LIVIVO - Search results -

Search results

Result 1 - 10 of total 414

Search options

Article ; Online: GNN Model for Time-Varying Matrix Inversion With Robust Finite-Time Convergence.

Zhang, Yinyan / Li, Shuai / Weng, Jian / Liao, Bolin

IEEE transactions on neural networks and learning systems

2024 Volume 35, Issue 1, Page(s) 559–569

Abstract: As a type of recurrent neural networks (RNNs) modeled as dynamic systems, the gradient neural network (GNN) is recognized as an effective method for static matrix inversion with exponential convergence. However, when it comes to time-varying matrix ... ...

Abstract	As a type of recurrent neural networks (RNNs) modeled as dynamic systems, the gradient neural network (GNN) is recognized as an effective method for static matrix inversion with exponential convergence. However, when it comes to time-varying matrix inversion, most of the traditional GNNs can only track the corresponding time-varying solution with a residual error, and the performance becomes worse when there are noises. Currently, zeroing neural networks (ZNNs) take a dominant role in time-varying matrix inversion, but ZNN models are more complex than GNN models, require knowing the explicit formula of the time-derivative of the matrix, and intrinsically cannot avoid the inversion operation in its realization in digital computers. In this article, we propose a unified GNN model for handling both static matrix inversion and time-varying matrix inversion with finite-time convergence and a simpler structure. Our theoretical analysis shows that, under mild conditions, the proposed model bears finite-time convergence for time-varying matrix inversion, regardless of the existence of bounded noises. Simulation comparisons with existing GNN models and ZNN models dedicated to time-varying matrix inversion demonstrate the advantages of the proposed GNN model in terms of convergence speed and robustness to noises.
Language	English
Publishing date	2024-01-04
Publishing country	United States
Document type	Journal Article
ISSN	2162-2388
ISSN (online)	2162-2388
DOI	10.1109/TNNLS.2022.3175899
Database	MEDical Literature Analysis and Retrieval System OnLINE

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.

Article ; Online: Distributed k-Winners-Take-All Network: An Optimization Perspective.

Zhang, Yinyan / Li, Shuai / Weng, Jian

IEEE transactions on cybernetics

2023 Volume 53, Issue 8, Page(s) 5069–5081

Abstract: In this article, we proposed an equivalent formulation of the k-winners-take-all (k-WTA) problem as a constrained optimization problem by including the Laplacian matrix of the undirected connected communication graph to adapt to the distributed computing ...

Abstract	In this article, we proposed an equivalent formulation of the k-winners-take-all (k-WTA) problem as a constrained optimization problem by including the Laplacian matrix of the undirected connected communication graph to adapt to the distributed computing scenario, where an additional auxiliary variable is introduced. To solve the optimization problem in a distributed fashion, we design projection neural networks by using the convex optimization theory, leading to the emergence of a distributed k-WTA network. Our theoretical analysis shows that the proposed distributed k-WTA network has a globally asymptotically stable equilibrium that is identical to the optimal solution to the optimization problem, that is, the correct k-WTA solution. The effectiveness and advantages, including the extendability to constrained k-WTA problems, of the proposed k-WTA network are demonstrated via simulations.
Language	English
Publishing date	2023-07-18
Publishing country	United States
Document type	Journal Article
ISSN	2168-2275
ISSN (online)	2168-2275
DOI	10.1109/TCYB.2022.3170236
Database	MEDical Literature Analysis and Retrieval System OnLINE

Order via subito

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.

Article ; Online: Dynamic Moore-Penrose Inversion With Unknown Derivatives: Gradient Neural Network Approach.

Zhang, Yinyan / Zhang, Jilian / Weng, Jian

IEEE transactions on neural networks and learning systems

2023 Volume 34, Issue 12, Page(s) 10919–10929

Abstract: Finding dynamic Moore-Penrose inverses (DMPIs) in real-time is a challenging problem due to the time-varying nature of the inverse. Traditional numerical methods for static Moore-Penrose inverse are not efficient for calculating DMPIs and are restricted ... ...

