检索结果-内蒙古大学图书馆

23rd International Joint Conference on Artificial Intelligence, IJCAI 2013

作者： Zhou, Junsheng Xu, Juhong Qu, Weiguang School of Computer Science and Technology Nanjing Normal University China Jiangsu Research Center of Information Security and Privacy Technology China State Key Lab. for Novel Software Technology Nanjing University China

ISBN: (纸本)9781577356332

Discriminative structured prediction models have been widely used in many natural language processing tasks, but it is challenging to apply the method to semantic parsing. In this paper, by introducing hybrid tree as a latent structure variable to close the gap between the input sentences and output representations, we formulate semantic parsing as a structured prediction problem, based on the latent variable perceptron model incorporated with a tree edit-distance loss as optimization criterion. The proposed approach maintains the advantage of a discriminative model in accommodating flexible combination of features and naturally incorporates an efficient decoding algorithm in learning and inference. Furthermore, in order to enhance the efficiency and accuracy of inference, we design an effective approach based on vector space model to extract a smaller subset of relevant MR productions for test examples. Experimental results on publicly available corpus show that our approach significantly outperforms previous systems.

关键词： Inference engines

来源：评论

学校读者我要写书评

暂无评论

Non-sparse Infinite-Kernel Learning for Automated Identification of Alzheimer's Disease Using PET Imaging

Non-sparse Infinite-Kernel Learning for Automated Identifica...

引用

International Conference on Control, Automation, Robotics & Vision

作者： Yong Xia Shen Lu Wei Wei David Dagan Feng Yanning Zhang Shaanxi Key Lab of Speech & Image Information Processing (SAIIP) School of Computer Science Northwestern Polytechnical University Xi'an 710072 China Biomedical and Multimedia Information Technology (BMIT) Research Group School of Information Technologies The University of Sydney NSW2006 Australia

ISBN: (纸本)9781479952007

Multi-kernel learning machine (MKLM) has recently been introduced to the research of computer-aided dementia identification and pathology progress tracking. Despite its good performance especially in case of using heterogeneous data, such learning schema and its variants usually utilize a L-1 norm constraint that promotes sparse solutions, which may cause loss of potentially important information. In this paper, we propose the non-sparse infinite-kernel learning machine (NS-IKLM) for automated identification of Alzheimer cases from normal controls. In our approach, a modified constraint is utilized to promotes non-sparse solutions and kernel parameters are automatically tuned during the learning process. The proposed algorithm has been evaluated on a set of FDG-PET images selected from the Alzheimer's disease neuroimaing initiative (ADNI) cohort. Our results demonstrate that the proposed non-sparse NS-IKLM is able to achieve satisfying dementia identification at a relatively low computational cost.

关键词： Infinite kernel learning dementia FDG-PET ADNI

来源：评论

学校读者我要写书评

暂无评论

Improvement on Ahn et al.'s RSA P-homomorphic signature scheme

Improvement on Ahn et al.'s RSA P-homomorphic signature sche...

引用

8th International ICST Conference on Security and Privacy in Communication Networks, SecureComm 2012

作者： Wang, Zhiwei College of Computer Nanjing University of Posts and Telecommunications Nanjing Jiangsu 210003 China State Key Laboratory of Information Security Institute of Information Engineering Chinese Academy of Sciences Beijing 100190 China Jiangsu High Technology Research Key Laboratory for Wireless Sensor Networks Nanjing Jiangsu 210003 China Key Lab. of Broadband Wireless Communication and Sensor Network Technology Nanjing University of Posts and Telecommunications Ministry of Education Jiangsu Province Nanjing Jiangsu 210003 China

ISBN: (纸本)9783642368820

P-homomorphic signature is a general framework for computing on authenticated data, which is recently proposed by Ahn et al. With P-homomorphic signature, any third party can derive a signature on the object message m′ from a signature of m, if m′ and m satisfy P(m,m′) = 1 for some predicate P which denotes the authenticatable relationship between m′ and m. Ahn et al. proposed a RSA P-homomorphic signature scheme by using a RSA accumulator, which is very efficient in space. However, the computational cost of verification and derivation is very heavy. We present an improved P-homomorphic signature scheme based on factoring problem. In our construction, the time efficiency of both verification and derivation are much better than Ahn's scheme. © 2013 ICST Institute for computer Science, Social Informatics and Telecommunications Engineering.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Boosting prediction performance of protein-protein interaction hot spots by using structural neighborhood properties (extended abstract)

引用

17th Annual International Conference on Research in Computational Molecular Biology, RECOMB 2013

