LIVIVO - The Search Portal for Life Sciences

zur deutschen Oberfläche wechseln
Advanced search

Search results

Result 1 - 10 of total 84

Search options

  1. Article ; Online: Span-based few-shot event detection via aligning external knowledge.

    Ling, Tongtao / Chen, Lei / Lai, Yutao / Liu, Hai-Lin

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

    2024  Volume 176, Page(s) 106327

    Abstract: Few-shot Event Detection (FSED) aims to identify novel event types in new domains with very limited annotated data. Previous PN-based (Prototypical Network) joint methods suffer from insufficient learning of token-wise label dependency and inaccurate ... ...

    Abstract Few-shot Event Detection (FSED) aims to identify novel event types in new domains with very limited annotated data. Previous PN-based (Prototypical Network) joint methods suffer from insufficient learning of token-wise label dependency and inaccurate prototypes. To solve these problems, we propose a span-based FSED model, called SpanFSED, which decomposes FSED into two subprocesses, including span extractor and event classifier. In span extraction, we convert sequential labels into a global boundary matrix that enables the span extractor to acquire precise boundary information irrespective of label dependency. In event classification, we align event types with an outside knowledge base like FrameNet and construct an enhanced support set, which injects more trigger information into the prototypical network of event prototypes. The superior performance of SpanFSED is demonstrated through extensive experiments on four event detection datasets, i.e., ACE2005, ERE, MAVEN and FewEvent. Access to our code and data is facilitated through the following link: .
    Language English
    Publishing date 2024-04-18
    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.2024.106327
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

  2. Article ; Online: A Surrogate-Assisted Differential Evolution Algorithm for High-Dimensional Expensive Optimization Problems.

    Wang, Weizhong / Liu, Hai-Lin / Tan, Kay Chen

    IEEE transactions on cybernetics

    2023  Volume 53, Issue 4, Page(s) 2685–2697

    Abstract: The radial basis function (RBF) model and the Kriging model have been widely used in the surrogate-assisted evolutionary algorithms (SAEAs). Based on their characteristics, a global and local surrogate-assisted differential evolution algorithm (GL-SADE) ... ...

    Abstract The radial basis function (RBF) model and the Kriging model have been widely used in the surrogate-assisted evolutionary algorithms (SAEAs). Based on their characteristics, a global and local surrogate-assisted differential evolution algorithm (GL-SADE) for high-dimensional expensive problems is proposed in this article, in which a global RBF model is trained with all samples to estimate a global trend, and then its optima is used to significantly accelerate the convergence process. A local Kriging model prefers to select points with good predicted fitness and great uncertainty, which can effectively prevent the search from getting trapped into local optima. When the local Kriging model finds the best solution so far, a reward search strategy is executed to further exploit the local Kriging model. The experiments on a set of benchmark functions with dimensions varying from 30 to 200 are conducted to evaluate the performance of the proposed algorithm. The experimental results of the proposed algorithm are compared to four state-of-the-art algorithms to show its effectiveness and efficiency in solving high-dimensional expensive problems. Besides, GL-SADE is applied to an airfoil optimization problem to show its effectiveness.
    Language English
    Publishing date 2023-03-16
    Publishing country United States
    Document type Journal Article
    ISSN 2168-2275
    ISSN (online) 2168-2275
    DOI 10.1109/TCYB.2022.3175533
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

  3. Article ; Online: EPC-DARTS: Efficient partial channel connection for differentiable architecture search.

    Cai, Zicheng / Chen, Lei / Liu, Hai-Lin

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

    2023  Volume 166, Page(s) 344–353

    Abstract: With weight-sharing and continuous relaxation strategies, the differentiable architecture search (DARTS) proposes a fast and effective solution to perform neural network architecture search in various deep learning tasks. However, unresolved issues, such ...

    Abstract With weight-sharing and continuous relaxation strategies, the differentiable architecture search (DARTS) proposes a fast and effective solution to perform neural network architecture search in various deep learning tasks. However, unresolved issues, such as the inefficient memory utilization, and the poor stability of the search architecture due to channels randomly selected, which has even caused performance collapses, are still perplexing researchers and practitioners. In this paper, a novel efficient channel attention mechanism based on partial channel connection for differentiable neural architecture search, termed EPC-DARTS, is proposed to address these two issues. Specifically, we design an efficient channel attention module, which is applied to capture cross-channel interactions and assign weight based on channel importance, to dramatically improve search efficiency and reduce memory occupation. Moreover, only partial channels with higher weights in the mixed calculation of operation are used through the efficient channel attention mechanism, and thus unstable network architectures obtained by the random selection operation can also be avoided in the proposed EPC-DARTS. Experimental results show that the proposed EPC-DARTS achieves remarkably competitive performance (CIFAR-10/CIFAR-100: a test accuracy rate of 97.60%/84.02%), compared to other state-of-the-art NAS methods using only 0.2 GPU-Days.
    MeSH term(s) Neural Networks, Computer
    Language English
    Publishing date 2023-07-24
    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.2023.07.029
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

  4. Article ; Online: Thirteen complete chloroplast genomes of the costaceae family: insights into genome structure, selective pressure and phylogenetic relationships.