Abstract	Finding dynamic Moore-Penrose inverses (DMPIs) in real-time is a challenging problem due to the time-varying nature of the inverse. Traditional numerical methods for static Moore-Penrose inverse are not efficient for calculating DMPIs and are restricted by serial processing. The current state-of-the-art method for finding DMPIs is called the zeroing neural network (ZNN) method, which requires that the time derivative of the associated matrix is available all the time during the solution process. However, in practice, the time derivative of the associated dynamic matrix may not be available in a real-time manner or be subject to noises caused by differentiators. In this article, we propose a novel gradient-based neural network (GNN) method for computing DMPIs, which does not need the time derivative of the associated dynamic matrix. In particular, the neural state matrix of the proposed GNN converges to the theoretical DMPI in finite time. The finite-time convergence is kept by simply setting a large parameter when there are additive noises in the implementation of the GNN model. Simulation results demonstrate the efficacy and superiority of the proposed GNN method.
Language	English
Publishing date	2023-11-30
Publishing country	United States
Document type	Journal Article
ISSN	2162-2388
ISSN (online)	2162-2388
DOI	10.1109/TNNLS.2022.3171715
Database	MEDical Literature Analysis and Retrieval System OnLINE

Order via subito

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.

Article ; Online: Sporopollenin exine capsules modulate the function of microglial cells.

Li, Mengwei / Hu, Banglian / Wu, Zhaojie / Wang, Ziwei / Weng, Jian / Zheng, Honghua / Sun, Liping

Biomaterials science

2024 Volume 12, Issue 3, Page(s) 710–724

Abstract: Immune cells are the housekeepers of the human body. They protect the body from pathogens, cellular damage, and foreign matter. Proper activation of immune cells is of great significance to diseases such as infection, inflammation, and neurodegeneration. ...

Abstract	Immune cells are the housekeepers of the human body. They protect the body from pathogens, cellular damage, and foreign matter. Proper activation of immune cells is of great significance to diseases such as infection, inflammation, and neurodegeneration. However, excessive activation of cells can be detrimental. An ideal biomaterial could enhance the cellular immune function without proinflammation. In this work, we used sporopollenin exine capsules (SEC) from pollen to promote functions of primary microglia, a typical resident immune cell of the brain. We found that microglia aggregated around SEC and did not undergo any proinflammation. SEC improved the viability, migration, phagocytosis, and anti-inflammatory ability of microglia. By exploring the underlying mechanism of microglial activation without the production of cytotoxic pro-inflammatory cytokines, we found that SEC protects microglia against inflammation induced by lipopolysaccharide (LPS), an immunostimulatory factor, through the toll-like receptor 4 (TLR4) signaling pathway in a myeloid differentiation factor 88-dependent manner. These findings might shed light on the potential application of SEC in microglia transplantation for treatment of microglia-associated degenerative central nervous system diseases.
MeSH term(s)	Humans ; Microglia/metabolism ; Inflammation/metabolism ; Phagocytosis ; Anti-Inflammatory Agents/pharmacology ; Biopolymers ; Carotenoids
Chemical Substances	sporopollenin (12712-72-0) ; Anti-Inflammatory Agents ; Biopolymers ; Carotenoids (36-88-4)
Language	English
Publishing date	2024-01-30
Publishing country	England
Document type	Journal Article
ZDB-ID	2693928-9
ISSN	2047-4849 ; 2047-4830
ISSN (online)	2047-4849
ISSN	2047-4830
DOI	10.1039/d3bm01154b
Database	MEDical Literature Analysis and Retrieval System OnLINE

Order via subito

Article ; Online: Explanatory Object Part Aggregation for Zero-Shot Learning.