作者： Deng, Lei Guan, Jihong Wei, Xiaoming Yi, Yuan Zhou, Shuigeng Department of Computer Science and Technology Tongji University Shanghai China Shanghai Key Lab. of Intelligent Information Processing School of Computer Science Fudan University Shanghai China School of Software Central South University Changsha China

ISBN: (纸本)9783642371943

Binding of one protein to another in a highly specific manner to form stable complexes is critical in most biological processes, yet the mechanisms involved in the interaction of proteins are not fully clear. The identification of hot spots, a small subset of binding interfaces that account for the majority of binding free energy, is becoming increasingly important in understanding the principles of protein interactions. Despite experiments like alanine scanning mutagenesis and a variety of computational methods have been applied to this problem, comparative studies suggest that the development of accurate and reliable solutions is still in its infant stage. We developed PredHS (Prediction of Hot Spots), a computational method that can effectively identify hot spots on protein binding interfaces by using 38 optimally chosen properties. The optimal combination of features was selected from a set of 324 novel structural neighborhood properties by a two-step feature selection method consisting of a random forest algorithm and a sequential backward elimination method. We evaluated the performance of PredHS using a benchmark of 265 alanine-mutated interface residues (Dataset I) and a trimmed subset (Dataset II) with 10-fold cross validation. Compared with the state of the art approaches, PredHS achieves a significant improvement on the prediction quality, which stems from the new structural neighborhood properties, the novel way of feature generation as well as the selection power of the proposed two-step method. We further validated the capability of our method by an independent test and obtained promising results. The PredHS web server and supplementary data are available at http://***/predhs. © 2013 Springer-Verlag.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Tumor gene expressive data classification based on locally linear representation Fisher criterion

引用

9th International Conference on Intelligent Computing, ICIC 2013

作者： Li, Bo Tian, Bei-Bei Liu, Jin School of Computer Science and Technology Wuhan University of Science and Technology 430081 Wuhan China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan China State Key Lab. of Software Engineering Wuhan China

ISBN: (纸本)9783642394812

In this paper, a discriminant manifold learning method based on Locally Linear Embedding (LLE), which is named Locally Linear Representation Fisher Criterion (LLRFC), is proposed for the classification of tumor gene expressive data. In the proposed LLRFC, an inter-class graph and intra-class graph is constructed based on the class information of tumor gene expressive data, where the weights between nodes in both graph are optimized using locally linear representation trick. Moreover, a Fisher criterion is modeled to maximize the inter-class scatter and minimize the intra-class scatter simultaneously. Experiments on some benchmark tumor gene expressive data validate its efficiency. © 2013 Springer-Verlag.

关键词： Genes

来源：评论

学校读者我要写书评

暂无评论

ENERGY EFFICIENT DISTRIBUTED STEGANOGRAPHY FOR SECURE COMMUNICATION IN WIRELESS MULTIMEDIA SENSOR NETWORKS

引用

Journal of Electronics(China) 2013年第1期30卷 9-16页

作者： Lin Qiaomin Wang Ruchuan Ye Ning Wang Zhongqin College of Computer Nanjing University of Posts and Telecommunications Jiangsu High Technology Research Key Laboratory for Wireless Sensor Networks Key Lab of Broadband Wireless Communication and Sensor Network Technology (Nanjing University of Posts and Telecommunications) Ministry of Education Department of Information Science Nanjing College for Population Management

A secure communication mechanism is necessary in the applications of Wireless Multimedia Sensor Networks (WMSNs), which is more vulnerable to security attacks due to the presence of multimedia data. Additionally, given the limited technological resources (in term of energy, computation, bandwidth, and storage) of sensor nodes, security and privacy policies have to be combined with energy-aware algorithms and distributed processing of multimedia contents in WMSNs. To solve these problems in this paper, an energy efficient distributed steganography scheme, which combines steganography technique with the concept of distributed computing, is proposed for secure communication in WMSNs. The simulation results show that the proposed method can achieve considerable energy efficiency while assuring the communication security simultaneously.

关键词： Discrete Wavelet Transform （DWT） Distributed steganography Energy efficiency Perfect hash Wireless Multimedia Sensor Networks （WMSNs）

来源：评论

学校读者我要写书评

暂无评论

Research on network malicious code dendritic cell immune algorithm based on fuzzy weighted support vector machine

Research on network malicious code dendritic cell immune alg...

