检索结果-内蒙古大学图书馆

作者： Gang Lin Yanchun Liang Xiaoyang Fu Guangshun Chen Shaocan Cai Zhuhai Laboratory of Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education Department of Computer Science and TechnologySchool of Computer Science Department of Computer Science and Technology School of Computer ScienceZhuhai College of Jilin University

In order to generate a report for an enterprise where there is neither the API supporting from their existing website systems nor the granted database access rights approval,a daily business report generator system based on web scraping with k nearest neighbor(kNN)classification algorithm is proposed in this *** covers the web crawler technology that is to access existing website system and extract business *** k NN algorithm is applied to identify the verification code on the login page,and the brief daily report generating in a spreadsheet style *** with some OCR engine for image recognition,the system in Python can automatically generate the brief daily business reports by the kNN algorithm,which is better than some library with default training set on validating the verification code.

关键词： image Design of a Daily Brief Business Report Generator based on Web Scraping with KNN Algorithm Web KNN

来源：评论

学校读者我要写书评

暂无评论

A Multi-Task-Based Deep Multi-Scale Information Fusion Method for Intelligent Diagnosis of Bearing Faults

SSRN

引用

SSRN 2022年

作者： Xin, Ruihao Wang, Tiantian Miao, Fengbo Yu, Cuinan Feng, Xin College of Information and Control Engineering Jilin Institute of Chemical Technology Jilin Jilin132000 China College of Computer Science and Technology Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Jilin Changchun130012 China School of Science Jilin Institute of Chemical Technology Jilin Jilin132000 China

The use of deep learning for fault diagnosis is already a commonly used method. However, complex operating conditions under different working conditions significantly impact bearing vibration signals. Integrating the discriminative information of fault type and size into the deep learning model to achieve rich multi-task fault feature diagnosis still deserves attention. This study proposes a deep multi-task-based multi-scale feature fusion network MEAT(multi-task-based deep multi-scale feature fusion network) model to address these issues. Solve the limitations and poor adaptability of traditional convolutional neural network models under complex work. This model considers two sub-tasks, fault scale discrimination, and fault type discrimination, in the fault diagnosis multi-classification task through multi-task mapping decomposition. First, multi-dimensional features are extracted by convolution at different scales to obtain multi-dimensional fault information at different levels. Then these features are weighted and fused using a multi-layer attention mechanism to get accurate diagnosis results of bearing faults. © 2022, The Authors. All rights reserved.

关键词： Failure analysis

来源：评论

学校读者我要写书评

暂无评论

Some new signature schemes and secret sharing schemes based on the Gröbner basis cryptosystems

引用

Journal of computational Information Systems 2013年第13期9卷 5133-5140页

作者： Li, Hengyan Chang, Shuizhen Xu, Zhonghai Mathematics and Information Science College North China University of Water Resources and Electric Power Zhengzhou 450011 China Mathematics and Information Science College Luoyang Normal University Luoyang 471022 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun 130012 China National Key Laboratory of Science and Technology on Advanced Composites in Special Environments Harbin Institute of Technology Harbin 150080 China

In this paper, we introduce some new signature schemes and secret sharing schemes from the known Gröbner basis cryptosystems. Then, we discuss the issues related to the security of these schemes. Finally, we draw... 详细信息

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Interference-Aware Opportunistic Job Placement for Shared Distributed Deep Learning Clusters

SSRN

引用

SSRN 2023年

作者： Li, Hongliang Zhao, Hairui Sun, Ting Li, Xiang Xu, Haixiao Li, Keqin College of Computer Science and Technology Jilin University Changchun China Key Laboratory of Symbolic Computation and Knowledge Engineering The Ministry of Education Changchun China High Performance Computing Center Jilin University Changchun China Department of Computer Science State University of New York New PaltzNY12561 United States

Distributed deep learning frameworks facilitate large deep learning workloads. These frameworks support sharing one GPU device among multiple jobs to improve resource utilization. Modern deep learning training jobs consume a large amount of GPU memory. Despite that, sharing GPU memory among jobs is still possible because a training job has iterative steps that its memory usage fluctuates over time. However, resource sharing also introduces the risk of job performance degradation. Colocated jobs sharing a GPU device may suffer from different levels of interference, mainly caused by memory oversharing. How to improve resource utilization while maintaining good job performance is a novel challenge for job placement strategies. This paper studies the job placement problem. We propose an opportunistic memory sharing model to describe the time-varying job memory requirements. Based on this model, we introduce an Opportunistic Job Placement Problem (OJPP) for shared GPU clusters that seek job placement configurations using a minimum number of GPU devices and guarantee user-defined performance requirements at the same time. We propose a greedy algorithm and a heuristic algorithm with computational complexities of O(n log n) and O(n2 log n), respectively, to solve the problem. We also propose an online adjustment algorithm with the computational complexity of O(n log n) to perform updates to job placement configurations in runtime. A machine-learning-based interference prediction method is used to prepare accurate interference estimations. Extensive experiments are conducted on a GPU cluster to verify the correctness and effectiveness of our algorithms. Compared with standalone training jobs on dedicated clusters, the proposed approach reduces resource consumption by 46% in a shared cluster, while guaranteeing over 92.97% of the job performance, in terms of average job completion time. © 2023, The Authors. All rights reserved.