Chen, Xin / Deng, Xiaoling / Lan, Yubin / Long, Yongbing / Weng, Jian / Liu, Zhiquan / Tian, Qi

IEEE transactions on pattern analysis and machine intelligence

2024 Volume 46, Issue 2, Page(s) 851–868

Abstract: Zero-shot learning (ZSL) aims to recognize objects from unseen classes only based on labeled images from seen classes. Most existing ZSL methods focus on optimizing feature spaces or generating visual features of unseen classes, both in conventional ZSL ... ...

Abstract	Zero-shot learning (ZSL) aims to recognize objects from unseen classes only based on labeled images from seen classes. Most existing ZSL methods focus on optimizing feature spaces or generating visual features of unseen classes, both in conventional ZSL and generalized zero-shot learning (GZSL). However, since the learned feature spaces are suboptimal, there exists many virtual connections where visual features and semantic attributes are not corresponding to each other. To reduce virtual connections, in this paper, we propose to discover comprehensive and fine-grained object parts by building explanatory graphs based on convolutional feature maps, then aggregate object parts to train a part-net to obtain prediction results. Since the aggregated object parts contain comprehensive visual features for activating semantic attributes, the virtual connections can be reduced by a large extent. Since part-net aims to extract local fine-grained visual features, some attributes related to global structures are ignored. To take advantage of both local and global visual features, we design a feature distiller to distill local features into a master-net which aims to extract global features. The experimental results on AWA2, CUB, FLO, and SUN dataset demonstrate that our proposed method obviously outperforms the state-of-the-arts in both conventional ZSL and GZSL tasks.
Language	English
Publishing date	2024-01-08
Publishing country	United States
Document type	Journal Article
ISSN	1939-3539
ISSN (online)	1939-3539
DOI	10.1109/TPAMI.2023.3325533
Database	MEDical Literature Analysis and Retrieval System OnLINE

Order via subito

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.

Article ; Online: Score-based Counterfactual Generation for Interpretable Medical Image Classification and Lesion Localization.

Wang, Ke / Chen, Zicong / Zhu, Mingjia / Li, Zhetao / Weng, Jian / Gu, Tianlong

IEEE transactions on medical imaging

2024 Volume PP

Abstract: Deep neural networks (DNNs) have immense potential for precise clinical decision-making in the field of biomedical imaging. However, accessing high-quality data is crucial for ensuring the high-performance of DNNs. Obtaining medical imaging data is often ...

Abstract	Deep neural networks (DNNs) have immense potential for precise clinical decision-making in the field of biomedical imaging. However, accessing high-quality data is crucial for ensuring the high-performance of DNNs. Obtaining medical imaging data is often challenging in terms of both quantity and quality. To address these issues, we propose a score-based counterfactual generation (SCG) framework to create counterfactual images from latent space, to compensate for scarcity and imbalance of data. In addition, some uncertainties in external physical factors may introduce unnatural features and further affect the estimation of the true data distribution. Therefore, we integrated a learnable FuzzyBlock into the classifier of the proposed framework to manage these uncertainties. The proposed SCG framework can be applied to both classification and lesion localization tasks. The experimental results revealed a remarkable performance boost in classification tasks, achieving an average performance enhancement of 3-5% compared to previous state-of-the-art (SOTA) methods in interpretable lesion localization.
Language	English
Publishing date	2024-03-14
Publishing country	United States
Document type	Journal Article
ZDB-ID	622531-7
ISSN	1558-254X ; 0278-0062
ISSN (online)	1558-254X
ISSN	0278-0062
DOI	10.1109/TMI.2024.3375357
Database	MEDical Literature Analysis and Retrieval System OnLINE

In stock of ZB MED Cologne/Königswinter

Zs.A 2546: 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

Details ▾
- See ZB MED holdings
- Order with fees

Article ; Online: Multi-Stage Network With Geometric Semantic Attention for Two-View Correspondence Learning.

Lin, Shuyuan / Chen, Xiao / Xiao, Guobao / Wang, Hanzi / Huang, Feiran / Weng, Jian

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society

2024 Volume 33, Page(s) 3031–3046

Abstract: The removal of outliers is crucial for establishing correspondence between two images. However, when the proportion of outliers reaches nearly 90%, the task becomes highly challenging. Existing methods face limitations in effectively utilizing geometric ... ...

