检索结果-内蒙古大学图书馆

Semi-Supervised Learning in Large Scale Text Categorization

Journal of Shanghai Jiaotong university(Science) 2017年第3期22卷 291-302页

作者：许泽文李建强刘博毕敬李蓉毛睿 School of Software Engineering Beijing University of Technology Beijing Engineering Research Center for Io T Software and Systems Beijing University of Technology Guangdong Key Laboratory of Popular High Performance Computers Shenzhen University Shenzhen Key Laboratory of Service Computing and Applications Shenzhen University

The rapid development of the Internet brings a variety of original information including text information, audio information, etc. However, it is difficult to find the most useful knowledge rapidly and accurately because of its huge number. Automatic text classification technology based on machine learning can classify a large number of natural language documents into the corresponding subject categories according to its correct semantics. It is helpful to grasp the text information directly. By learning from a set of hand-labeled documents,we obtain the traditional supervised classifier for text categorization(TC). However, labeling all data by human is labor intensive and time consuming. To solve this problem, some scholars proposed a semi-supervised learning method to train classifier, but it is unfeasible for various kinds and great number of Web data since it still needs a part of hand-labeled data. In 2012, Li et al. invented a fully automatic categorization approach for text(FACT)based on supervised learning, where no manual labeling efforts are required. But automatically labeling all data can bring noise into experiment and cause the fact that the result cannot meet the accuracy requirement. We put forward a new idea that part of data with high accuracy can be automatically tagged based on the semantic of category name, then a semi-supervised way is taken to train classifier with both labeled and unlabeled data,and ultimately a precise classification of massive text data can be achieved. The empirical experiments show that the method outperforms the supervised support vector machine(SVM) in terms of both F1 performance and classification accuracy in most cases. It proves the effectiveness of the semi-supervised algorithm in automatic TC.

关键词： text data mining semi-supervised automatic tagging classifier

来源：评论

学校读者我要写书评

暂无评论

A light-weight hot data identification scheme via grouping-based LRU lists 15th

A light-weight hot data identification scheme via grouping-b...

引用

15th International Conference on Algorithms and Architectures for Parallel Processing, ICA3PP 2015

作者： Shen, Biaobiao Li, Yongkun Xu, Yinlong Pan, Yubiao School of Computer Science and Technology University of Science and Technology of China Hefei230026 China Guangdong Key Laboratory of Popular High Performance Computers Shenzhen518060 China Shenzhen Key Laboratory of Service Computing and Applications Shenzhen518060 China

ISBN: (纸本)9783319271392

Real-world workloads generally exhibit high skewness in access patterns, and it is a consensus that separating hot and cold data may greatly improve storage system performance such as Solid State Drive (SSD) garbage collection(GC) performance. To achieve this, the key issue is how to accurately identify hot data, which is really challenging due to the large diversity and dynamics of workloads. In this paper, we propose a light-weight and high-accuracy identification scheme, which is developed via a group of Least Recently Used (LRU) lists and requires only a small amount of memory and CPU cycles. We further deploy our scheme on SSDs with DiskSim simulator, and results show that comparing to two state-of-the-art identification schemes, our scheme further reduces SSD GC cost by up to 59.1% (62.1%), and saves 44.3% (77.5%) of computational cost. Due to the light-weight and parameter-insensitive feature, our scheme can be easily deployed at various system levels and adaptable to different workloads. © 2015 Springer International Publishing Switzerland.

