interpolation (CB-SI). The average relative errors for the body height, lumbar height, body length, and chest girth of the 23 measured beef cattle were 1.28%, 3.02%, 6.47%, and 4.43%, respectively. The results show that the method proposed in this study has high accuracy and can provide a new approach to non-contact beef cattle dimension measurement. Full article

In online video understanding, which has a wide range of real-world applications, inference speed is crucial. Many approaches involve frame-level visual feature extraction, which often represents the biggest bottleneck. We propose RetinaViT, an efficient method for extracting frame-level visual features in an online video stream, aiming to fundamentally enhance the efficiency of online video understanding tasks. RetinaViT is composed of efficiently approximated Transformer blocks that only take changed tokens (event tokens) as queries and reuse the already processed tokens from the previous timestep for the others. Furthermore, we restrict keys and values to the spatial neighborhoods of event tokens to further improve efficiency. RetinaViT involves tuning multiple parameters, which we determine through a multi-step process. During model training, we randomly vary these parameters and then perform black-box optimization to maximize accuracy and efficiency on the pre-trained model. We conducted extensive experiments on various online video recognition tasks, including action recognition, pose estimation, and object segmentation, validating the effectiveness of each component in RetinaViT and demonstrating improvements in the speed/accuracy trade-off compared to baselines. In particular, for action recognition, RetinaViT built on ViT-B16 reduces inference time by approximately 61.9% on the CPU and 50.8% on the GPU, while achieving slight accuracy improvements rather than degradation. Full article

The detection of concealed suspicious objects in public places is a critical issue and a popular research topic. Terahertz (THz) imaging technology, as an emerging detection method, can penetrate materials without emitting ionizing radiation, providing a new approach to detecting concealed suspicious objects. This study focuses on the detection of concealed suspicious objects wrapped in different materials such as polyethylene and kraft paper, including items like scissors, pistols, and blades, using THz imaging technology. To address issues such as the lack of texture details in THz images and the contour similarity of different objects, which can lead to missed detections and false alarms, we propose a THz concealed suspicious object detection model based on SMR–YOLO (SPD_Mobile + RFB + YOLO). This model, based on the MobileNext network, introduces the spatial-to-depth convolution (SPD-Conv) module to replace the backbone network, reducing computational and parameter load. The inclusion of the receptive field block (RFB) module, which uses a multi-branch structure of dilated convolutions, enhances the network’s depth features. Using the EIOU loss function to assess the accuracy of predicted box localization further optimizes convergence speed and localization accuracy. Experimental results show that the improved model achieved [email protected] and [email protected]:0.95 scores of 98.9% and 89.4%, respectively, representing improvements of 0.2% and 1.8% over the baseline model. Additionally, the detection speed reached 108.7 FPS, an improvement of 23.2 FPS over the baseline model. The model effectively identifies concealed suspicious objects within packages, offering a novel approach for detection in public places. Full article

Accurate recognition of tool state is important for maximizing tool life. However, the tool sensor data collected in real-life scenarios has unbalanced characteristics. Additionally, although graph neural networks (GNNs) show excellent performance in feature extraction in the spatial dimension of data, it is difficult to extract features in the temporal dimension efficiently. Therefore, we propose a tool state recognition method based on the Pruned Optimized Graph Neural Network-Gated Recurrent Unit (POGNN-GRU) under unbalanced data. Firstly, design the Improved-Majority Weighted Minority Oversampling Technique (IMWMOTE) by introducing an adaptive noise removal strategy and improving the MWMOTE to alleviate the unbalanced problem of data. Subsequently, propose a POG graph data construction method based on a multi-scale multi-metric basis and a Gaussian kernel weight function to solve the problem of one-sided description of graph data under a single metric basis. Then, construct the POGNN-GRU model to deeply mine the spatial and temporal features of the data to better identify the state of the tool. Finally, validation and ablation experiments on the PHM 2010 and HMoTP datasets show that the proposed method outperforms the other models in terms of identification, and the highest accuracy improves by 1.62% and 1.86% compared with the corresponding optimal baseline model. Full article