Abstract	The removal of outliers is crucial for establishing correspondence between two images. However, when the proportion of outliers reaches nearly 90%, the task becomes highly challenging. Existing methods face limitations in effectively utilizing geometric transformation consistency (GTC) information and incorporating geometric semantic neighboring information. To address these challenges, we propose a Multi-Stage Geometric Semantic Attention (MSGSA) network. The MSGSA network consists of three key modules: the multi-branch (MB) module, the GTC module, and the geometric semantic attention (GSA) module. The MB module, structured with a multi-branch design, facilitates diverse and robust spatial transformations. The GTC module captures transformation consistency information from the preceding stage. The GSA module categorizes input based on the prior stage's output, enabling efficient extraction of geometric semantic information through a graph-based representation and inter-category information interaction using Transformer. Extensive experiments on the YFCC100M and SUN3D datasets demonstrate that MSGSA outperforms current state-of-the-art methods in outlier removal and camera pose estimation, particularly in scenarios with a high prevalence of outliers. Source code is available at https://github.com/shuyuanlin.
Language	English
Publishing date	2024-04-30
Publishing country	United States
Document type	Journal Article
ISSN	1941-0042
ISSN (online)	1941-0042
DOI	10.1109/TIP.2024.3391002
Database	MEDical Literature Analysis and Retrieval System OnLINE

Order via subito

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.

Article ; Online: A quadratic isothermal amplification fluorescent biosensor without intermediate purification for ultrasensitive detection of circulating tumor DNA.

Wu, Zhaojie / Zheng, Hongshan / Bian, Yongjun / Weng, Jian / Zeng, Ru / Sun, Liping

The Analyst

2024

Abstract: Circulating tumor DNA (ctDNA) is an auspicious tumor biomarker released into the bloodstream by tumor cells, offering abundant information concerning cancer genes. It plays a crucial role in the early diagnosis of cancer. However, due to extremely low ... ...

Abstract	Circulating tumor DNA (ctDNA) is an auspicious tumor biomarker released into the bloodstream by tumor cells, offering abundant information concerning cancer genes. It plays a crucial role in the early diagnosis of cancer. However, due to extremely low levels in body fluids, achieving a simple, sensitive, and highly specific detection of ctDNA remains challenging. Here, we constructed a purification-free fluorescence biosensor based on quadratic amplification of ctDNA by combining nicking enzyme mediated amplification (NEMA) and catalytic hairpin assembly (CHA) reactions. After double isothermal amplification, this biosensor achieved an impressive signal amplification of nearly 10
Language	English
Publishing date	2024-05-07
Publishing country	England
Document type	Journal Article
ZDB-ID	210747-8
ISSN	1364-5528 ; 0003-2654
ISSN (online)	1364-5528
ISSN	0003-2654
DOI	10.1039/d4an00460d
Database	MEDical Literature Analysis and Retrieval System OnLINE

In stock of ZB MED Cologne/Königswinter

Zs.A 2423: 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

Details ▾
- See ZB MED holdings
- Order with fees

Article ; Online: A label-free colorimetric biosensor utilizing natural material for highly sensitive exosome detection.

Wu, Yibin / Wu, Zhaojie / Xu, Wan / Zeng, Ru / Weng, Jian / Sun, Liping

Talanta

2024 Volume 275, Page(s) 126182

Abstract: Exosomes, extracellular vesicles secreted by cells, play a crucial role in intercellular communication by transferring information from source cells to recipient cells. These vesicles carry important biomarkers, including nucleic acids and proteins, ... ...

