检索结果-内蒙古大学图书馆

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Du, Zhihua Zhong, Ningyu Li, Jianqiang Shenzhen University College of Computer Science and Software Engineering Shenzhen China

ISBN: (纸本)9798350386226

Natural products, abundant in biological activities, are synthesized by bacteria during secondary metabolism, yielding a plethora of antibiotics, anticancer drugs, and other potential therapeutics. These compounds are directed by biosynthetic gene clusters (BGCs), which encode the necessary enzymes and regulatory elements for their production. With the rapid advancement of sequencing technology, the number of fully sequenced bacterial genomes has exponentially increased, providing researchers with an unprecedented opportunity to discover more BGCs. However, current identification methods are significantly constrained by their reliance on database quantity and predominantly utilize local features inherent in the BGC sequences. In this study, we introduce Biosynthetic Gene Clusters Catcher: GCN-BERT(BGCCGB), a deep learning model leveraging natural language processing for the identification of BGCs in bacterial genomes and classification of BGCs product types. Our approach represents BGCs as sequences represented by protein family (Pfam) identifiers and performs data augmentation on existing BGC data by introducing a synonym replacement method. Local and global features in BGCs sequences are then integrated by BERT and its self-attention mechanism, in conjunction with Graph Convolutional Networks (GCN). The experiment results indicate that BGCCGB effectively learns the features of BGCs, localizes BGCs in bacterial genomes, and predicts the product types of BGCs. Notably, BGCCGB demonstrates a significant performance improvement over previous methods, with an average precision 6.9% in BGC identification. These enhancements underscore the potential of BGCCGB in advancing the discovery and understanding of natural products synthesized by bacteria. © 2024 IEEE.

关键词： Genome

来源：评论

学校读者我要写书评

暂无评论

Application of fractal theory to study morphology of manganese sulfide inclusion in resulfurized free-cutting steels

引用

Journal of Iron and Steel Research International 2023年第1期30卷 137-149页

作者： Xiang-yu Xu Zhi-qi Zeng Qian-ren Tian Chen-wei Cao Ping Shen Jian-xun Fu Center for Advanced Solidification Technology(CAST) State Key Laboratory of Advanced Special SteelSchool of Materials Science and EngineeringShanghai UniversityShanghai 200444China Baosight Software Co. Ltd.Information Service HeadquartersShanghai 201203China

The morphology and distribution of manganese sulfide(MnS)inclusions have a significant influence on the comprehensive performance,which is an important research field for resulfurized *** on the experiments of non-aqueous electrolyte and scanning electron microscope observation,the fractal theory was employed to study the three-dimensional morphologies of MnS *** results showed that the edge fractal dimension of MnS inclusions was between 1.59 and *** addition,similar morphology of MnS inclusions had a close fractal *** MnS edge fractal dimension is highly positively correlated with the morphological *** multifractal spectrums of MnS inclusions on two-dimensional plane of as-cast and as-rolled resulfurized free-cutting steels were *** large-size MnS inclusions belong to large probability subset,while the small-size MnS inclusions belong to small probability *** multifractal spectrum can truly and effectively reflect the difference and non-uniformity of distribution of MnS inclusions on 2D *** the premise of similar content of MnS,with the refinement of MnS inclusions,the multifractal spectrum width and the multifractal spectrum symmetry parameter were *** multifractal spectrum provides a new method for studying the second phase in materials.

关键词： MnS inclusion Morphology Fractal dimension Multifractal Resulfurized steel

来源：评论

学校读者我要写书评

暂无评论

Study on the Rainfall-flood Association Pattern Database Based on Image Features 7

Study on the Rainfall-flood Association Pattern Database Bas...

引用

7th IEEE International Conference on Big Data and Artificial Intelligence, BDAI 2024

作者： Yu, Yufeng Cai, Difei Wu, Panqi Liu, Weifu Wang, Xuhang Hohai University College of Computer Science and Software Engineering Nanjing China

ISBN: (纸本)9798350352009

Precipitation images can clearly reflect the rainfall spatio-temporal features and play an important role in hydrological analysis and flood forecasting. However, it is challenging to mine the association response relationship between rainfall and flood events. This paper proposed a rainfall-flood association pattern database construction method based on rainfall image features. First, the rainfall pattern database and flood pattern database are constructed respectively through the steps of hydrological process segmentation, feature extraction, similarity measurement and cluster analysis. Additionally, association rule mining algorithm is used to conduct rainfall-flood association pattern mining and consrtuct the rainfall-flood association pattern database. The experimental results in the Jialing River basin show that the method proposed in this paper can effectively mine the rainfall-flood association pattern database and provide technical support for intelligent flood prediction based on historical scene patterns. © 2024 IEEE.

