RESUMEN
BACKGROUND: The study aimed to construct an intelligent difficulty scoring and assistance system (DSAS) for endoscopic retrograde cholangiopancreatography (ERCP) treatment of common bile duct (CBD) stones. METHODS: 1954 cholangiograms were collected from three hospitals for training and testing the DSAS.âThe D-LinkNet34 and U-Net were adopted to segment the CBD, stones, and duodenoscope. Based on the segmentation results, the stone size, distal CBD diameter, distal CBD arm, and distal CBD angulation were estimated. The performance of segmentation and estimation was assessed by mean intersection over union (mIoU) and average relative error. A technical difficulty scoring scale, which was used for assessing the technical difficulty of CBD stone removal, was developed and validated. We also analyzed the relationship between scores evaluated by the DSAS and clinical indicators including stone clearance rate and need for endoscopic papillary large-balloon dilation (EPLBD) and lithotripsy. RESULTS: The mIoU values of the stone, CBD, and duodenoscope segmentation were 68.35â%, 86.42â%, and 95.85â%, respectively. The estimation performance of the DSAS was superior to nonexpert endoscopists. In addition, the technical difficulty scoring performance of the DSAS was more consistent with expert endoscopists than two nonexpert endoscopists. A DSAS assessment score ≥â2 was correlated with lower stone clearance rates and more frequent EPLBD. CONCLUSIONS: An intelligent DSAS based on deep learning was developed. The DSAS could assist endoscopists by automatically scoring the technical difficulty of CBD stone extraction, and guiding the choice of therapeutic approach and appropriate accessories during ERCP.
Asunto(s)
Aprendizaje Profundo , Cálculos Biliares , Colangiopancreatografia Retrógrada Endoscópica , Conducto Colédoco/diagnóstico por imagen , Conducto Colédoco/cirugía , Cálculos Biliares/diagnóstico por imagen , Cálculos Biliares/cirugía , Humanos , Esfinterotomía Endoscópica , Resultado del TratamientoRESUMEN
The ecosystem gross primary productivity (GPP) is crucial to land-atmosphere carbon exchanges, and changes in global GPP as well as its influencing factors have been well studied in recent years. However, identifying the spatio-temporal variations of global GPP under future climate changes is still a challenging issue. This study aims to develop data-driven approach for predicting the global GPP as well as its monthly and annual variations up to the year 2100 under changing climate. Specifically, Catboost was employed to examine the potential relationship between the GPP and environmental factors, with climate variables, CO2 concentration and terrain attributes being selected as environmental factors. The predicted monthly and annual GPP from Coupled Model Intercomparison Project phase 6 (CMIP6) under future SSP1-2.6, SSP2-4.5, SSP3-7.0 and SSP5-8.5 scenarios were analyzed. The results indicate that the global GPP is predicted to increase under the future climate change in the 21st century. The annual GPP is expected to be 115.122 Pg C, 116.537 Pg C, 117.626 Pg C, and 120.097 Pg C in 2100 under four future scenarios, and the predicted monthly GPP shows seasonal difference. Meanwhile, GPP tends to increase in the northern mid-high latitude regions and decrease in the equatorial regions. For the climate zones form Köppen-Geiger classification, the arid, cold, and polar zones present increased GPP, while GPP in the tropical zone will decrease in the future. Moreover, the high importance of climate variables in GPP prediction illustrates that the future climate change is the main driver of the global GPP dynamics. This study provides a basis for predicting how global GPP responds to future climate change in the coming decades, which contribute to understanding the interactions between vegetation and climate.
RESUMEN
Real hyperspectral images (HSIs) are ineluctably contaminated by diverse types of noise, which severely limits the image usability. Recently, transfer learning has been introduced in hyperspectral denoising networks to improve model generalizability. However, the current frameworks often rely on image priors and struggle to retain the fidelity of background information. In this article, an unsupervised adaptation learning (UAL)-based hyperspectral denoising network (UALHDN) is proposed to address these issues. The core idea is first learning a general image prior for most HSIs, and then adapting it to a real HSI by learning the deep priors and maintaining background consistency, without introducing hand-crafted priors. Following this notion, a spatial-spectral residual denoiser, a global modeling discriminator, and a hyperspectral discrete representation learning scheme are introduced in the UALHDN framework, and are employed across two learning stages. First, the denoiser and the discriminator are pretrained using synthetic noisy-clean ground-based HSI pairs. Subsequently, the denoiser is further fine-tuned on the real multiplatform HSI according to a spatial-spectral consistency constraint and a background consistency loss in an unsupervised manner. A hyperspectral discrete representation learning scheme is also designed in the fine-tuning stage to extract semantic features and estimate noise-free components, exploring the deep priors specific for real HSIs. The applicability and generalizability of the proposed UALHDN framework were verified through the experiments on real HSIs from various platforms and sensors, including unmanned aerial vehicle-borne, airborne, spaceborne, and Martian datasets. The UAL denoising scheme shows a superior denoising ability when compared with the state-of-the-art hyperspectral denoisers.