Abstract	Exosomes, extracellular vesicles secreted by cells, play a crucial role in intercellular communication by transferring information from source cells to recipient cells. These vesicles carry important biomarkers, including nucleic acids and proteins, which provide valuable insights into the parent cells' status. As a result, exosomes have emerged as noninvasive indicators for the early diagnosis of cancer. Colorimetric biosensors have garnered significant attention due to their cost-effectiveness, simplicity, rapid response, and reproducibility. In this study, we employ sporopollenin microcapsules (SP), a natural biopolymer material derived from pollen, as a substrate for gold nanoparticles (AuNPs). By modifying the SP-Au complex with CD63 aptamers, we develop a label-free colorimetric biosensor for exosome detection. In the absence of exosomes, the SP-Au complex catalyzes the oxidation of 3,3',5,5'-tetramethylbenzidine (TMB), resulting in a color change from colorless to blue. However, the addition of exosomes inhibits the catalytic activity of the SP-Au complex due to coverage of exosomes on AuNPs. This colorimetric biosensor exhibits high sensitivity and selectivity for exosome detection, with a detection limit of 10 particles/μL and a wide linear range of 10 - 10
Language	English
Publishing date	2024-04-28
Publishing country	Netherlands
Document type	Journal Article
ZDB-ID	1500969-5
ISSN	1873-3573 ; 0039-9140
ISSN (online)	1873-3573
ISSN	0039-9140
DOI	10.1016/j.talanta.2024.126182
Database	MEDical Literature Analysis and Retrieval System OnLINE

Full text online

Accessible to users with ZB MED library card

Order via subito

Details ▾
- Full text online
- Order with fees

Article: Simulation of Work Hardening in Machining Inconel 718 with Multiscale Grain Size.

Zhuang, Kejia / Wang, Zhuo / Zou, Linli / Fu, Changni / Weng, Jian

Materials (Basel, Switzerland)

2023 Volume 16, Issue 9

Abstract: Machining nickel-based alloys always exhibits significant work-hardening behavior, which may help to improve the part quality by building a hardened layer on the surface, while also causing severe tool wear during machining. Hence, modeling the work- ... ...

Abstract	Machining nickel-based alloys always exhibits significant work-hardening behavior, which may help to improve the part quality by building a hardened layer on the surface, while also causing severe tool wear during machining. Hence, modeling the work-hardening phenomenon plays a critical role in the evaluation of tool wear and part quality. This paper aims to propose a numerical model to estimate the work-hardening layer for a deeper understanding of this behavior, employing both recrystallization-based and dislocation-based models to cover workpieces with multiscale grain sizes. Different user routines are implemented in the finite element method to simulate the increase in hardness in the deformed area due to recrystallization or changes in the dislocation density. The validation of the proposed model is performed with both literature and experimental data for Inconel 718 with small or large grain sizes. It is found that the recrystallization-based model is more suitable for predicting the work-hardening behavior of small-grain-size Inconel 718 and the dislocation-based model is better for that of large-grain-size Inconel 718. Further, as an important type of cutting tool in machining Inconel 718, the chamfered tools with different edge geometries are employed in the simulations of machining-induced work hardening. The results illustrate that the uncut chip thickness and chamfer angle have a significant influence on the work-hardening behavior.
Language	English
Publishing date	2023-05-06
Publishing country	Switzerland
Document type	Journal Article
ZDB-ID	2487261-1
ISSN	1996-1944
ISSN	1996-1944
DOI	10.3390/ma16093562
Database	MEDical Literature Analysis and Retrieval System OnLINE

Order via subito

To top

More links

Kategorien

Order via subito

Inter-library loan at ZB MED

More links

Kategorien

Order via subito

Inter-library loan at ZB MED

More links

Kategorien

Order via subito

Inter-library loan at ZB MED

More links

Kategorien

Order via subito

More links

Kategorien

Order via subito

Inter-library loan at ZB MED

More links

Kategorien

In stock of ZB MED Cologne/Königswinter

Order via subito

More links

Kategorien

Order via subito

Inter-library loan at ZB MED

More links

Kategorien

In stock of ZB MED Cologne/Königswinter

Order via subito

Full text online

More links

Kategorien

Order via subito

More links

Kategorien

Order via subito