LIVIVO - The Search Portal for Life Sciences

zur deutschen Oberfläche wechseln
Advanced search

Search results

Result 1 - 10 of total 38

Search options

  1. Article ; Online: Deep Residual Involution Network for Hyperspectral Image Classification

    Zhe Meng / Feng Zhao / Miaomiao Liang / Wen Xie

    Remote Sensing, Vol 13, Iss 3055, p

    2021  Volume 3055

    Abstract: Convolutional neural networks (CNNs) have achieved great results in hyperspectral image (HSI) classification in recent years. However, convolution kernels are reused among different spatial locations, known as spatial-agnostic or weight-sharing kernels. ... ...

    Abstract Convolutional neural networks (CNNs) have achieved great results in hyperspectral image (HSI) classification in recent years. However, convolution kernels are reused among different spatial locations, known as spatial-agnostic or weight-sharing kernels. Furthermore, the preference of spatial compactness in convolution (typically, <math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>3</mn><mo>×</mo><mn>3</mn></mrow></semantics></math> kernel size) constrains the receptive field and the ability to capture long-range spatial interactions. To mitigate the above two issues, in this article, we combine a novel operation called involution with residual learning and develop a new deep residual involution network (DRIN) for HSI classification. The proposed DRIN could model long-range spatial interactions well by adopting enlarged involution kernels and realize feature learning in a fairly lightweight manner. Moreover, the vast and dynamic involution kernels are distinct over different spatial positions, which could prioritize the informative visual patterns in the spatial domain according to the spectral information of the target pixel. The proposed DRIN achieves better classification results when compared with both traditional machine learning-based and convolution-based methods on four HSI datasets. Especially in comparison with the convolutional baseline model, i.e., deep residual network (DRN), our involution-powered DRIN model increases the overall classification accuracy by 0.5%, 1.3%, 0.4%, and 2.3% on the University of Pavia, the University of Houston, the Salinas Valley, and the recently released HyRANK HSI benchmark datasets, respectively, demonstrating the potential of involution for HSI classification.
    Keywords involution ; residual network ; hyperspectral image (HSI) classification ; Science ; Q
    Subject code 006
    Language English
    Publishing date 2021-08-01T00:00:00Z
    Publisher MDPI AG
    Document type Article ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  2. Article ; Online: Densely Connected Pyramidal Dilated Convolutional Network for Hyperspectral Image Classification

    Feng Zhao / Junjie Zhang / Zhe Meng / Hanqiang Liu

    Remote Sensing, Vol 13, Iss 3396, p

    2021  Volume 3396

    Abstract: Recently, with the extensive application of deep learning techniques in the hyperspectral image (HSI) field, particularly convolutional neural network (CNN), the research of HSI classification has stepped into a new stage. To avoid the problem that the ... ...

    Abstract Recently, with the extensive application of deep learning techniques in the hyperspectral image (HSI) field, particularly convolutional neural network (CNN), the research of HSI classification has stepped into a new stage. To avoid the problem that the receptive field of naive convolution is small, the dilated convolution is introduced into the field of HSI classification. However, the dilated convolution usually generates blind spots in the receptive field, resulting in discontinuous spatial information obtained. In order to solve the above problem, a densely connected pyramidal dilated convolutional network (PDCNet) is proposed in this paper. Firstly, a pyramidal dilated convolutional (PDC) layer integrates different numbers of sub-dilated convolutional layers is proposed, where the dilated factor of the sub-dilated convolution increases exponentially, achieving multi-sacle receptive fields. Secondly, the number of sub-dilated convolutional layers increases in a pyramidal pattern with the depth of the network, thereby capturing more comprehensive hyperspectral information in the receptive field. Furthermore, a feature fusion mechanism combining pixel-by-pixel addition and channel stacking is adopted to extract more abstract spectral–spatial features. Finally, in order to reuse the features of the previous layers more effectively, dense connections are applied in densely pyramidal dilated convolutional (DPDC) blocks. Experiments on three well-known HSI datasets indicate that PDCNet proposed in this paper has good classification performance compared with other popular models.
    Keywords hyperspectral image classification ; convolutional neural network ; dilated convolution ; dense connection ; Science ; Q
    Subject code 006
    Language English
    Publishing date 2021-08-01T00:00:00Z
    Publisher MDPI AG
    Document type Article ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  3. Article ; Online: SS-MLP

