LIVIVO - The Search Portal for Life Sciences

zur deutschen Oberfläche wechseln
Advanced search

Search results

Result 1 - 10 of total 40

Search options

  1. Article ; Online: Understanding the role of pathways in a deep neural network.

    Lyu, Lei / Pang, Chen / Wang, Jihua

    Neural networks : the official journal of the International Neural Network Society

    2024  Volume 172, Page(s) 106095

    Abstract: Deep neural networks have demonstrated superior performance in artificial intelligence applications, but the opaqueness of their inner working mechanism is one major drawback in their application. The prevailing unit-based interpretation is a statistical ...

    Abstract Deep neural networks have demonstrated superior performance in artificial intelligence applications, but the opaqueness of their inner working mechanism is one major drawback in their application. The prevailing unit-based interpretation is a statistical observation of stimulus-response data, which fails to show a detailed internal process of inherent mechanisms of neural networks. In this work, we analyze a convolutional neural network (CNN) trained in the classification task and present an algorithm to extract the diffusion pathways of individual pixels to identify the locations of pixels in an input image associated with object classes. The pathways allow us to test the causal components which are important for classification and the pathway-based representations are clearly distinguishable between categories. We find that the few largest pathways of an individual pixel from an image tend to cross the feature maps in each layer that is important for classification. And the large pathways of images of the same category are more consistent in their trends than those of different categories. We also apply the pathways to understanding adversarial attacks, object completion, and movement perception. Further, the total number of pathways on feature maps in all layers can clearly discriminate the original, deformed, and target samples.
    MeSH term(s) Artificial Intelligence ; Neural Networks, Computer ; Algorithms
    Language English
    Publishing date 2024-01-04
    Publishing country United States
    Document type Journal Article
    ZDB-ID 740542-x
    ISSN 1879-2782 ; 0893-6080
    ISSN (online) 1879-2782
    ISSN 0893-6080
    DOI 10.1016/j.neunet.2024.106095
    Database MEDical Literature Analysis and Retrieval System OnLINE

    Full text online

    More links

    Kategorien

    In stock of ZB MED Cologne/Königswinter

    Zs.A 2365: Show issues Location:
    Je nach Verfügbarkeit (siehe Angabe bei Bestand)
    bis Jg. 1994: Bestellungen von Artikeln über das Online-Bestellformular
    Jg. 1995 - 2021: Lesesall (2.OG)
    ab Jg. 2022: Lesesaal (EG)

    Order via subito

    This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

  2. Article ; Online: Self-Adaptive Graph With Nonlocal Attention Network for Skeleton-Based Action Recognition.

    Pang, Chen / Gao, Xingyu / Chen, Zhenyu / Lyu, Lei

    IEEE transactions on neural networks and learning systems

    2023  Volume PP

    Abstract: Graph convolutional networks (GCNs) have achieved encouraging progress in modeling human body skeletons as spatial-temporal graphs. However, existing methods still suffer from two inherent drawbacks. Firstly, these models process the input data based on ... ...

    Abstract Graph convolutional networks (GCNs) have achieved encouraging progress in modeling human body skeletons as spatial-temporal graphs. However, existing methods still suffer from two inherent drawbacks. Firstly, these models process the input data based on the physical structure of the human body, which leads to some latent correlations among joints being ignored. Furthermore, the key temporal relationships between nonadjacent frames are overlooked, preventing to fully learn the changes of the body joints along the temporal dimension. To address these issues, we propose an innovative spatial-temporal model by introducing a self-adaptive GCN (SAGCN) with global attention network, collectively termed SAGGAN. Specifically, the SAGCN module is proposed to construct two additional dynamic topological graphs to learn the common characteristics of all data and represent a unique pattern for each sample, respectively. Meanwhile, the global attention module (spatial attention (SA) and temporal attention (TA) modules) is designed to extract the global connections between different joints in a single frame and model temporal relationships between adjacent and nonadjacent frames in temporal sequences. In this manner, our network can capture richer features of actions for accurate action recognition and overcome the defect of the standard graph convolution. Extensive experiments on three benchmark datasets (NTU-60, NTU-120, and Kinetics) have demonstrated the superiority of our proposed method.
    Language English
    Publishing date 2023-09-13
    Publishing country United States
    Document type Journal Article
    ISSN 2162-2388
    ISSN (online) 2162-2388
    DOI 10.1109/TNNLS.2023.3298950
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

    Order via subito

    This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

    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: Towards artefact-free AFM image presentation and interpretation.

