Search Results (21)

Gene regulatory networks (GRN) govern cellular identity and function through precise control of gene transcription. Single-cell technologies have provided powerful means to dissect regulatory mechanisms within specific cellular states. However, existing computational approaches for modeling single-cell RNA sequencing (scRNA-seq) data often infer local regulatory interactions independently, which limits their ability to resolve regulatory mechanisms from a global perspective. Here, we propose a deep learning framework (Planet) based on diffusion models for constructing cell-specific GRN, thereby providing a systems-level view of how protein regulators orchestrate transcriptional programs. Planet jointly optimizes local network structures in conjunction with gene expression profiles, thereby enhancing the structural consistency of the resulting networks at the global level. Specifically, Planet decomposes GRN generation into a series of Markovian evolution steps and introduces a Triple Hybrid-Attention Transformer to capture long-range regulatory dependencies across diffusion time-steps. Benchmarks on multiple scRNA-seq datasets demonstrate that Planet achieves competitive performance against state-of-the-art methods and yields only a slight improvement over DigNet under comparable conditions. Compared with conventional diffusion models that rely on fixed sampling schedules, Planet employs a fast-sampling strategy that accelerates inference with only minimal accuracy trade-off. When applied to mouse-lung Cd8⁺Gzmk⁺ T cells, Planet successfully reconstructs a cell-type-specific GRN, recovers both established and previously uncharacterized regulators, and delineates the dynamic immunoregulatory changes that accompany ageing. Overall, Planet provides a practical framework for constructing cell-specific GRNs with improved global consistency, offering a complementary perspective to existing methods and new insights into regulatory dynamics in health and disease. Full article

In this paper, we develop a deep learning neural network characterized by feature fusion and physical guidance (denoted as FFPG-net) for reconstructing subsurface sea temperature (T) and salinity (S) from sea surface data. Designed with the idea of feature fusion, FFPG-net combines the deep learning algorithms of residual and channel attention with the physical constraints of vertical modes of T/S profiles decomposed by empirical orthogonal functions (EOFs). The results from a series of single point experiments show that FFPG-net outperforms the CNN or CNN-PG (without physical guidance or feature fusion) in the reconstruction of subsurface T/S in a region of the South China Sea (SCS), with monthly mean RMSEs of 0.31 °C (0.35 °C) and 0.06 psu (0.07 psu) for the reconstructed T/S profiles in winter (summer), averaged over the water depth of 1200 m and the study area. In addition, the performance of the FFPG-net can be improved significantly by incorporating full surface currents or geostrophic currents derived from SSH into the input variables for training the neural network. The preliminary application of FFPG-net in the SCS using satellite-derived sea surface observations indicates that FFPG-net is reliable and feasible for reconstructing subsurface ocean thermal fields in real situations. Our study highlights the advantages and necessity of combining deep learning algorithms with physical constraints in reconstructing subsurface T/S profiles. It provides an effective tool for reconstructing the subsurface global ocean from remote-sensing sea surface observations in the future. Full article

Small defects on the surface of copper strips have a significant impact on key properties such as electrical conductivity and corrosion resistance, and existing inspection techniques struggle to meet the demand in terms of accuracy and generalisability. Although there have been some studies on metal surface defect detection, there is a relative lack of research on highly reflective copper strips. In this paper, a lightweight and efficient copper strip defect detection algorithm, SC-AttentiveNet, is proposed, aiming to solve the problems of the large model size, slow speed, insufficient accuracy and poor generalisability of existing models. The algorithm is based on ConvNeXt V2, and combines the SCDown module and group normalisation to design the SCGNNet feature extraction network, which significantly reduces the computational overhead while maintaining excellent feature extraction capability. In addition, the algorithm introduces the SPPF-PSA module to enhance the multi-scale feature extraction capability, and constructs a new neck feature fusion network via the HD-CF Fusion Block module, which further enhances the feature diversity and fine granularity. The experimental results show that SC-AttentiveNet has a mAP of 90.11% and 64.14% on the KUST-DET and VOC datasets, respectively, with a parameter count of only 6.365 MB and a computational complexity of 14.442 GFLOPs. Tests on the NEU-DET dataset show that the algorithm has an excellent generalisation performance, with a mAP of 76.41% and a detection speed of 78 FPS, demonstrating a wide range of practical application potential. Full article