    Zhe Meng / Feng Zhao / Miaomiao Liang

    Remote Sensing, Vol 13, Iss 4060, p

    A Novel Spectral-Spatial MLP Architecture for Hyperspectral Image Classification

    2021  Volume 4060

    Abstract: Convolutional neural networks (CNNs) are the go-to model for hyperspectral image (HSI) classification because of the excellent locally contextual modeling ability that is beneficial to spatial and spectral feature extraction. However, CNNs with a limited ...

    Abstract Convolutional neural networks (CNNs) are the go-to model for hyperspectral image (HSI) classification because of the excellent locally contextual modeling ability that is beneficial to spatial and spectral feature extraction. However, CNNs with a limited receptive field pose challenges for modeling long-range dependencies. To solve this issue, we introduce a novel classification framework which regards the input HSI as a sequence data and is constructed exclusively with multilayer perceptrons (MLPs). Specifically, we propose a spectral-spatial MLP (SS-MLP) architecture, which uses matrix transposition and MLPs to achieve both spectral and spatial perception in global receptive field, capturing long-range dependencies and extracting more discriminative spectral-spatial features. Four benchmark HSI datasets are used to evaluate the classification performance of the proposed SS-MLP. Experimental results show that our pure MLP-based architecture outperforms other state-of-the-art convolution-based models in terms of both classification performance and computational time. When comparing with the SSSERN model, the average accuracy improvement of our approach is as high as 3.03%. We believe that our impressive experimental results will foster additional research on simple yet effective MLP-based architecture for HSI classification.
    Keywords hyperspectral image (HSI) ; multilayer perceptrons (MLPs) ; spectral-spatial classification ; Science ; Q
    Subject code 006
    Language English
    Publishing date 2021-10-01T00:00:00Z
    Publisher MDPI AG
    Document type Article ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  4. Article ; Online: Lightweight Multilevel Feature Fusion Network for Hyperspectral Image Classification

    Miaomiao Liang / Huai Wang / Xiangchun Yu / Zhe Meng / Jianbing Yi / Licheng Jiao

    Remote Sensing, Vol 14, Iss 79, p

    2022  Volume 79

    Abstract: Hyperspectral images (HSIs), acquired as a 3D data set, contain spectral and spatial information that is important for ground–object recognition. A 3D convolutional neural network (3DCNN) could therefore be more suitable than a 2D one for extracting ... ...

    Abstract Hyperspectral images (HSIs), acquired as a 3D data set, contain spectral and spatial information that is important for ground–object recognition. A 3D convolutional neural network (3DCNN) could therefore be more suitable than a 2D one for extracting multiscale neighborhood information in the spectral and spatial domains simultaneously, if it is not restrained by mass parameters and computation cost. In this paper, we propose a novel lightweight multilevel feature fusion network (LMFN) that can achieve satisfactory HSI classification with fewer parameters and a lower computational burden. The LMFN decouples spectral–spatial feature extraction into two modules: point-wise 3D convolution to learn correlations between adjacent bands with no spatial perception, and depth-wise convolution to obtain local texture features while the spectral receptive field remains unchanged. Then, a target-guided fusion mechanism (TFM) is introduced to achieve multilevel spectral–spatial feature fusion between the two modules. More specifically, multiscale spectral features are endowed with spatial long-range dependency, which is quantified by central target pixel-guided similarity measurement. Subsequently, the results obtained from shallow to deep layers are added, respectively, to the spatial modules, in an orderly manner. The TFM block can enhance adjacent spectral correction and focus on pixels that actively boost the target classification accuracy, while performing multiscale feature fusion. Experimental results across three benchmark HSI data sets indicate that our proposed LMFN has competitive advantages, in terms of both classification accuracy and lightweight deep network architecture engineering. More importantly, compared to state-of-the-art methods, the LMFN presents better robustness and generalization.
    Keywords hyperspectral image (HSI) classification ; 3D convolution ; lightweight network ; target-guided fusion ; multilevel feature fusion ; Science ; Q
    Subject code 571 ; 006
    Language English
    Publishing date 2022-12-01T00:00:00Z
    Publisher MDPI AG
    Document type Article ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  5. Article ; Online: The Conserved and Specific Roles of the LUX ARRHYTHMO in Circadian Clock and Nodulation