Synthetic aperture radar (SAR) is a technique widely used in the field of ship detection. However, due to the high ship density, fore-ground-background imbalance, and varying target sizes, achieving lightweight and high-precision multiscale ship object detection remains a significant challenge. In response to these challenges, this research presents YOLO-MSD, a multiscale SAR ship detection method. Firstly, we propose a Deep Poly Kernel Backbone Network (DPK-Net) that utilizes the Optimized Convolution (OC) Module to reduce data redundancy and the Poly Kernel (PK) Module to improve the feature extraction capability and scale adaptability. Secondly, we design a BiLevel Spatial Attention Module (BSAM), which consists of the BiLevel Routing Attention (BRA) and the Spatial Attention Module. The BRA is first utilized to capture global information. Then, the Spatial Attention Module is used to improve the network’s ability to localize the target and capture high-quality detailed information. Finally, we adopt a Powerful-IoU (P-IoU) loss function, which can adjust to the ship size adaptively, effectively guiding the anchor box to achieve faster and more accurate detection. Using HRSID and SSDD as experimental datasets, mAP of 90.2% and 98.8% are achieved, respectively, outperforming the baseline by 5.9% and 6.2% with a model size of 12.3 M. Furthermore, the network exhibits excellent performance across various ship scales. Full article

The accurate prediction of vessel trajectory is of crucial importance in order to improve navigational efficiency, optimize routes, enhance the effectiveness of search and rescue operations at sea, and ensure maritime safety. However, the spatial interaction among vessels can have a certain impact on the prediction accuracy of the models. To overcome such a problem in predicting the vessel trajectory, this research proposes a novel hybrid methodology incorporating the graph attention network (GAT) and long short-term memory network (LSTM). The proposed GAT-LSTM model can comprehensively consider spatio-temporal features in the prediction process, which is expected to significantly improve the accuracy and robustness of the trajectory prediction. The Automatic Identification System (AIS) data from the surrounding waters of Xiamen Port is collected and utilized as the empirical case for model validation. The experimental results demonstrate that the GAT-LSTM model outperforms the best baseline model in terms of the reduction on the average displacement error and final displacement error, which are 44.52% and 56.20%, respectively. These improvements will translate into more accurate vessel trajectories, helping to minimize route deviations and improve the accuracy of collision avoidance systems, so that this research can effectively provide support for warning about potential collisions and reducing the risk of maritime accidents. Full article

Assessing sleep posture, a critical component in sleep tests, is crucial for understanding an individual’s sleep quality and identifying potential sleep disorders. However, monitoring sleep posture has traditionally posed significant challenges due to factors such as low light conditions and obstructions like blankets. The use of radar technolsogy could be a potential solution. The objective of this study is to identify the optimal quantity and placement of radar sensors to achieve accurate sleep posture estimation. We invited 70 participants to assume nine different sleep postures under blankets of varying thicknesses. This was conducted in a setting equipped with a baseline of eight radars—three positioned at the headboard and five along the side. We proposed a novel technique for generating radar maps, Spatial Radio Echo Map (SREM), designed specifically for data fusion across multiple radars. Sleep posture estimation was conducted using a Multiview Convolutional Neural Network (MVCNN), which serves as the overarching framework for the comparative evaluation of various deep feature extractors, including ResNet-50, EfficientNet-50, DenseNet-121, PHResNet-50, Attention-50, and Swin Transformer. Among these, DenseNet-121 achieved the highest accuracy, scoring 0.534 and 0.804 for nine-class coarse- and four-class fine-grained classification, respectively. This led to further analysis on the optimal ensemble of radars. For the radars positioned at the head, a single left-located radar proved both essential and sufficient, achieving an accuracy of 0.809. When only one central head radar was used, omitting the central side radar and retaining only the three upper-body radars resulted in accuracies of 0.779 and 0.753, respectively. This study established the foundation for determining the optimal sensor configuration in this application, while also exploring the trade-offs between accuracy and the use of fewer sensors. Full article

