检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Song, Rui Li, Yingji Shi, Lida Giunchiglia, Fausto Xu, Hao College of Computer Science and Technology Jilin University Changchun China Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education Jilin University China Department of Information Engineering and Computer Science University of Trento Italy

Shortcut learning refers to the phenomenon where models employ simple, non-robust decision rules in practical tasks, which hinders their generalization and robustness. With the rapid development of Large Language Models (LLMs) in recent years, an increasing number of studies have shown the impact of shortcut learning on LLMs. This paper provides a novel perspective to review relevant research on shortcut learning in In-Context Learning (ICL). It conducts a detailed exploration of the types of shortcuts in ICL tasks, their causes, available benchmarks, and strategies for mitigating shortcuts. Based on the corresponding observations, we summarize the unresolved issues in existing research and attempts to outline the future research landscape of shortcut learning. © 2024, CC BY.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Deep Feature-Based Text Clustering and Its Explanation

Deep Feature-Based Text Clustering and Its Explanation

引用

International Conference on Data engineering

作者： Renchu Guan Hao Zhang Yanchun Liang Fausto Giunchiglia Lan Huang Xiaoyue Feng Key Laboratory for Symbol Computation and Knowledge Engineering of the Ministry of Education College of Computer Science and Technology Jilin University Changchun China DISI University of Trento Trento Italy

Text clustering is a critical step in text data analysis and has been extensively studied by the text mining community. Most existing text clustering algorithms are based on the bag-of-words model, which faces the high-dimensional and sparsity problems and ignores text structural and sequence information. Deep learning-based models such as convolutional neural networks and recurrent neural networks regard texts as sequences but lack supervised signals and explainable results. In this paper, we propose a deep feature-based text clustering (DFTC) framework that incorporates pretrained text encoders into text clustering tasks. This model, which is based on sequence representations, breaks the dependency on supervision. The experimental results show that our model outperforms classic text clustering algorithms on almost all the considered datasets. In addition, the explanation of the clustering results is significant for understanding the principles of the deep learning approach. Our proposed clustering framework includes an explanation module that can help users understand the meaning and quality of the clustering results. Our code is available at https://***/KEAML-JLU/DeepTextClustering.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Community discovery algorithm and its technical improvement based on link structure–taking web community algorithm as an example

Community discovery algorithm and its technical improvement ...

引用

International Conference on Applications and Techniques in Cyber Intelligence, ATCI 2020

作者： Gao, Rui Yang, Wenzhe Shi, Xiaohu Key Laboratory of Symbol Computation and Knowledge Engineering of the Ministry of Education College of Computer Science and Technology Jilin University 2699 Qianjin Street Changchun130012 China

ISBN: (纸本)9783030539795

Link analysis is an important way to discover potential web communities. This paper analyzes the characteristics of the Web link structure, and studies the traditional maximum flow algorithm and the maximum flow algorithm based on HITS algorithm for edge capacity allocation. The traditional maximum flow problem, but there are still shortcomings. Based on the analysis of existing link similarity definitions, this paper proposes a new definition of link similarity and topic dissimilarity to better describe the relationship between linked pages, and to measure based on link similarity and topic dissimilarity. The similarity of the pages gives a more reasonable and efficient maximum flow-side capacity allocation scheme. The community discovery of 6 topics shows that the maximum flow algorithm proposed in this paper using the link similarity and topic dissimilarity model to allocate edge capacity can better solve the problems of existing algorithms and significantly improve the quality of the Web community. This paper proposes new methods and ideas for page similarity measurement, and provides new strategies for improving the Web community discovery algorithm based on link analysis. © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2021.

关键词： Computer programming

来源：评论

学校读者我要写书评

暂无评论

A Novel Iterative Velocity Control Algorithm and Its FPGA Implementation Based on Trigonometric Function

引用

Chinese Journal of Electronics 2019年第2期28卷 237-245页

作者： WEN Quangang LIANG Yanchun Adriano Tavares Ricardo Teixeira WU Chunguo Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education College of Computer Science and Technology Jilin University Zhuhai Laboratory of Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education Zhuhai College of Jilin University Department of Industrial Electronics University of Minho Campus de Azurm

The servo motor’s flexible acceleration/deceleration(acc/dec) control is an emerging research topic in the automation field. A velocity control algorithm based on trigonometric function is proposed in this *** required parameters, it transforms trigonometric calculations into elementary mathematical operations and calculates the velocity controlling values iteratively, which could avoid trigonometric calculation and reduce the computation time. Experimental results show that the proposed algorithm is suitable for implementation on field programmable gate arrays and achieves a flexible controlling, enhancing both the equipment’s stability and reliability. It is promising to significantly improve the high-speed computerized numerical control equipment’s controlling accuracy, without a huge hardware resource consumption.