关键词： Rain

来源：评论

学校读者我要写书评

暂无评论

SFTCS: Multiform Semantic Fusion Based on Transformer for Code Summarization 14

SFTCS: Multiform Semantic Fusion Based on Transformer for Co...

引用

14th International Conference on software Technology and Engineering, ICSTE 2024

作者： Yang, Jun Ao, Longhao Qi, Rongzhi College of Computer Science and Software Engineering Hohai University Nanjing China

ISBN: (纸本)9798350378955

Automatic code summarization aims to create co-herent natural language descriptions for code snippets. Recent studies indicate that integrating additional code representation structures improve the quality of generated summaries beyond token sequence-based approaches. Current technical research mainly concentrates on the graph structure information of code snippets. However, using a graph method makes it challenging to extract meaningful semantic information from the code snippets. To address the issue, we investigate how to learn more about code semantics and information from the perspective of code text feature representation. Consequently, we propose a novel model named SFTCS. SFTCS employs a conjoint feature fusion strategy, focusing on two types of information in code snippets: code token sequence features and FGT features based on Abstract Syntax Trees (AST) sequence and graph sequence. An N-adjacency ma-trix based on AST features is constructed, and the corresponding feature for AST block are optimized through a graph-based structure. Subsequently, a FGC decoder processes the two types of features. With the aid of an attention mechanism for feature enhancement, the SFTCS model ultimately predicts the results concretely. Evaluations on two publicly available Java datasets validate the effectiveness of SFTCS, showing its superiority over six advanced code summarization models. Ablation studies further elucidate the contributions of each component within the SFTCS model. © 2024 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Match, Compare, or Select? An Investigation of Large Language Models for Entity Matching 31

Match, Compare, or Select? An Investigation of Large Languag...

引用

31st International Conference on computational Linguistics, COLING 2025

作者： Wang, Tianshu Chen, Xiaoyang Lin, Hongyu Chen, Xuanang Han, Xianpei Wang, Hao Zeng, Zhenyu Sun, Le Chinese Information Processing Laboratory Institute of Software Chinese Academy of Sciences China Hangzhou Institute for Advanced Study University of Chinese Academy of Sciences China University of Chinese Academy of Sciences China State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences China Alibaba Cloud Intelligence Group China

ISBN: (纸本)9798891761964

Entity matching (EM) is a critical step in entity resolution (ER). Recently, entity matching based on large language models (LLMs) has shown great promise. However, current LLM-based entity matching approaches typically follow a binary matching paradigm that ignores the global consistency among record relationships. In this paper, we investigate various methodologies for LLM-based entity matching that incorporate record interactions from different perspectives. Specifically, we comprehensively compare three representative strategies: matching, comparing, and selecting, and analyze their respective advantages and challenges in diverse scenarios. Based on our findings, we further design a compound entity matching framework (COMEM) that leverages the composition of multiple strategies and LLMs. COMEM benefits from the advantages of different sides and achieves improvements in both effectiveness and efficiency. Experimental results on 8 ER datasets and 10 LLMs verify the superiority of incorporating record interactions through the selecting strategy, as well as the further cost-effectiveness brought by COMEM. © 2025 Association for computational Linguistics.

关键词： computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Self-stabilizing (Δ+ 1 ) -Coloring in Sublinear (in Δ ) Rounds via Locally-Iterative Algorithms 29th

Self-stabilizing (Δ+ 1 ) -Coloring in Sublinear (in Δ ) R...

引用

29th International Computing and Combinatorics Conference, COCOON 2023

作者： Fu, Xinyu Yin, Yitong Zheng, Chaodong State Key Laboratory for Novel Software Technology Nanjing University Nanjing China

ISBN: (纸本)9783031491894

Fault-tolerance is a central theme in distributed computing. Self-stabilization is a key property that guarantees a distributed system starting from an arbitrary state eventually converges to a desired behavior. Such strong level of fault-tolerance is often desirable due to the error-prone nature of distributed systems. Developing fast and robust coloring algorithms has been a central topic in the study of distributed graph algorithms. In this paper, we give a (Δ+ 1 ) -coloring algorithm with O(Δ3 / 4log Δ) + log ∗n stabilization time, only using messages of size O(log n), on input graphs of n vertices and maximum degree Δ. This is the first self-stabilizing (Δ+ 1 ) -coloring algorithm with sublinear-in- Δ stabilization time. The key building block of our algorithm is a new locally-iterative (Δ+ 1 ) -coloring algorithm with O(Δ3 / 4log Δ) + log ∗n runtime. To the best of our knowledge, this is the first locally-iterative (Δ+ 1 ) -coloring algorithm with sublinear-in- Δ runtime. This answers an open question raised in [Barenboim, Elkin, and Goldberg, JACM ’21]. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Fault tolerance

