期刊:
Lecture Notes in Computer Science,2016年10102:583-594 ISSN:0302-9743
通讯作者:
Zong, Chengqing
作者机构:
[Li, Junjie; Zong, Chengqing] Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing, Peoples R China.;[Yang, Haitong] Univ Chinese Acad Sci, Beijing, Peoples R China.;[Li, Junjie; Zong, Chengqing] Cent China Normal Univ, Sch Comp, Wuhan 430079, Peoples R China.
通讯机构:
[Zong, Chengqing] C;Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing, Peoples R China.;Cent China Normal Univ, Sch Comp, Wuhan 430079, Peoples R China.
会议名称:
5th International Conference on Natural Language Processing and Chinese Computing (NLPCC) / 24th International Conference on Computer Processing of Oriental Languages (ICCPOL)
会议时间:
DEC 02-06, 2016
会议地点:
Kunming Univ Sci & Technol, Kunming, PEOPLES R CHINA
作者机构:
[杨从平] Department of Economics and Management, Guangxi Normal University for Nationalities, Chongzuo, 532200, China;[郑世珏; 党永杰; 杨从平; 杨青] School of Computer, Central China Normal University, Wuhan, 430079, China
作者机构:
[He, Tingting; Zhou, Guangyou; Zhou, Yin] Cent China Normal Univ, Sch Comp, Wuhan 430079, Peoples R China.;[Wu, Wensheng] Univ So Calif, Dept Comp Sci, Los Angeles, CA 90089 USA.
通讯机构:
[Zhou, Guangyou] C;Cent China Normal Univ, Sch Comp, Wuhan 430079, Peoples R China.
关键词:
Community question answering;Question retrieval;Text mining;Yahoo! Answers
摘要:
Learning the semantic representation using neural network architecture.The neural network is trained via pre-training and fine-tuning phase.The learned semantic level feature is incorporated into a LTR framework. In community question answering (cQA), users pose queries (or questions) on portals like Yahoo! Answers which can then be answered by other users who are often knowledgeable on the subject. cQA is increasingly popular on the Web, due to its convenience and effectiveness in connecting users with queries and those with answers. In this article, we study the problem of finding previous queries (e.g., posed by other users) which may be similar to new queries, and adapting their answers as the answers to the new queries. A key challenge here is to the bridge the lexical gap between new queries and old answers. For example, "company" in the queries may correspond to "firm" in the answers. To address this challenge, past research has proposed techniques similar to machine translation that "translate" old answers to ones using the words in the new queries. However, a key limitation of these works is that they assume queries and answers are parallel texts, which is hardly true in reality. As a result, the translated or rephrased answers may not look intuitive.In this article, we propose a novel approach to learn the semantic representation of queries and answers by using a neural network architecture. The learned semantic level features are finally incorporated into a learning to rank framework. We have evaluated our approach using a large-scale data set. Results show that the approach can significantly outperform existing approaches. Learning the semantic representation using neural network architecture.The neural network is trained via pre-training and fine-tuning phase.The learned semantic level feature is incorporated into a LTR framework. In community question answering (cQA), users pose queries (or questions) on portals like Yahoo! Answers which can then be answered by other users who are often knowledgeable on the subject. cQA is increasingly popular on the Web, due to its convenience and effectiveness in connecting users with queries and those with answers. In this article, we study the problem of finding previous queries (e.g., posed by other users) which may be similar to new queries, and adapting their answers as the answers to the new queries. A key challenge here is to the bridge the lexical gap between new queries and old answers. For example, "company" in the queries may correspond to "firm" in the answers. To address this challenge, past research has proposed techniques similar to machine translation that "translate" old answers to ones using the words in the new queries. However, a key limitation of these works is that they assume queries and answers are parallel texts, which is hardly true in reality. As a result, the translated or rephrased answers may not look intuitive.In this article, we propose a novel approach to learn the semantic representation of queries and answers by using a neural network architecture. The learned semantic level features are finally incorporated into a learning to rank framework. We have evaluated our approach using a large-scale data set. Results show that the approach can significantly outperform existing approaches.