关键词： computational complexity

来源：评论

学校读者我要写书评

暂无评论

A Coarse-to-fine Cascaded Evidence-Distillation Neural Network for Explainable Fake News Detection

arXiv

引用

arXiv 2022年

作者： Yang, Zhiwei Ma, Jing Chen, Hechang Lin, Hongzhan Luo, Ziyang Chang, Yi College of Computer Science and Technology Jilin University Changchun China Department of Computer Science Hong Kong Baptist University Hong Kong School of Artificial Intelligence Jilin University China International Center of Future Science Jilin University China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education China

Existing fake news detection methods aim to classify a piece of news as true or false and provide veracity explanations, achieving remarkable performances. However, they often tailor automated solutions on manual fact-checked reports, suffering from limited news coverage and debunking delays. When a piece of news has not yet been fact-checked or debunked, certain amounts of relevant raw reports are usually disseminated on various media outlets, containing the wisdom of crowds to verify the news claim and explain its verdict. In this paper, we propose a novel Coarse-to-fine Cascaded Evidence-Distillation (CofCED) neural network for explainable fake news detection based on such raw reports, alleviating the dependency on fact-checked ones. Specifically, we first utilize a hierarchical encoder for web text representation, and then develop two cascaded selectors to select the most explainable sentences for verdicts on top of the selected top-K reports in a coarse-to-fine manner. Besides, we construct two explainable fake news datasets, which are publicly available. Experimental results demonstrate that our model significantly outperforms state-of-the-art baselines and generates high-quality explanations from diverse evaluation perspectives. Copyright © 2022, The Authors. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

CellMirror: Deciphering Cell Populations from Spatial Transcriptomics Data by Interpretable Contrastive Learning 1

CellMirror: Deciphering Cell Populations from Spatial Transc...

引用

1st IEEE International Conference on Medical Artificial Intelligence, MedAI 2023

作者： Xia, Junjie Cui, Jiangnan Huang, Zhenyu Zhang, Shuangquan Yao, Fang Zhang, Yijian Zuo, Chunman Institute of Artificial Intelligence Donghua University Department of Applied Mathematics Shanghai China College of Computer Science and Technology Jilin University Changchun China School of Cyber Science and Engineering Nanjing University of Science and Technology Nanjing China Institute of Maternal and Child Medicine Southern Medical University Affiliated Shenzhen Maternity and Child Healthcare Hospital Shenzhen China Xinhua Hospital Affiliated Shanghai Jiao Tong University of Medicine Department of General Surgery Shanghai China Institute of Artificial Institute Donghua University Shanghai China Jilin University Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education Changchun China

ISBN: (纸本)9798350358780

Spatial transcriptomics (ST) has enabled us elucidating tumor microenvironments, however, the technological limitations without single-cell resolution severely hinder its application. Here, we propose CellMirror, an interpretable contrastive learning model to decipher heterogeneous cell populations in ST data by single-cell RNA-sequencing (scRNA-seq) data. Specifically, CellMirror learns the disentangled shared (representing biological variations in both data) and salient features (specific to ST data) by two contrastive variational encoders, while constructing the relations between genes and features by a shared linear decoder. In various cancer samples, CellMirror outperforms other tools in learning common features for label transfer, and interpretation of features. Particularly, in breast cancer studies, CellMirror detects finer domains in ST data missed by other methods, and is robust to dissect cell populations in ST data using independent scRNA-seq data. These results demonstrate applications of CellMirror in interpreting the complex tumor structure in ST data by integrating scRNA-seq data. © 2023 IEEE.

关键词： Data integration

来源：评论

学校读者我要写书评

暂无评论

Convergence-Aware Optimal Checkpointing for Exploratory Deep Learning Training Jobs

SSRN

引用

SSRN 2024年

作者： Li, Hongliang Wang, Zichen Zhao, Hairui Zhang, Meng Li, Xiang Xu, Haixiao College of Computer Science and Technology Jilin University Qianjin street 2699 Jilin Changchun130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering The Ministry of Education Qianjin street 2699 Jilin Changchun130012 China High Performance Computing Center Qianjin street 2699 Jilin Changchun130012 China