    Yiming Kong / Yuxue Zhang / Xiu Liu / Zhe Meng / Xiaolin Yu / Chuanen Zhou / Lu Han

    International Journal of Molecular Sciences, Vol 23, Iss 3473, p

    2022  Volume 3473

    Abstract: LUX ARRHYTHMO ( LUX ) plays a key role in circadian rhythms and flowering. Here, we identified the MtLUX gene which is the putative ortholog of LUX in Medicago truncatula . The roles of MtLUX , in both the nodulation belowground and leaf movement ... ...

    Abstract LUX ARRHYTHMO ( LUX ) plays a key role in circadian rhythms and flowering. Here, we identified the MtLUX gene which is the putative ortholog of LUX in Medicago truncatula . The roles of MtLUX , in both the nodulation belowground and leaf movement aboveground, were investigated by characterizing a loss-of-function mtlux mutant. MtLUX was required for the control of flowering time under both long-day and short-day conditions. Further investigations showed that the early flowering in the mtlux mutant was correlated with the elevated expression level of the MtFTa1 gene but in a CO - like independent manner. MtLUX played a conserved role in the regulatory interactions with MtLHY , MtTOC1 , and MtPRR genes, which is similar to those in other species. Meanwhile, the unexpected functions of MtLUX were revealed in nodule formation and nyctinastic leaf movement, probably through the indirect regulation in MtLHY . Its participation in nodulation is of interest in the context of functional conservation and the neo-functionalization of the products of LUX orthologs.
    Keywords legume ; Medicago truncatula ; MtLUX ; MtFTa1 ; circadian clock ; photoperiodic flowering ; Biology (General) ; QH301-705.5 ; Chemistry ; QD1-999
    Subject code 580
    Language English
    Publishing date 2022-03-01T00:00:00Z
    Publisher MDPI AG
    Document type Article ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  6. Article ; Online: Quantum process tomography on holographic metasurfaces

    Qing-Yuan Wu / Zhe Meng / Jia-Zhi Yang / An-Ning Zhang

    npj Quantum Information, Vol 8, Iss 1, Pp 1-

    2022  Volume 6

    Abstract: Abstract Holographic metasurfaces and their applications have garnered significant attention owing to their role in polarization control. In this study, we demonstrate that the quantum properties of holographic metasurfaces can be obtained by quantum ... ...

    Abstract Abstract Holographic metasurfaces and their applications have garnered significant attention owing to their role in polarization control. In this study, we demonstrate that the quantum properties of holographic metasurfaces can be obtained by quantum state tomography (QST) and quantum process tomography (QPT). We perform QST to obtain the experimental output states by extracting information from holograms encoded on the holographic metasurface, and develop a QPT-based method to estimate the quantum process of the metasurface. The theoretical output states derived from the estimated quantum process are in good agreement with the experimental output states, proving the effectiveness of our method. Our work not only provides theoretical and experimental analysis for understanding the quantum properties of holographic metasurfaces, but also paves the way for the application of holographic metasurfaces in quantum field.
    Keywords Physics ; QC1-999 ; Electronic computers. Computer science ; QA75.5-76.95
    Subject code 541
    Language English
    Publishing date 2022-04-01T00:00:00Z
    Publisher Nature Portfolio
    Document type Article ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  7. Article ; Online: A Dual Multi-Head Contextual Attention Network for Hyperspectral Image Classification

    Miaomiao Liang / Qinghua He / Xiangchun Yu / Huai Wang / Zhe Meng / Licheng Jiao

    Remote Sensing, Vol 14, Iss 3091, p

    2022  Volume 3091

    Abstract: To learn discriminative features, hyperspectral image (HSI), containing 3-D cube data, is a preferable means of capturing multi-head self-attention from both spatial and spectral domains if the burden in model optimization and computation is low. In this ...

