作者机构:
[Wang, Yanru; Ma, Huifang; Zhang, Di] Northwest Normal Univ, Coll Comp Sci & Engn, Lanzhou 730070, Gansu, Peoples R China.;[Ma, Huifang] Guilin Univ Elect Technol, Guangxi Key Lab Trusted Software, Guilin 541004, Guangxi, Peoples R China.;[Zhao, Weizhong] Cent China Normal Univ, Sch Comp, Wuhan 430079, Hubei, Peoples R China.;[Shi, Zhongzhi] Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China.
会议名称:
18th IEEE International Conference on Data Mining Workshops (ICDMW)
会议时间:
NOV 17-20, 2018
会议地点:
Singapore, SINGAPORE
会议主办单位:
[Ma, Huifang;Zhang, Di;Wang, Yanru] Northwest Normal Univ, Coll Comp Sci & Engn, Lanzhou 730070, Gansu, Peoples R China.^[Ma, Huifang] Guilin Univ Elect Technol, Guangxi Key Lab Trusted Software, Guilin 541004, Guangxi, Peoples R China.^[Zhao, Weizhong] Cent China Normal Univ, Sch Comp, Wuhan 430079, Hubei, Peoples R China.^[Shi, Zhongzhi] Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China.
会议论文集名称:
IEEE International Conference on Data Mining
摘要:
Recommending valuable contents for microblog users is an important way to improve users' experiences. As high quality descriptors of user semantics, tags have always been used to represent users' interests or attributes. In this work, we propose a microblog recommendation approach via hypergraph random walk tag expansion and user social relation. More specifically, microblogs are considered as hyperedges and terms are taken as hypervertexs for each user, and the weighting strategies for both hyperedges and hypervertexs are established. Random walk is performed on the weighted hypergraph to obtain a number of terms as tags for users. And then the tag similarity matrix and the user-tag matrix can be constructed based on tag probability correlations and weight of each tag. Besides, the significance of user social relation is also considered for ecommendation. Moreover, an iterative updating scheme is developed to get the final user-tag matrix for computing the similarities between microblogs and users. Experimental results show that the algorithm is effective in microblog recommendation.
期刊:
Lecture Notes in Computer Science,2018年11108:464-474 ISSN:0302-9743
通讯作者:
Hu, Po
作者机构:
[Hu, Po; Hou, Liwei; Wang, Xia; Jiang, Xiaoping] Cent China Normal Univ, Sch Comp Sci, Wuhan 430079, Peoples R China.
通讯机构:
[Hu, Po] C;Cent China Normal Univ, Sch Comp Sci, Wuhan 430079, Peoples R China.
会议名称:
2018自然语言处理与中文计算国际会议(NLPCC2018)
会议时间:
2018-08-26
会议地点:
呼和浩特
会议主办单位:
[Jiang, Xiaoping;Hu, Po;Hou, Liwei;Wang, Xia] Cent China Normal Univ, Sch Comp Sci, Wuhan 430079, Peoples R China.
会议论文集名称:
2018自然语言处理与中文计算国际会议(NLPCC2018)论文集
关键词:
Abstractive summarization;Sequence to sequence model;Pointer-generator network;Topical keywords;Attention mechanism
摘要:
Recently sequence-to-sequence (Seq2Seq) model and its variants are widely used in multiple summarization tasks e.g., sentence compression, headline generation, single document summarization, and have achieved significant performance. However, most of the existing models for abstractive summarization suffer from some undesirable shortcomings such as generating inaccurate contents or insufficient summary. To alleviate the problem, we propose a novel approach to improve the summary’s informativeness by explicitly incorporating topical keywords information from the original document into a pointer-generator network via a new attention mechanism so that a topic-oriented summary can be generated in a context-aware manner with guidance. Preliminary experimental results on the NLPCC 2018 Chinese document summarization benchmark dataset have demonstrated the effectiveness and superiority of our approach. We have achieved significant performance close to that of the best performing system in all the participating systems.