RESUMEN
Planning a practical three-dimensional (3-D) flight path for unmanned aerial vehicles (UAVs) is a key challenge for the follow-up management and decision making in disaster emergency response. The ideal flight path is expected to balance the total flight path length and the terrain threat, to shorten the flight time and reduce the possibility of collision. However, in the traditional methods, the tradeoff between these concerns is difficult to achieve, and practical constraints are lacking in the optimized objective functions, which leads to inaccurate modeling. In addition, the traditional methods based on gradient optimization lack an accurate optimization capability in the complex multimodal objective space, resulting in a nonoptimal path. Thus, in this article, an accurate UAV 3-D path planning approach in accordance with an enhanced multiobjective swarm intelligence algorithm is proposed (APPMS). In the APPMS method, the path planning mission is converted into a multiobjective optimization task with multiple constraints, and the objectives based on the total flight path length and degree of terrain threat are simultaneously optimized. In addition, to obtain the optimal UAV 3-D flight path, an accurate swarm intelligence search approach based on improved ant colony optimization is introduced, which can improve the global and local search capabilities by using the preferred search direction and random neighborhood search mechanism. The effectiveness of the proposed APPMS method was demonstrated in three groups of simulated experiments with different degrees of terrain threat, and a real-data experiment with 3-D terrain data from an actual emergency situation.
RESUMEN
Geospatial object segmentation, a fundamental Earth vision task, always suffers from scale variation, the larger intra-class variance of background, and foreground-background imbalance in high spatial resolution (HSR) remote sensing imagery. Generic semantic segmentation methods mainly focus on the scale variation in natural scenarios. However, the other two problems are insufficiently considered in large area Earth observation scenarios. In this paper, we propose a foreground-aware relation network (FarSeg++) from the perspectives of relation-based, optimization-based, and objectness-based foreground modeling, alleviating the above two problems. From the perspective of the relations, the foreground-scene relation module improves the discrimination of the foreground features via the foreground-correlated contexts associated with the object-scene relation. From the perspective of optimization, foreground-aware optimization is proposed to focus on foreground examples and hard examples of the background during training to achieve a balanced optimization. Besides, from the perspective of objectness, a foreground-aware decoder is proposed to improve the objectness representation, alleviating the objectness prediction problem that is the main bottleneck revealed by an empirical upper bound analysis. We also introduce a new large-scale high-resolution urban vehicle segmentation dataset to verify the effectiveness of the proposed method and push the development of objectness prediction further forward. The experimental results suggest that FarSeg++ is superior to the state-of-the-art generic semantic segmentation methods and can achieve a better trade-off between speed and accuracy.
RESUMEN
Aircraft recognition is crucial in both civil and military fields, and high-spatial resolution remote sensing has emerged as a practical approach. However, existing data-driven methods fail to locate discriminative regions for effective feature extraction due to limited training data, leading to poor recognition performance. To address this issue, we propose a knowledge-driven deep learning method called the explicable aircraft recognition framework based on a part parsing prior (APPEAR). APPEAR explicitly models the aircraft's rigid structure as a pixel-level part parsing prior, dividing it into five parts: 1) the nose; 2) left wing; 3) right wing; 4) fuselage; and 5) tail. This fine-grained prior provides reliable part locations to delineate aircraft architecture and imposes spatial constraints among the parts, effectively reducing the search space for model optimization and identifying subtle interclass differences. A knowledge-driven aircraft part attention (KAPA) module uses this prior to achieving a geometric-invariant representation for identifying discriminative features. Part features are generated by part indexing in a specific order and sequentially embedded into a compact space to obtain a fixed-length representation for each part, invariant to aircraft orientation and scale. The part attention module then takes the embedded part features, adaptively reweights their importance to identify discriminative parts, and aggregates them for recognition. The proposed APPEAR framework is evaluated on two aircraft recognition datasets and achieves superior performance. Moreover, experiments with few-shot learning methods demonstrate the robustness of our framework in different tasks. Ablation analysis illustrates that the fuselage and wings of the aircraft are the most effective parts for recognition.
