Explore the vast range of titles available.

Soybean is one of the world’s major oil-bearing crops and occupies an important role in the daily diet of human beings. However, the frequent occurrence of soybean leaf diseases caused serious threats to its yield and quality during soybean cultivation. Rapid identification of soybean leaf diseases could provide a better solution for efficient control and subsequent precision application. In this study, a lightweight deep convolutional neural network (CNN) based on multiscale feature extraction fusion (MFEF) and combined with a dense connectivity (DC) network (MFEF-DCNet) was proposed for soybean leaf disease identification. In MFEF-DCNet, a multiscale feature extraction fusion (MFEF) module for soybean leaves was constructed by utilizing a convolutional attention module and depth-separable convolution to improve the model feature extraction capability. Multiscale features are fused by using dense connections (DC) in the backbone network to improve the model generalization capability. Experiments were implemented on eight distinct disease and deficiency classes of soybean images (including bacterial blight, cercospora leaf blight, downy mildew, frogeye leaf spot, healthy, potassium deficiency, soybean rust, and target spot) using the proposed network. The results showed that the MFEF-DCNet had an accuracy of 0.9470, an average precision of 0.9510, an average recall of 0.9480, and an F1-score of 0.9490 for soybean leaf disease identification. And MFEF-DCNet had certain performance advantages in terms of classification accuracy, convergence speed and other effects compared with VGG16, ResNet50, DenseNet201, EfficientNetB0, Xception and MobileNetV3_small models. In addition, the accuracy of the MFEF-DCNet model in recognizing soybean diseases in local data was 0.9024, which indicated that the MFEF-DCNet model had favorable application in practical applications. The proposed model and experience in this study could provide useful inspiration for automated disease identification in soybean and other crops.

To address the challenges that convolutional neural networks (CNNs) face in extracting small objects and handling class imbalance in remote sensing imagery, this paper proposes a novel spatial contextual information and multiscale feature fusion encoding–decoding network, SCIMF-Net. Firstly, SCIMF-Net employs an improved ResNeXt-101 deep backbone network, significantly enhancing the extraction capability of small object features. Next, a novel PMFF module is designed to effectively promote the fusion of features at different scales, deepening the model’s understanding of global and local spatial contextual information. Finally, introducing a weighted joint loss function improves the SCIMF-Net model’s performance in extracting LULC information under class imbalance conditions. Experimental results show that compared to other CNNs such as Res-FCN, U-Net, SE-U-Net, and U-Net++, SCIMF-Net improves PA by 0.68%, 0.54%, 1.61%, and 3.39%, respectively; MPA by 2.96%, 4.51%, 2.37%, and 3.45%, respectively; and MIOU by 3.27%, 4.89%, 4.2%, and 5.68%, respectively. Detailed comparisons of locally visualized LULC information extraction results indicate that SCIMF-Net can accurately extract information from imbalanced classes and small objects.

BackgroundExtreme wildfires pose a serious threat to forest vegetation and human life because they spread more rapidly and are more intense than conventional wildfires. Detecting extreme wildfires is challenging due to their visual similarities to traditional fires, and existing models primarily detect the presence or absence of fires without focusing on distinguishing extreme wildfires and providing warnings.AimsTo test a system for real time detection of four extreme wildfires.MethodsWe proposed a novel lightweight model, called LEF-YOLO, based on the YOLOv5 framework. To make the model lightweight, we introduce the bottleneck structure of MobileNetv3 and use depthwise separable convolution instead of conventional convolution. To improve the model’s detection accuracy, we apply a multiscale feature fusion strategy and use a Coordinate Attention and Spatial Pyramid Pooling-Fast block to enhance feature extraction.Key resultsThe LEF-YOLO model outperformed the comparison model on the extreme wildfire dataset we constructed, with our model having excellent performance of 2.7 GFLOPs, 61 FPS and 87.9% mAP.ConclusionsThe detection speed and accuracy of LEF-YOLO can be utilised for the real-time detection of four extreme wildfires in forest fire scenes.ImplicationsThe system can facilitate fire control decision-making and foster the intersection between fire science and computer science.

