LIVIVO - The Search Portal for Life Sciences

zur deutschen Oberfläche wechseln
Advanced search

Search results

Result 1 - 10 of total 445

Search options

  1. Article ; Online: Event Scene Method of Legal Domain Knowledge Map Based on Neural Network Hybrid Model

    Lu Zhou

    Applied Bionics and Biomechanics, Vol

    2022  Volume 2022

    Abstract: Event extraction technology is one of the important researches in the field of information extraction, which helps people accurately retrieve, find, classify, and summarize effective information from a large amount of information streams. This paper uses ...

    Abstract Event extraction technology is one of the important researches in the field of information extraction, which helps people accurately retrieve, find, classify, and summarize effective information from a large amount of information streams. This paper uses the neural network hybrid model to identify the trigger words and event categories of the legal domain knowledge graph events, extracts the events of interest from a large amount of free text, and displays them in a structured format. First, the original text is preprocessed, and then, the distributed semantic word vector is combined with the dependent syntactic structure and location attributes to create a semantic representation in the form of a vector. The combined deep learning model is used to extract activated words, the long-term memory loop neural network uses temporal semantics to extract deep features, and the convergent neural network completes the extraction of activated words and event categories. Finally, the experimental results show that the accuracy of event extraction of the neural network hybrid model designed in this paper has reached 77.1%, and the recall rate has reached 76.8%, which is greatly improved compared with the traditional model.
    Keywords Biotechnology ; TP248.13-248.65 ; Biology (General) ; QH301-705.5
    Subject code 006
    Language English
    Publishing date 2022-01-01T00:00:00Z
    Publisher Hindawi Limited
    Document type Article ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    More links

    Kategorien

  2. Book ; Online: A Theory of Multimodal Learning

    Lu, Zhou

    2023  

    Abstract: Human perception of the empirical world involves recognizing the diverse appearances, or 'modalities', of underlying objects. Despite the longstanding consideration of this perspective in philosophy and cognitive science, the study of multimodality ... ...

    Abstract Human perception of the empirical world involves recognizing the diverse appearances, or 'modalities', of underlying objects. Despite the longstanding consideration of this perspective in philosophy and cognitive science, the study of multimodality remains relatively under-explored within the field of machine learning. Nevertheless, current studies of multimodal machine learning are limited to empirical practices, lacking theoretical foundations beyond heuristic arguments. An intriguing finding from the practice of multimodal learning is that a model trained on multiple modalities can outperform a finely-tuned unimodal model, even on unimodal tasks. This paper provides a theoretical framework that explains this phenomenon, by studying generalization properties of multimodal learning algorithms. We demonstrate that multimodal learning allows for a superior generalization bound compared to unimodal learning, up to a factor of $O(\sqrt{n})$, where $n$ represents the sample size. Such advantage occurs when both connection and heterogeneity exist between the modalities.

    Comment: Added reference
    Keywords Computer Science - Machine Learning
    Subject code 006
    Publishing date 2023-09-21
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    More links

    Kategorien

  3. Book ; Online: On the Computational Benefit of Multimodal Learning

    Lu, Zhou

    2023  

    Abstract: Human perception inherently operates in a multimodal manner. Similarly, as machines interpret the empirical world, their learning processes ought to be multimodal. The recent, remarkable successes in empirical multimodal learning underscore the ... ...

    Abstract Human perception inherently operates in a multimodal manner. Similarly, as machines interpret the empirical world, their learning processes ought to be multimodal. The recent, remarkable successes in empirical multimodal learning underscore the significance of understanding this paradigm. Yet, a solid theoretical foundation for multimodal learning has eluded the field for some time. While a recent study by Lu (2023) has shown the superior sample complexity of multimodal learning compared to its unimodal counterpart, another basic question remains: does multimodal learning also offer computational advantages over unimodal learning? This work initiates a study on the computational benefit of multimodal learning. We demonstrate that, under certain conditions, multimodal learning can outpace unimodal learning exponentially in terms of computation. Specifically, we present a learning task that is NP-hard for unimodal learning but is solvable in polynomial time by a multimodal algorithm. Our construction is based on a novel modification to the intersection of two half-spaces problem.