摘要:
Here we propose a trajectory privacy model to solve privacy and security problems with radio-frequency identification (RFID) systems. The model first formalizes an Adversary Model and then defines an adversary indistinguishability privacy game and interval security privacy game according to the ability of the adversary. Based on the privacy game between adversary and challenger, the author gives the definition of weak trajectory privacy and strong trajectory privacy. Finally, we analyzed the privacy protection level of present RFID systems with the help of this trajectory privacy model. It can be seen that the trajectory privacy model can effectively analyze and find the privacy vulnerabilities of RFID security protocols.
作者机构:
[Tan, Liansheng; Ge, Fei] Huazhong Normal Univ, Dept Comp Sci, 152 Luoyu Rd, Wuhan 430079, Hubei, Peoples R China.
通讯机构:
[Tan, Liansheng] H;Huazhong Normal Univ, Dept Comp Sci, 152 Luoyu Rd, Wuhan 430079, Hubei, Peoples R China.
关键词:
Dynamic path service;Blocking probability approximation;Flexi-grid networks
摘要:
The blocking probability to the path requests is an important issue in flexible bandwidth optical communications. In this paper, we propose a blocking probability approximation method of path requests in flexi-grid networks. It models the bundled neighboring carrier allocation with a group of birth-death processes and provides a theoretical analysis to the blocking probability under variable bandwidth traffic. The numerical results show the effect of traffic parameters to the blocking probability of path requests. We use the first fit algorithm in network nodes to allocate neighboring carriers to path requests in simulations, and verify approximation results. (C) 2016 Elsevier Inc. All rights reserved.
期刊:
Lecture Notes in Computer Science,2016年10102:300-311 ISSN:0302-9743
通讯作者:
Zhou, Guangyou
作者机构:
[He, Tingting; Zeng, Zhao; Zhou, Guangyou; Xie, Zhiwen] Cent China Normal Univ, Sch Comp, Wuhan 430079, Peoples R China.
通讯机构:
[Zhou, Guangyou] C;Cent China Normal Univ, Sch Comp, Wuhan 430079, Peoples R China.
会议名称:
第五届自然语言处理与中文计算会议(NLPCC-ICCPOL2016)
会议时间:
2016-12-02
会议地点:
昆明
会议主办单位:
Kunming Univ Sci & Technol
会议论文集名称:
第五届自然语言处理与中文计算会议(NLPCC-ICCPOL2016)论文集
摘要:
This paper focuses on the task of knowledge-based question answering (KBQA). KBQA aims to match the questions with the structured semantics in knowledge base. In this paper, we propose a two-stage method. Firstly, we propose a topic entity extraction model (TEEM) to extract topic entities in questions, which does not rely on hand-crafted features or linguistic tools. We extract topic entities in questions with the TEEM and then search the knowledge triples which are related to the topic entities from the knowledge base as the candidate knowledge triples. Then, we apply Deep Structured Semantic Models based on convolutional neural network and bidirectional long short-term memory to match questions and predicates in the candidate knowledge triples. To obtain better training dataset, we use an iterative approach to retrieve the knowledge triples from the knowledge base. The evaluation result shows that our system achieves an \(\text {Average} F_1\) measure of 79.57% on test dataset.
摘要:
Visualization is an important method of data analysis in the study of microbiome, with the dimensionality reduction techniques as its prerequisites for high-dimensional data. Multidimensional scaling (MDS), as a popular method for data visualization, can provide a low-dimensional representation of the original data utilizing its distance matrix. Meanwhile, the unique fraction metric (UniFrac) is a very reasonable and biologically meaningful metric for calculating distance matrices through a phylogenetic tree constructed from microbiome data. However, due to the complexity of the phylogenetic tree and the notable high dimensionality of the microbiome data, applying the MDS with UniFrac would require costly calculations. In this paper, we propose a novel dimensionality reduction algorithm based on Laplace matrix (DRLM) for microbiome data analysis. The experimental results from both synthesized and real microbiome data demonstrate the proposed DRLM is able to conduct more distinct clustering while significantly reducing the computational cost for the dimensionality reduction and visualization in the microbiome data analysis.