    Burnham, Nancy A / Lyu, Lei / Poulikakos, Lily

    Journal of microscopy

    2023  Volume 291, Issue 2, Page(s) 163–176

    Abstract: Atomic force microscopy (AFM) is based upon a simple operational principle. However, the presentation and interpretation of AFM images can easily suffer from consequential artefacts that are easily overlooked. Here we discuss results from AFM and its ... ...

    Abstract Atomic force microscopy (AFM) is based upon a simple operational principle. However, the presentation and interpretation of AFM images can easily suffer from consequential artefacts that are easily overlooked. Here we discuss results from AFM and its companion variations AFM-IR (AFM combined with infrared spectroscopy) and PF-QNM (an AFM mode called peak-force quantitative nano-mechanical mapping) by imaging 'bee' structures in asphalt binder (bitumen) as examples. We show how common problems manifest themselves and provide solutions, with the intent that authors can present their results clearly and avoid interpreting artefacts as true physical properties, thereby raising the quality of AFM research.
    Language English
    Publishing date 2023-06-02
    Publishing country England
    Document type Journal Article
    ZDB-ID 219263-9
    ISSN 1365-2818 ; 0022-2720
    ISSN (online) 1365-2818
    ISSN 0022-2720
    DOI 10.1111/jmi.13193
    Database MEDical Literature Analysis and Retrieval System OnLINE

    Full text online

    More links

    Kategorien

    In stock of ZB MED Cologne/Königswinter

    Zs.A 838: Show issues Location:
    Je nach Verfügbarkeit (siehe Angabe bei Bestand)
    bis Jg. 1994: Bestellungen von Artikeln über das Online-Bestellformular
    Jg. 1995 - 2021: Lesesall (1.OG)
    ab Jg. 2022: Lesesaal (EG)

    Order via subito

    This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

  4. Article ; Online: Two highly stable isoreticular M

    Ma, Fa-Xue / Lyu, Lei-Yan / Chen, Jiawei / Huang, Tao / Zhang, Teng / Cao, Rong

    Chemical communications (Cambridge, England)

    2024  Volume 60, Issue 10, Page(s) 1293–1296

    Abstract: Two isoreticular metal-organic frameworks (MOFs) constructed from ... ...

    Abstract Two isoreticular metal-organic frameworks (MOFs) constructed from M
    Language English
    Publishing date 2024-01-30
    Publishing country England
    Document type Journal Article
    ZDB-ID 1472881-3
    ISSN 1364-548X ; 1359-7345 ; 0009-241X
    ISSN (online) 1364-548X
    ISSN 1359-7345 ; 0009-241X
    DOI 10.1039/d3cc05270b
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

    Order via subito

    This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

  5. Article: Identification of CeRNA Regulatory Networks in Atrial Fibrillation Using Nanodelivery.

    Lin, Ping / Meng, Lingqiang / Lyu, Lei

    Evidence-based complementary and alternative medicine : eCAM

    2022  Volume 2022, Page(s) 1046905

    Abstract: The initiation and maintenance of AF is a complex biological process that is the ultimate manifestation of many cardiovascular diseases. And the pathogenesis of atrial fibrillation (AF) is unclear. Therefore, this study aimed to find the potential ... ...