    Comment: ALT 2024, to appear
    Keywords Computer Science - Machine Learning ; Computer Science - Artificial Intelligence
    Publishing date 2023-09-24
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    More links

    Kategorien

  4. Book ; Online: Non-uniform Online Learning

    Lu, Zhou

    Towards Understanding Induction

    2023  

    Abstract: Can a physicist make only finite errors in the endless pursuit of the law of nature? This millennium-old question of inductive inference is a fundamental, yet mysterious problem in philosophy, lacking rigorous justifications. While classic online ... ...

    Abstract Can a physicist make only finite errors in the endless pursuit of the law of nature? This millennium-old question of inductive inference is a fundamental, yet mysterious problem in philosophy, lacking rigorous justifications. While classic online learning theory and inductive inference share a similar sequential decision-making spirit, the former's reliance on an adaptive adversary and worst-case error bounds limits its applicability to the latter. In this work, we introduce the concept of non-uniform online learning, which we argue aligns more closely with the principles of inductive reasoning. This setting assumes a predetermined ground-truth hypothesis and considers non-uniform, hypothesis-wise error bounds. In the realizable setting, we provide a complete characterization of learnability with finite error: a hypothesis class is non-uniform learnable if and only if it's a countable union of Littlestone classes, no matter the observations are adaptively chosen or iid sampled. Additionally, we propose a necessary condition for the weaker criterion of consistency which we conjecture to be tight. To further promote our theory, we extend our result to the more realistic agnostic setting, showing that any countable union of Littlestone classes can be learnt with regret $\tilde{O}(\sqrt{T})$. We hope this work could offer a new perspective of interpreting the power of induction from an online learning viewpoint.

    Comment: A manuscript. Comments are most welcome!
    Keywords Computer Science - Machine Learning
    Subject code 004
    Publishing date 2023-11-30
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    More links

    Kategorien

  5. Article ; Online: Can digital economy improve employment structure?—Mediating effect based on a spatial Durbin model

    Yang Lu / Lu Lu Zhou

    PLoS ONE, Vol 18, Iss

    2023  Volume 11

    Keywords Medicine ; R ; Science ; Q
    Language English
    Publishing date 2023-01-01T00:00:00Z
    Publisher Public Library of Science (PLoS)
    Document type Article ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    More links

    Kategorien

  6. Article ; Online: Ultimately Adaptive Fluid Interfacial Phospholipid Membranes Unveiled Unanticipated High Cellular Mechanical Work.

    Lu, Zhou / Tenjimbayashi, Mizuki / Zhou, Junhong / Nakanishi, Jun

    Advanced materials (Deerfield Beach, Fla.)

    2024  , Page(s) e2403396

    Abstract: Living cells actively interact biochemically and mechanically with the surrounding extracellular matrices (ECMs) and undergo dramatic morphological and dimensional transitions, concomitantly remodeling ECMs. However, there is no suitable method to ... ...

    Abstract Living cells actively interact biochemically and mechanically with the surrounding extracellular matrices (ECMs) and undergo dramatic morphological and dimensional transitions, concomitantly remodeling ECMs. However, there is no suitable method to quantitatively discuss the contribution of mechanical interactions in such mutually adaptive processes. Herein, a highly deformable "living" cellular scaffold is developed to evaluate overall mechanical energy transfer between cell and ECMs. It is based on the water-perfluorocarbon interface decorated with phospholipids bearing a cell-adhesive ligand and fluorescent tag. The bioinert nature of the phospholipid membranes prevents the formation of solid-like protein nanofilms at the fluid interface, enabling to visualize and quantify cellular mechanical work against the ultimately adaptive model ECM. A new cellular wetting regime is identified, wherein interface deformation proceeds to cell flattening, followed by its eventual restoration. The cellular mechanical work during this adaptive wetting process is one order of magnitude higher than those reported with conventional elastic platforms. The behavior of viscous liquid drops at the air-water interface can simulate cellular adaptive wetting, suggesting that overall viscoelasticity of the cell body predominates the emergent wetting regime and regulates mechanical output. Cellular-force-driven high-energy states on the adaptive platform can be useful for cell fate manipulation.
    Language English
    Publishing date 2024-04-13
    Publishing country Germany
    Document type Journal Article
    ZDB-ID 1474949-X
    ISSN 1521-4095 ; 0935-9648
    ISSN (online) 1521-4095
    ISSN 0935-9648
    DOI 10.1002/adma.202403396
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