关键词： Refuse collection

来源：评论

学校读者我要写书评

暂无评论

Unsupervised feature selection via adaptive embedding and sparse learning for Parkinson’s disease diagnosis 1

引用

3rd International Workshop on Connectomics in NeuroImaging, CNI 2019 held in conjunction with the 22nd International Conference on Medical Image computing and Computer Assisted Intervention, MICCAI 2019

作者： Huang, Zhongwei Lei, Haijun Chen, Guoliang Li, Shiqi Li, Hancong Elazab, Ahmed Lei, Baiying Key Laboratory of Service Computing and Applications Guangdong Province Key Laboratory of Popular High Performance Computers College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China National-Regional Key Technology Engineering Laboratory for Medical Ultrasound Guangdong Key Laboratory for Biomedical Measurements and Ultrasound Imaging School of Biomedical Engineering Health Science Center Shenzhen University Shenzhen518060 China

ISBN: (数字)9783030323912

ISBN: (纸本)9783030323905

Parkinson’s disease (PD) is known as a progressive neurodegenerative disease in elderly people. Apart from decelerating the disease exacerbation, early and accurate diagnosis also alleviates mental and physical sufferings and provides timely and appropriate medication. In this paper, we propose an unsupervised feature selection method via adaptive manifold embedding and sparse learning exploiting longitudinal multimodal neuroimaging data for classification and regression prediction. Specifically, the proposed method simultaneously carries out feature selection and dynamic local structure learning to obtain the structural information inherent in the neuroimaging data. We conduct extensive experiments on the publicly available Parkinson’s progression markers initiative (PPMI) dataset to validate the proposed method. Our proposed method outperforms other state-of-the-art methods in terms of classification and regression prediction performance. © Springer Nature Switzerland AG 2019.

关键词： Neuroimaging

来源：评论

学校读者我要写书评

暂无评论

Incorporating language patterns and domain knowledge into feature-opinion extraction

Incorporating language patterns and domain knowledge into fe...

引用

17th International Conference on Text, Speech, and Dialogue, TSD 2014

作者： Zhou, Erqiang Luo, Xi Qin, Zhiguang School of Computer Science and Engineering University of Electronic Science and Technology of China No.2006 Xiyuan Ave Chengdu 611731 Sichuan China Guangdong Key Laboratory of Popular High Performance Computers Shenzhen Key Laboratory of Service Computing and Applications No. 3688 Nanhai Ave Shenzhen 518060 Guangdong China

ISBN: (纸本)9783319108155

We present a hybrid method for aspect-based sentiment analysis of Chinese restaurant reviews. Two main components are employed so as to extract feature-opinion pairs in the proposed method: domain independent language patterns found in Chinese and a lexical base built for restaurant reviews. The language patterns focus on the general knowledge which is implicit contained in Chinese, thus can be used directly by other domains without any modification. The lexical base, on the other hand, targets for particular characteristics of a given domain and acts as a plug-in part in our prototype system, thus does not affect the portability when applying the proposed approach in practice. Empirical evaluation shows that our method performs well and it can gain a progressive result when each component takes into effective. © 2014 Springer International Publishing.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Parallel Identifying Motifs in Biological Network on Multicore System

Parallel Identifying Motifs in Biological Network on Multico...

引用

2015全国理论计算机科学学术年会

作者： Cheng ZHONG Jing ZHAO Feng YANG Mengxiao YIN School of Computer and Electronics and Information Guangxi UniversityNanningChinaGuangdong Key Laboratory of Popular High Performance ComputersShenzhen Key Laboratory of Service Computing and ApplicationsShenzhenChina

The required time to indentify the motifs in biological networks will be sharply increased with increase of the scale of the original network or the size of motifs in the *** is very necessary to develop the fast algorithms to indentify larger motifs in large-scale biological networks.A thread-level parallel indentifying motifs algorithm is proposed on multicore machine, in which the local hash tables are used to store the subgraph SIKs mined by parallel threads and a task queue is used to dlistribute the data blocks to parallel threads to balance their loads.A dynamic task scheduling strategy is used to balance the loads among nodes on multi-core cluster, and an efficient parallel algorithn is designed to identify the motifs in biological *** experiment results in undirected network YeastPPI and directed network yeast show that compared with the existing parallel indentifying motifs algorithm, the presented parallel algorithms are faster and obtain good speedup, and it can identify larger motifs in the biological networks.