    Li, Dong-Mei / Pan, Yan-Gu / Liu, Hai-Lin / Yu, Bo / Huang, Dan / Zhu, Gen-Fa

    BMC genomics

    2024  Volume 25, Issue 1, Page(s) 68

    Abstract: Background: Costaceae, commonly known as the spiral ginger family, consists of approximately 120 species distributed in the tropical regions of South America, Africa, and Southeast Asia, of which some species have important ornamental, medicinal and ... ...

    Abstract Background: Costaceae, commonly known as the spiral ginger family, consists of approximately 120 species distributed in the tropical regions of South America, Africa, and Southeast Asia, of which some species have important ornamental, medicinal and ecological values. Previous studies on the phylogenetic and taxonomic of Costaceae by using nuclear internal transcribed spacer (ITS) and chloroplast genome fragments data had low resolutions. Additionally, the structures, variations and molecular evolution of complete chloroplast genomes in Costaceae still remain unclear. Herein, a total of 13 complete chloroplast genomes of Costaceae including 8 newly sequenced and 5 from the NCBI GenBank database, representing all three distribution regions of this family, were comprehensively analyzed for comparative genomics and phylogenetic relationships.
    Result: The 13 complete chloroplast genomes of Costaceae possessed typical quadripartite structures with lengths from 166,360 to 168,966 bp, comprising a large single copy (LSC, 90,802 - 92,189 bp), a small single copy (SSC, 18,363 - 20,124 bp) and a pair of inverted repeats (IRs, 27,982 - 29,203 bp). These genomes coded 111 - 113 different genes, including 79 protein-coding genes, 4 rRNA genes and 28 - 30 tRNAs genes. The gene orders, gene contents, amino acid frequencies and codon usage within Costaceae were highly conservative, but several variations in intron loss, long repeats, simple sequence repeats (SSRs) and gene expansion on the IR/SC boundaries were also found among these 13 genomes. Comparative genomics within Costaceae identified five highly divergent regions including ndhF, ycf1-D2, ccsA-ndhD, rps15-ycf1-D2 and rpl16-exon2-rpl16-exon1. Five combined DNA regions (ycf1-D2 + ndhF, ccsA-ndhD + rps15-ycf1-D2, rps15-ycf1-D2 + rpl16-exon2-rpl16-exon1, ccsA-ndhD + rpl16-exon2-rpl16-exon1, and ccsA-ndhD + rps15-ycf1-D2 + rpl16-exon2-rpl16-exon1) could be used as potential markers for future phylogenetic analyses and species identification in Costaceae. Positive selection was found in eight protein-coding genes, including cemA, clpP, ndhA, ndhF, petB, psbD, rps12 and ycf1. Maximum likelihood and Bayesian phylogenetic trees using chloroplast genome sequences consistently revealed identical tree topologies with high supports between species of Costaceae. Three clades were divided within Costaceae, including the Asian clade, Costus clade and South American clade. Tapeinochilos was a sister of Hellenia, and Parahellenia was a sister to the cluster of Tapeinochilos + Hellenia with strong support in the Asian clade. The results of molecular dating showed that the crown age of Costaceae was about 30.5 Mya (95% HPD: 14.9 - 49.3 Mya), and then started to diverge into the Costus clade and Asian clade around 23.8 Mya (95% HPD: 10.1 - 41.5 Mya). The Asian clade diverged into Hellenia and Parahellenia at approximately 10.7 Mya (95% HPD: 3.5 - 25.1 Mya).
    Conclusion: The complete chloroplast genomes can resolve the phylogenetic relationships of Costaceae and provide new insights into genome structures, variations and evolution. The identified DNA divergent regions would be useful for species identification and phylogenetic inference in Costaceae.
    MeSH term(s) Genome, Chloroplast ; Phylogeny ; Bayes Theorem ; Genomics/methods ; DNA
    Chemical Substances DNA (9007-49-2)
    Language English
    Publishing date 2024-01-17
    Publishing country England
    Document type Journal Article
    ZDB-ID 2041499-7
    ISSN 1471-2164 ; 1471-2164
    ISSN (online) 1471-2164
    ISSN 1471-2164
    DOI 10.1186/s12864-024-09996-4
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

  5. Article ; Online: The pain incidence of the injection site and analgesic effect of quadratus lumborum block and transversus abdominis plane block for cesarean delivery.