关键词： Acceleration Velocity control Algorithm design and analysis Field programmable gate arrays Servomotors

来源：评论

学校读者我要写书评

暂无评论

Toward Moiré-Free and Detail-Preserving Demosaicking

arXiv

引用

arXiv 2023年

作者： Li, Xuanchen Niu, Yan Zhao, Bo Shi, Haoyuan An, Zitong State Key Laboratory of Symbol Computation and Knowledge Engineering College of Computer Science and Technology Ministry of Education Jilin University Changchun China The College of Software Jilin University Changchun130012 China

3D convolutions are commonly employed by demosaicking neural models, in the same way as solving other image restoration problems. Counter-intuitively, we show that 3D convolutions implicitly impede the RGB color spectra from exchanging complementary information, resulting in spectral-inconsistent inference of the local spatial high frequency components. As a consequence, shallow 3D convolution networks suffer the Moiré artifacts, but deep 3D convolutions cause over-smoothness. We analyze the fundamental difference between demosaicking and other problems that predict lost pixels between available ones (e.g., super-resolution reconstruction), and present the underlying reasons for the confliction between Moiré-free and detail-preserving. From the new perspective, our work decouples the common standard convolution procedure to spectral and spatial feature aggregations, which allow strengthening global communication in the spectral dimension while respecting local contrast in the spatial dimension. We apply our demosaicking model to two tasks: Joint Demosaicking-Denoising and Independently Demosaicking. In both applications, our model substantially alleviates artifacts such as Moiré and over-smoothness at similar or lower computational cost to currently top-performing models, as validated by diverse evaluations. Source code will be released along with paper publication. Copyright © 2023, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Aspect Based Fine-Grained Sentiment Analysis for Public Policy Opinion Mining 21st

Aspect Based Fine-Grained Sentiment Analysis for Public Poli...

引用

21st International Symposium on knowledge and Systems Sciences, KSS 2022

作者： Zhao, Yueming Li, Ying Liu, Yijun Li, Qianqian College of Computer Science and Technology Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun130012 China Institutes of Science and Development Chinese Academy of Sciences Beijing100190 China School of Public Policy and Management University of Chinese Academy of Sciences Beijing100049 China

ISBN: (纸本)9789811936098

Fine-grained mining has substantial practical significance for understanding public opinion toward public policies and optimizing relevant decision-making processes. In this study, an aspect-based sentiment analysis model integrated with both a sentiment lexicon for the policy domain and mutual information (MI) is established from the perspective of attitudinal orientations toward several elements of public policies, including subjects, objects, and tools to analyze comments. First, terms related to the aspects of comments on different policy elements are extracted using the association rules in conjunction with the word2vec algorithm. In addition, the contextual neighbor principle is employed to extract terms that express evaluative opinions and to extricate aspect-based two-tuples from comments. Subsequently, the sentiment lexicon for the policy domain is expanded using the sentiment orientation pointwise mutual information (SO-PMI) algorithm. Four machine learning models (i.e., the support vector machine, logistic regression, naive Bayes, and k-nearest neighbors models) and two deep learning models (i.e., the convolutional neural network (CNN) and long short-term memory models) are compared in terms of their classification performance based on 87,304 comments on public policies crawled from the Weibo platform. The results show that the CNN model integrated with the domain-specific sentiment lexicon and mutual information is effective at facilitating policy element-oriented fine-grained sentiment analysis of public opinion toward policies and therefore has practical decision-making value for the government to better understand the policy demands of the public. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Public policy

来源：评论

学校读者我要写书评

暂无评论

Time and Time-Frequency Features Integrated CNN Model for Heart Sound Signals Detection

Time and Time-Frequency Features Integrated CNN Model for He...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Zhimin Ren Yuheng Qiao Yuping Yuan You Zhou Yanchun Liang Xiaohu Shi College of Computer Science and Technology of Jilin University Changchun China Laboratory of Symbol Computation and Knowledge Engineering of the Ministry of Education Changchun China School of Computer Science Zhuhai College of Science and Technology Zhuhai China

ISBN: (数字)9781665468190

ISBN: (纸本)9781665468206

Automatic heart sound diagnosis plays an important role in the early detection of cardiovascular diseases. Phonocardiogram (PCG) signals are often used in this field f or its low cost and non-invasive advantages. In this paper, we design a new time and time-frequency features integrated CNN (TTFI-CNN) model for heart sound signals detection. In the model, a 1D CNN and a BiLSTM are combined into 1D CRNN module to extract temporal features from the original PCG signal, and a 2D CNN module is applied to capture high-level features from time-frequency domain MFCCs inputs. The outputs of the two modules are recalibrated by attention mechanism to selectively emphasize informative features and suppress less useful ones. To verify the proposed TTFI-CNN model, it is applied to two public datasets with different classification t asks (binary and multiclassification). The TTFI-CNN model has achieved 97.15% accuracy, 97.13% sensitivity, and 97.17% specificity on physionet/cinc database, and obtained 3.31 and 2.61 precision scores on the PASCAL database A and B, respectively. Compared with the previous state-of-the-art methods, the TTFI-CNN performs best on all the above metrics. https://***/XxxNnnSssWww/TTFI-CNN.