关键词： biological network motif identification multicore architecture parallel algorithms subgraph enumeration subgraph isomorphism task scheduling

来源：评论

学校读者我要写书评

暂无评论

Risk Matrix and D-S Theory Based Trustworthiness Assessment Method for Cloud services

Risk Matrix and D-S Theory Based Trustworthiness Assessment ...

引用

IEEE International Conference on Web services (ICWS)

作者： Tilei Gao Ming Yang Rong Jiang Tao Zhang Leijin Long School of Information Yunnan Key Laboratory of Service Computing Yunnan University of Finance and Economics Kunming China Institute of Intelligence Applications Faculty of Information Engineering and Automation Yunnan Key Laboratory of Service Computing Yunnan University of Finance and Economics Kunming China School of Information Yunnan University of Finance and Economics Kunming China Yunnan Key Laboratory of Service Computing Kunming China

ISBN: (数字)9798350368550

ISBN: (纸本)9798350368567

In the context of the digital economy, cloud services have become the preferred digital solutions for enterprises. However, even cloud services guaranteed by international authoritative platforms may still have numerous trustworthiness issues. The trustworthiness of cloud services has become one of the unavoidable key issues in the digital transformation process of current enterprises. This article starts from the perspective of the risks faced by cloud services, analyzes the current situation of cloud service trustworthiness, and proposes a cloud service trustworthiness assessment method based on fuzzy analytic hierarchy process, risk matrix, and D-S theory. The method can effectively assess the trustworthiness status of cloud services. It has significant research significance and practical value for users choosing cloud services to build digital systems, and monitoring and managing the trustworthiness of currently used cloud services.

关键词： Cloud computing Accuracy Web services Digital transformation Computational modeling Analytic hierarchy process Risk management Information technology Standards Monitoring

来源：评论

学校读者我要写书评

暂无评论

Acoustic Feedback Effect Reduction Based on Path Compensation in Multichannel FXLMS Sound Inhibition Systems

Acoustic Feedback Effect Reduction Based on Path Compensatio...

引用

International Conference on Digital Home (ICDH)

作者： Xiao'e Liu Qiwen Zou Xue Wang Ge Lin National Engineering Research Center of Digital Life Sun Yat-sen University Guangzhou China Guangdong Key Laboratory of Popular High Performance Computers Shenzhen Key Laboratory of Service Computing and Applications Shenzhen China

ISBN: (纸本)9781479942831

This paper investigates the issues of acoustic feedback in a new kind of application, sound inhibition (SI) system, which is based on the multiple channel active noise control (ANC) technique and implemented by using Filtered-X Least Mean Square (FXLMS) algorithm. The presence of acoustic feedback degrades the performance of SI system, and in the worst case the SI system may be unstable. Here we propose a method based on path compensation through feedback path modeling to complete the acoustic feedback effect reduction (FBER). Computer simulations are carried out for a 1×2×2 system consists of one reference microphone, two loudspeakers and two error microphones. It is demonstrated that the proposed method achieves better performance than the existing method.

关键词： Acoustics Silicon Microphones Noise Mathematical model Least squares approximations Loudspeakers

来源：评论

学校读者我要写书评

暂无评论

引用

IEEE International Conference on Computer Design: VLSI in Computers and Processors, (ICCD)

作者： Si Wu Yinlong Xu Yongkun Li Yunfeng Zhu University of Science and Technology of China Hefei Anhui CN School of Computer Science and Technology University of Science & Technology of China Shenzhen Key Laboratory of Service Computing and Applications

The ever-increasing demand of storage capability leads to scaling requirement in RAID-structured storage systems. Previous approaches to RAID scaling mainly focus on minimizing data migration, without considering the user-level application accesses. However, the mixed scaling I/Os and user accesses in practical systems will interfere with each other, which results in significant performance degradation of both the data migration time and the user response time. In this paper, we divide the whole storage space into multiple zones and measure the popularity (mainly using the metric of access frequency) of each zone. Based on the measured popularity, we propose an online scheme, namely Popularity-based Online Scaling (POS), to scale RAID-structured storage systems. The main idea of POS is to scale storage areas with high popularity first so as to better exploit workload locality. POS can efficiently alleviate the performance degradation of user response time and data migration time during the scaling process. It can be readily deployed atop various conventional RAID scaling approaches to improve their performance. To evaluate the performance of POS, we implement FastScale and FastScale with POS (POS-FS) in the same system. Through extensive benchmark studies on real-system workloads, we show that POS can efficiently reduce the response time to user requests and scaling I/Os and improve the sequentiality of data accesses.

