检索结果-内蒙古大学图书馆

5th Asian Conference on Machine Learning, ACML 2013

作者： Wu, Lei Zhang, Min-Ling MOE Key Laboratory of Computer Network and Information Integration School of Computer Science and Engineering Southeast University Nanjing210096 China

The problem of multi-label classification has attracted great interests in the last decade. Multi-label classification refers to the problems where an example that is represented by a single instance can be assigned to more than one category. Until now, most of the researches on multi-label classification have focused on supervised settings whose assumption is that large amount of labeled training data is available. Unfortunately, labeling training example is expensive and time-consuming, especially when it has more than one label. However, in many cases abundant unlabeled data is easy to obtain. Current attempts toward exploiting unlabeled data for multi-label classification work under the transductive setting, which aim at making predictions on existing unlabeled data while can not generalize to new unseen data. In this paper, the problem of inductive semi-supervised multi-label classification is studied, where a new approach named iMLCU, i.e. inductive Multi-Label Classification with Unlabeled data, is proposed. We formulate the inductive semi-supervised multi-label learning as an optimization problem of learning linear models and ConCave Convex Procedure (CCCP) is applied to optimize the non-convex optimization problem. Empirical studies on twelve diversified real-word multi-label learning tasks clearly validate the superiority of iMLCU against the other well-established multi-label learning approaches. © 2013 L. Wu & M.-L. Zhang.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

Implementation and evaluation of a backtracking algorithm for finding all justifications in OWL 2 EL

Implementation and evaluation of a backtracking algorithm fo...

引用

7th Chinese Semantic Web Symposium and the 2nd Chinese Web ScienceConference, CSWS 2013

作者： Zhou, Zhangquan Qi, Guilin Key Laboratory of Computer Network and Information Integration of State Education Ministry School of Computer Science and Engineering Southeast University China

ISBN: (纸本)9783642540240

Finding justifications plays an important role in the development and maintenance of ontologies. It helps users or developers to understand the entailments by presenting the minimal subsets of the ontology which are responsible for the entailment (called justification). In our previous work, we have proposed a backtracking algorithm for finding justifications in description logic ΕL+, which underpins OWL 2 EL, a profile of the latest version of Web Ontology Language (OWL). However, the algorithm is not implemented. In this paper, we implement this algorithm and conduct experiments on some real world ontologies, including Snomed-CT. We compare our algorithm with a black-box algorithm for finding all justification in OWL 2 EL. The experimental results show that in most cases, the backtracking algorithm outperforms the black-box one. © Springer-Verlag Berlin Heidelberg 2013.

关键词： Ontology

来源：评论

学校读者我要写书评

暂无评论

Disambiguation-free partial label learning 14

Disambiguation-free partial label learning

引用

14th SIAM International Conference on Data Mining, SDM 2014

作者： Zhang, Min-Ling School of Computer Science and Engineering MOE Key Laboratory of Computer Network and Information Integration Southeast University Nanjing210096 China

ISBN: (纸本)9781510811515

Partial label learning deals with the problem where each training example is associated with a set of candidate labels, among which only one is correct. The common strategy is to try to disambiguate their candidate labels, such as by identifying the ground-truth label iteratively or by treating each candidate label equally. Nevertheless, the above disambiguation strategy is prone to be misled by the false positive label(s) within candidate label set. In this paper, a new disambiguation-free approach to partial label learning is proposed by employing the well-known error-correcting output codes (ECOC) techniques. Specifically, to build the binary classifier with respect to each column coding, any partially labeled example will be regarded as a positive or negative training example only if its candidate label set entirely falls into the coding dichotomy. Experiments on controlled and real-world data sets clearly validate the effectiveness of the proposed approach. Copyright © SIAM.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

keyphrase generation algorithm based on co-occurrence graph

Keyphrase generation algorithm based on co-occurrence graph

引用

2022 International Conference on Applied Mathematics and Computional Mechanics, AMCM 2022

作者： Fang, Haisheng Yang, Peng School of Computer Science and Engineering Key Laboratory of Computer Network and Information Integration Ministry of Education Southeast University Nanjing China