关键词： Heart Time-frequency analysis Sensitivity Costs Databases Feature extraction Time-domain analysis

来源：评论

学校读者我要写书评

暂无评论

A novel multi-task learning network for skin lesion classification based on multi-modal clues and label-level fusion

引用

Computers in Biology and Medicine 2024年 175卷 108549-108549页

作者： Lin, Qifeng Guo, Xiaoxin Feng, Bo Guo, Juntong Ni, Shuang Dong, Hongliang Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education Jilin University 2699 Qianjin Street Changchun130012 China College of Computer Science and Technology Jilin University 2699 Qianjin Street Changchun130012 China College of Software Jilin University 2699 Qianjin Street Changchun130012 China

In this paper, we propose a multi-task learning (MTL) network based on the label-level fusion of metadata and hand-crafted features by unsupervised clustering to generate new clustering labels as an optimization goal. We propose a MTL module (MTLM) that incorporates an attention mechanism to enable the model to learn more integrated, variable information. We propose a dynamic strategy to adjust the loss weights of different tasks, and trade off the contributions of multiple branches. Instead of feature-level fusion, we propose label-level fusion and combine the results of our proposed MTLM with the results of the image classification network to achieve better lesion prediction on multiple dermatological datasets. We verify the effectiveness of the proposed model by quantitative and qualitative measures. The MTL network using multi-modal clues and label-level fusion can yield the significant performance improvement for skin lesion classification. © 2024 Elsevier Ltd

关键词： Metadata

来源：评论

学校读者我要写书评

暂无评论

Unsupervised and Semi-Supervised Domain Adaptation Networks Based on Instance-Level Contrastive Prototype Matching for Motor Imagery Classification

SSRN

引用

SSRN 2023年

作者： Zhang, Dongxue Li, Huiying Xie, Jingmeng College of Computer Science and Technology Jilin Province Changchun China Key Laboratory of Symbol Computation and Knowledge Engineering Jilin University Changchun130012 China Xi’an Jiaotong University College of Electronic information Shanxi Province Xi’an China

Due to the convenience and safety of EEG signals, it is widely used in motor imagery (MI) brain-computer interface (BCI). However, there exist distribution differences between different sessions of the same subject. Models trained with data from previous sessions (source domain) often perform poorly on the current sessions (target domain). Domain adaptation techniques have met this challenge to great effect. However, most of these existing studies only consider coarse-grained methods with global information. In this paper, we propose a method for instance-level comparative prototype (ICP) analysis. The approach incorporates global domain alignment and fine-grained local subdomain alignment to simultaneously account for both global and local differences. Depending on the amount of labeled data available in the target domain, the method is implemented in both unsupervised and semi-supervised versions. Specifically, at the domain level, we employ the maximum mean difference (MMD) loss to globally constrain the feature space, achieving comprehensive alignment. In the context of class-level operations, we propose two memory banks designed to house class prototypes within each domain. We meticulously regulate feature embeddings through the application of two contrastive losses based on prototypes. Among them, source contrastive loss is used to spatially organize source features according to categories, thereby mediating inter- and intra-class relationships. At the same time, we propose an entropy-aware interactive contrastive loss to dynamically and personalized apply class information across domains by evaluating the confidence level of target data. To validate our approach, extensive experiments were conducted on a highly regarded public EEG dataset, namely Dataset IIa of the BCI Competition IV, as well as a large-scale EEG dataset called GigaDB. The experiments yielded average classification accuracies of 86.03% and 84.22% respectively. These results demonstrate that o

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

COVID-19 knowledge Graph for Drug and Vaccine Development

COVID-19 Knowledge Graph for Drug and Vaccine Development

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Lan Huang Hongrui Guan Yanchun Liang Renchu Guan Xiaoyue Feng The Key Laboratory for Symbolic Computation and Knowledge Engineering of the Ministry of Education College of Computer Science and Technology Jilin University Changchun China Zhuhai Sub Laboratory Key Laboratory of Symbolic Computation and Knowledge Engineering of the Ministry of Education Zhuhai College of Science and Technology Zhuhai China

ISBN: (纸本)9781665429825

The worldwide spread of COVID-19 has made a severe impact on human health and life. It has shown rapid propagation, long in vitro survival, and a long incubation period. More seriously, COVID-19 is more susceptible to variation, as it is an RNA virus. Mutations of COVID-19 have been reported in multiple countries worldwide, which makes drug and vaccine development a significant challenge. To search for potential drugs and vaccines and reveal the atlas of COVID-19 evolution, we extract information from massive unstructured data and construct a COVID-19 knowledge graph using the COVID-19 data. Based on machine learning approaches, we infer and predict novel coronavirus pneumonia-related diseases, drug action targets, etc. to speculate on new and more effective treatment methods. In addition, to study transcriptome of SARS-CoV-2, new ideas can be provided to biomedical experts with flexible responses to viral variation. An in-depth analysis of the COVID-19 pathomechanism at the pharmaceutical, genetic, and protein levels provides effective means and tools for novel coronavirus pneumonia vaccines, drug development, and therapeutic program design.

关键词： COVID-19 Drugs Proteins Protein engineering Pulmonary diseases RNA Machine learning

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：