期刊:
Lecture Notes in Computer Science,2018年10619:329-338 ISSN:0302-9743
通讯作者:
Hu, Po
作者机构:
[Hu, Po; Hou, Liwei] Cent China Normal Univ, Sch Comp Sci, Wuhan 430079, Hubei, Peoples R China.;[Bei, Chao] Global Tone Commun Technol Co Ltd, Beijing 100043, Peoples R China.
通讯机构:
[Hu, Po] C;Cent China Normal Univ, Sch Comp Sci, Wuhan 430079, Hubei, Peoples R China.
会议名称:
6th CCF International Conference on Natural Language Processing and Chinese Computing (NLPCC)
会议时间:
NOV 08-12, 2017
会议地点:
Dalian Univ Technol, Dalian, PEOPLES R CHINA
摘要:
Due to the difficulty of abstractive summarization, the great majority of past work on document summarization has been extractive, while the recent success of sequence-to-sequence framework has made abstractive summarization viable, in which a set of recurrent neural networks models based on attention encoder-decoder have achieved promising performance on short-text summarization tasks. Unfortunately, these attention encoder-decoder models often suffer from the undesirable shortcomings of generating repeated words or phrases and inability to deal with out-of-vocabulary words appropriately. To address these issues, in this work we propose to add an attention mechanism on output sequence to avoid repetitive contents and use the subword method to deal with the rare and unknown words. We applied our model to the public dataset provided by NLPCC 2017 shared task3. The evaluation results show that our system achieved the best ROUGE performance among all the participating teams and is also competitive with some state-of-the-art methods.
摘要:
Aiming at the problem of "learning defiance" and "information overload" brought by educating big data to learners, this paper proposes an online learning community personalized learning path recommendation algorithm based on ant colony algorithm: in terms of computing pheromone, it combines individuality. Based on the characteristics of the learning path, a learning path scoring method based on multi-factor fuzzy evaluation is proposed to quantify the learning path evaluation as a score to solve the problem that it is difficult for the subjective score to accurately represent the pheromone concentration; in terms of pheromone updating rules, The introduction of pheromone restriction intervals avoids the problems associated with excessive or small learning path pheromone concentration in global updating; in the calculation of the selection probability of local search, the positive and negative feedback effects of pheromones can be better used. Search for a local optimal solution. The related experiments show that this algorithm can effectively solve the recommendation of the personalized learning path of the online learning community.
作者机构:
[Jiang, Shouyong; Kaiser, Marcus; Krasnogor, Natalio] Newcastle Univ, Sch Comp, Newcastle Upon Tyne, Tyne & Wear, England.;[Guo, Jinglei] Cent China Normal Univ, Dept Comp Sci, Wuhan, Peoples R China.;[Yang, Shengxiang] De Montfort Univ, Sch Comp Sci & Informat, Leicester, Leics, England.
会议名称:
Genetic and Evolutionary Computation Conference (GECCO)
会议时间:
JUL 15-19, 2018
会议地点:
Kyoto, JAPAN
会议主办单位:
[Jiang, Shouyong;Kaiser, Marcus;Krasnogor, Natalio] Newcastle Univ, Sch Comp, Newcastle Upon Tyne, Tyne & Wear, England.^[Guo, Jinglei] Cent China Normal Univ, Dept Comp Sci, Wuhan, Peoples R China.^[Yang, Shengxiang] De Montfort Univ, Sch Comp Sci & Informat, Leicester, Leics, England.
关键词:
less detectable environment (LDE);environmental changes;dynamic multiobjective optimisation
摘要:
Multiobjective optimisation in dynamic environments is challenging due to the presence of dynamics in the problems in question. Whilst much progress has been made in benchmarks and algorithm design for dynamic multiobjective optimisation, there is a lack of work on the detectability of environmental changes and how this affects the performance of evolutionary algorithms. This is not intentionally left blank but due to the unavailability of suitable test cases to study. To bridge the gap, this work presents several scenarios where environmental changes are less likely to be detected. Our experimental studies suggest that the less detectable environments pose a big challenge to evolutionary algorithms. CCS CONCEPTS • Theory of computation → Evolutionary algorithms; • Computing methodologies → Optimization algorithms; KEYWORDS less detectable environment (LDE), environmental changes, dynamic multiobjective optimisation ACM Reference Format:
作者机构:
[Wei, Jiangyong; Yan, Yan] Zhongnan Univ Econ & Law, Sch Math & Stat, Wuhan 430073, Hubei, Peoples R China.;[Hu, Xiaohua] Cent China Normal Univ, Sch Comp, Wuhan 430079, Hubei, Peoples R China.;[Tian, Tianhai] Monash Univ, Sch Math Sci, Melbourne, Vic 3800, Australia.