引用

6th China Conference of Wireless Sensor Networks, CWSN 2012

作者： Li, Peng Wang, Ruchuan Zhou, Yanting Dai, Qiuyu College of Computer Nanjing University of Posts and Telecommunications Nanjing Jiangsu 210003 China Jiangsu High Technology Research Key Laboratory for Wireless Sensor Networks Nanjing Jiangsu 210003 China Key Lab. of Broadband Wireless Communication and Sensor Network Technology Nanjing University of Posts and Telecommunications Ministry of Education Jiangsu Province Nanjing Jiangsu 210003 China College of Telecommunications and Information Engineering Nanjing University of Posts and Telecommunications Nanjing Jiangsu 210003 China

ISBN: (纸本)9783642362514

According to the significant impact on the accuracy rate of detection of current immune algorithms brought by incorrect classification of signal, it proposes network malicious code dendritic cell immune algorithm based on fuzzy weighted support vector machine. It summarizes and compares the pros and cons of the four methods, which are basic artificial intelligence immune algorithm, detection of unknown viruses based on immunity theory, malicious code immunity based on cryptography and automated intrusion response based on danger theory. It elaborates the process of the algorithm of the proposed immune algorithm, discusses a variety of input and output signals, gives the samples of the actual input signals, applies the coefficient of variation method to determine the values of the weights so as to enhance the discrimination ability of signal processing results, describes the principle and algorithm steps of fuzzy weighted support vector machine clustering method within immune algorithm proposed. By comparing the fuzzy aggregation before and after the immunization program experiments, it draws the conclusion that the proposed immune algorithm can optimize the input signal, fuzzy clustering the signal and the antigen, so as to bring down the number of immunization strategies and reduce the immune response time, as a result it improve the efficiency and performance of the immune system. © 2013 Springer-Verlag.

关键词： Cells

来源：评论

学校读者我要写书评

暂无评论

Kinetics and Modeling of Chemical Leaching of Sphalerite Concentrate Using Ferric Iron in a Redox-controlled Reactor

引用

Chinese Journal of Chemical Engineering 2013年第8期21卷 933-936页

作者：宋健高玲林建群吴洪斌林建强 State Key Lab of Microbial Technology Shandong University Department of Pharmacy and Biotechnology Zibo Vocational Institute Shandong Provincial Key Lab for Distributed Computer Software Novel Technology School of Information Science and EngineeringShandong Normal University Institute of Agro-products Processing Science and Technology Xinjiang Academy of Agricultural and Reclamation Science

This work presents a study for chemical leaching of sphalerite concentrate under various constant Fe3+ concentrations and redox potential conditions. The effects of Fe3+ concentration and redox potential on chemical leaching of sphalerite were investigated. The shrinking core model was applied to analyze the experimental results. It was found that both the Fe3+ concentration and the redox potential controlled the chemical leaching rate of sphalerite. A new kinetic model was developed, in which the chemical leaching rate of sphalerite was proportional to Fe3+ concentration and Fe3+ /Fe2+ ratio. All the model parameters were evaluated from the experimental data. The model predictions fit well with the experimental observed values.

关键词： sphalerite leaching kinetic model Fe3＋ concentration redox potential labVIEW

来源：评论

学校读者我要写书评

暂无评论

A novel neural network classification model based on covering and Affinity Propagation clustering algorithm

引用

Journal of Computational information Systems 2013年第7期9卷 2565-2573页

作者： Li, Hui Ding, Shifei School of Computer Science and Technology China University of Mining and Technology Xuzhou 221116 China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China Jiangsu Normal University Xuzhou 221116 China

Affinity Propagation (AP) algorithm can automatically determine the cluster center and does not need a pre-determined number of clustering. This paper presents a novel neural network classification model, using AP clustering method as a pre-processor to cluster high dimensional massive data samples, and combining covering algorithm to automatically determine the center of the covering, and calculating its radius, and then converting these parameters into the weights and thresholds of the hidden layer of classification neural network. The number of hidden layer neurons is the number of covering. The output layer is the M-P neuron layer. By evaluating the input feature of hidden layer to complete the mapping from covering to the output, and gain the corresponding output category of the input feature. Simulation results show that our proposed neural network classification model can get better performance. Copyright © 2013 Binary information Press.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Bivariate symmetry associated continued fractions blending rational interpolation

Bivariate symmetry associated continued fractions blending r...

引用

2013 5th International Conference on Computational and information Sciences, ICCIS 2013

作者： Zou, Le Li, Changwen Xie, Jin Li, Chuanlin Key Lab of Network and Intelligent Information Processing Hefei University Hefei China Department of Mathematics Huaibei Normal University Huaibei China Department of Mathematics and Physics Hefei University Hefei China Department of Computer Science and Technology Hefei University Hefei China

ISBN: (纸本)9780769550046

By introducing partial divided differences and partial inverse differences, bivariate symmetry associated continued fractions blending rational interpolation is constructed. We discuss the recursive algorithm, interpolation theorem and error estimation. We extend the conclusion to vector valued, matrix valued cases and the triangular net case. © 2013 IEEE.

关键词： Blending

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：