Training Deep Learning (DL) models are becoming more time-consuming, thus interruptions to the training processes are inevitable. Existing fault-tolerant work adopted checkpoint/recovery mechanism from traditional HPC platforms that makes periodical persistent copies of model states to save execution progress. These checkpoints have fixed time intervals that they are evenly placed across the training. We can obtain an optimal checkpointing interval for an HPC job with the precondition that the progress of a job is proportional to its execution time. Unfortunately, it is not the case in DL model training where a DL training job yields diminishing returns across its lifetime. It makes the early progress of a DL training job more valuable than the later ones. Even placement of checkpoints would either increase the risks in the early stages or waste resources overprotecting the latter stages. Meanwhile, the issue can get amplified for exploratory training jobs, where early terminations are common. Moreover, in data parallelism, the state-of-art quality-driven scheduling strategies allocate more resources for the early stages of a job than the later ones to accelerate the training progress which further amplifies the issue. This paper introduces a novel checkpointing interval problem for exploratory DL training jobs based on model convergence progress. We present COCI, an approach to compute optimal checkpointing configuration for a DL training job, minimizing the fault-tolerant overhead, including checkpointing cost and recovery cost. We implement COCI based on state-of-art iteration-level checkpointing mechanism, as a pluggable module compatible with PyTorch. COCI requires no extra user input. We conduct comprehensive evaluations with real DL application setups. The experimental results show that COCI reduces up to 40.18% fault-tolerant overhead compared to existing state-of-the-art DL fault-tolerant methods in serial scenario, 57.26% in data parallel scenario and 63.8

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

A non-genetic algorithm for solving multi-objective decision-making problems

引用

Journal of computational Information Systems 2012年第17期8卷 7401-7408页

Multi-objective decision-making problems have been widely applied to business, financial investment, transportation, optimal routing design, environment protection, and military strategies. In this paper, we give a non-genetic algorithm for solving multi-objective decision-making problems. Under suitable conditions, a smooth path will be proven to exist. This can lead to an implementable globally convergent algorithm. We also give some numerical examples to illustrate the effectiveness of the algorithm in this paper. © 2012 Binary Information Press.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

A hybrid algorithm of minimum spanning tree and nearest neighbor for classifying human cancers

A hybrid algorithm of minimum spanning tree and nearest neig...

引用

International Conference on Advanced Computer Theory and engineering, ICACTE

作者： Chunbao Zhou Liming Wan Yanchun Liang College of Computer Science and Technology Key Laboratory of Symbol Computation and Knowledge Engineering of the Ministry of Education Jilin University Changchun China Research Institute on General Development and Evaluation of Equipment EAAF of PLA Beijing China

ISBN: (纸本)9781424465392

Classification and prediction of different cancers based on gene expression profiles are important for cancer diagnosis, cancer treatment and medication discovery. The k nearest neighbor algorithm (k-NN) is one easy and efficient machine learning method for cancer classification and the parameter k is crucial. In this paper, we integrate minimum spanning tree (MST) and k nearest neighbor algorithm (k-NN) for cancer classification. The MST is designed for the selection of parameter k and the nearest neighbors for k-NN. Firstly we build a minimum spanning tree (MST) based on Euclidean distance between each two samples for gene expression data only including one unknown class sample. Secondly for unknown class sample in the gene expression data, we find the connected samples and then apply majority vote principle. Thirdly if there are tied votes then we expend the connected samples with the nearest neighbors for unknown class sample until all the samples are expended or the class for unknown sample is obtained. This hybrid algorithm is referred to as MSTNN. The hybrid algorithm MSTNN is compared with k-NN and other 3 existing classification algorithms on CNS dataset, Colon dataset and Lung dataset, 3 binary class gene expression datasets and 3 multi-class gene expression datasets: Leukemia1, Leukemia2, and Leukemia3 involving human cancers. The MSTNN algorithm improves 5.65% better than k-NN on average LOOCV accuracy and 13.80% better than k-NN on testing datasets classification average accuracy, and achieves the best performance in all the 5 algorithms. The results demonstrate that the proposed MSTNN algorithm is feasible to classify human cancers.

关键词： Classification algorithms Artificial neural networks Niobium Lungs Colon Support vector machines Cancer

来源：评论

学校读者我要写书评

暂无评论

Fold-based meta-analysis: a method for identifying differentially expressed genes in microarray data

引用

Journal of Information and computational Science 2013年第11期10卷 3453-3462页

作者： Tian, Yuan Bai, Tian Liu, Guixia Li, Zhangxiu Wu, Jianan Zhou, Chunguang College of Computer Science and Technology Jilin University Changchun 130012 China Key Laboratory of Symbol Computation and Knowledge Engineering of the Ministry of Education Jilin University Changchun 130012 China College of Computer Science and Technology Changchun University Changchun 130022 China

The increase of microarray experiments brings a fresh challenge to analyze microarray data across datasets. Several methods have been developed and implemented. But the current tools were either complicated software with inefficiency methods or web applications, among which some were limited to specific data format. In this paper, we propose Fold-based Meta-analysis (FM), a method to identify Differentially Expressed Genes (DEGs) in microarray data. It could meta-analyze datasets in either the same or different platforms. We test FMT, respectively, on two published Arabidopsis datasets in one platform and three Mouse datasets in three different platforms, and then analyze the Gene Ontology (GO) terms or metabolic pathways of the most DEGs. Our results show that they are highly agreed on DEGs, and many of them are crucial and functional. In summary, our method is fast and practical. © 2013 Binary Information Press.

关键词： Genes

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：