检索结果-内蒙古大学图书馆

An interpretation of Erlang into value-passing calculus

Journal of Networks 2013年第7期8卷 1504-1513页

作者： Huang, Hao Yang, Fei Department of Computer Science Shanghai Jiaotong University MOE-MS Key Laboratory for Intelligent Computing and Intelligent Systems China

In this paper we present a new process calculus VPCΣ and an interpretation for core Erlang. VPCΣ is at least as expressive as VPC and it is more effective for verification with some built-in functions. The wellestablished symbolic bisimulation in value-passing calculus is now helpful for solving the infinite-state space problem of data values in equivalence checking and verfication. Compared to the previous formalization work of modeling core Erlang in π-calculus, the new interpretation has the following main merits: some essential features for Erlang are implemented faithfully;and above all the soundness of the interpretation is proved with respect to late symbolic bisimulation. © 2013 ACADEMY PUBLISHER.

关键词： Calculations

来源：评论

学校读者我要写书评

暂无评论

Comparative analysis of motor imagery on different scales based on brain computer interface

Comparative analysis of motor imagery on different scales ba...

引用

作者： Li, Junhua Zhang, Liqing Department of Computer Science and Engineering MOE-Microsoft Key Laboratory for Intelligent Computing and Intelligent Systems Shanghai Jiao Tong University Shanghai 200240 China

The event-related brain oscillatory responses have a substantial role in motor imagery experiments. There are two patterns, i.e. event-related desynchronization (ERD) and eventrelated synchronization (ERS). In clinical applications and scientific experiments, an obvious event-related potential (ERP) is pivotal to achieve required tasks. Therefore, we explore how subjects generate the obvious ERP more easily. Eight healthy subjects participated in the experiments and completed motor imagery on two different scales (index finger versus arm). The results indicate that the motor imagery of arm reaches the better performance compared with the motor imagery of index finger. Furthermore, we make a comparative analysis in averaged power spectrum in order to reveal inherent phenomenon. The analysis of power spectrum further confirms that arm motor imagery has an advantage over index finger motor imagery.

关键词： Brain computer interface

来源：评论

学校读者我要写书评

暂无评论

Image denoising based on overcomplete topographic sparse coding

Image denoising based on overcomplete topographic sparse cod...

引用

20th International Conference on Neural Information Processing, ICONIP 2013

作者： Zhao, Haohua Luo, Jun Huang, Zhiheng Nagumo, Takefumi Murayama, Jun Zhang, Liqing MOE-Microsoft Key Laboratory for Intelligent Computing and Intelligent Systems Dep. of Computer Science and Engineering Shanghai Jiao Tong Univ. Shanghai China SONY Corporation Tokyo Japan

ISBN: (纸本)9783642420504

This paper presents a novel image denoising framework using overcomplete topographic model. To adapt to the statistics of natural images, we impose sparseness constraints on the denoising model. Based on the overcomplete topographic model, our denoising system improves over previous work on the following aspects: multi-category based sparse coding, adaptive learning, local normalization, and shrinkage function. A large number of simulations have been performed to show the performance of the modified model, demonstrating that the proposed model achieves better denoising performance. © Springer-Verlag 2013.

关键词： Shrinkage

来源：评论

学校读者我要写书评

暂无评论

Hybrid rule-based algorithm for coreference resolution

Hybrid rule-based algorithm for coreference resolution

引用

2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, EMNLP-CoNLL 2012 - Shared Task: Modeling Multilingual Unrestricted Coreference in OntoNotes

作者： Shou, Heming Zhao, Hai Center for Brain-Like Computing and Machine Intelligence Department of Computer Science and Engineering Shanghai Jiao Tong University China MOE-Microsoft Key Laboratory for Intelligent Computing and Intelligent Systems Shanghai Jiao Tong University China

ISBN: (纸本)9781937284459

This paper describes our coreference resolution system for the CoNLL-2012 shared task. Our system is based on the Stanford's dcoref deterministic system which applies multiple sieves with the order from high precision to low precision to generate coreference chains. We introduce the newly added constraints and sieves and discuss the improvement on the original system. We evaluate the system using OntoNotes data set and report our results of average F-score 58.25 in the closed track. © 2012 Association for Computational Linguistics.

关键词： Sieves

来源：评论

学校读者我要写书评

暂无评论

Labeled Alignment for Recognizing Textual Entailment 6

Labeled Alignment for Recognizing Textual Entailment

引用

6th International Joint Conference on Natural Language Processing, IJCNLP 2013

作者： Wang, Xiao-Lin Zhao, Hai Lu, Bao-Liang Center for Brain-Like Computing and Machine Intelligence MOE-Microsoft Key Laboratory for Intelligent Computing and Intelligent Systems Department of Computer Science and Engineering Shanghai Jiao Tong University 800 Dongchuan Road Shanghai 200240 China

ISBN: (纸本)9784990734800

Recognizing Textual Entailment (RTE) is to predict whether one text fragment can semantically infer another, which is required across multiple applications of natural language processing. The conventional alignment scheme, which is developed for machine translation, only marks the paraphrases and hyponyms to justify the entailment pairs, while provides less support for the non-entailment ones. This paper proposes a novel alignment scheme, named labeled alignment, to address this problem, which introduces negative links to explicitly mark the contradictory expressions to justify the non-entailment pairs. Thus the alignment-based RTE method employing the proposed scheme, compared with those employing the conventional one, can gain accuracy improvement through actively detecting the signals of non-entailment. The experimental results on the data sets of two shared RTE tasks indicate the implemented system significantly outperforms both the baseline system and all the other submitted systems. © IJCNLP *** right reserved.