    Yang, Dong-Xia / Zhou, Rui-Hao / Liu, Hai-Lin / Luo, He-Guo

    Asian journal of surgery

    2022  Volume 45, Issue 12, Page(s) 3014–3016

    MeSH term(s) Pregnancy ; Female ; Humans ; Incidence ; Nerve Block ; Abdominal Muscles ; Pain ; Analgesics ; Pain, Postoperative/etiology ; Pain, Postoperative/prevention & control ; Analgesics, Opioid
    Chemical Substances Analgesics ; Analgesics, Opioid
    Language English
    Publishing date 2022-07-03
    Publishing country China
    Document type Letter
    ZDB-ID 1068461-x
    ISSN 0219-3108 ; 1015-9584
    ISSN (online) 0219-3108
    ISSN 1015-9584
    DOI 10.1016/j.asjsur.2022.06.148
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

  6. Article ; Online: Elevated cervical shoulder position and traditional supine position in the ultrasound-guided brachial plexus block: A randomized controlled trial.

    Bian, Wen-Gong / Zhou, Rui-Hao / Liu, Hai-Lin / Luo, He-Guo

    Asian journal of surgery

    2022  Volume 45, Issue 11, Page(s) 2300–2301

    MeSH term(s) Anesthetics, Local ; Brachial Plexus/diagnostic imaging ; Brachial Plexus Block ; Humans ; Shoulder ; Supine Position ; Ultrasonography, Interventional
    Chemical Substances Anesthetics, Local
    Language English
    Publishing date 2022-05-18
    Publishing country China
    Document type Letter ; Randomized Controlled Trial
    ZDB-ID 1068461-x
    ISSN 0219-3108 ; 1015-9584
    ISSN (online) 0219-3108
    ISSN 1015-9584
    DOI 10.1016/j.asjsur.2022.05.019
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

  7. Article ; Online: Comparative Chloroplast Genomics of 21 Species in Zingiberales with Implications for Their Phylogenetic Relationships and Molecular Dating.

    Li, Dong-Mei / Liu, Hai-Lin / Pan, Yan-Gu / Yu, Bo / Huang, Dan / Zhu, Gen-Fa

    International journal of molecular sciences

    2023  Volume 24, Issue 19

    Abstract: Zingiberales includes eight families and more than 2600 species, with many species having important economic and ecological value. However, the backbone phylogenetic relationships of Zingiberales still remain controversial, as demonstrated in previous ... ...

    Abstract Zingiberales includes eight families and more than 2600 species, with many species having important economic and ecological value. However, the backbone phylogenetic relationships of Zingiberales still remain controversial, as demonstrated in previous studies, and molecular dating based on chloroplast genomes has not been comprehensively studied for the whole order. Herein, 22 complete chloroplast genomes from 21 species in Zingiberales were sequenced, assembled, and analyzed. These 22 genomes displayed typical quadripartite structures, which ranged from 161,303 bp to 163,979 bp in length and contained 111-112 different genes. The genome structures, gene contents, simple sequence repeats, long repeats, and codon usage were highly conserved, with slight differences among these genomes. Further comparative analysis of the 111 complete chloroplast genomes of Zingiberales, including 22 newly sequenced ones and the remaining ones from the national center for biotechnology information (NCBI) database, identified three highly divergent regions comprising
    MeSH term(s) Humans ; Phylogeny ; Zingiberales/genetics ; Bayes Theorem ; Genomics ; Chloroplasts/genetics ; Genome, Chloroplast
    Language English
    Publishing date 2023-10-09
    Publishing country Switzerland
    Document type Journal Article
    ZDB-ID 2019364-6
    ISSN 1422-0067 ; 1422-0067 ; 1661-6596
    ISSN (online) 1422-0067
    ISSN 1422-0067 ; 1661-6596
    DOI 10.3390/ijms241915031
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

  8. Article ; Online: A Cooperative Evolutionary Framework Based on an Improved Version of Directed Weight Vectors for Constrained Multiobjective Optimization With Deceptive Constraints.

    Peng, Chaoda / Liu, Hai-Lin / Goodman, Erik D

    IEEE transactions on cybernetics

    2021  Volume 51, Issue 11, Page(s) 5546–5558

    Abstract: When solving constrained multiobjective optimization problems (CMOPs), the most commonly used way of measuring constraint violation is to calculate the sum of all constraint violations of a solution as its distance to feasibility. However, this kind of ... ...