    Abstract The initiation and maintenance of AF is a complex biological process that is the ultimate manifestation of many cardiovascular diseases. And the pathogenesis of atrial fibrillation (AF) is unclear. Therefore, this study aimed to find the potential competing endogenous RNAs (ceRNAs) network and molecular dysregulation mechanism associated with AF. GSE135445, GSE2240, and GSE68475 were obtained from the Gene Expression Omnibus (GEO). Differential analysis was utilized to identify the differentially expressed mRNAs, miRNAs, and lncRNAs between AF and sinus rhythms (SR). AF-associated mRNAs and nanomaterials were screened and their biological functions and KEGG signaling pathways were identified. Nanomaterials for targeted delivery are uniquely capable of localizing the delivery of therapeutics and diagnostics to diseased tissues. The target mRNAs and target lncRNAs of differentially expressed miRNAs were identified using TargetScan and LncBase databases. Finally, we constructed the ceRNAs network and its potential molecular regulatory mechanism. We obtained 643 AF-associated mRNAs. They were significantly involved in focal adhesion and the PI3K-Akt signaling pathway. Among the 16 differentially expressed miRNAs identified, 31 differentially expressed target mRNAs, as well as 5 differentially expressed target lncRNAs were identified. Among them, we obtained 2 ceRNAs networks (hsa-miR-125a-5p and hsa-let-7a-3p). The aberrant expression of network target genes in AF mainly activated the HIF-1 signaling pathway. We speculated that the interaction pairs of miR-125a-5p and let-7a-3p with target mRNAs and target lncRNAs may be involved in AF. Our findings have a positive influence on investigating the pathogenesis of AF and identifying potential therapeutic targets.
    Language English
    Publishing date 2022-09-29
    Publishing country United States
    Document type Journal Article
    ZDB-ID 2171158-6
    ISSN 1741-4288 ; 1741-427X
    ISSN (online) 1741-4288
    ISSN 1741-427X
    DOI 10.1155/2022/1046905
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

    In stock of ZB MED Cologne/Königswinter

    Zs.A 5995: Show issues Location:
    Je nach Verfügbarkeit (siehe Angabe bei Bestand)
    bis Jg. 1994: Bestellungen von Artikeln über das Online-Bestellformular
    Jg. 1995 - 2021: Lesesall (2.OG)
    ab Jg. 2022: Lesesaal (EG)

    Order via subito

    This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

  6. Article ; Online: HRANet: Hierarchical region-aware network for crowd counting.

    Xie, Jinyang / Gu, Lingyu / Li, Zhonghui / Lyu, Lei

    Applied intelligence (Dordrecht, Netherlands)

    2022  Volume 52, Issue 11, Page(s) 12191–12205

    Abstract: Aiming to tackle the most intractable problems of scale variation and complex backgrounds in crowd counting, we present an innovative framework called Hierarchical Region-Aware Network (HRANet) for crowd counting in this paper, which can better focus on ... ...

    Abstract Aiming to tackle the most intractable problems of scale variation and complex backgrounds in crowd counting, we present an innovative framework called Hierarchical Region-Aware Network (HRANet) for crowd counting in this paper, which can better focus on crowd regions to accurately predict crowd density. In our implementation, first, we design a Region-Aware Module (RAM) to capture the internal differences within different regions of the feature map, thus adaptively extracting contextual features within different regions. Furthermore, we propose a Region Recalibration Module (RRM) which adopts a novel region-aware attention mechanism (RAAM) to further recalibrate the feature weights of different regions. By the integration of the above two modules, the influence of background regions can be effectively suppressed. Besides, considering the local correlations within different regions of the crowd density map, a Region Awareness Loss (RAL) is designed to reduce false identification while producing the locally consistent density map. Extensive experiments on five challenging datasets demonstrate that the proposed method significantly outperforms existing methods in terms of counting accuracy and quality of the generated density map. In addition, a series of specific experiments in crowd gathering scenes indicate that our method can be practically applied to crowd localization.
    Language English
    Publishing date 2022-02-02
    Publishing country Netherlands
    Document type Journal Article
    ZDB-ID 1479519-X
    ISSN 1573-7497 ; 0924-669X
    ISSN (online) 1573-7497
    ISSN 0924-669X
    DOI 10.1007/s10489-021-03030-w
    Database MEDical Literature Analysis and Retrieval System OnLINE

    Full text online

    More links

    Kategorien

    Order via subito

    This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

  7. Article ; Online: Cascaded parallel crowd counting network with multi-resolution collaborative representation.

    Lyu, Lei / Han, Run / Chen, Ziming

    Applied intelligence (Dordrecht, Netherlands)

    2022  , Page(s) 1–15

    Abstract: Accurately estimating the size and density distribution of a crowd from images is of great importance to public safety and crowd management during the COVID-19 pandemic, but it is very challenging as it is affected by many complex factors, including ... ...