The complexity of various factors influencing online learning makes it difficult to characterize learning concentration, while Accurately estimating students’ gaze points during learning video sessions represents a critical scientific challenge in assessing and enhancing the attentiveness of online learners. However, current appearance-based gaze estimation models lack a focus on extracting essential features and fail to effectively model the spatio-temporal relationships among the head, face, and eye regions, which limits their ability to achieve lower angular errors. This paper proposes an appearance-based gaze estimation model (RSP-MCGaze). The model constructs a feature extraction backbone network for gaze estimation (ResNetSC) by integrating ResNet and SCConv; this integration enhances the model’s ability to extract important features while reducing spatial and channel redundancy. Based on the ResNetSC backbone, the method for video gaze estimation was further optimized by jointly locating the head, eyes, and face. The experimental results demonstrate that our model achieves significantly higher performance compared to existing baseline models on public datasets, thereby fully confirming the superiority of our method in the gaze estimation task. The model achieves a detection error of 9.86 on the Gaze360 dataset and a detection error of 7.11 on the detectable face subset of Gaze360. Full article

This study presents a new image inpainting model based on U-Net and incorporating the Wasserstein Generative Adversarial Network (WGAN). The model uses skip connections to connect every encoder block to the corresponding decoder block, resulting in a strictly symmetrical architecture referred to as Symmetric Connected U-Net (SC-Unet). By combining SC-Unet with a GAN, the study aims to reconstruct images more effectively and seamlessly. The traditional discriminators only differentiate the entire image as true or false. In this study, the discriminator calculated the probability of each pixel belonging to the hole and non-hole regions, which provided the generator with more gradient loss information for image inpainting. Additionally, every block of SC-Unet incorporated a Dilated Convolutional Neural Network (DCNN) to increase the receptive field of the convolutional layers. Our model also integrated Multi-Head Self-Attention (MHSA) into selected blocks to enable it to efficiently search the entire image for suitable content to fill the missing areas. This study adopts the publicly available datasets CelebA-HQ and ImageNet for evaluation. Our proposed algorithm demonstrates a 10% improvement in PSNR and a 2.94% improvement in SSIM compared to existing representative image inpainting methods in the experiment. Full article

Detecting the quantity and diversity of diatoms is of great significance in areas such as climate change, water quality assessment, and oil exploration. Here, an efficient and accurate object detection model, named SC-DiatomNet, is proposed for diatom detection in complex environments. This model is based on the YOLOv3 architecture and uses the K-means++ algorithm for anchor box clustering on the diatom dataset. A convolutional block attention module is incorporated in the feature extraction network to enhance the model’s ability to recognize important regions. A spatial pyramid pooling module and adaptive anchor boxes are added to the encoder to improve detection accuracy for diatoms of different sizes. Experimental results show that SC-DiatomNet can successfully detect and classify diatoms accurately without reducing detection speed. The recall, precision, and F1 score were 94.96%, 94.21%, and 0.94, respectively. It further improved the mean average precision (mAP) of YOLOv3 by 9.52% on the diatom dataset. Meanwhile, the detection accuracy was improved compared with those of other advanced deep learning algorithms. SC-DiatomNet has potential applications in water quality analysis and monitoring of harmful algal blooms. Full article