摘要:
Secret sharing (SS) is one of the most important cryptographic primitives used for data outsourcing. The (t, n,) SS was introduced by Shamir and Blakley separately in 1979. The secret sharing policy of the (t, n) threshold SS is far too simple for many applications because it assumes that every shareholder has equal privilege to the secret or every shareholder is equally trusted. Ito et al. introduced the concept of a general secret sharing scheme (GSS). In a GSS, a secret is divided among a set of shareholders in such a way that any "qualified" subset of shareholders can access the secret, but any "unqualified" subset of shareholders cannot access the secret. The secret access structure of GSS is far more flexible than threshold SS. In this paper, we propose an optimized implementation of GSS. Our proposed scheme first uses Boolean logic to derive two important subsets, one is called Min which is the minimal positive access subset and the other is called Max which is the maximal negative access subset, of a given general secret sharing structure. Then, conditions of parameters of a GSS are established based on these two important subsets. Furthermore, integer linear/non-linear programming is used to optimize the size of shares of a GSS. The complexity of linear/non-linear programming is O(n), where n is the number of shares generated by the dealer. This proposed design can be applied to implement GSS based on any classical SS. However, our proposed method is limited to be applicable to some general secret sharing policies. We use two GSSs, one is based on Shamir's weighted SS (WSS) using linear polynomial and the other is based on Asmuth-Bloom's SS using Chinese Remainder Theorem (CRT), to demonstrate our design. In comparing with existing GSSs, our proposed scheme is more efficient and can be applied to all classical SSs. (C) 2016 Elsevier Inc. All rights reserved.
期刊:
IET Systems Biology,2016年10(3):107-115 ISSN:1751-8849
通讯作者:
Jin, Cong
作者机构:
[Jin, Cong] Cent China Normal Univ, Sch Comp, Wuhan 430079, Peoples R China.;[Jin, Shu-Wei] Ecole Normale Super, Dept Phys, 24 Rue Lhomond, F-75231 Paris 5, France.
通讯机构:
[Jin, Cong] C;Cent China Normal Univ, Sch Comp, Wuhan 430079, Peoples R China.
摘要:
A number of different gene selection approaches based on gene expression profiles (GEP) have been developed for tumour classification. A gene selection approach selects the most informative genes from the whole gene space, which is an important process for tumour classification using GEP. This study presents an improved swarm intelligent optimisation algorithm to select genes for maintaining the diversity of the population. The most essential characteristic of the proposed approach is that it can automatically determine the number of the selected genes. On the basis of the gene selection, the authors construct a variety of the tumour classifiers, including the ensemble classifiers. Four gene datasets are used to evaluate the performance of the proposed approach. The experimental results confirm that the proposed classifiers for tumour classification are indeed effective.
期刊:
International Journal of Emerging Technologies in Learning,2016年11(6):62-67 ISSN:1863-0383
通讯作者:
Zhang Hua
作者机构:
[Hua, Zhang] Fuyang Vocational and Technical College, Department of Electronic Engineering and Information Technology, Fuyang, Anhui, 236031, China;[Shi-Jue, Zheng; Hong, Xu; Hua, Zhang] Huazhong Normal University, Department of Computer Science, Wuhan, 430079, China
摘要:
To solve the problem of low WEB course resources utilization rate and help users quickly find the highquality course resources, a WEB course resources recommendation system based on WP algorithm was established. In this system, course resources were automatically classified using WP algorithm and a course quality evaluation model based on user implicit evaluation was also set up. The experimental results showed that the method had a very good classification effect and it could effectively narrow the scope of the resources searched by users and improve resource search quality.
