通讯机构:
[Li, Z.] C;[Li, Z.] S;Sichuan Key Laboratory of Agricultural Information Engineering, Ya’an 625000, Sichuan, China<&wdkj&>College of Information Engineering, Sichuan Agricultural University, Ya’an 625000, Sichuan, China<&wdkj&>Author to whom correspondence should be addressed.
摘要:
In the research of green vegetation coverage in the field of remote sensing image segmentation, crop planting area is often obtained by semantic segmentation of images taken from high altitude. This method can be used to obtain the rate of cultivated land in a region (such as a country), but it does not reflect the real situation of a particular farmland. Therefore, this paper takes low-altitude images of farmland to build a dataset. After comparing several mainstream semantic segmentation algorithms, a new method that is more suitable for farmland vacancy segmentation is proposed. Additionally, the Strip Pooling module (SPM) and the Mixed Pooling module (MPM), with strip pooling as their core, are designed and fused into the semantic segmentation network structure to better extract the vacancy features. Considering the high cost of manual data annotation, this paper uses an improved ResNet network as the backbone of signal transmission, and meanwhile uses data augmentation to improve the performance and robustness of the model. As a result, the accuracy of the proposed method in the test set is 95.6%, mIoU is 77.6%, and the error rate is 7%. Compared to the existing model, the mIoU value is improved by nearly 4%, reaching the level of practical application.
作者机构:
[Li, Qian; Wang, Yuchao; Zeng, Jian; Wang, Qichen; Chen, Lei; Lei, Yongpeng; Ye, Tong; Tang, Yougen] Cent South Univ, Coll Chem & Chem Engn, State Key Lab Powder Met, Hunan Prov Key Lab Chem Power Sources, Changsha 410083, Peoples R China.;[He, Chaozheng; Wang, Ran] Xian Technol Univ, Sch Mat Sci & Chem Engn, Inst Environm & Energy Catalysis, Xian 710021, Peoples R China.;[Liu, Wei] Dalian Univ Technol, Sch Chem Engn, Dept Chem, State Key Lab Fine Chem, Dalian 116024, Peoples R China.;[He, Chaozheng] Xian Technol Univ, Sch Mat Sci & Chem Engn, Shaanxi Key Lab Optoelect Funct Mat & Devices, Xian 710021, Peoples R China.;[Li, Qian; Wang, Yuchao] Cent South Univ Forestry & Technol, Sch Mat Sci & Engn, Changsha 410004, Peoples R China.
通讯机构:
[Lei, Yongpeng] C;Cent South Univ, Coll Chem & Chem Engn, State Key Lab Powder Met, Hunan Prov Key Lab Chem Power Sources, Changsha 410083, Peoples R China.
关键词:
Active sites;Density functional theory;Electrocatalysis;N2 reduction reaction;Single atom catalysts
摘要:
Single atom catalysts (SACs) with isolated metal atoms dispersed on supports exhibit distinctive performances for electrocatalysis reactions. The designable realization of well-dispersed single metal atoms is still a great challenge owing to their ease of aggregation. Here, Mo single atomic sites (Mo-N3C) combined with some ultrasmall Mo2C/MoN clusters (Mo-SA/Mo2C-MoN-Cs, mean diameter < 2 nm) on nitrogen-doped porous carbon were synthesized via a simple pyrolysis of bimetallic Zn/Mo metalorganic frameworks. X-ray absorption near edge spectra (XANES) in combination with various characterizations show that most of Mo species in sample exist in the form of single sites and the exact structure is Mo-N3C. Density functional theory (DFT) calculation further shows that as the number of N-coordination in the Mo-NxC moieties increases, the positive charge of Mo atoms increases. The single Mo atoms in Mo-N3C have the best capability of N-2 adsorption, which may serve as main active sites for further electrochemical N-2 reduction. (C) 2020 Chinese Chemical Society and Institute of Materia Medica, Chinese Academy of Medical Sciences. Published by Elsevier B.V. All rights reserved.
期刊:
Multimedia Tools and Applications,2021年80(7):11291-11312 ISSN:1380-7501
通讯作者:
Wei, Zhanguo
作者机构:
[Li, Meilin; Wei, Zhanguo; Cai, Weiwei] Cent South Univ Forestry & Technol, Sch Logist & Transportat, Changsha 410004, Peoples R China.;[Cai, Weiwei] Changsha Astra Informat Technol Co Ltd, Changsha 410219, Peoples R China.;[Liu, Botao] Cent South Univ, Changsha 410083, Peoples R China.;[Kan, Jiangming] Beijing Forestry Univ, Beijing 100083, Peoples R China.