    Abstract Accurately estimating the size and density distribution of a crowd from images is of great importance to public safety and crowd management during the COVID-19 pandemic, but it is very challenging as it is affected by many complex factors, including perspective distortion and background noise information. In this paper, we propose a novel multi-resolution collaborative representation framework called the cascaded parallel network (CP-Net), consisting of three parallel scale-specific branches connected in a cascading mode. In the framework, the three cascaded multi-resolution branches efficiently capture multi-scale features through their specific receptive fields. Additionally, multi-level feature fusion and information filtering are performed continuously on each branch to resist noise interference and perspective distortion. Moreover, we design an information exchange module across independent branches to refine the features extracted by each specific branch and deal with perspective distortion by using complementary information of multiple resolutions. To further improve the robustness of the network to scale variance and generate high-quality density maps, we construct a multi-receptive field fusion module to aggregate multi-scale features more comprehensively. The performance of our proposed CP-Net is verified on the challenging counting datasets (UCF_CC_50, UCF-QNRF, Shanghai Tech A&B, and WorldExpo'10), and the experimental results demonstrate the superiority of the proposed method.
    Language English
    Publishing date 2022-05-19
    Publishing country Netherlands
    Document type Journal Article
    ZDB-ID 1479519-X
    ISSN 1573-7497 ; 0924-669X
    ISSN (online) 1573-7497
    ISSN 0924-669X
    DOI 10.1007/s10489-022-03639-5
    Database MEDical Literature Analysis and Retrieval System OnLINE

    Full text online

    More links

    Kategorien

    Order via subito

    This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

  8. Book ; Online: Skeleton-based Action Recognition through Contrasting Two-Stream Spatial-Temporal Networks

    Pang, Chen / Lu, Xuequan / Lyu, Lei

    2023  

    Abstract: For pursuing accurate skeleton-based action recognition, most prior methods use the strategy of combining Graph Convolution Networks (GCNs) with attention-based methods in a serial way. However, they regard the human skeleton as a complete graph, ... ...

    Abstract For pursuing accurate skeleton-based action recognition, most prior methods use the strategy of combining Graph Convolution Networks (GCNs) with attention-based methods in a serial way. However, they regard the human skeleton as a complete graph, resulting in less variations between different actions (e.g., the connection between the elbow and head in action ``clapping hands''). For this, we propose a novel Contrastive GCN-Transformer Network (ConGT) which fuses the spatial and temporal modules in a parallel way. The ConGT involves two parallel streams: Spatial-Temporal Graph Convolution stream (STG) and Spatial-Temporal Transformer stream (STT). The STG is designed to obtain action representations maintaining the natural topology structure of the human skeleton. The STT is devised to acquire action representations containing the global relationships among joints. Since the action representations produced from these two streams contain different characteristics, and each of them knows little information of the other, we introduce the contrastive learning paradigm to guide their output representations of the same sample to be as close as possible in a self-supervised manner. Through the contrastive learning, they can learn information from each other to enrich the action features by maximizing the mutual information between the two types of action representations. To further improve action recognition accuracy, we introduce the Cyclical Focal Loss (CFL) which can focus on confident training samples in early training epochs, with an increasing focus on hard samples during the middle epochs. We conduct experiments on three benchmark datasets, which demonstrate that our model achieves state-of-the-art performance in action recognition.

    Comment: 14 pages, 9 figures
    Keywords Computer Science - Computer Vision and Pattern Recognition
    Subject code 006
    Publishing date 2023-01-26
    Publishing country us
    Document type Book ; 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. Book ; Online: Contrastive Multi-Level Graph Neural Networks for Session-based Recommendation

    Wang, Fuyun / Gao, Xingyu / Chen, Zhenyu / Lyu, Lei

    2023  

    Abstract: Session-based recommendation (SBR) aims to predict the next item at a certain time point based on anonymous user behavior sequences. Existing methods typically model session representation based on simple item transition information. However, since ... ...