Improving the accuracy and detection speed of bolt recognition under the complex background of the train underframe is crucial for the safety of train operation. To achieve efficient detection, a lightweight detection method based on SFCA-YOLOv8s is proposed. The underframe bolt images are captured by a self-designed track-based inspection robot, and a dataset is constructed by mixing simulated platform images with real train underframe bolt images. By combining the C2f module with ScConv lightweight convolution and replacing the Bottleneck structure with the Faster_Block structure, the SFC2f module is designed for feature extraction to improve detection accuracy and speed. It is compared with FasterNet, GhostNet, and MobileNetV3. Additionally, the CA attention mechanism is introduced, and MPDIoU is used as the loss function of YOLOv8s. LAMP scores are used to rank the model weight parameters, and unimportant weight parameters are pruned to achieve model compression. The compressed SFCA-YOLOv8s model is compared with models such as YOLOv5s, YOLOv7, and YOLOX-s in comparative experiments. The results indicate that the final model achieves an average detection accuracy of 93.3% on the mixed dataset, with a detection speed of 261 FPS. Compared with other classical deep learning models, the improved model demonstrates superior performance in detection effectiveness, robustness, and generalization. Even in the absence of sufficient real underframe bolt images, the algorithm enables the trained network to better adapt to real environments, improving bolt recognition accuracy and detection speed, thus providing technical references and theoretical support for subsequent related research. Full article

Enhancing regional ecosystem stability and managing land resources effectively requires identifying ecological function zones and understanding the factors that influence them. However, most current studies have primarily focused on ecosystem service bundles, paying less attention to the trade-offs, synergies, and ecological sensitivity, leading to a more uniform approach to functional zoning. This study aimed to analyze and describe the spatial and temporal patterns of four essential ecosystem services, including water yield (WY), net primary productivity (NPP), soil conservation (SC), and habitat quality (HQ), in the Sichuan-Yunnan ecological buffer area over the period from 2005 to 2019. Spatial overlay analysis was used to assess ecological sensitivity, trade-offs, synergies, and ecosystem service bundles to define ecological functional zones. Geographic detectors were then applied to identify the primary drivers of spatial variation in these zones. The findings showed a progressive improvement in ecosystem service functions within the Sichuan-Yunnan ecological buffer zone. Between 2005 and 2019, NPP, soil conservation, and water yield all demonstrated positive trends, while HQ displayed a declining trend. There was significant spatial heterogeneity and distinct regional patterns in ecosystem service functions, with a general decrease from southwest to northeast, particularly in NPP and HQ. Trade-offs were evident in most ecosystem services, with the most significant between WY and HQ and most in the northeast and east regions. Ecological sensitivity decreased from southwest to northeast. Regions with a higher ecological sensitivity were primarily situated in the southwestern region, and their spatial distribution pattern was comparable to that of high habitat quality. The spatial overlay analysis categorized areas into various types, including human production and settlement zones, ecologically vulnerable zones, ecological transition zones, and ecological conservation zones, accounting for 17.28%, 22.30%, 7.41%, and 53.01% of the total area, respectively. The primary environmental factor affecting ecological function zoning was identified as precipitation, while the main social variables were human activity and population density. This study enhances the understanding of ecological functions and supports sustainable development in the Sichuan-Yunnan ecological buffer area, offering important guidance for ecological zoning. Full article

The accurate detection of railway tracks is essential for ensuring the safe operation of railways. This study introduces an innovative algorithm that utilizes a graph convolutional network (GCN) and deep neural residual network to enhance feature extraction from high-resolution aerial imagery. The traditional encoder–decoder architecture is expanded with GCN, which improves neighborhood definitions and enables long-range information exchange in a single layer. As a result, complex track features and contextual information are captured more effectively. The deep neural residual network, which incorporates depthwise separable convolution and an inverted bottleneck design, improves the representation of long-distance positional information and addresses occlusion caused by train carriages. The scSE attention mechanism reduces noise and optimizes feature representation. The algorithm was trained and tested on custom and Massachusetts datasets, demonstrating an 89.79% recall rate. This is a 3.17% improvement over the original U-Net model, indicating excellent performance in railway track segmentation. These findings suggest that the proposed algorithm not only excels in railway track segmentation but also offers significant competitive advantages in performance. Full article