通讯机构:
[Wei, Zhanguo] C;Cent South Univ Forestry & Technol, Sch Logist & Transportat, Changsha 410004, Peoples R China.
关键词:
Triple-attention mechanism;Hyperspectral image;Residual and dense networks;Bi-directional long-short term memory networks
摘要:
AbstractEach sample in the hyperspectral remote sensing image has high-dimensional features and contains rich spatial and spectral information, which greatly increases the difficulty of feature selection and mining. In view of these difficulties, we propose a novel Triple-attention Guided Residual Dense and BiLSTM networks(TARDB-Net) to reduce redundant features while increasing feature fusion capabilities, which ultimately improves the ability to classify hyperspectral images. First, a novel Triple-attention mechanism is proposed to assign different weights to each feature. Then, the residual network is used to perform the residual operation on the features, and the initial features of the multiple residual blocks and the generated deep residual features are intensively fused, retaining a host number of prior features. And use the bidirectional long short-term memory network to integrate the contextual semantics of deep fusion features. Finally, the classification task is completed by Softmax classifier. Experiments on three hyperspectral datasets—Indian Pines, University of Pavia, and Salinas—show that under 10% of the training samples, the overall accuracy of our method is 87%, 96% and 96%, which is superior to several well-known methods.
期刊:
Mobile Information Systems,2021年2021:9962057:1-9962057:15 ISSN:1574-017X
作者机构:
[Li, Guangjun; Liu, Runmin] Wuhan Sports Univ, Coll Sports Engn & Informat Technol, Wuhan 430079, Peoples R China.;[Liu, Runmin] Wuhan Sports Univ, Sch Grad, Wuhan 430079, Peoples R China.;[Ning, Xin] Chinese Acad Sci, Inst Semicond, Beijing 100083, Peoples R China.;[Cai, Weiwei] Cent South Univ Forestry & Technol, Changsha 410004, Peoples R China.
摘要:
In recent years, learning algorithms based on deep convolution frameworks have gradually become the research hotspots in hyperspectral image classification tasks. However, in the classification process, high-dimensionality problems with large amounts of data and feature redundancy with interspectral correlation of hyperspectral images have not been solved efficiently. Therefore, this paper investigates data dimensionality reduction and feature extraction and proposes a novel multiscale dense cross-attention mechanism algorithm with covariance pooling (MDCA-CP) for hyperspectral image scene classification. The multisize convolution module can detect subtle changes in the hyperspectral images’ spatial and spectral dimensions between the pixels in the local areas and are suitable for extracting hyperspectral data with complex and diverse types of structures. For traditional algorithms that assign attention weights in a one-way manner, thus leading to the loss of feature information, the dense cross-attention mechanism proposed in this study can jointly distribute the attention weights horizontally and vertically to efficiently capture the most representative features. In addition, this study also uses covariance pooling to further extract the features of hyperspectral images from the second order. Experiments have been conducted on three well-known hyperspectral datasets, and the results thus obtained show that the MDCA-CP algorithm is superior compared to the other well-known methods.
摘要:
E-commerce offers various merchandise for selling and purchasing with frequent transactions and commodity flows. An accurate prediction of customer needs and optimized allocation of goods is required for cost reduction. The existing solutions have significant errors and are unsuitable for addressing warehouse needs and allocation. That is why businesses cannot respond to customer demands promptly, as they need accurate and reliable demand forecasting. Therefore, this paper proposes spatial feature fusion and grouping strategies based on multimodal data and builds a neural network prediction model for e-commodity demand. The designed model extracts order sequence features, consumer emotional features, and facial value features from multimodal data from e-commerce products. Then, a bidirectional long short-term memory network- (BiLSTM-) based grouping strategy is proposed. The proposed strategy fully learns the contextual semantics of time series data while reducing the influence of other features on the group's local features. The output features of multimodal data are highly spatially correlated, and this paper employs the spatial dimension fusion strategy for feature fusion. This strategy effectively obtains the deep spatial relations among multimodal data by integrating the features of each column in each group across spatial dimensions. Finally, the proposed model's prediction effect is tested using e-commerce dataset. The experimental results demonstrate the proposed algorithm's effectiveness and superiority.