会议名称:
IEEE International Conference on Bioinformatics and Biomedicine (BIBM) - Human Genomics
会议时间:
DEC 03-06, 2018
会议地点:
Madrid, SPAIN
会议主办单位:
[Yan, Yan;Wei, Jiangyong] Zhongnan Univ Econ & Law, Sch Math & Stat, Wuhan 430073, Hubei, Peoples R China.^[Hu, Xiaohua] Cent China Normal Univ, Sch Comp, Wuhan 430079, Hubei, Peoples R China.^[Tian, Tianhai] Monash Univ, Sch Math Sci, Melbourne, Vic 3800, Australia.
会议论文集名称:
IEEE International Conference on Bioinformatics and Biomedicine-BIBM
关键词:
protein-protein network;proteomics data;network inference;triple-negative breast cancer
摘要:
The advances in proteomic technologies have offered an unprecedented opportunity and valuable resources to reveal molecular targets for treatment. Although a number of approaches have been designed to develop mathematical models using the time series proteomic profiles, the recently published single-patient proteomic data raised substantial challenges for analysing these non-time series datasets. To address this issue, this work proposes the first attempt for designing mathematical models using the non-time series proteomic data. Using the triple-negative breast cancer (TNBC) as the test system, we first use the single-cell analysis algorithm to derive the pseudo-time trajectory of the protein activities. Our integrated approach includes both a top-down approach (namely the Gaussian graphical model) and a bottom-up approach (i.e. differential equation model) to reverse-engineer the regulatory network. Based on the information from GO-enrichment analysis and KEGG database, we select 16 proteins that are key components in the mitogen-activated protein (MAP) kinase pathways. We construct the structure of a network with 16 proteins and a dynamic model for a network of 12 proteins. The derived protein-protein relationships are partially supported by the established protein activation relationships, and our model also predicts potential protein relationships that may be confirmed by further experimental studies. In summary, our results suggest that the proposed integrated framework is an effective approach to reconstruct regulatory networks using non-time course proteomic data.
摘要:
Computation outsourcing is a vital cloud service that can be provided for users. Using the cloud to address complex computations is crucial to users with lightweight devices. However, computations may not be correctly executed by the cloud due to monetary reasons. In this paper, we propose a secure publicly verifiable computation scheme in cloud computing, which is designed based on the polynomial commitment. Owing to the public key de-commitment of the polynomial commitment, our scheme can provide public verifiability for computation results. Security analysis shows that the proposed scheme is correct and can support public verifiability. Comparison and simulation results reveal that our scheme can be performed with low computational cost compared to previous schemes.
摘要:
According to the growth of reality demand of digital media, the 5.1 surround is widely used and researched. To further improve the listening experience of the 5.1 channel audio, the primary-ambient extraction (PAE) is introduced to facilitate flexible rendering in spatial audio reproduction. The common multichannel PAE approach is principle component analysis (PCA), which suffers from high extraction errors and long computation time. In this letter, we proposed a novel approach based on channel pair for 5.1 channel audio, which considers the five channels as a set of channel pairs. Then a linear estimation framework is applied at any one time to only one pair, which converts the problem of PAE into the estimation of weight matrix, thus the weight of each component can be computed by using the Least Square. The experimental results indicate that the novel approach significantly outperforms the existing approach PCA.
