期刊:
JOURNAL OF THE ASSOCIATION FOR INFORMATION SCIENCE AND TECHNOLOGY,2020年71(3):282-299 ISSN:2330-1635
通讯作者:
Zhang, Jin
作者机构:
[Zhang, Jin; Wolfram, Dietmar] Univ Wisconsin, Sch Informat Studies, Milwaukee, WI 53201 USA.;[Chen, Ye] Cent China Normal Univ, Sch Informat Management, Wuhan, Peoples R China.;[Zhao, Yuehua] Nanjing Univ, Sch Informat Management, Nanjing, Peoples R China.;[Ma, Feicheng] Wuhan Univ, Sch Informat Management, Wuhan, Peoples R China.
通讯机构:
[Zhang, Jin] U;Univ Wisconsin, Sch Informat Studies, Milwaukee, WI 53201 USA.
摘要:
This study investigates the content of questions and responses about the Zika virus on Yahoo! Answers as a recent example of how public concerns regarding an international health issue are reflected in social media. We investigate the contents of posts about the Zika virus on Yahoo! Answers, identify and reveal subject patterns about the Zika virus, and analyze the temporal changes of the revealed subject topics over 4 defined periods of the Zika virus outbreak. Multidimensional scaling analysis, temporal analysis, and inferential statistical analysis approaches were used in the study. A resulting 2‐layer Zika virus schema, and term connections and relationships are presented. The results indicate that consumers’ concerns changed over the 4 defined periods. Consumers paid more attention to the basic information about the Zika virus, and the prevention and protection from the Zika virus at the beginning of the outbreak of the Zika virus. During the later periods, consumers became more interested in the role that the government and health organizations played in the public health emergency. This study investigates the content of questions and responses about the Zika virus on Yahoo! Answers as a recent example of how public concerns regarding an international health issue are reflected in social media. We investigate the contents of posts about the Zika virus on Yahoo! Answers, identify and reveal subject patterns about the Zika virus, and analyze the temporal changes of the revealed subject topics over 4 defined periods of the Zika virus outbreak. Multidimensional scaling analysis, temporal analysis, and inferential statistical analysis approaches were used in the study. A resulting 2‐layer Zika virus schema, and term connections and relationships are presented. The results indicate that consumers’ concerns changed over the 4 defined periods. Consumers paid more attention to the basic information about the Zika virus, and the prevention and protection from the Zika virus at the beginning of the outbreak of the Zika virus. During the later periods, consumers became more interested in the role that the government and health organizations played in the public health emergency.
作者:
Pan, Min;Huang, Jimmy Xiangji*;He, Tingting(何婷婷);Mao, Zhiming;Ying, Zhiwei;...
期刊:
JOURNAL OF THE ASSOCIATION FOR INFORMATION SCIENCE AND TECHNOLOGY,2020年71(3):264-281 ISSN:2330-1635
通讯作者:
Huang, Jimmy Xiangji
作者机构:
[Pan, Min] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Informat Retrieval & Knowledge Management Res Lab, Wuhan, Peoples R China.;[Pan, Min; Mao, Zhiming] Hubei Normal Univ, Sch Comp & Informat Engn, Huangshi, Hubei, Peoples R China.;[Huang, Jimmy Xiangji; Pan, Min; Ying, Zhiwei] York Univ, Sch Informat Technol, Informat Retrieval & Knowledge Management Res Lab, Toronto, ON, Canada.;[He, Tingting; Tu, Xinhui; Mao, Zhiming] Cent China Normal Univ, Sch Comp, Informat Retrieval & Knowledge Management Res Lab, Wuhan, Peoples R China.;[Ying, Zhiwei] Cent China Normal Univ, Sch Informat Management, Informat Retrieval & Knowledge Management Res Lab, Wuhan, Peoples R China.
通讯机构:
[Huang, Jimmy Xiangji] Y;York Univ, Sch Informat Technol, Informat Retrieval & Knowledge Management Res Lab, Toronto, ON, Canada.
摘要:
Pseudo-relevance feedback is a well-studied query expansion technique in which it is assumed that the top-ranked documents in an initial set of retrieval results are relevant and expansion terms are then extracted from those documents. When selecting expansion terms, most traditional models do not simultaneously consider term frequency and the co-occurrence relationships between candidate terms and query terms. Intuitively, however, a term that has a higher co-occurrence with a query term is more likely to be related to the query topic. In this article, we propose a kernel co-occurrence-based framework to enhance retrieval performance by integrating term co-occurrence information into the Rocchio model and a relevance language model (RM3). Specifically, a kernel co-occurrence-based Rocchio method (KRoc) and a kernel co-occurrence-based RM3 method (KRM3) are proposed. In our framework, co-occurrence information is incorporated into both the factor of the term discrimination power and the factor of the within-document term weight to boost retrieval performance. The results of a series of experiments show that our proposed methods significantly outperform the corresponding strong baselines over all data sets in terms of the mean average precision and over most data sets in terms of P@10. A direct comparison of standard Text Retrieval Conference data sets indicates that our proposed methods are at least comparable to state-of-the-art approaches.