    Abstract To learn discriminative features, hyperspectral image (HSI), containing 3-D cube data, is a preferable means of capturing multi-head self-attention from both spatial and spectral domains if the burden in model optimization and computation is low. In this paper, we design a dual multi-head contextual self-attention (DMuCA) network for HSI classification with the fewest possible parameters and lower computation costs. To effectively capture rich contextual dependencies from both domains, we decouple the spatial and spectral contextual attention into two sub-blocks, SaMCA and SeMCA, where depth-wise convolution is employed to contextualize the input keys in the pure dimension. Thereafter, multi-head local attentions are implemented as group processing when the keys are alternately concatenated with the queries. In particular, in the SeMCA block, we group the spatial pixels by evenly sampling and create multi-head channel attention on each sampling set, to reduce the number of the training parameters and avoid the storage increase. In addition, the static contextual keys are fused with the dynamic attentional features in each block to strengthen the capacity of the model in data representation. Finally, the decoupled sub-blocks are weighted and summed together for 3-D attention perception of HSI. The DMuCA module is then plugged into a ResNet to perform HSI classification. Extensive experiments demonstrate that our proposed DMuCA achieves excellent results over several state-of-the-art attention mechanisms with the same backbone.
    Keywords hyperspectral image classification ; dual attention ; contextual keys ; grouping perception ; multi-head self-attention ; Science ; Q
    Language English
    Publishing date 2022-06-01T00:00:00Z
    Publisher MDPI AG
    Document type Article ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  8. Article ; Online: Three New Species of Microdochium ( Sordariomycetes , Amphisphaeriales ) on Miscanthus sinensis and Phragmites australis from Hainan, China

    Shubin Liu / Xiaoyong Liu / Zhaoxue Zhang / Jiwen Xia / Xiuguo Zhang / Zhe Meng

    Journal of Fungi, Vol 8, Iss 577, p

    2022  Volume 577

    Abstract: Species in Microdochium , potential agents of biocontrol, have often been reported as plant pathogens, occasionally as endophytes and fungicolous fungi. Combining multiple molecular markers (ITS rDNA, LSU rDNA, TUB2 and RPB2) with morphological ... ...

    Abstract Species in Microdochium , potential agents of biocontrol, have often been reported as plant pathogens, occasionally as endophytes and fungicolous fungi. Combining multiple molecular markers (ITS rDNA, LSU rDNA, TUB2 and RPB2) with morphological characteristics, this study proposes three new species in the genus Microdochium represented by seven strains from the plant hosts Miscanthus sinensis and Phragmites australis in Hainan Island, China. These three species, Microdochium miscanthi sp. Nov., M. sinens e sp. Nov. and M. hainanense sp. Nov., are described with MycoBank number, etymology, typification, morphological features and illustrations, as well as placement on molecular phylogenetic trees. Their affinity with morphologically allied and molecularly closely related species are also analyzed. For facilitating identification, an updated key to the species of Microdochium is provided herein.
    Keywords Ascomycota ; Amphisphaeriaceae ; taxonomy ; multigene phylogeny ; new taxon ; Biology (General) ; QH301-705.5
    Language English
    Publishing date 2022-05-01T00:00:00Z
    Publisher MDPI AG
    Document type Article ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  9. Article ; Online: Experimental realization of a quantum classification

    Qing-Yuan Wu / Zhe Meng / Xiao-Xiao Chen / Jian Li / Jia-Zhi Yang / An-Ning Zhang

    APL Machine Learning, Vol 1, Iss 3, Pp 036111-036111-

    Bell state measurement via machine learning

    2023  Volume 8

    Abstract: The Bell state is a crucial resource for the realization of quantum information tasks, and when combined with orbital angular momentum (OAM), it enables a high-dimensional Hilbert space, which is essential for high-capacity quantum communication. In this ...