摘要:
Dynamic network is drawing more and more attention due to its potential in capturing time-dependent phenomena such as online public opinion and biological system. Microbial interaction networks that model the microbial system are often dynamic, static analysis methods are difficult to obtain reliable knowledge on evolving communities. To fulfill this gap, a dynamic clustering approach based on evolutionary symmetric nonnegative matrix factorization (ESNMF) is used to analyze the microbiome time-series data. To our knowledge, this is the first attempt to extract dynamic modules across time-series microbial interaction network. ESNMF systematically integrates temporal smoothness cost into the objective function by simultaneously refining the clustering structure in the current network and minimizing the clustering deviation in successive timestamps. We apply the proposed framework on a human microbiome datasets from infants delivered vaginally and ones born via C-section. The proposed method cannot only identify the evolving modules related to certain functions of microbial communities, but also discriminate differences in two kinds of networks obtained from infants delivered vaginally and via C-section.
作者机构:
[Zhu, Qiang] Cent China Normal Univ, Sch Informat Management, Wuhan 430079, Hubei, Peoples R China.;[Jiang, Xingpeng; He, Tingting; Hu, Xiaohua; Pan, Min; Hu, XH; Liu, Lei; Li, Bojing] Cent China Normal Univ, Sch Comp, Wuhan 430079, Hubei, Peoples R China.;[Hu, Xiaohua] Drexel Univ, Coll Comp & Informat, Philadelphia, PA 19104 USA.
会议名称:
IEEE International Conference on Bioinformatics and Biomedicine (BIBM) - Human Genomics
会议时间:
DEC 03-06, 2018
会议地点:
Madrid, SPAIN
会议主办单位:
[Zhu, Qiang] Cent China Normal Univ, Sch Informat Management, Wuhan 430079, Hubei, Peoples R China.^[Pan, Min;Liu, Lei;Li, Bojing;He, Tingting;Jiang, Xingpeng;Hu, Xiaohua] Cent China Normal Univ, Sch Comp, Wuhan 430079, Hubei, Peoples R China.^[Hu, Xiaohua] Drexel Univ, Coll Comp & Informat, Philadelphia, PA 19104 USA.
会议论文集名称:
IEEE International Conference on Bioinformatics and Biomedicine-BIBM
摘要:
With the rapid advancement of DNA sequencing, metagenomics and metatranscriptomics have made great progress, which deepen our understanding on the human microbiome and its impact on human health and diseases. The microbiome, which is characterized by small samples, high dimensions and complicated relationships with hosts, refers to the species, genes and genomes of the microbiota, as well as the products of the microbiota and the host environment. In fact, many machine learning methods have been used to conduct Microbiome-Wide Association Studies which can link the microbiome with the phenotypes, such as the status of human health and diseases. However, existing methods such as Support Vector Machines (SVMs) have some limitations on deep representation learning with deep architectures which can promote the reuse of features and potentially lead to progressively more abstract features at higher layers of representations. Recently, Deep Neural Networks (DNNs), a kind of deep learning models, are widely used for metagenomic data analysis and can perform well on representation learning. But they are considered as a black box and sufferring from criticisms due to theirs lacking of interpretability. Thus, it is interesting to explore other deep learning models for metagenomic data analysis. In this work, we introduce a deep learning model called Deep Forest to study the microbiome associations and we also present an ensemble method for feature selection. Experimental results show that Deep Forest outperforms the traditional machine learning methods. In addition, compared to DNNs, Deep Forest has better interpretability and less hyperparameters.
期刊:
PROCEEDINGS 2018 IEEE INTERNATIONAL CONFERENCE ON BIOINFORMATICS AND BIOMEDICINE (BIBM),2018年:197-200 ISSN:2156-1125
通讯作者:
Hu, XH
作者机构:
[Ma, Yingjun] Cent China Normal Univ, Sch Math & Stat, Wuhan, Hubei, Peoples R China.;[Ge, Leixin] Cent China Normal Univ, Sch Life Sci, Wuhan, Hubei, Peoples R China.;[Ma, Yuanyuan] Anyang Normal Univ, Sch Comp & Informat Engn, Anyang, Peoples R China.;[Jiang, Xingpeng; He, Tingting; Hu, Xiaohua; Hu, XH] Cent China Normal Univ, Sch Comp, Wuhan, Hubei, Peoples R China.