关键词： Time factors Degradation Bandwidth Computers Frequency measurement Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

A Microfluidic Spherical Helix Module Using Liquid Metal and Additive Manufacturing for Drug Delivery applications

A Microfluidic Spherical Helix Module Using Liquid Metal and...

引用

Microwave, MTT-S International Symposium

作者： Yangyang Guan Shicong Wang Manos M. Tentzeris Yuanan Liu Beijing Key Laboratory of Work Safety Intelligent Monitoring Beijing University of Posts and Telecommunications China Key Laboratory of Embedded System and Service Computing of the Ministry of Education Tongji University China Agile Technologies for High-performance Electromagnetic Novel Applications Georgia Institute of Technology USA

In this paper, a spherical helix module based on 3D printing and microfluidic technologies was fabricated, tested and applied to drug delivery applications. A liquid metal alloy is introduced to enhance the sensitivity of the complex and drug-/liquid-reconfigurable helix topology. Moreover, the influence of the dimensions of the hemisphere inscribed by the helical turns on the resonant frequency of the structure is researched. The microfluidic channels with 1 mm radius are shaped in the form of double semispherical helix using a Form-2 3D printer. To fulfill effectively the liquid metal (LM) injection, movement and recycle for reuse, a syringe pump is integrated to flexibly control the flow of the fluid. Besides, the proof-of-concept prototype achieves excellent radiation gain and impedance matching. The realized sensitivity is 0.96 mL/GHz and 0.33 mL/GHz corresponding with the frequency shift from 2.28 to 2.01 GHz and 2.01 to 1.65 GHz.

关键词： Resonant frequency Monitoring Microfluidics Liquids Drugs Mathematical model Three-dimensional printing

来源：评论

学校读者我要写书评

暂无评论

An Electronic Medical Record Access Control Model Based on Intuitionistic Fuzzy Trust

SSRN

引用

SSRN 2023年

作者： Jiang, Rong Liu, Rui Zhang, Tao Ding, Weiping Tian, Shenghu Yunnan Key Laboratory of Service Computing Yunnan University of Finance and Economics Kunming China Institute of Intelligence Applications Yunnan University of Finance and Economics Kunming China School of Information Science and Technology Nantong University Nantong China

Electronic Medical Record (EMR), as the core data of medical big data, has improved the efficiency of medical services in the process of sharing and using, but a series of data privacy leakage problems have emerged. Access control technology can ensure users' legitimate and appropriate access to data resources, but traditional access control has many limitations such as static and coarse-grained, which is difficult to meet the dynamic and complex healthcare environment. Therefore, this article proposes an intuitionistic fuzzy trust-based access control model to solve the data privacy leakage problem in order to promote medical information sharing. The model proposes a new trust evaluation method that uses Latent Dirichlet Allocation (LDA) topic model and intuitionistic fuzzy theory to more accurately quantify doctors' trust;In trust aggregation, time windows and time decay are used to enhance the timeliness of trust aggregation;The model also adopts an intuitionistic fuzzy clustering algorithm based on relative entropy and a reward and punishment mechanism to achieve adaptive dynamic access control of doctors' access behavior. Experiments prove that the access control model based on intuitionistic fuzzy trust proposed in this article has a certain control effect on the privacy leakage problem of electronic medical record system. © 2023, The Authors. All rights reserved.

关键词： Clustering algorithms

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：