    Abstract The Bell state is a crucial resource for the realization of quantum information tasks, and when combined with orbital angular momentum (OAM), it enables a high-dimensional Hilbert space, which is essential for high-capacity quantum communication. In this study, we demonstrate the recognition of OAM Bell states using interference patterns generated by a classical light source and a single-photon source from a Sagnac interferometer-based OAM Bell state evolution device. The interference patterns exhibit a one-to-one correspondence with the input Bell states, providing conclusive evidence for the full recognition of OAM Bell states. Furthermore, we introduce machine learning to the field of Bell state recognition by proposing a neural network model capable of accurately recognizing higher order single-photon OAM Bell states, even in the undersampling case. In particular, the model’s training set includes interference patterns of OAM Bell states generated by classical light sources, yet it is able to recognize single-photon OAM Bell states with high accuracy, without relying on quantum resources during training. Our innovative application of neural networks to the recognition of single-photon OAM Bell states not only circumvents the resource consumption and experimental difficulties associated with quantum light sources but also facilitates the study of OAM-based quantum information.
    Keywords Physics ; QC1-999 ; Electronic computers. Computer science ; QA75.5-76.95
    Subject code 190
    Language English
    Publishing date 2023-09-01T00:00:00Z
    Publisher AIP Publishing LLC
    Document type Article ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  10. Article ; Online: Virulence gene detection and antimicrobial resistance analysis of Enterococcus faecium in captive giant pandas (Ailuropoda melanoleuca) in China

    Hai-Feng Liu / Xiao-Yao Huang / Zhe-Meng Li / Zi-Yao Zhou / Zhi-Jun Zhong / Guang-Neng Peng

    Acta Veterinaria Scandinavica, Vol 65, Iss 1, Pp 1-

    2023  Volume 9

    Abstract: Abstract Background The emergence of multidrug resistance among enterococci makes effective treatment of enterococcal infections more challenging. Giant pandas (Ailuropoda melanoleuca) are vulnerable to oral trauma and lesions as they feast on bamboo. ... ...

    Abstract Abstract Background The emergence of multidrug resistance among enterococci makes effective treatment of enterococcal infections more challenging. Giant pandas (Ailuropoda melanoleuca) are vulnerable to oral trauma and lesions as they feast on bamboo. Enterococci may contaminate such oral lesions and cause infection necessitating treatment with antibiotics. However, few studies have focused on the virulence and drug resistance of oral-derived enterococci, including Enterococcus faecium, in giant pandas. In this study, we analyzed the prevalence of 8 virulence genes and 14 drug resistance genes in E. faecium isolates isolated from saliva samples of giant pandas held in captivity in China and examined the antimicrobial drug susceptibility patterns of the E. faecium isolates. Results Twenty-eight isolates of E. faecium were successfully isolated from the saliva samples. Four virulence genes were detected, with the acm gene showing the highest prevalence (89%). The cylA, cpd, esp, and hyl genes were not detected. The isolated E. faecium isolates possessed strong resistance to a variety of drugs; however, they were sensitive to high concentrations of aminoglycosides. The resistance rates to vancomycin, linezolid, and nitrofurantoin were higher than those previously revealed by similar studies in China and other countries. Conclusions The findings of the present study indicate the drugs of choice for treatment of oral E. faecium infection in the giant panda.
    Keywords Drug resistance ; Enterococcus faecium ; Giant panda ; Virulence gene ; Veterinary medicine ; SF600-1100
    Subject code 610
    Language English
    Publishing date 2023-02-01T00:00:00Z
    Publisher BMC
    Document type Article ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

To top