通讯机构:
[Hu, XH] C;Cent China Normal Univ, Sch Comp, Wuhan, Hubei, Peoples R China.
会议名称:
IEEE International Conference on Bioinformatics and Biomedicine (BIBM)
会议时间:
DEC 03-06, 2018
会议地点:
Madrid, SPAIN
会议主办单位:
[Ma, Yingjun] Cent China Normal Univ, Sch Math & Stat, Wuhan, Hubei, Peoples R China.^[Ge, Leixin] Cent China Normal Univ, Sch Life Sci, Wuhan, Hubei, Peoples R China.^[Ma, Yuanyuan] Anyang Normal Univ, Sch Comp & Informat Engn, Anyang, Peoples R China.^[Jiang, Xingpeng;He, Tingting;Hu, Xiaohua] Cent China Normal Univ, Sch Comp, Wuhan, Hubei, Peoples R China.
会议论文集名称:
IEEE International Conference on Bioinformatics and Biomedicine-BIBM
摘要:
Studies have shown that microRNAs are functionally related to human diseases. However, experimental methods for detecting miRNA-disease associations are both time consuming and laborious. Therefore, a large number of computational models for predicting potential miRNA-disease interaction have been proposed. However, few methods take into account the nonlinear structural similarity of miRNAs (diseases) and effectively integrate multiple similar metrics into one network. In this paper, we propose a kernel-based soft-neighborhood network propagation algorithm (LKSNF) to predict potential miRNA-disease interactions, which not only exploits the potential nonlinear relationship, but also effectively integrates different similar measures of miRNA (disease). The results of the 5-fold cross-validation show that the LKSNF model has significantly better predictive performance than other state-of-the-art methods. Case study further illustrates the effectiveness of LKSNF in predicting new miRNA-disease interactions.
作者机构:
[Shen, Xianjun; Hu, Xiaohua; Zhu, Huan; Jiang, Xingpeng; Yang, Jincai] Cent China Normal Univ, Sch Comp, Wuhan, Hubei, Peoples R China.;[Hu, Xiaohua] Drexel Univ, Coll Comp & Informat, Philadelphia, PA 19104 USA.
会议名称:
14th International Conference on Intelligent Computing (ICIC)
会议时间:
AUG 15-18, 2018
会议地点:
Wuhan, PEOPLES R CHINA
会议主办单位:
[Shen, Xianjun;Zhu, Huan;Jiang, Xingpeng;Hu, Xiaohua;Yang, Jincai] Cent China Normal Univ, Sch Comp, Wuhan, Hubei, Peoples R China.^[Hu, Xiaohua] Drexel Univ, Coll Comp & Informat, Philadelphia, PA 19104 USA.
会议论文集名称:
Lecture Notes in Artificial Intelligence
关键词:
Microbe-disease associations;Bi-Random Walk;Computational prediction model
摘要:
An increasing number of clinical observations have confirmed that the microbes inhabiting in human body have critical impacts on the progression of human disease, which provides promising insights into understanding the mechanism of diseases. However, the known microbe-disease associations remain limited. So, we proposed Bi-Random Walk based on Multiple Path (BiRWMP) to predict microbe-disease associations. Leave-one-out cross-validation (LOOCV) and 5-fold cross-validation were adopted to demonstrate the capability of proposed method. BiRWMP performed better than other methods. Finally, we listed 2 common disease and potential microbes ranked at top 10, and we demonstrated its reasonableness through looking up literatures.
摘要:
The study of microbe-disease associations can be utilized as a valuable material for understanding disease pathogenesis. Developing a highly accurate algorithm model for predicting disease-related microbes will provide a basis for targeted treatment of the disease. In this paper, we propose an approach based on Kernelized Bayesian Matrix Factorization (KBMF) to predict microbe-disease association, based on the Gaussian interaction profile kernel similarity for microbes and diseases. The prediction performance of the method was evaluated by five-fold cross validation. KBMF achieved reliable results which is better than several state-of-the-art methods with around 8% improvement of AUC. Furthermore, case studies have demonstrated the reliability of the method.