摘要:
No-tillage (NT) practice is extensively adopted with aims to improve soil physical conditions, carbon (C) sequestration and to alleviate greenhouse gases (GHGs) emissions without compromising crop yield. However, the influences of NT on GHGs emissions and crop yields remains inconsistent. A global meta-analysis was performed by using fifty peer-reviewed publications to assess the effectiveness of soil physicochemical properties, nitrogen (N) fertilization, type and duration of crop, water management and climatic zones on GHGs emissions and crop yields under NT compared to conventional tillage (CT) practices. The outcome reveals that compared to CT, NT increased CO2, N2O, and CH4 emissions by 7.1, 12.0, and 20.8%, respectively. In contrast, NT caused up to 7.6% decline in global warming potential as compared to CT. However, absence of difference in crop yield was observed both under NT and CT practices. Increasing N fertilization rates under NT improved crop yield and GHGs emission up to 23 and 58%, respectively, compared to CT. Further, NT practices caused an increase of 16.1% CO2 and 14.7% N2O emission in the rainfed areas and up to 54.0% CH4 emission under irrigated areas as compared to CT practices. This meta-analysis study provides a scientific basis for evaluating the effects of NT on GHGs emissions and crop yields, and also provides basic information to mitigate the GHGs emissions that are associated with NT practice. (C) 2020 Elsevier B.V. All rights reserved.
摘要:
How to rely on market mechanism for achieving industrial sustainable development is an important issue both to current scholars and policymakers. Technological innovation is regarded as a mediator to construct a driving mechanism that flexible environmental policy affects sustainable development from the "narrow" perspective of Porter's hypothesis. Meanwhile, environment regulatory enforcement is introduced as a moderator to explore the institutional scenario that drives sustainable development of China's industry. Then we have adopted industrial panel data of 30 provinces in 2006-2015 and employed the sys-GMM method for empirical test. The findings show that: (1) flexible environmental policy can significantly facilitate industrial sustainable development. (2) Flexible environmental policy has a significantly positive impact on technological innovation. Meanwhile, technological innovation is significantly and positively related to industrial sustainable development, and technological innovation partially mediates the relationship between flexible environmental policy and industrial sustainable development. (3) Environment regulatory enforcement positively moderates the relationship between flexible environmental policy and technological innovation. However, it has a potentially positive but not significant moderating impact on the relationship between technological innovation and industrial sustainable development, indicating that there is still an "implementation gap". (4) From a regional point of view, technological innovation has partly mediating effects between flexible environmental policy and industrial sustainable development in the eastern and western regions, and environmental regulatory enforcement can positively moderate the role of flexible environmental policy in promoting technological innovation in the eastern region. Finally, this paper puts forward the policy implications. (C) 2019 Elsevier Ltd. All rights reserved.
摘要:
Although hyperspectral remote sensing images have rich spectral features, for small samples of remote sensing images, feature selection, feature mining, and feature integration are very important. A single model is difficult to apply to multiple tasks such as feature selection, feature mining, and feature integration during training, resulting in poor classification results for small sample classification of hyperspectral images. To improve the classification of small samples, a sequential joint deep learning algorithm is proposed in this paper. (In this algorithm, the deep features of multiscale convolution under an attention mechanism are integrated by using Bidirectional Long Short-Term Memory(Bi-LSTM) and AML.) First, we used principal component analysis (PCA) to reduce the dimensionality of the hyperspectral data and retain their key features. Second, the model uses an integrated attention mechanism to distribute the probability weight of the key input feature. Third, the model uses multiscale convolution to mine features after the distribution weight to obtain deep features. Fourth, the model uses bidirectional long short-term memory (Bi-LSTM) to integrate the convolution results at different scales. Finally, the softmax classifier is used to complete the classification of multiclass hyperspectral remote sensing images. Experiments were carried out on three public hyperspectral data sets, and the results proved that our proposed AML algorithm is effective, thus demonstrating powerful performance in the prediction of hyperspectral images (HSIs) of small samples.
摘要:
The latest methods based on deep learning have achieved amazing results regarding the complex work of inpainting large missing areas in an image. But this type of method generally attempts to generate one single & x201C;optimal & x201D; result, ignoring many other plausible results. Considering the uncertainty of the inpainting task, one sole result can hardly be regarded as a desired regeneration of the missing area. In view of this weakness, which is related to the design of the previous algorithms, we propose a novel deep generative model equipped with a brand new style extractor which can extract the style feature (latent vector) from the ground truth. Once obtained, the extracted style feature and the ground truth are both input into the generator. We also craft a consistency loss that guides the generated image to approximate the ground truth. After iterations, our generator is able to learn the mapping of styles corresponding to multiple sets of vectors. The proposed model can generate a large number of results consistent with the context semantics of the image. Moreover, we evaluated the effectiveness of our model on three datasets, i.e., CelebA, PlantVillage, and MauFlex. Compared to state-of-the-art inpainting methods, this model is able to offer desirable inpainting results with both better quality and higher diversity. The code and model will be made available on <uri>https://github.com/vivitsai/PiiGAN</uri>.