  7. Article ; Online: Pan-cancer analysis identified IGF2BP2 as a potential prognostic biomarker for multiple tumor types

    Hong-Lu Zhou / Dan-Dan Chen / Xiu-Ling Li

    Egyptian Journal of Medical Human Genetics, Vol 25, Iss 1, Pp 1-

    2024  Volume 15

    Abstract: Abstract Background Insulin-like growth factor 2 (IGF2) mRNA-binding proteins 2 (IGF2BP2/IMP2), an RNA-binding protein encoded by the IGF2BP2 gene, exerts its influence across diverse pathological pathways. While accumulating evidence underscores the ... ...

    Abstract Abstract Background Insulin-like growth factor 2 (IGF2) mRNA-binding proteins 2 (IGF2BP2/IMP2), an RNA-binding protein encoded by the IGF2BP2 gene, exerts its influence across diverse pathological pathways. While accumulating evidence underscores the potential significance of IGF2BP2 in the tumorigenesis of specific cancers, a comprehensive pan-cancer investigation into its role remains absent. Methods Consequently, we conducted an exhaustive exploration employing a multitude of databases to elucidate the plausible oncogenic implications of IGF2BP2. This encompassed a comprehensive scrutiny of its expression profiles, prognostic implications, association with cancer-associated fibroblast infiltration, biological functionality in distinct tumor contexts, and plausible correlations with drug sensitivities. Results Our findings showed that IGF2BP2 was highly expressed in some types of cancers, but presented at low levels in several cancer types. Furthermore, the role of IGF2BP2 in predicting prognosis exhibited a dichotomous interplay across varied cancer types. Remarkably, observations unveiled the cancer-associated fibroblast infiltration within specific tumors, notably encompassing breast invasive carcinoma of the luminal A subtype, kidney renal clear cell carcinoma, ovarian serous cystadenocarcinoma, pheochromocytoma and paraganglioma, and prostate adenocarcinoma, and thymoma. Intriguingly, gene enrichment analyses spotlighted the co-expression of IGF2BP2 with genes implicated in pivotal biological processes, including DNA replication and recombinational repair. Conclusion Our investigation intricately unveils the potential of IGF2BP2 as a versatile prognostic biomarker across diverse tumor categories. This study bridges existing knowledge gaps and augments the understanding of IGF2BP2’s intricate involvement in tumorigenesis, underscoring its significance as a prospective avenue for therapeutic intervention.
    Keywords IGF2BP2 ; Prognosis ; Pan-cancer ; Biomarker ; Immune infiltration ; Medicine (General) ; R5-920 ; Genetics ; QH426-470
    Subject code 616
    Language English
    Publishing date 2024-01-01T00:00:00Z
    Publisher SpringerOpen
    Document type Article ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    More links

    Kategorien

  8. Article ; Online: Effects of ICMT gene silencing on the invasion and migration of human salivary adenoid cystic carcinoma cells in vitro

    LU Zhou / GONG Wenhong / XU Xiao / CHEN Zhenggang

    口腔疾病防治, Vol 31, Iss 6, Pp 400-

    2023  Volume 407

    Abstract: Objective To investigate the effect of isoprene cysteine carboxymethyltransferase (ICMT) gene on the migration and invasion of salivary adenoid cystic cancer cells (SACC) and the related mechanism, to provide experimental evidence for molecular targeted ... ...