    Abstract When solving constrained multiobjective optimization problems (CMOPs), the most commonly used way of measuring constraint violation is to calculate the sum of all constraint violations of a solution as its distance to feasibility. However, this kind of constraint violation measure may not reflect the distance of an infeasible solution from feasibility for some problems, for example, when an infeasible solution closer to a feasible region does not have a smaller constraint violation than the one farther away from a feasible region. Unfortunately, no set of artificial benchmark problems focusing on this area exists. To remedy this issue, a set of CMOPs with deceptive constraints is introduced in this article. It is the first attempt to consider CMOPs with deceptive constraints (DCMOPs). Based on our previous work, which designed a set of directed weight vectors to solve CMOPs, this article proposes a cooperative framework with an improved version of directed weight vectors to solve DCMOPs. Specifically, the cooperative framework consists of two switchable phases. The first phase uses two subpopulations-one to explore feasible regions and the other to explore the entire space. The two subpopulations provide useful information about the optimal direction of objective improvement to each other. The second phase aims mainly at finding Pareto-optimal solutions. Then an infeasibility utilization strategy is used to improve the objective function values. The two phases are switchable based on the information found to date at any time in the evolutionary process. The experimental results show that this method significantly outperforms the algorithms with which it is compared on most of the DCMOPs, in terms of reliability and stability in finding a set of well-distributed optimal solutions.
    Language English
    Publishing date 2021-11-09
    Publishing country United States
    Document type Journal Article
    ISSN 2168-2275
    ISSN (online) 2168-2275
    DOI 10.1109/TCYB.2020.2998038
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

  9. Article ; Online: A Rough-to-Fine Evolutionary Multiobjective Optimization Algorithm.

    Gu, Fangqing / Liu, Hai-Lin / Cheung, Yiu-Ming / Zheng, Minyi

    IEEE transactions on cybernetics

    2022  Volume 52, Issue 12, Page(s) 13472–13485

    Abstract: This article presents a rough-to-fine evolutionary multiobjective optimization algorithm based on the decomposition for solving problems in which the solutions are initially far from the Pareto-optimal set. Subsequently, a tree is constructed by a ... ...

    Abstract This article presents a rough-to-fine evolutionary multiobjective optimization algorithm based on the decomposition for solving problems in which the solutions are initially far from the Pareto-optimal set. Subsequently, a tree is constructed by a modified k -means algorithm on N uniform weight vectors, and each node of the tree contains a weight vector. Each node is associated with a subproblem with the help of its weight vector. Consequently, a subproblem tree can be established. It is easy to find that the descendant subproblems are refinements of their ancestor subproblems. The proposed algorithm approaches the Pareto front (PF) by solving a few subproblems in the first few levels to obtain a rough PF and gradually refining the PF by involving the subproblems level-by-level. This strategy is highly favorable for solving problems in which the solutions are initially far from the Pareto set. Moreover, the proposed algorithm has lower time complexity. Theoretical analysis shows the complexity of dealing with a new candidate solution is O(M logN) , where M is the number of objectives. Empirical studies demonstrate the efficacy of the proposed algorithm.
    Language English
    Publishing date 2022-11-18
    Publishing country United States
    Document type Journal Article
    ISSN 2168-2275
    ISSN (online) 2168-2275
    DOI 10.1109/TCYB.2021.3081357
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

  10. Book ; Online: Evolutionary Verbalizer Search for Prompt-based Few Shot Text Classification

    Ling, Tongtao / Chen, Lei / Lai, Yutao / Liu, Hai-Lin

    2023  

    Abstract: Recent advances for few-shot text classification aim to wrap textual inputs with task-specific prompts to cloze questions. By processing them with a masked language model to predict the masked tokens and using a verbalizer that constructs the mapping ... ...

    Abstract Recent advances for few-shot text classification aim to wrap textual inputs with task-specific prompts to cloze questions. By processing them with a masked language model to predict the masked tokens and using a verbalizer that constructs the mapping between predicted words and target labels. This approach of using pre-trained language models is called prompt-based tuning, which could remarkably outperform conventional fine-tuning approach in the low-data scenario. As the core of prompt-based tuning, the verbalizer is usually handcrafted with human efforts or suboptimally searched by gradient descent. In this paper, we focus on automatically constructing the optimal verbalizer and propose a novel evolutionary verbalizer search (EVS) algorithm, to improve prompt-based tuning with the high-performance verbalizer. Specifically, inspired by evolutionary algorithm (EA), we utilize it to automatically evolve various verbalizers during the evolutionary procedure and select the best one after several iterations. Extensive few-shot experiments on five text classification datasets show the effectiveness of our method.

    Comment: 12 pages, accepted by KSEM 2023
    Keywords Computer Science - Computation and Language
    Subject code 006
    Publishing date 2023-06-18
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    More links

    Kategorien

To top