Synchronous monitoring electroencephalogram (EEG) and functional near-infrared spectroscopy (fNIRS) have received significant attention in brain science research for their provision of more information on neuro-loop interactions. There is a need for an integrated hybrid EEG-fNIRS patch to synchronously monitor surface EEG and deep brain fNIRS signals. Here, we developed a hybrid EEG-fNIRS patch capable of acquiring high-quality, co-located EEG and fNIRS signals. This patch is wearable and provides easy cognition and emotion detection, while reducing the spatial interference and signal crosstalk by integration, which leads to high spatial–temporal correspondence and signal quality. The modular design of the EEG-fNIRS acquisition unit and optimized mechanical design enables the patch to obtain EEG and fNIRS signals at the same location and eliminates spatial interference. The EEG pre-amplifier on the electrode side effectively improves the acquisition of weak EEG signals and significantly reduces input noise to 0.9 μV_rms, amplitude distortion to less than 2%, and frequency distortion to less than 1%. Detrending, motion correction algorithms, and band-pass filtering were used to remove physiological noise, baseline drift, and motion artifacts from the fNIRS signal. A high fNIRS source switching frequency configuration above 100 Hz improves crosstalk suppression between fNIRS and EEG signals. The Stroop task was carried out to verify its performance; the patch can acquire event-related potentials and hemodynamic information associated with cognition in the prefrontal area. Full article

Currently, the intelligent defect detection of massive grid transmission line inspection pictures using AI image recognition technology is an efficient and popular method. Usually, there are two technical routes for the construction of defect detection algorithm models: one is to use a lightweight network, which improves the efficiency, but it can generally only target a few types of defects and may reduce the detection accuracy; the other is to use a complex network model, which improves the accuracy, and can identify multiple types of defects at the same time, but it has a large computational volume and low efficiency. To maintain the model’s high detection accuracy as well as its lightweight structure, this paper proposes a lightweight and efficient multi type defect detection method for transmission lines based on DCP-YOLOv8. The method employs deformable convolution (C2f_DCNv3) to enhance the defect feature extraction capability, and designs a re-parameterized cross phase feature fusion structure (RCSP) to optimize and fuse high-level semantic features with low level spatial features, thus improving the capability of the model to recognize defects at different scales while significantly reducing the model parameters; additionally, it combines the dynamic detection head and deformable convolutional v3’s detection head (DCNv3-Dyhead) to enhance the feature expression capability and the utilization of contextual information to further improve the detection accuracy. Experimental results show that on a dataset containing 20 real transmission line defects, the method increases the average accuracy ([email protected]) to 72.2%, an increase of 4.3%, compared with the lightest baseline YOLOv8n model; the number of model parameters is only 2.8 M, a reduction of 9.15%, and the number of processed frames per second (FPS) reaches 103, which meets the real time detection demand. In the scenario of multi type defect detection, it effectively balances detection accuracy and performance with quantitative generalizability. Full article