作者机构:
[Chen, Jiageng] Computer School, Central China Normal University, Wuhan, 430079, China;[Fang, Junbin] Department of Optoelectronic Engineering, Jinan University, Guangzhou, 510632, China;[Su, Chunhua] School of Information Science, Japan Advanced Institute of Science and Technology, 1-1 Asahidai, Nomi, Ishikawa, 923-1292, Japan;[Samsudin, Azman; Teh, Je Sen] School of Computer Sciences, Universiti Sains Malaysia, George Town, Malaysia
会议名称:
Australasian Conference on Information Security and Privacy
摘要:
Effective appearance models are one critical factor for robust object tracking. In this paper, we introduce foreground feature saliency concept into the background modelling, and put forward a novel foreground saliency-based background-weighted histogram scheme (FSBWH) for target representation and tracking, which exploits salient features from both foreground and background. We think that background and foreground salient features are both crucial for target representation and tracking. Experimental results show that the proposed FSBWH scheme can improve the robustness and performance of tracker significantly especially in complex occlusions and similar background scenes.
期刊:
Lecture Notes in Computer Science,2016年9544:127-140 ISSN:0302-9743
通讯作者:
He, Tingting(tthe@mail.ccnu.edu.cn)
作者机构:
[Guo, Xiyue] National Engineering Research Center for E-learning, Central China Normal University, Wuhan, China;[Guo, Xiyue] School of Information Technology, Xingyi Normal University for Nationalities, Xingyi, China;[He, Tingting] School of Computer, Central China Normal University, Wuhan, China
期刊:
International Journal of Wireless and Mobile Computing,2016年11(3):190-197 ISSN:1741-1084
通讯作者:
Guo, Jinglei(guojinglei@mail.ccnu.edu.cn)
作者机构:
[Li, Zhijian; Guo, Jinglei] School of Computer Science, Central China Normal University, Wuhan, 430079, China;[Yang, Shengxiang] Centre for Computational Intelligence (CCI), School of Computer Science and Informatics, De Montfort Univesity, Leicester, LE1 9BH, United Kingdom
通讯机构:
School of Computer Science, Central China Normal University, Wuhan, China
摘要:
Differential evolution (DE) is one of the most powerful and popular evolutionary algorithms for real parameter global optimisation problems. However, the performance of DE highly depends on the selection of control parameters, e.g. the population size, scaling factor and crossover rate. How to set these parameters is a challenging task because they are problem dependent. In order to tackle this problem, a JADE variant, denoted CJADE, is proposed in this paper. In the proposed algorithm, the successful parameters are clustered with the k-means clustering algorithm to reduce the impact of poor parameters. Simulation results show that CJADE is better than, or at least comparable to, several state-of-the-art DE algorithms.
作者机构:
[Jin, Cong] Cent China Normal Univ, Sch Comp, Wuhan 430079, Peoples R China.;[Jin, Shu-Wei] Ecole Normale Super, Dept Phys, 24 Rue Lhomond, F-75231 Paris 5, France.
通讯机构:
[Jin, Cong] C;Cent China Normal Univ, Sch Comp, Wuhan 430079, Peoples R China.
摘要:
Statistical cryptanalysis is one of the most powerful tools to analyze symmetric key cryptographic primitives such as block ciphers. One of these attacks, the differential attack has been demonstrated to break a wide range of block ciphers. Block cipher proposals previously obtain a rough estimate of their security margin against differential attacks by counting the number of active S-Box along a differential path. However this method does not take into account the complex clustering effect of multiple differential paths. Analysis under full differential distributions have been studied for some extremely lightweight block ciphers such as KATAN and SIMON, but is still unknown for ciphers with relatively large block sizes. In this paper, we provide a framework to accurately estimate the full differential distribution of General Feistel Structure (GFS) block ciphers with relatively large block sizes. This framework acts as a convenient tool for block cipher designers to determine the security margin of their ciphers against differential attacks. We describe our theoretical model and demonstrate its correctness by performing experimental verification on a toy GFS cipher. We then apply our framework to two concrete GFS ciphers, LBlock and TWINE to derive their full differential distribution by using super computer. Based on the results, we are able to attack 25 rounds of TWINE-128 using a distinguishing attack, which is comparable to the best attack to date. Besides that, we are able to depict a correlation between the hamming weight of an input differential characteristic and the complexity of the attack. Based on the proposed framework, LBlock and TWINE have shown to have 178 and 208-bit security respectively.