摘要:
Knowledge flow between disciplines is typically measured through citations among publications. In this study, we quantify cross-disciplinary knowledge diffusion from the novel perspective of content by introducing knowledge memes, a special type of knowledge unit. Diffusion cascade is proposed to model the diffusion process of knowledge memes. By taking Medical Informatics (MI) as an exemplary interdisciplinary discipline, we measure the knowledge relationships between it and four related disciplines. The diffusion patterns of cross-disciplinary memes are also identified by analyzing the network structure of the diffusion cascade. The results present the knowledge relationships among disciplines measured by knowledge memes, which are different from those measured by citations. It is shown that preferential attachment takes effect in cross-disciplinary knowledge meme diffusion. In addition, cross-disciplinary knowledge memes generally originate earlier and have higher impact than the memes of MI. This study provides insights into new approaches to quantifying knowledge relationships among disciplines and furthers the understanding of content diffusion mechanisms through measurable knowledge units. (C) 2020 Elsevier Ltd. All rights reserved.
关键词:
Age progression regression;Generative adversarial networks;Image-to-image translation
摘要:
Face age progression/regression is enjoying renewed interest due to the remarkable improvements in image synthesis achieved by the deep generative models (e.g. the Generative Adversarial Networks (GANs)) and its tremendous impact on a wide-range of practical applications like finding back missing individuals with photos of childhood, entertainment, etc. Most existing approaches are focusing on face age progression and have proven to be successful and effective in learning the transformation between age groups with the aid of paired samples, i.e., face images of the same person at different ages. Although some signs of aging are synthesized by these approaches, they heavily rely on the availability of paired samples which are difficult and costly to collect. Inspired by the significant success achieved by using GANs in unsupervised image transduction, in this paper, we formulate this task as an unsupervised multi-domain image-to-image translation problem, and devise a novel generative framework using only a single generative adversarial network, dubbed FaceGAN which is capable of synthesizing photo-realistic face images with aging effects without paired samples and achieves face age progression and regression in a holistic framework. Experimental results show the superiority of our proposed method in terms of visual fidelity. We further empirically demonstrate the broad application capability of our approach on a facial attribute transfer and a facial expression synthesis tasks. (C) 2019 Elsevier B.V. All rights reserved.
作者机构:
[Li, Yu-Hai; Hu, Yan-Hong] Cent China Normal Univ, Dept Informat Management, Wuhan, Hubei, Peoples R China.;[Li, Yu-Hai; Hu, Yan-Hong] Cent China Normal Univ, Coll Vocat & Continuing Educ, Wuhan, Hubei, Peoples R China.;[Zhao, Ming] Yangtze Univ, Sch Comp Sci, Jingzhou, Peoples R China.
通讯机构:
[Li, Yu-Hai] C;Cent China Normal Univ, Dept Informat Management, Wuhan, Hubei, Peoples R China.;Cent China Normal Univ, Coll Vocat & Continuing Educ, Wuhan, Hubei, Peoples R China.
摘要:
This study proposes a method to reduce the carrying amount of Electrocardiogram (ECG) network transmission while preserving the original characteristics of ECG and protecting personal privacy. In watermarking part, we perform the quantization-based digital watermark encryption technology on the ECG signals to protect patient rights and information. In addition, the hidden information can be extracted without the original ECG. In compression part, we adopt the threshold-based compression technology to reduce the data amount of the ECG signal and preserve the original characteristics of ECG signals at the same time. The recovery of the compressed ECG signal adopts cubic spline. Experimental results verify the efficiency of the proposed method.
作者机构:
[Ying, Zhiwei] Cent China Normal Univ, Sch Informat Management, Wuhan 430079, Hubei, Peoples R China.;[Huang, Jimmy Xiangji; Ying, Zhiwei] York Univ, Sch Informat Technol, Informat Retrieval & Knowledge Management Res Lab, Toronto, ON M3J 1P3, Canada.;[Zhou, Jie] East China Normal Univ, Dept Comp Sci & Technol, Shanghai 200062, Peoples R China.;[Jian, Fanghong] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan 430079, Hubei, Peoples R China.;[He, Tingting] Cent China Normal Univ, Sch Comp Sci, Wuhan 430079, Hubei, Peoples R China.
通讯机构:
[Huang, Jimmy Xiangji] Y;York Univ, Sch Informat Technol, Informat Retrieval & Knowledge Management Res Lab, Toronto, ON M3J 1P3, Canada.