Semantic segmentation of high-resolution remote sensing images is highly challenging due to the presence of a complicated background, irregular target shapes, and similarities in the appearance of multiple target categories. Most of the existing segmentation methods that rely only on simple fusion of the extracted multi-scale features often fail to provide satisfactory results when there is a large difference in the target sizes. Handling this problem through multi-scale context extraction and efficient fusion of multi-scale features, in this paper we present an end-to-end multi-scale adaptive feature fusion network (MANet) for semantic segmentation in remote sensing images. It is a coding and decoding structure that includes a multi-scale context extraction module (MCM) and an adaptive fusion module (AFM). The MCM employs two layers of atrous convolutions with different dilatation rates and global average pooling to extract context information at multiple scales in parallel. MANet embeds the channel attention mechanism to fuse semantic features. The high- and low-level semantic information are concatenated to generate global features via global average pooling. These global features are used as channel weights to acquire adaptive weight information of each channel by the fully connected layer. To accomplish an efficient fusion, these tuned weights are applied to the fused features. Performance of the proposed method has been evaluated by comparing it with six other state-of-the-art networks: fully convolutional networks (FCN), U-net, UZ1, Light-weight RefineNet, DeepLabv3+, and APPD. Experiments performed using the publicly available Potsdam and Vaihingen datasets show that the proposed MANet significantly outperforms the other existing networks, with overall accuracy reaching 89.4% and 88.2%, respectively and with average of F1 reaching 90.4% and 86.7% respectively.

Remote sensing spatiotemporal fusion is an effective method for generating high spatiotemporal resolution remote sensing images. Current spatiotemporal fusion models use a single pair of coarse-fine resolution images for prediction. They struggle to capture significant changes at the same location over short time intervals. This limitation makes it difficult to achieve high-accuracy image predictions. However, by using two pairs of coarse-fine resolution images for auxiliary prediction, continuous changes in data can be fully utilized, effectively addressing the issue of dramatic image changes. Therefore, this paper proposes the Two-Stream High Temporal Sensitive Convolutional Neural Network (TSCNN). TSCNN introduces the Long-Term Dynamic Capture module (LTDC), which incorporates the temporal variation information extracted from coarse-resolution images into fine-resolution images, enhancing the weight of post-prediction images and preserving the integrity of temporal information, thus reducing the uncertainty of image mutations. To address the issue of inconsistent multiscale features in remote sensing images and improve image accuracy, we design an encoder-decoder structure. The encoder uses a multiscale extraction module to extract features from remote sensing images, expanding the range of contextual information and enhancing the utilization of features at different scales. In the decoder, the Global-Local Attentional Feature Fusion module (GLAFF) is introduced to capture global and local semantic features, which are then fused and reconstructed. This approach improves the completeness of the acquired information. Based on the quantitative results of three datasets, the proposed method improves the quantitative indices of spectral angle mapper (SAM), relative dimensionless global error (ERGAS), correlation coefficient (CC), and structural similarity (SSIM) by up to 0.3360, 0.1111, 0.0308, and 0.0308 at most compared with the best comparison method. TSCNN improves the accuracy of prediction. It has a wide application prospect.

Automatic building extraction has been applied in many domains. It is also a challenging problem because of the complex scenes and multiscale. Deep learning algorithms, especially fully convolutional neural networks (FCNs), have shown robust feature extraction ability than traditional remote sensing data processing methods. However, hierarchical features from encoders with a fixed receptive field perform weak ability to obtain global semantic information. Local features in multiscale subregions cannot construct contextual interdependence and correlation, especially for large-scale building areas, which probably causes fragmentary extraction results due to intra-class feature variability. In addition, low-level features have accurate and fine-grained spatial information for tiny building structures but lack refinement and selection, and the semantic gap of across-level features is not conducive to feature fusion. To address the above problems, this paper proposes an FCN framework based on the residual network and provides the training pattern for multi-modal data combining the advantage of high-resolution aerial images and LiDAR data for building extraction. Two novel modules have been proposed for the optimization and integration of multiscale and across-level features. In particular, a multiscale context optimization module is designed to adaptively generate the feature representations for different subregions and effectively aggregate global context. A semantic guided spatial attention mechanism is introduced to refine shallow features and alleviate the semantic gap. Finally, hierarchical features are fused via the feature pyramid network. Compared with other state-of-the-art methods, experimental results demonstrate superior performance with 93.19 IoU, 97.56 OA on WHU datasets and 94.72 IoU, 97.84 OA on the Boston dataset, which shows that the proposed network can improve accuracy and achieve better performance for building extraction.