    Abstract Objective To investigate the effect of isoprene cysteine carboxymethyltransferase (ICMT) gene on the migration and invasion of salivary adenoid cystic cancer cells (SACC) and the related mechanism, to provide experimental evidence for molecular targeted therapy of SACC. Methods Adenoid cystic cancer cells SACC-LM and SACC-83 were cultured in vitro, and siRNA was transfected into human SACC-LM and SACC-83 cells (experimental group) by transient transfection of a liposome vector. A blank control group and negative control group were set up respectively (transfected NC-siRNA). qRT-PCR was peformed to measure the mRNA expression of ICMT and RhoA in each group after transfection and to determine the silencing efficiency. The expression of ICMT, membrane RhoA, total RhoA, matrix metalloproteinase-2 (MMP-2), matrix metalloproteinase-9 (MMP-9) and Rho associated with coiled helical binding protein kinase 1 (ROCK1) in each group was detected by Western blot. The proliferation abilityies of SACC cells was detected by CCK-8 assay. The migration and invasion ability of SACC cells were detected by comparing the relative healing area of cell scratch assay and the number of Transwell assay cells. Results After transfection of ICMT-siRNA into SACC-LM and SACC-83 cells, the expression of ICMT gene and protein in the experimental group was significantly decreased compared with the negative control group and blank control group (P<0.05), but there were no significant differences in the expression of RhoA gene and total protein among all groups (P>0.05). The expression of RhoA membrane proteins, ROCK1, MMP-2, MMP-9 in the experimental group was significantly decreased compared with that in the negative control group and blank control group (P<0.05). Cell proliferation ability was significantly decreased (P<0.05). The migration and invasion abilities were significantly decreased (P<0.05). Conclusion In vitro silencing of ICMT gene can effectively inhibit the migration and invasion of human SACC-LM and SACC-83 cells, ...
    Keywords adenoid cystic carcinoma ; rhoa ; isoprene cysteine carboxymethyl transferase ; small interfering rna ; invade ; transfer ; rho associations contain curly helical binding protein kinase 1 ; matrix metalloproteinase-2 ; matrix metalloproteinase-9 ; rhoa-rock signaling pathway ; Medicine ; R
    Subject code 571
    Language Chinese
    Publishing date 2023-06-01T00:00:00Z
    Publisher Editorial Department of Journal of Prevention and Treatment for Stomatological Diseases
    Document type Article ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    More links

    Kategorien

  9. Book ; Online: A Note on John Simplex with Positive Dilation

    Lu, Zhou

    2020  

    Abstract: We prove a Johns theorem for simplices in $R^d$ with positive dilation factor $d+2$, which improves the previously known $d^2$ upper bound. This bound is tight in view of the $d$ lower bound. Furthermore, we give an example that $d$ isn't the optimal ... ...

    Abstract We prove a Johns theorem for simplices in $R^d$ with positive dilation factor $d+2$, which improves the previously known $d^2$ upper bound. This bound is tight in view of the $d$ lower bound. Furthermore, we give an example that $d$ isn't the optimal lower bound when $d=2$. Our results answered both questions regarding Johns theorem for simplices with positive dilation raised by \cite{leme2020costly}.

    Comment: A short note on a technical problem. Not intended to publish
    Keywords Mathematics - Metric Geometry ; Computer Science - Machine Learning
    Publishing date 2020-12-06
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    More links

    Kategorien

  10. Article ; Online: Nanostructured SnO

    Zhang, Yu / Xie, Quan / Lyu, Lin / Zou, Jiang / Lu, Zhou

    ACS omega

    2024  Volume 9, Issue 14, Page(s) 16055–16062

    Abstract: A specific matrix sensor that can operate at low temperatures and has a high sensing response is crucial for monitoring flammable VOC gases. In this study, a nanostructured ... ...

    Abstract A specific matrix sensor that can operate at low temperatures and has a high sensing response is crucial for monitoring flammable VOC gases. In this study, a nanostructured SnO
    Language English
    Publishing date 2024-03-29
    Publishing country United States
    Document type Journal Article
    ISSN 2470-1343
    ISSN (online) 2470-1343
    DOI 10.1021/acsomega.3c09623
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

To top