检索结果-内蒙古大学图书馆

7th International Conference on Big Data Computing and Communications, BigCom 2021

作者： Zhao, Fucheng Han, Xiaosong Zhang, Yikun Niu, Peiyu Cheng, Jun Yi, Wan Jilin University Key Laboratory for Symbol Computation and Knowledge Engineering of National Education Ministry College of Computer Science and Technology Changchun130012 China

ISBN: (纸本)9781665442527

In TCM (Traditional Chinese Medicine) theory, the cold-and-hot property of food is considered as an important information to guide people's daily diet and keep them healthy. But the classification of this property mostly relies on experience from medical books, which lacks corresponding molecular chemistry basis and makes differentiation very difficult for ordinary people. To solve above question, in this paper, we collected 500 kinds of food and their nutrients, used ANOVA algorithm for feature selection to find out the nutrient feature that have a greater correlation with the cold and hot properties of food, and then used LightGBM algorithm to classify the processed data set. Finally, we constructed a reliable and accurate classification model and found the related nutritional elements are Tyrosine, Arginine, Thiamine, Vitamin B6 and Selenium. © 2021 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

2.5D ASF-UNet: Adjacent Slice Spatial Feature Fusion Model for WMH Segmentation from 3D MR Brain Image

2.5D ASF-UNet: Adjacent Slice Spatial Feature Fusion Model f...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Lan Huang Yinglu Sun Ziqi Zhao Chunjie Guo Yan Wang Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education College of Computer Science and Technology Jilin University Changchun China Department of Radiology the First Hospital of Jilin University Changchun China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

Segmenting brain white matter hyperintensities (WMH) from 3D Magnetic Resonance (MR) images is crucial for the diagnosis, treatment, and prognosis of Multiple Sclerosis (MS). Unlike common 2D images, this task is more challenging and time-consuming. Classical deep learning methods for 3D image segmentation face two main challenges: 1) Pure 3D networks have more parameters and are prone to overfitting. 2) When using 2D networks to segment slices of 3D images, the lack of 3D structural information results in suboptimal segmentation after reconstruction. To address these difficulties, we propose the 2.5D ASF-UNet, which employs the 2.5D workflow and uses adjacent slices as the input for 2D segmentation network ASF-UNet. In ASF-UNet, separate down-sampling paths are used for the adjacent slices, and the Local Spatial Attention Module (LSAM) is designed to more effectively integrate 3D spatial information into the 2D network. Additionally, the Conv_Spectral_Block (CSB) is designed to extract and integrate local and global features. It allows the model to capture global spatial structures while preserving detailed information. Experimental results on MICCAI MSSEG 2016 and Local MS datasets show that 2.5D ASF-UNet achieve better segmentation performance than other deep learning methods.

关键词： Deep learning Image segmentation Solid modeling Three-dimensional displays Multiple sclerosis Feature extraction Brain modeling White matter Prognostics and health management Overfitting

来源：评论

学校读者我要写书评

暂无评论

A Survey on Performance Optimization of High-Level Synthesis Tools

引用

Journal of Computer Science & Technology 2020年第3期35卷 697-720页

作者： Lan Huang Da-Lin Li Kang-Ping Wang Teng Gao Adriano Tavares College of Computer Science and Technology Jilin UniversityChangchun 130012China Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun 130012China Zhuhai Laboratory of Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education Zhuhai College of Jilin University Zhuhai 519041China Algorithm Center University of MinhoGuimaraes 4800058Portugal

Field-programmable gate arrays(FPGAs)have recently evolved as a valuable component of the heterogeneous *** register transfer level(RTL)design flows demand the designers to be experienced in hardware,resulting in a possible failure of ***-level synthesis(HLS)permits designers to work at a higher level of abstraction through synthesizing high-level language programs to RTL *** provides a promising approach to solve these ***,the performance of HLS tools still has *** example,designers remain exposed to various aspects of hardware design,development cycles are still time consuming,and the quality of results(QoR)of HLS tools is far behind that of RTL *** this paper,we survey the literature published since 2014 focusing on the performance optimization of HLS *** with previous work,we extend the scope of the performance of HLS tools,and present a set of three-level evaluation criteria,covering from ease of use of the HLS tools to promotion on specific metrics of *** also propose performance evaluation equations for describing the relation between the performance optimization and the *** find that it needs more efforts on the ease of use for efficient HLS *** suggest that it is better to draw an analogy between the HLS development process and the embedded system design process,and to provide more elastic HLS methodology which integrates FPGAs virtual machines.

关键词： evaluation criterion field-programmable gate array(FPGA) high-level synthesis(HLS) performance optimization quality of results(QoR)

来源：评论

学校读者我要写书评

暂无评论

Crossed-Time Delay Neural Network for Speaker Recognition 1

引用

27th International Conference on MultiMedia Modeling, MMM 2021

作者： Chen, Liang Liang, Yanchun Shi, Xiaoshu Zhou, You Wu, Chunguo Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education College of Computer Science and Technology Jilin University Changchun130012 China Zhuhai Laboratory of Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education School of Computer Zhuhai College of Jilin University Zhuhai519041 China

ISBN: (数字)9783030678326

ISBN: (纸本)9783030678319

Time Delay Neural Network (TDNN) is a well-performing structure for deep neural network-based speaker recognition systems. In this paper we introduce a novel structure, named Crossed-Time Delay Neural Network (CTDNN) to enhance the performance of current TDNN for speaker recognition. Inspired by the multi-filters setting of convolution layers from convolution neural networks, we set multiple time delay units with different context size at the bottom layer and construct a multilayer parallel network. The proposed CTDNN gives significant improvements over original TDNN on both speaker verification and identification tasks. It outperforms in VoxCeleb1 dataset in verification experiment with a 2.6% absolute Equal Error Rate improvement. In few shots condition, CTDNN reaches 90.4% identification accuracy, which doubles the identification accuracy of original TDNN. We also compare the proposed CTDNN with another new variant of TDNN, Factorized-TDNN, which shows that our model has a 36% absolute identification accuracy improvement under few shots condition. Moreover, the proposed CTDNN can handle training with a larger batch more efficiently and hence, utilize calculation resources economically. © 2021, Springer Nature Switzerland AG.

关键词： Convolution

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

Shortcut Learning in In-Context Learning: A Survey

arXiv

引用

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

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

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

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：