关键词： Alignment

来源：评论

学校读者我要写书评

暂无评论

Chinese coreference resolution via ordered filtering

Chinese coreference resolution via ordered filtering

引用

作者： Zhang, Xiaotian Wu, Chunyang Zhao, Hai Center for Brain-Like Computing and Machine Intelligence Department of Computer Science and Engineering Shanghai Jiao Tong University China MOE-Microsoft Key Laboratory for Intelligent Computing and Intelligent Systems Shanghai Jiao Tong University China

ISBN: (纸本)9781937284459

We in this paper present the model for our participation (BCMI) in the CoNLL-2012 Shared Task. This paper describes a pure rule-based method, which assembles different filters in a proper order. Different filters handle different situations and the filtering strategies are designed manually. These filters are assigned to different ordered tiers from general to special cases. We participated in the Chinese and English closed tracks, scored 51.83 and 59.24 respectively. © 2012 Association for Computational Linguistics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Grammatical error correction as multiclass classification with single model 17

Grammatical error correction as multiclass classification wi...

引用

17th Conference on Computational Natural Language Learning: Shared Task, CoNLL 2013

作者： Jia, Zhongye Wang, Peilu Zhao, Hai MOE-Microsoft Key Laboratory for Intelligent Computing and Intelligent Systems Center for Brain-Like Computing and Machine Intelligence Department of Computer Science and Engineering Shanghai Jiao Tong University 800 Dongchuan Road Shanghai200240 China

ISBN: (纸本)9781937284718

This paper describes our system in the shared task of CoNLL-2013. We illustrate that grammatical error detection and correction can be transformed into a multiclass classification task and implemented as a single-model system regardless of various error types with the aid of maximum entropy modeling. Our system achieves the F1 score of 17.13% on the standard test set. © 2013 Association for Computational Linguistics.

关键词： Error correction

来源：评论

学校读者我要写书评

暂无评论

KySS 1.0: a Framework for Automatic Evaluation of Chinese Input Method Engines 6

KySS 1.0: a Framework for Automatic Evaluation of Chinese In...

引用

6th International Joint Conference on Natural Language Processing, IJCNLP 2013

作者： Jia, Zhongye Zhao, Hai MOE-Microsoft Key Laboratory for Intelligent Computing and Intelligent Systems Center for Brain-Like Computing and Machine Intelligence Department of Computer Science and Engineering Shanghai Jiao Tong University 800 Dongchuan Road Shanghai200240 China

ISBN: (纸本)9784990734800

Chinese Input Method Engine (IME) plays an important role in Chinese language processing. However, it has been subjected to lacking a proper evaluation metric for a long time. The natural metric for IME is user experience, which is a rather vague goal for research purpose. We propose a novel approach of quantifying user experience by using keystroke count and then correspondingly develop a framework of IME evaluation, which is fast and accurate. With the underlying linguistic background, the proposed evaluation framework can properly model the user behavior as Chinese is input through English keyboard. It is helpful to point out a way to improve the current Chinese IME performance. © IJCNLP *** right reserved.

关键词： Engines

来源：评论

学校读者我要写书评

暂无评论

A game theoretic model and tree analysis method for fair exchange protocols

A game theoretic model and tree analysis method for fair exc...

引用

5th International Conference on Theoretical Aspects of Software Engineering, TASE 2011

作者： Li, Guoqiang Gu, Yonggen Tao, Xiuting Tao, Jie School of Software Shanghai Jiao Tong University MOE-MS Key Laboratory for Intelligent Computing and Intelligent Systems Shanghai China School of Information and Engineering Huzhou Teachers College Zhejiang China College of Mathematics Physics and Information Engineering Zhejiang Normal University China

ISBN: (纸本)9780769545066

Exchange protocols are an important theoretic basis to make secure electronic commerce and electronic business transactions possible, in which the fairness is a crucial property. To ensure and verify the property, a specific model is proposed, based on the extensive game with imperfect information. Fairness is built in the protocol game and the corresponding game tree. To verify the property, a tree analysis method is offered, and a linear time algorithm is given. As a case study, some flaws of ASW protocol are found. © 2011 IEEE.

关键词： Game theory

来源：评论

学校读者我要写书评

暂无评论

Emotion classification based on gamma-band EEG

Emotion classification based on gamma-band EEG

引用

31st Annual International Conference of the IEEE Engineering in Medicine and Biology Society: Engineering the Future of Biomedicine, EMBC 2009

作者： Li, Mu Lu, Bao-Liang Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai 200240 China MOE-Microsoft Key Laboratory for Intelligent Computing and Intelligent Systems Shanghai Jiao Tong University Shanghai 200240 China

ISBN: (纸本)9781424432967

In this paper, we use EEG signals to classify two emotions-happiness and sadness. These emotions are evoked by showing subjects pictures of smile and cry facial expressions. We propose a frequency band searching method to choose an optimal band into which the recorded EEG signal is filtered. We use common spatial patterns (CSP) and linear-SVM to classify these two emotions. To investigate the time resolution of classification, we explore two kinds of trials with lengths of 3s and 1s. Classification accuracies of 93:5% ± 6:7% and 93:0%±6:2% are achieved on 10 subjects for 3s-trials and 1s-trials, respectively. Our experimental results indicate that the gamma band (roughly 30-100 Hz) is suitable for EEG-based emotion classification. ©2009 IEEE.

关键词： Signal processing

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：