期刊:
PROCEEDINGS OF THE 2018 IEEE INTERNATIONAL CONFERENCE ON PROGRESS IN INFORMATICS AND COMPUTING (PIC),2018年:180-184 ISSN:2474-0209
通讯作者:
Tang, Xiangru
作者机构:
[Tang, Xiangru] Peking Univ, Inst Comp Sci & Technol, Beijing, Peoples R China.;[Tang, Xiangru; Gao, Hanning; Gao, Junjie] Cent China Normal Univ, Sch Comp, Wuhan, Hubei, Peoples R China.
通讯机构:
[Tang, Xiangru] P;[Tang, Xiangru] C;Peking Univ, Inst Comp Sci & Technol, Beijing, Peoples R China.;Cent China Normal Univ, Sch Comp, Wuhan, Hubei, Peoples R China.
会议名称:
IEEE International Conference on Progress in Informatics and Computing (PIC)
会议时间:
DEC 14-16, 2018
会议地点:
Suzhou, PEOPLES R CHINA
会议主办单位:
[Tang, Xiangru] Peking Univ, Inst Comp Sci & Technol, Beijing, Peoples R China.^[Tang, Xiangru;Gao, Hanning;Gao, Junjie] Cent China Normal Univ, Sch Comp, Wuhan, Hubei, Peoples R China.
会议论文集名称:
Proceedings of the IEEE International Conference on Progress in Informatics and Computing
关键词:
language generation;Sequence-to-Sequence model;attention mechanism;copynet;Chinese knowledge graph
摘要:
Building human-computer interaction engines is a fundamental challenge in Artificial Intelligence, with the goal of building a system which can automatically talk to human in natural language. Therefore, the ability to ask thought-provoking questions and contain valuable information in a conversational system is obviously quite crucial and challenging. In this paper, we build a knowledge-based question generation(KBQG) system which can generate natural language questions based on the given knowledge triples to demonstrate how large-scale knowledge base can facilitate language understanding and generation. We propose to apply the neural SEQ2SEQ learning model to generate meaningful questions from the given triples. The encoder reads in triples and produces an answer-aware input representation, which is fed to the decoder to generate an answer-focused question. To he able to express semantics completely and guarantee semantic integrity, we develop a flexible copy-attention mechanism that automatically replicates words from triples when needed. Both automatic and human evaluation results show that our model achieves outstanding performance. Furthermore, we establish a new evaluation metrics called GLAVE(Generated Language's automatic vector-pooling evaluation) to measure the similarity by pooling of word embeddings instead of word overlapping information, on account of the diversity and uncertainty of utterances. There are also a series of experiments which can demonstrate the effectiveness of our model is much stronger than state-of-the-art baselines.
摘要:
Representation learning of knowledge graph aims to transform both the entities and relations into continuous low-dimensional vector space. Though there have been a variety of models for knowledge graph embedding, most existing latent-based models merely explain triples via latent features, while supplementary rich inference patterns hidden in the observed graph features have not been fully employed. For this reason, in this paper we propose the discriminative path-based embedding model (DPTransE) which jointly learns from the latent features and graph features. Our model builds interactions between these two features, and uses the graph features as the crucial prior to offer precise and discriminative embedding. Experimental results demonstrate that our method outperforms other baselines on the task of link prediction and entity classification.
摘要:
This work studies the emerging C-RAN market in a 5G wireless network where mobile operators lease computation and communication resources from the tower company to serve wireless users. We propose an online C-RAN auction where each mobile operator bids for three types of resources in a future time window: wireless spectrum at base stations (BSs), front-haul link capacities, and mobile BS instances at the mobile cloud. We target an online C-RAN auction that executes in polynomial time, elicits truthful bids from mobile operators, and maximizes the social welfare of the C-RAN eco-system with both spectrum cost at BSs and server cost at the mobile cloud considered. We show how the marriage of (i) a new Fenchel dual approach to convex optimization with (ii) the posted pricing framework for online auction design can help achieve the three goals simultaneously, and evaluate the efficiency of our online C-RAN auction through both theoretical analysis and empirical studies.