Accurate breast lesion segmentation is a great help in the initial stage of breast cancer treatment planning. Ultrasound is considered the safe and cheapest method for the breast screening process. However, ultrasound images inherently contain speckle noise, unclear boundaries, and complex shapes, making it more challenging for automatic segmentation methods. This work proposes a multiscale dual attention-based network (MDA-Net) for concurrent segmentation of breast lesions images. The multiscale fusion (MF) block is introduced that addresses the classical fixed receptive field issues, and helps to extract more semantic features and aims to achieve more features diversity. A dual-attention (dA) is also proposed, which is a hybrid of channel-based attention (cA) and lesion attention (lA) blocks that improves the feature representation capability and adaptatively learns a discriminative representation of high-level features. As a result, a combination of two attention blocks helped the proposed network to concentrate on a more relevant field of view of targets. The MDA-Net is extensively tested on both self-collected private datasets and two public UDIAT, BUSIS datasets. Furthermore, our method is also evaluated on MRI datasets to observe the broad applicability of our method in a different imaging modality. The MDA-Net has achieved the DSC of 87.68%, 91.85%, 90.41%, 83.47% on UDIAT, BUSIS, Private, and RIDER breast MRI datasets (p-value<0.05 with paired t-test). Our MDA-Net implementation code and pretrained models are released at GitHub: https://github.com/ahmedeqbal/MDA-Net.

Background and objectiveSudden cardiac death (SCD) is one of the leading causes of death in cardiovascular diseases. Monitoring the state of the heart in real time and giving early warning of possible dangers by using ambulate electrocardiogram signals are the keys to prevent cardiovascular death. However, due to the diversity inducing factors of SCD and great individual differences, accurate prediction of SCD using electrocardiogram is a hard task, especially applied in portable electrocardiograph.MethodsThis paper proposed a multi-domain features fusion algorithm to predict SCD. Heart rate variability (HRV) signals was used to investigate the characters of SCD. A multiscale variation feature extracted from multiscale poincare plots was proposed to demonstrate the dynamic changes of HRV along different scales. A time-domain feature, Shannon entropy and this multiscale variation feature were combined by using SVM classifier to classify SCD. HRV signals from different time periods prior to SCD onset were used to test the effectiveness of the SCD prediction algorithm. And the dynamic variation characteristics of SCD prediction accuracy for each minute were also studied.ResultsIn the prediction of SCD using the 70-min HRV signals before the onset of SCD, the average prediction accuracy only using the multiscale variation feature reached to 85.83%, which verified the effectiveness and high specificity of this multiscale variation feature. By combining time domain, Shannon entropy and the multiscale variation feature, the average prediction accuracy was improved to 91.22%. Through fusing multi-domain feature extracted in this paper, the advance prediction time was increased to 70 min before the onset of SCD.ConclusionsA feature with high sensitivity and specificity is proposed to predict SCD. By fusing multi-domain features of HRV signals, a high prediction accuracy is achieved and the advance prediction ability is improved. The algorithm is low computational complexity and easy to integrate into cardiovascular intelligent monitoring equipment, making the intelligent monitoring and real-time early warning of SCD becomes possible.

Recently, networks consider spectral-spatial information in multiscale inputs less, even though there are some networks that consider this factor, however these networks cannot guarantee to get optimal features, which are extracted from each scale input. Furthermore, these networks do not consider the complementary and related information among different scale features. To address these issues, a multiscale deep middle-level feature fusion network (MMFN) is proposed in this paper for hyperspectral classification. In MMFN, the network fully fuses the strong complementary and related information among different scale features to extract more discriminative features. The training of network contains two stages: the first stage obtains the optimal models corresponding to different scale inputs and extracts the middle-level features under the corresponding scale model. It can guarantee the multiscale middle-level features are optimal. The second stage fuses the optimal multiscale middle-level features in the convolutional layer, and the subsequent residual blocks can learn the complementary and related information among different scale middle-level features. Moreover, the idea of identity mapping in residual learning can help the network obtain a higher accuracy when the network is deeper. The effectiveness of our method is proved on four HSI data sets and the experimental results show that our method outperforms the other state-of-the-art methods especially with small training samples.

Deep-learning-based methods are crucial for building extraction from high-resolution remote sensing images, playing a key role in applications like natural disaster response, land resource management, and smart city development. However, extracting precise building from complex urban and rural environments remains challenging due to spectral variability and intricate background interference, particularly in densely packed and small buildings. To address these issues, we propose an enhanced U2-Net architecture, MFA-Net, which incorporates two key innovations: a Multidimensional Feature Adjustment (MFA) module that refines feature representations through Cascaded Channel, Spatial, and Multiscale Weighting Mechanisms and a Dynamic Fusion Loss function that enhances edge geometric fidelity. Evaluation on three datasets (Urban, Rural, and WHU) reveals that MFA-Net outperforms existing methods, with average improvements of 6% in F1-score and 7.3% in IoU and an average increase of 9.9% in training time. These advancements significantly improve edge delineation and the segmentation of dense building clusters, making MFA-Net especially beneficial for urban planning and land resource management.