In the keyphrase prediction task, it is usually difficult for a single corpus information to help the model learn enough core information, so this paper improves the current keyphrase generation method based on the corpus. From the developments of the co-occurrence, the use of the word conformity is mentioned in the original selection of the relevant text, and the purpose of achieving the maximum utilization of the spending information is achieved. At the same time, this paper proposes the CG-Net model, which uses the GAT network to learn co-present diagrams and implements a replication mechanism, which ultimately surpasses the current optimal method on the NUS test set. © Published under licence by IOP Publishing Ltd.

关键词： Co-Occurrence Relationship GAT keyphrase Generation

来源：评论

学校读者我要写书评

暂无评论

Conflict Resolution in Partially Ordered OWL DL Ontologies 21

Conflict Resolution in Partially Ordered OWL DL Ontologies

引用

21st European Conference on Artificial Intelligence (ECAI)

作者： Ji, Qiu Gao, Zhiqiang Huang, Zhisheng School of Computer Science and Engineering Southeast University Key Laboratory of Computer Network and Information Integration China Department of Mathematics and Computer Science Vrije University Amsterdam Netherlands

ISBN: (纸本)9781614994190;9781614994183

Inconsistency handling in OWL DL ontologies is an important problem because an ontology can easily be inconsistent when it is generated or modified. Current approaches to dealing with inconsistent ontologies often assume that there exists a total order over axioms and use such an order to select axioms to remove. However, in some cases, such as ontology merging, a total order may not be available and we only have a partial order over axioms. In this paper, we consider a general notion of logical inconsistency and define the notion of conflict of an inconsistent ontology. We then propose a general approach to resolving inconsistency of a partially ordered ontology. We instantiate this approach by proposing two algorithms to calculate prioritized hitting sets for a set of conflicts. We implement the algorithms and provide evaluation results on the efficiency and effectiveness by considering both artificial and real-life data sets.

关键词： Ontology

来源：评论

学校读者我要写书评

暂无评论

A reputation-based trust model for P2P systems

A reputation-based trust model for P2P systems

引用

2009 International Conference on Computational Intelligence and Security, CIS 2009

作者： Wu, Peng Wu, Guoxin Key Laboratory of Computer Network and Information Integration Ministry of Education School of Computer Science and Engineering Southeast University Nanjing China

ISBN: (纸本)9780769539317

One of the fundamental challenges for Peer to Peer (P2P) systems is the ability to manage risks involved in interacting and collaborating with prior unknown and potentially malicious parties. Reputation-based trust management systems have proven to be essential to enforcing cooperative behavior in P2P networks. However, in many existing reputation-based trust models, the validity of peers' trust valuation is seriously affected by peers' malicious behaviors, such as strategic cheating, dishonest recommending and collusion. In this paper, we propose a novel reputationbased trust model for P2P systems. In our approach, the trustworthiness of peers consists of the experience-based and recommendation-based trust. To provide adequate reaction to peers' malicious behaviors, some factors are introduced to distinguish these experiences about peers' behaviors. Simulation shows that the proposed model has advantages in countering peers' malicious behaviors over the existing trust models. © 2009 IEEE.

关键词： Peer to peer networks

来源：评论

学校读者我要写书评

暂无评论

ISS: An iterative scrubbing strategy for improving memory reliability against MBU 2nd

ISS: An iterative scrubbing strategy for improving memory re...

引用

2nd International Conference on Human Centered Computing, HCC 2016

作者： Wang, Hui Wang, Yun Key Laboratory of Computer Network and Information Integration MOE Department of Computer Science and Engineering Southeast University Nanjing210096 China

ISBN: (纸本)9783319318530

As technology scales, multiple bit upsets (MBUs) have shown prominent effect, thus affecting the reliability of memory to a great extent. In order to mitigate MBUs errors, interleaving schemes together with single error correction (SEC) codes can be used to provide the greatest protection for advanced computer memories. In this paper, an algorithm of iterative scrubbing strategy (ISS) is proposed for the optimal interleaving distance (ID), which should be maximized under some conditions. The proposed algorithm should keep the complexity and the area overhead of designing ID as low as possible without compromising memory reliability. The key principle is to take advantage of the locality of MBU errors and to realize efficient scrubbing. The efficiency of the proposed approach will be compared with conventional strategy. © Springer International Publishing Switzerland 2016.