RESUMEN
Improper discharge of slag from mining will pollute the surrounding soil, thereby affecting the ecology and becoming an important global problem. The available copper (ACu) content in polluted soil is an important factor affecting plant growth and development. When investigating a large area of soil with ACu, manual sampling by points and inspection are mainly used, due to the heterogeneity of soil, the efficiency and accuracy are lower. The Unmanned aerial vehicle (UAV) equipped with a hyperspectral sensor as a remote sensing technology is widely used in soil indicator monitoring because of its rapid and convenience. Meanwhile, using the relationship between soil organic matter and available copper has the potential to predict available copper. In this study, we selected the study area with tailings area in the Jianghan Plain of China and used a UAV equipped with a hyperspectral sensor to predict ACu and soil organic matter (SOM) in the soil with two datasets. Firstly, 74 soil samples were collected in the study area, and the ACu and SOM of the soil samples were determined. Second, a hyperspectral image of the study area is obtained using a UAV equipped with a hyperspectral sensor. Thirdly, we combine hyperspectral data with competitive adaptive reweighted sampling (CARS) to obtain feature bands and utilize simulated annealing deep neural network (SA-DNN) to generate estimation models. Finally, maps of the distribution of ACu and SOM in the area were generated using the model. In two datasets, the model of ACu with R2 values both are 0.89, and R2 on the model of SOM is 0.89 and 0.88. The results show that the combination of UAV hyperspectral imagery with the SA-DNN model has good performance in the prediction of organic matter and available copper, which is helpful for soil environmental monitoring.
Asunto(s)
Cobre , Suelo , Dispositivos Aéreos No Tripulados , Estanques , Redes Neurales de la ComputaciónRESUMEN
Affected by tectonics, soft and hard composite coal seams are widely distributed in China; the soft stratification in the soft and hard composite coal seam is the key to controlling the occurrence of coal and gas outburst accidents. Based on this, for soft and hard composite coal seams, in order to accurately extract soft layers, a directional hydraulic coal mining equipment has been developed, including a drilling rig pump truck system, a directional coal wireless measurement system, and a cutter drill pipe system. By constructing a mathematical model and conducting numerical simulations, it was found that the vertical stress, horizontal stress, and gas pressure of the coal body around the borehole after coal extraction decreased significantly compared to normal borehole conditions; the on-site test results indicate that the hydraulic coal extraction volume of directional hydraulic coal extraction boreholes reaches 0.25 m3 per meter. The total amount of coal extracted accounts for more than 3 of the total amount of coal within the coverage area. The average concentration of gas extraction in the coal extraction area is 80.15%, and the net amount of gas extraction from 100 m boreholes reaches 0.17 m3/(min·hm). After extraction, the measured residual gas content in the coal extraction and non-extraction areas decreased by 59.27 and 40.38%, respectively. Directional hydraulic coal mining technology can effectively solve the problem of coal and gas outburst prevention in soft and hard composite coal seams and has good application prospects.
RESUMEN
High-precision road detection from very high resolution (VHR) remote sensing images has broad application value. However, the most advanced deep learning based methods often fail to identify roads when there is a distribution discrepancy between the training samples and test samples, due to their limited generalization ability. In this paper, to address this problem, an open-source data-driven domain-specific representation (OSM-DOER) framework is proposed for cross-domain road detection. On the one hand, as the spatial structure information of the source and target domains is similar, but the texture information is different, the domain-specific representation (DOER) framework is proposed, which not only aligns the distributions of the spatial structure information, but also learns the domain-specific texture information. Furthermore, in order to enhance the representation of the target domain data distribution, open-source and freely available OpenStreetMap (OSM) road centerline data are utilized to generate target domain samples, which are then used in the network training as the supervised information for the target domain. Finally, to verify the superiority of the proposed OSM-DOER framework, we conducted extensive experiments with the public SpaceNet and DeepGlobe road datasets, and large-scale road datasets from Birmingham in the UK and Shanghai in China. The experimental results demonstrate that the proposed OSM-DOER framework shows obvious advantages over the mainstream road detection methods, and the use of OSM road centerline data has great potential for the road detection task.
RESUMEN
Remote sensing image data clustering is a tough task, which involves classifying the image without any prior information. Remote sensing image clustering, in essence, belongs to a complex optimization problem, due to the high dimensionality and complexity of remote sensing imagery. Therefore, it can be easily affected by the initial values and trapped in locally optimal solutions. Meanwhile, remote sensing images contain complex and diverse spatial-spectral information, which makes them difficult to model with only a single objective function. Although evolutionary multiobjective optimization methods have been presented for the clustering task, the tradeoff between the global and local search abilities is not well adjusted in the evolutionary process. In this article, in order to address these problems, a multiobjective sine cosine algorithm for remote sensing image data spatial-spectral clustering (MOSCA_SSC) is proposed. In the proposed method, the clustering task is converted into a multiobjective optimization problem, and the Xie-Beni (XB) index and Jeffries-Matusita (Jm) distance combined with the spatial information term (SI_Jm measure) are utilized as the objective functions. In addition, for the first time, the sine cosine algorithm (SCA), which can effectively adjust the local and global search capabilities, is introduced into the framework of multiobjective clustering for continuous optimization. Furthermore, the destination solution in the SCA is automatically selected and updated from the current Pareto front through employing the knee-point-based selection approach. The benefits of the proposed method were demonstrated by clustering experiments with ten UCI datasets and four real remote sensing image datasets.