Different types of rural settlement agglomerations have been formed and mixed in space during the rural revitalization strategy implementation in China. Discriminating them from remote sensing images is of great significance for rural land planning and living environment improvement. Currently, there is a lack of automatic methods for obtaining information on rural settlement differentiation. In this paper, an improved encoder–decoder network structure, ASCEND-UNet, was designed based on the original UNet. It was implemented to segment and classify dispersed and clustered rural settlement buildings from high-resolution satellite images. The ASCEND-UNet model incorporated three components: firstly, the atrous spatial pyramid pooling (ASPP) multi-scale feature fusion module was added into the encoder, then the spatial and channel squeeze and excitation (scSE) block was embedded at the skip connection; thirdly, the hybrid dilated convolution (HDC) block was utilized in the decoder. In our proposed framework, the ASPP and HDC were used as multiple dilated convolution blocks to expand the receptive field by introducing a series of dilated rate convolutions. The scSE is an attention mechanism block focusing on features both in the spatial and channel dimension. A series of model comparisons and accuracy assessments with the original UNet, PSPNet, DeepLabV3+, and SegNet verified the effectiveness of our proposed model. Compared with the original UNet model, ASCEND-UNet achieved improvements of 4.67%, 2.80%, 3.73%, and 6.28% in precision, recall, F1-score and MIoU, respectively. The contributions of HDC, ASPP, and scSE modules were discussed in ablation experiments. Our proposed model obtained more accurate and stable results by integrating multiple dilated convolution blocks with an attention mechanism. This novel model enriches the automatic methods for semantic segmentation of different rural settlements from remote sensing images. Full article

The identification and enumeration of peach seedling fruits are pivotal in the realm of precision agriculture, greatly influencing both yield estimation and agronomic practices. This study introduces an innovative, lightweight YOLOv8 model for the automatic detection and quantification of peach seedling fruits, designated as YOLO-Peach, to bolster the scientific rigor and operational efficiency of orchard management. Traditional identification methods, which are labor-intensive and error-prone, have been superseded by this advancement. A comprehensive dataset was meticulously curated, capturing the rich characteristics and diversity of peach seedling fruits through high-resolution imagery at various times and locations, followed by meticulous preprocessing to ensure data quality. The YOLOv8s model underwent a series of lightweight optimizations, including the integration of MobileNetV3 as its backbone, the p2BiFPN architecture, spatial and channel reconstruction convolution, and coordinate attention mechanism, all of which have significantly bolstered the model’s capability to detect small targets with precision. The YOLO-Peach model excels in detection accuracy, evidenced by a precision and recall of 0.979, along with an mAP50 of 0.993 and an mAP50-95 of 0.867, indicating its superior capability for peach sapling identification with efficient computational performance. The findings underscore the model’s efficacy and practicality in the context of peach seedling fruit recognition. Ablation studies have shed light on the indispensable role of each component, with MobileNetV3 streamlining the model’s complexity and computational load, while the p2BiFPN architecture, ScConv convolutions, and coordinate attention mechanism have collectively enhanced the model’s feature extraction and detection precision for minute targets. The implications of this research are profound, offering a novel approach to peach seedling fruit recognition and serving as a blueprint for the identification of young fruits in other fruit species. This work holds significant theoretical and practical value, propelling forward the broader field of agricultural automation. Full article

Among the existing insulator defect detection methods, the automatic detection of inspection robots based on the instance segmentation algorithm is relatively more efficient, but the problem of the limited accuracy of the segmentation algorithm is still a bottleneck for increasing inspection efficiency. Therefore, we propose a single-stage insulator instance defect segmentation method based on both an attention mechanism and improved feature fusion network. YOLACT is selected as the basic instance segmentation model. Firstly, to improve the segmentation speed, MobileNetV2 embedded with an scSE attention mechanism is introduced as the backbone network. Secondly, a new feature map that combines semantic and positional information is obtained by improving the FPN module and fusing the feature maps of each layer, during which, an attention mechanism is introduced to further improve the quality of the feature map. Thirdly, in view of the problems that affect the insulator segmentation, a Restrained-IoU (RIoU) bounding box loss function which covers the area deviation, center deviation, and shape deviation is designed for object detection. Finally, for the validity evaluation of the proposed method, experiments are performed on the insulator defect data set. It is shown in the results that the improved algorithm achieves a mask accuracy improvement of 5.82% and a detection speed of 37.4 FPS, which better complete the instance segmentation of insulator defect images. Full article