关键词： Reliability

来源：评论

学校读者我要写书评

暂无评论

Enhancing Security of FPGA-Based Embedded Systems with Combinational Logic Binding

引用

Journal of computer Science & Technology 2017年第2期32卷 329-339页

作者： Ji-Liang Zhang Wei-Zheng Wang Xing-Wei Wang Zhi-Hua Xia Software College Northeastern University Shenyang 110169 China Key Laboratory of Computer Network and Information Integration (Southeast University) Ministry of Education Nanjing 210096 China Department of Computer and Communication Engineering Changsha University of Science and Technology Changsha 410014 China School of Computer and Software Nanjing University of Information Science and Technology Nanjing 210044 China

With the increasing use of field-programmable gate arrays （FPGAs） in embedded systems and many embedded applications, the failure to protect FPGA-based embedded systems from cloning attacks has brought serious losses to system developers. This paper proposes a novel combinational logic binding technique to specially protect FPGA-based embedded systems from cloning attacks and provides a pay-per-device licensing model for the FPGA market. Security analysis shows that the proposed binding scheme is robust against various types of malicious attacks. Experimental evaluations demonstrate the low overhead of the proposed technique.

关键词： cloning attack reverse engineering FPGA （field-programmable gate array） security hardware security

来源：评论

学校读者我要写书评

暂无评论

Efficient iterated greedy algorithm to minimize makespan for the no-wait flowshop with sequence dependent setup times

Efficient iterated greedy algorithm to minimize makespan for...

引用

2012 IEEE 16th International Conference on computer Supported Cooperative Work in Design, CSCWD 2012

作者： Xu, Tao Zhu, Xia Li, Xiaoping School of Computer Science and Engineering Southeast University 211189 Nanjing China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education China

ISBN: (纸本)9781467312127

In this paper, an efficient iterated greedy algorithm is proposed for the SDST (Sequence Dependent Setup Time) no-wait flowshop with makespan minimization, which is known to be NP-hard. By introducing effective operators, the Iterated Greedy algorithm is adapted to the considered problem. To improve the quality of solutions, Local Search is incorporated into the modified Iterated Greedy algorithm. The proposed algorithm is compared with BIH, GAPH1∼GAPH4, and IG-Ruiz on Taillard's instances of ssd10, ssd50, ssd100, and ssdl25. Experimental results demonstrate that the proposal outperforms BIH and GAPH1∼GAPH4. As well, the proposal is more effective than IG-Ruiz under the same computation-time criterion. © 2012 IEEE.

关键词： Local search (optimization)

来源：评论

学校读者我要写书评

暂无评论

Hybrid heuristic for total flowtime minimization in no-wait flow shops

Hybrid heuristic for total flowtime minimization in no-wait ...

引用

11th International Conference on computer Supported Cooperative Work in Design, CSCWD 2007

作者： Zhu, Xia Li, Xiaoping Wang, Qian School of Computer Science and Engineering Southeast University Nanjing China Key Laboratory of Computer Network and Information Integration Ministry of Education Southeast University Nanjing China

ISBN: (纸本)1424409632

In this paper, no-wait flow shop scheduling problem with total flowtime minimization is considered. A hybrid heuristic is proposed, which is based on PH1 (p) (presented by Aldowaisan and Allahverdi, OMEGA, 2004). A composite algorithm is adopted to generate the initial seed. Job insertion in PH1 (p) is replaced with an existing constructive heuristic. Experimental results show that the proposal outperforms PH1 (p), especially for large scale instances. ©2007 IEEE.

关键词： Scheduling

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：