通讯机构:
[Qin, JH; Xiang, XY] C;[Xiang, Xuyu] U;Cent South Univ Forestry & Technol, Coll Comp Sci & Informat Technol, Changsha, Peoples R China.;Univ Alabama, Coll Commun & Informat Sci, Tuscaloosa, AL 35487 USA.
关键词:
Coverless information hiding;Data hiding;Deep learning;DCT;DenseNet;Real-time image processing
摘要:
Information security has become a key issue of public concern recently. In order to radically resist the decryption and analysis in the field of image information hiding and significantly improve the security of the secret information, a novel coverless information hiding approach based on deep learning is proposed in this paper. Deep learning can select the appropriate carrier according to requirements to achieve real-time image data hiding and the high-level semantic features extracted by CNN are more accurate than the low-level features. This method does not need to employ the designated image for embedding the secret data but transfer a set of real-time stego-images which share one or several visually similar blocks with the given secret image. In this approach, a group of real-time images searched online are segmented according to specific requirements. Then, the DenseNet is used to extract the high-level semantic features of each similar block. At the same time, a robust hash sequence with feature sequence, DC and location is generated by DCT. The inverted index structure based on the hash sequence is constructed to attain real-time image matching efficiently. At the sending end, the stego-images are matched and sent through feature retrieval. At the receiving end, the secret image can be recovered by extracting similar blocks through the received stego-images and stitching the image blocks according to the location information. Experimental results demonstrate that the proposed method without any modification traces provides better robustness and has higher retrieval accuracy and capacity when compared with some existing coverless image information hiding.
摘要:
The European Journal of Migration and Law is a quarterly journal onmigration law and policy with specific emphasis on the European Union, theCouncil of Europe and migration activities within the Organisation forSecurity and Cooperation in Europe. This journal differs from othermigration journals by focusing on both the law and policy within the fieldof migration, as opposed to examining immigration and migration policiesfrom a wholly sociological perspective. This Journal is the initiative ofthe Centre for Migration Law of the University of Nijmegen, in co-operationwith the Brussels-based Migration Policy Group.The European Journal of Migration and Law provides an invaluable source ofinformation and a platform for discussion for government and publicofficials, academics, lawyers and NGOs interested in migration issues in theEuropean context. Devoted exclusively to migration law and policy, theoriginal research and analysis the Journal presents will emphasize thedevelopment of migration policies across Europe. Each issue will have across-disciplinary approach to migration and social issues such as access ofmigrants to social security and assistance benefits, including socio-legaland meta-juridical perspectives.This journal will be of inestimable value to people working on policy issuesand academics as well as lobbyists, NGOs and policy makers. The informationand articles will also be of interest to lawyers specialising in migrationlaw who wish to keep abreast of developments at the European level.Coverage in the Journals&commat;Ovid database begins with the Volume 2, Issue 1, 2000 issue.
摘要:
Various types of biochar have beenwidely used to remediate soil contamination fromheavy metals (HMs) and to reduce HM mobility and bioavailability in soils in recent years. Most researchers have paid attention to the beneficial effects of biochar during the remediation process, but few have emphasized their negative effects and the challenges for their application. In this review, the negative effects and challenges of applying biochar for the remediation of HM-contaminated soils are thoroughly summarized and discussed, including the changeable characteristics of biochar, biochar over-application, toxic substances in biochar, activation of some HMs in soils by biochar, nonspecific adsorption, and the negative influences of biochar on soilmicroorganisms and plants. In addition, further research directions and several recommendations (standardization, long-term field experiments, mechanisms research and designer biochars) were also proposed to enable the large-scale application of biochar for the remediation of HM-contaminated soils. (C) 2020 Elsevier B.V. All rights reserved.
摘要:
Land use reflects human activities on land. Urban land use is the highest level human alteration on Earth, and it is rapidly changing due to population increase and urbanization. Urban areas have widespread effects on local hydrology, climate, biodiversity, and food production [1,2]. However, maps, that contain knowledge on the distribution, pattern and composition of various land use types in urban areas, are limited to city level. The mapping standard on data sources, methods, land use classification schemes varies from city to city, due to differences in financial input and skills of mapping personnel. To address various national and global environmental challenges caused by urbanization, it is important to have urban land uses at the national and global scales that are derived from the same or consistent data sources with the same or compatible classification systems and mapping methods. This is because, only with urban land use maps produced with similar criteria, consistent environmental policies can be made, and action efforts can be compared and assessed for large scale environmental administration. However, despite of the fact that a number of urban-extent maps exist at global scales [3,4], more detailed urban land use maps do not exist at the same scale. Even at big country or regional levels such as for the United States, China and European Union, consistent land use mapping efforts are rare [5,6](e.g., https://sdi4apps.eu/open_land_use/).