来源：评论

学校读者我要写书评

暂无评论

A topical VAEGAN-IHMM approach for automatic story segmentation

引用

Mathematical Biosciences and Engineering 2024年第7期21卷 6608-6630页

作者： Yu, Jia Peng, Huiling Wang, Guoqiang Shi, Nianfeng School of Computer and Information Engineering Luoyang Institute of Science and Technology China Software Research Institute Technological University of Shannon Ireland

Feature representations with rich topic information can greatly improve the performance of story segmentation tasks. VAEGAN offers distinct advantages in feature learning by combining variational autoencoder (VAE) and generative adversarial network (GAN), which not only captures intricate data representations through VAE's probabilistic encoding and decoding mechanism but also enhances feature diversity and quality via GAN's adversarial training. To better learn topical domain representation, we used a topical classifier to supervise the training process of VAEGAN. Based on the learned feature, a segmentor splits the document into shorter ones with different topics. Hidden Markov model (HMM) is a popular approach for story segmentation, in which stories are viewed as instances of topics (hidden states). The number of states has to be set manually but it is often unknown in real scenarios. To solve this problem, we proposed an infinite HMM (IHMM) approach which utilized an HDP prior on transition matrices over countably infinite state spaces to automatically infer the state's number from the data. Given a running text, a Blocked Gibbis sampler labeled the states with topic classes. The position where the topic changes was a story boundary. Experimental results on the TDT2 corpus demonstrated that the proposed topical VAEGAN-IHMM approach was significantly better than the traditional HMM method in story segmentation tasks and achieved state-of-the-art performance. © 2024 the Author(s).

关键词： Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

Medicine and Disease Association Prediction via Attention-Based Medical Heterogeneous Information Network Representation Learning

IAENG International Journal of Computer Science

引用

IAENG International Journal of Computer science 2022年第1期49卷 69-78页

作者： Zhang, Bin Yang, Dan Lin, Zhihuang Master of Computer Science and Software Engineering Department University of Science and Technology Liao Ning Anshan China School of Computer Science and Software Engineering University of Science and Technology Liao Ning Anshan China

Knowledge of medication and disease has been rapidly accumulated. Also, an increasing number of researchers have paid more attention to predicting medicine-disease associations by machine learning methods. The associations of entities in the medical heterogeneous information network involve different association types. In this paper, we propose MHIN-MD, a representation learning of medical heterogeneous network model to solve the association between medicines and diseases in medical heterogeneous information network. Specifically, we first construct a medical heterogeneous information network contains diseases, medicines, diagnosis, etc. Next, we design a neural network model to learn the feature vector representation of medical nodes information. We try to find the association between medicines and diseases through the characteristics of medicines structure and the interaction between medicines. Using the Euclidean distance to calculate medicine similarity and disease similarity, generates a set of similar nodes between medicines and diseases to prediction association between medicines and diseases. Finally, our extensive experiments on MIMIC- III datasets and DrugBank datasets, the result demonstrates that MHIN-MD can outperform baselines in the association prediction. © 2022. All Rights Reserved.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Self-healing automation testing with Selenium and ChatGPT API integration to improve the efficiency of the maintenance 2

Self-healing automation testing with Selenium and ChatGPT AP...

引用

2nd International Conference on Foundation and Large Language Models, FLLM 2024

作者： Kim, Yunjin Kouatly, Rand University of Europe for Applied Science Department of Tech & Software Potsdam Germany

ISBN: (纸本)9798350354799

The rapid delivery in software development life cycle demands more adaptable automation testing frameworks. The current automation test frameworks struggle with maintaining the scripts due to frequent changes in web elements. To resolve this issue, this paper introduces a self-healing automation testing framework that updates broken locators without human intervention. ChatGPT API is integrated within the newly developed automation framework to reduce time and effort for maintenance. The results show the potential of the self-healing automation testing framework with ChatGPT API integration compared to traditional automation tests. © 2024 IEEE.

关键词： Life cycle

来源：评论

学校读者我要写书评

暂无评论

Leveraging Computer Vision for Automatic Modulation Classification: Insights from Spectrum and Constellation Diagram Analysis 27th

Leveraging Computer Vision for Automatic Modulation Classifi...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Zhao, Wenjie Luo, Qiuming College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China

ISBN: (纸本)9783031783821

Automated modulation recognition is a challenging task in communication systems. Leveraging recent advancements in transfer learning, this paper proposes a novel method for automatic modulation recognition using transferred computer vision models. The method allows fine-tuning of the vision models to recognize modulation signals through spectrum and constellation diagrams. Experiments on the Radioml dataset demonstrate that the proposed method outperforms recent traditional methods by 8.97%, with an average accuracy of 0.5732. An ablation study confirms the effectiveness of using spectrum and constellation diagrams. This study verifies the feasibility of transferring vision models to AMC tasks. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Signal modulation

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：