As urbanization and rapid industrialization accelerate, rural areas face increasing pressure on resources and the environment, leading to challenges such as energy waste and reduced comfort. Traditional village planning and design methods are based on economic benefits and often lack consideration of climate adaptability. To address these issues, a comprehensive assessment of building and courtyard performance should be introduced early in the planning of traditional villages. This approach can better adapt the buildings to their climatic conditions. Introducing relevant performance indicators, such as outdoor comfort, indoor lighting, and building energy consumption, at the initial design stage is crucial. This article employs performance-based multi-objective optimization algorithms and machine learning techniques to investigate the design workflow of courtyards and their combinations. The goal is to enhance planners’ design efficiency in village planning by integrating data-driven and performance-driven methods. The research results show that during the performance-driven phase, by adjusting the spatial morphology and architectural parameters, the performance of the courtyard significantly improved compared to the baseline model. Energy efficiency increased by 32.3%, the physiological equivalent temperature (PET) comfort time ratio in winter was enhanced by 8.3%, and the ratio in summer increased by 3.8%. During the data-driven phase, the classification prediction accuracy of courtyard performance can reach 83%, and the F₁ score is 0.81. In the project validation phase, it has also been proven that the performance of different plans can be quickly verified. Compared to the base’s original status, the design solutions’ performance score can be improved from 59.12 to 85.62. In summary, this workflow improves the efficiency of the interaction between design decisions and performance evaluation in the conceptual stage of village planning, providing a solid foundation for promoting subsequent solutions. Full article

Ecological carbon sinks, pivotal in mitigating carbon emissions, are indispensable for climate change mitigation. Counties, as the fundamental units of ecological space management, directly impact the achievement of regional dual carbon targets through their levels of carbon sink. However, existing research has overlooked the intricate relationship between terrain features and ecological spaces, leading to a lack of specific guidance on enhancing the carbon sink for counties with diverse landform characteristics. This study focused on Jingbian County (Loess Plateau), Fuping County (Guanzhong Plain), and Chenggu County (Qinba Mountains), each characterized by distinct landform characteristics. This study proposes a comprehensive identification model for ecological space within the context of dual carbon targets. Utilizing this model as a basis, the land use structure, carbon sink potential, and ecological spatial patterns of different counties were systematically analyzed. The results indicated substantial disparities in land use structure, carbon sink capabilities, and ecological space distributions among counties with different landform types. Specifically, Jingbian County was predominantly covered by grassland, exhibiting a moderate overall carbon sink capacity, with baseline ecological spaces playing a significant role. Conversely, Fuping County, dominated by cultivated land and construction land, exhibited the lowest carbon sink capacity, with non-ecological spaces accounting for a staggering 85.93%. Chenggu County, on the other hand, was characterized by the dominance of forestland, with nearly all its carbon sink originating from forestland, and core ecological spaces occupying a leading position. Tailored optimization strategies are recommended based on varying terrain features: Jingbian County should prioritize ecosystem restoration and conservation, while Fuping County should concentrate on optimizing land use structure and promoting urban greening. Reinforcing the carbon sink capacity of existing ecosystems is crucial for Chenggu County. This study broadens the perspective on ecological space optimization and provides scientific guidance and pragmatic insights tailored to regional disparities, which are instrumental in assisting various regions to achieve their dual carbon targets. Full article

This paper proposes PestNet, a lightweight method for classifying crop pests, which improves upon MobileNet-V2 to address the high model complexity and low classification accuracy commonly found in pest classification research. Firstly, the training phase employs the AdamW optimizer and mixup data augmentation techniques to enhance the model’s convergence and generalization capabilities. Secondly, the Adaptive Spatial Group-Wise Enhanced (ASGE) attention mechanism is introduced and integrated into the inverted residual blocks of the MobileNet-V2 model, boosting the model’s ability to extract both local and global pest information. Additionally, a dual-branch feature fusion module is developed using convolutional kernels of varying sizes to enhance classification performance for pests of different scales under real-world conditions. Lastly, the model’s activation function and overall architecture are optimized to reduce complexity. Experimental results on a proprietary pest dataset show that PestNet achieves classification accuracy and an F1 score of 87.62% and 86.90%, respectively, marking improvements of 4.20 percentage points and 5.86 percentage points over the baseline model. Moreover, PestNet’s parameter count and floating-point operations are reduced by 14.10% and 37.50%, respectively, compared to the baseline model. When compared with ResNet-50, MobileNet V3-Large, and EfficientNet-B1, PestNet offers superior parameter efficiency and floating-point operation requirements, as well as improved pest classification accuracy. Full article