In the context of difficulty in detection problems and the limited computing resources of various fault scales in aerial images of transmission line UAV inspections, this paper proposes a TD-YOLO algorithm (YOLO for transmission detection). Firstly, the Ghost module is used to lighten the model’s feature extraction network and prediction network, significantly reducing the number of parameters and the computational effort of the model. Secondly, the spatial and channel attention mechanism scSE (concurrent spatial and channel squeeze and channel excitation) is embedded into the feature fusion network, with PA-Net (path aggregation network) to construct a feature-balanced network, using channel weights and spatial weights as guides to achieving the balancing of multi-level and multi-scale features in the network, significantly improving the detection capability under the coexistence of multiple targets of different categories. Thirdly, a loss function, NWD (normalized Wasserstein distance), is introduced to enhance the detection of small targets, and the fusion ratio of NWD and CIoU is optimized to further compensate for the loss of accuracy caused by the lightweightedness of the model. Finally, a typical fault dataset of transmission lines is built using UAV inspection images for training and testing. The experimental results show that the TD-YOLO algorithm proposed in this article compresses 74.79% of the number of parameters and 66.92% of the calculation amount compared to YOLOv7-Tiny and increases the mAP (mean average precision) by 0.71%. The TD-YOLO was deployed into Jetson Xavier NX to simulate the UAV inspection process and was run at 23.5 FPS with good results. This study offers a reference for power line inspection and provides a possible way to deploy edge computing devices on unmanned aerial vehicles. Full article

Sea ice extraction and segmentation of remote sensing images is the basis for sea ice monitoring. Traditional image segmentation methods rely on manual sampling and require complex feature extraction. Deep-learning-based semantic segmentation methods have the advantages of high efficiency, intelligence, and automation. Sea ice segmentation using deep learning methods faces the following problems: in terms of datasets, the high cost of sea ice image label production leads to fewer datasets for sea ice segmentation; in terms of image quality, remote sensing image noise and severe weather conditions affect image quality, which affects the accuracy of sea ice extraction. To address the quantity and quality of the dataset, this study used multiple data augmentation methods for data expansion. To improve the semantic segmentation accuracy, the SC-U²-Net network was constructed using multiscale inflation convolution and a multilayer convolutional block attention module (CBAM) attention mechanism for the U²-Net network. The experiments showed that (1) data augmentation solved the problem of an insufficient number of training samples to a certain extent and improved the accuracy of image segmentation; (2) this study designed a multilevel Gaussian noise data augmentation scheme to improve the network’s ability to resist noise interference and achieve a more accurate segmentation of images with different degrees of noise pollution; (3) the inclusion of a multiscale inflation perceptron and multilayer CBAM attention mechanism improved the ability of U²-Net network feature extraction and enhanced the model accuracy and generalization ability. Full article

Automatic crack detection is always a challenging task due to the inherent complex backgrounds, uneven illumination, irregular patterns, and various types of noise interference. In this paper, we proposed a U-shaped encoder–decoder semantic segmentation network combining Unet and Resnet for pixel-level pavement crack image segmentation, which is called RUC-Net. We introduced the spatial-channel squeeze and excitation (scSE) attention module to improve the detection effect and used the focal loss function to deal with the class imbalance problem in the pavement crack segmentation task. We evaluated our methods using three public datasets, CFD, Crack500, and DeepCrack, and all achieved superior results to those of FCN, Unet, and SegNet. In addition, taking the CFD dataset as an example, we performed ablation studies and compared the differences of various scSE modules and their combinations in improving the performance of crack detection. Full article