RESUMEN
Hyperspectral videos can provide the spatial, spectral, and motion information of targets, which makes it possible to track camouflaged targets that are similar to the background. However, hyperspectral object tracking is a challenging task, due to the huge hyperspectral video data dimension and the "data hungry" problem for the model training. Insufficient training data can seriously interfere with the accuracy and generalization of the tracking models. In this paper, a dual deep Siamese network framework for hyperspectral object tracking (SiamHYPER) is proposed for learning a hyperspectral tracker from a pretrained RGB tracker in the case of the "data hungry" problem. Specifically, in addition to a pretrained RGB-based Siamese tracker, a hyperspectral target-aware module is designed to mine the spectral information during the target prediction, and a spatial-spectral cross-attention module is introduced to further fuse the deep spatial and spectral features extracted from the RGB tracker and the hyperspectral target-aware module. Benefiting from the guidance training of the RGB tracker, a robust hyperspectral object tracker can be trained effectively with only a small number of hyperspectral video samples, to overcome the "data hungry" problem. In the experiments conducted in this study, the SiamHYPER framework was verified using SiamBAN and SiamRPN++, with 13 000 frames of hyperspectral videos for training, and achieved the best performance on the publicly available hyperspectral dataset released as part of the WHISPERS Hyperspectral Object Tracking Challenge. The area under the curve (AUC) of SiamHYPER was increased by nearly 8.9% and 7.2%, respectively, when compared with the current state-of-the-art RGB-based and hyperspectral trackers. In addition, the processing speed of SiamHYPER was 19 FPS, which is much higher than that of the current state-of-the-art hyperspectral trackers. The source code is available at zhenliuzhenqi/HOT: Hyperspectral object tracking (github.com).
RESUMEN
Remote sensing image scene classification methods based on deep learning have been widely studied and discussed. However, most of the network architectures are directly reliant on natural image processing methods and are fixed. A few studies have focused on automatic search mechanisms, but they cannot weigh the interpretation accuracy and the parameter quantity for practical application. As a result, automatic global search methods based on multiobjective evolutionary computation have more advantages. However, in the ranking process, the network individuals with large parameter quantities are easy to eliminate, but a higher accuracy may be obtained after full training. In addition, evolutionary neural architecture search methods often take several days. In this article, in order to solve the above concerns, we propose an efficient multiobjective evolutionary automatic search framework for remote sensing image scene classification deep learning network architectures (E2SCNet). In E2SCNet, eight kinds of lightweight operators are used to build a diversified search space, and the coding connection mode is flexible. In the search process, a large model retention mechanism is implemented through two-step multiobjective modeling and evolutionary search, where one step involves the "parameter quantity and accuracy", and the other step involves the "parameter quantity and accuracy growth quantity." Moreover, a super network is constructed to share the weight in the process of individual network evaluation and promote the search speed. The effectiveness of E2SCNet is proven by comparison with several networks designed by human experts and networks obtained by gradient and evolutionary computing-based search methods.
RESUMEN
Deep learning techniques have been widely applied to hyperspectral image (HSI) classification and have achieved great success. However, the deep neural network model has a large parameter space and requires a large number of labeled data. Deep learning methods for HSI classification usually follow a patchwise learning framework. Recently, a fast patch-free global learning (FPGA) architecture was proposed for HSI classification according to global spatial context information. However, FPGA has difficulty in extracting the most discriminative features when the sample data are imbalanced. In this article, a spectral-spatial-dependent global learning (SSDGL) framework based on the global convolutional long short-term memory (GCL) and global joint attention mechanism (GJAM) is proposed for insufficient and imbalanced HSI classification. In SSDGL, the hierarchically balanced (H-B) sampling strategy and the weighted softmax loss are proposed to address the imbalanced sample problem. To effectively distinguish similar spectral characteristics of land cover types, the GCL module is introduced to extract the long short-term dependency of spectral features. To learn the most discriminative feature representations, the GJAM module is proposed to extract attention areas. The experimental results obtained with three public HSI datasets show that the SSDGL has powerful performance in insufficient and imbalanced sample problems and is superior to other state-of-the-art methods.