    Abstract Session-based recommendation (SBR) aims to predict the next item at a certain time point based on anonymous user behavior sequences. Existing methods typically model session representation based on simple item transition information. However, since session-based data consists of limited users' short-term interactions, modeling session representation by capturing fixed item transition information from a single dimension suffers from data sparsity. In this paper, we propose a novel contrastive multi-level graph neural networks (CM-GNN) to better exploit complex and high-order item transition information. Specifically, CM-GNN applies local-level graph convolutional network (L-GCN) and global-level network (G-GCN) on the current session and all the sessions respectively, to effectively capture pairwise relations over all the sessions by aggregation strategy. Meanwhile, CM-GNN applies hyper-level graph convolutional network (H-GCN) to capture high-order information among all the item transitions. CM-GNN further introduces an attention-based fusion module to learn pairwise relation-based session representation by fusing the item representations generated by L-GCN and G-GCN. CM-GNN averages the item representations obtained by H-GCN to obtain high-order relation-based session representation. Moreover, to convert the high-order item transition information into the pairwise relation-based session representation, CM-GNN maximizes the mutual information between the representations derived from the fusion module and the average pool layer by contrastive learning paradigm. We conduct extensive experiments on multiple widely used benchmark datasets to validate the efficacy of the proposed method. The encouraging results demonstrate that our proposed method outperforms the state-of-the-art SBR techniques.
    Keywords Computer Science - Information Retrieval ; Computer Science - Artificial Intelligence
    Subject code 006
    Publishing date 2023-11-06
    Publishing country us
    Document type Book ; 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: Prognostic value of inflammation and immune-related gene NOD2 in clear cell renal cell carcinoma.

    Lyu, Lei / Min, Rui / Zheng, Fuxin / Xiang, Wei / Huang, Tao / Feng, Yan / Zhang, Chuanhua / Yuan, Jingdong

    Human cell

    2024  Volume 37, Issue 3, Page(s) 782–800

    Abstract: Inflammation and immune responses play important roles in cancer development and prognosis. We identified 59 upregulated inflammation- and immune-related genes (IIRGs) in clear cell renal cell carcinoma (ccRCC) from The Cancer Genome Atlas database. ... ...

    Abstract Inflammation and immune responses play important roles in cancer development and prognosis. We identified 59 upregulated inflammation- and immune-related genes (IIRGs) in clear cell renal cell carcinoma (ccRCC) from The Cancer Genome Atlas database. Among the upregulated IIRGs, nucleotide binding oligomerization domain 2 (NOD2), PYD and CARD domain (PYCARD) were also confirmed to be upregulated in the Oncomine database and in three independent GEO data sets. Tumor immune infiltration resource database analysis revealed that NOD2 and PYCARD levels were significantly positively correlated with infiltration levels of B cells, CD4+ T cells, CD8+ T cells, neutrophils, macrophages and dendritic cells. Multivariate Cox hazards regression analysis indicated that based on clinical variables (age, gender, tumor grade, pathological TNM stage), NOD2, but not PYCARD, was an independent, unfavorable ccRCC prognostic biomarker. Functional enrichment analyses (GSEA) showed that NOD2 was involved in innate immune responses, inflammatory responses, and regulation of cytokine secretion. Meanwhile, mRNA and protein levels of NOD2 were elevated in four ccRCC cell lines (786-O, ACHN, A498 and Caki-1), and its knockdown significantly inhibited IL-8 secretion, thereby inhibiting ccRCC cell proliferation and invasion. Furthermore, results showed that miR-20b-5p targeted NOD2 to alleviate NOD2-mediated IL-8 secretion. In conclusion, NOD2 is a potential prognostic biomarker for ccRCC and the miR-20b-5p/NOD2/IL-8 axis may regulate inflammation- and immune-mediated tumorigenesis in ccRCC.
    MeSH term(s) Humans ; Carcinoma, Renal Cell/genetics ; Prognosis ; Interleukin-8/genetics ; Inflammation/genetics ; Carcinoma ; Kidney Neoplasms/genetics ; Biomarkers ; MicroRNAs/genetics ; Nod2 Signaling Adaptor Protein/genetics
    Chemical Substances Interleukin-8 ; Biomarkers ; MicroRNAs ; NOD2 protein, human ; Nod2 Signaling Adaptor Protein
    Language English
    Publishing date 2024-03-21
    Publishing country Japan
    Document type Journal Article
    ZDB-ID 1149134-6
    ISSN 1749-0774 ; 0914-7470
    ISSN (online) 1749-0774
    ISSN 0914-7470
    DOI 10.1007/s13577-024-01045-2
    Database MEDical Literature Analysis and Retrieval System OnLINE

    Full text online

    More links

    Kategorien

    In stock of ZB MED Cologne/Königswinter

    Zs.A 3676: Show issues Location:
    Je nach Verfügbarkeit (siehe Angabe bei Bestand)
    bis Jg. 1994: Bestellungen von Artikeln über das Online-Bestellformular
    Jg. 1995 - 2021: Lesesall (2.OG)
    ab Jg. 2022: Lesesaal (EG)

    Order via subito

    This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

To top