Asunto(s)
Aprendizaje Profundo , Redes Neurales de la ComputaciónRESUMEN
Hydrogen is a promising substitute for non-renewable fossil fuels. Producing hydrogen fuel by electrolyzing water is an effective strategy to address the growing environmental problems. Platinum (Pt) is still the most active electrocatalyst to catalyze the hydrogen evolution reaction (HER) in alkaline media. Herein, we demonstrate that ultrafine candied haws-shaped PtWNi nanoalloys modified with the Ni species (Nin+) could be formed in the alkaline electroactivation process of PtWNi alloys. Notably, the Ni species (Nin+) promoted the decomposition of water and produced hydrogen intermediates, which were then immediately adsorbed on the surface of Pt and recombined into molecular hydrogen. Moreover, these hydrogen intermediates also enhanced the instability of the HO-H bond, leading to an increase in the total activity.
RESUMEN
Surfactants or capping agents are usually employed to control the shapes and sizes of metal nanowires (NWs). Polyvinylpyrrolidone (PVP) and oleylamine (OAm) are the most common capping agents used in the synthesis of metal nanowires. However, these capping agents bind strongly onto the surface of the nanowires and severely prevent the reactant molecules from entering the active sites. In the present research, a facile acetic acid/NaBH4 treatment technology is reported to effectively remove PVP and OAm from the surface of the co-doped Pt NWs. Interestingly, the morphology of poor crystalline platinum nanowires treated with NaBH4 solution is transformed into nanowire networks (NWNs) with higher crystallinity. Furthermore, in comparison with the commercial Pt/C catalyst, the catalytic activity of co-doped Pt NWNs with clean surfaces shows improvements of up to 4.1 times for mass activity and 5.1 times for specific activity, respectively.
RESUMEN
With the increase in the availability of high-resolution remote sensing imagery, classification is becoming an increasingly useful technique for providing a large area of detailed land-cover information by the use of these high-resolution images. High-resolution images have the characteristics of abundant geometric and detail information, which are beneficial to detailed classification. In order to make full use of these characteristics, a classification algorithm based on conditional random fields (CRFs) is presented in this paper. The proposed algorithm integrates spectral, spatial contextual, and spatial location cues by modeling the probabilistic potentials. The spectral cues modeled by the unary potentials can provide basic information for discriminating the various land-cover classes. The pairwise potentials consider the spatial contextual information by establishing the neighboring interactions between pixels to favor spatial smoothing. The spatial location cues are explicitly encoded in the higher order potentials. The higher order potentials consider the nonlocal range of the spatial location interactions between the target pixel and its nearest training samples. This can provide useful information for the classes that are easily confused with other land-cover types in the spectral appearance. The proposed algorithm integrates spectral, spatial contextual, and spatial location cues within a CRF framework to provide complementary information from varying perspectives, so that it can address the common problem of spectral variability in remote sensing images, which is directly reflected in the accuracy of each class and the average accuracy. The experimental results with three high-resolution images show the validity of the algorithm, compared with the other state-of-the-art classification algorithms.
RESUMEN
In this paper, a novel subpixel mapping algorithm based on an adaptive differential evolution (DE) algorithm, namely, adaptive-DE subpixel mapping (ADESM), is developed to perform the subpixel mapping task for remote sensing images. Subpixel mapping may provide a fine-resolution map of class labels from coarser spectral unmixing fraction images, with the assumption of spatial dependence. In ADESM, to utilize DE, the subpixel mapping problem is transformed into an optimization problem by maximizing the spatial dependence index. The traditional DE algorithm is an efficient and powerful population-based stochastic global optimizer in continuous optimization problems, but it cannot be applied to the subpixel mapping problem in a discrete search space. In addition, it is not an easy task to properly set control parameters in DE. To avoid these problems, this paper utilizes an adaptive strategy without user-defined parameters, and a reversible-conversion strategy between continuous space and discrete space, to improve the classical DE algorithm. During the process of evolution, they are further improved by enhanced evolution operators, e.g., mutation, crossover, repair, exchange, insertion, and an effective local search to generate new candidate solutions. Experimental results using different types of remote images show that the ADESM algorithm consistently outperforms the previous subpixel mapping algorithms in all the experiments. Based on sensitivity analysis, ADESM, with its self-adaptive control parameter setting, is better than, or at least comparable to, the standard DE algorithm, when considering the accuracy of subpixel mapping, and hence provides an effective new approach to subpixel mapping for remote sensing imagery.