关键词:
digital signal processing;Information retrieval;probabilistic and statistical models
摘要:
Recently, researchers mainly focus on three categories of models in the field of Information Retrieval (IR), namely vector-space models, probabilistic models, and statistical language models. The existing studies have always developed IR models through refining or combining these traditional models. However, some new frameworks (e.g., digital signal processing (DSP)-based IR framework) have not been well-developed. In our research, we propose a new DSP-based IR Framework (DSPF) introducing the theories from the field of the DSP and present two corresponding DSP-based IR models, denoted as DSPF-BM25 and DSPF-DLM, which incorporate the term weighting schemes from two well-performed probabilistic IR models, the BM25, and the Dirichlet Language Model (DLM). In particular, first, we consider each query term as a spectrum with Gaussian form. Second, instead of transforming the signals from the time domain to frequency domain, we directly represent the query terms in the frequency domain. It is much more controllable and precise to adjust the values of the parameters for getting better performance of our proposed models. To testify the effectiveness of our proposed models, we conduct extensive experiments on seven standard datasets. The results show that in most cases our proposed models outperform the strong baselines in terms of MAP.
摘要:
With the development of national strategies (such as Industrial 4.0 and Made in China 2025), how to build digital enterprises and cultivate innovation capabilities of enterprises has become a critical problem to Chinese manufacturing enterprises. However, the literature on the specific path of information technology (IT) capabilities to the innovation of enterprises is still lacking a body of relevant empirical research. In particular, it has not yet thought to explore the information technology capabilities, digital transformation, and then innovation performance of manufacturing enterprises. By performing a questionnaire investigation for 138 Chinese manufacturing enterprises, this study adopted both a fuzzy-set qualitative comparative analysis (fsQCA) and structural equation modeling (SEM) to explore the set relations of the conjunctions and conditions and the statistical associations by studying the relationships among information technology capabilities, digital transformation and innovation performance. The results show that the positive impacts of information technology capabilities on the process innovation performance and the digital transformation, as well as the positive impacts of digital transformation on both process innovation performance and product innovation performance. Specifically, digital transformation takes on a new function of partial mediation of IT capabilities and process innovation performance, and digital transformation functions as a complete mediator for IT capabilities and product innovation performance. The combinations of causal recipes related to innovation performance are provided by a fuzzy-set qualitative comparative analysis (fsQCA). Through the analyses of SEM and fsQCA, this research develops the formation mechanisms of both process innovation performance and product innovation performance, and provides guidance for both IT and innovation management of manufacturing enterprises in China.
通讯机构:
[Dong, Qingxing] C;Cent China Normal Univ, Sch Informat Management, 152 Luoyu Rd, Wuhan 430079, Hubei, Peoples R China.
关键词:
Group decision making;Opinion dynamics;Co-evolving networks;Bounded confidence
摘要:
Polarization in a group's opinions drives to disagreements and dissent among individuals, which make it harder to achieve group satisfactory decisions. Within Group Decision Making (GDM) problems to soften disagreements, lots of consensus reaching processes (CRPs) have been proposed to converge opinions but rarely consider the existing dynamic relationships among the experts. Meanwhile, Opinion Dynamics studies the evolution of opinions based on the relationships existing among the group members by using Social Network Analysis (SNA). In real-world GDM problems the application of CRPs alone may not be enough to achieve the desired level of agreement when there is too much dissent among experts. In this paper, a novel framework is proposed that hybridizes both the process of making closer opinions realized by CRPs and the evolving relationships among experts based on SNA. This new framework addresses when it might be impossible to achieve the agreement through CRPs, which tries to achieve a potential consensus considering that if opinions are too polarized, maybe different stable opinions states are still suitable and easier to achieve by applying a SNA together with the CRP. This framework is further analyzed through simulation experiments for demonstrating its validity and some properties. (C) 2019 Elsevier Inc. All rights reserved.
作者:
Li, Xia*;Fong, Patrick S. W.;Dai, Shengli;Li, Yingchun
期刊:
Journal of Cleaner Production,2019年215:730-743 ISSN:0959-6526
通讯作者:
Li, Xia
作者机构:
[Li, Xia] Cent China Normal Univ, Sch Informat Management, Wuhan 430079, Hubei, Peoples R China.;[Fong, Patrick S. W.] Hong Kong Polytech Univ, Dept Bldg & Real Estate, Hong Kong 999077, Peoples R China.;[Li, Yingchun; Dai, Shengli] Cent China Normal Univ, Coll Publ Adm, Wuhan 430079, Hubei, Peoples R China.
通讯机构:
[Li, Xia] C;Cent China Normal Univ, Sch Informat Management, Wuhan 430079, Hubei, Peoples R China.
摘要:
Dramatically increased societal demands on the municipal services that contradict environmental protection and information processing capability oriented to resource utilization efficiency suffer from opposing simultaneous requirements. The smart city provides better solutions for urban areas which are increasing at an unprecedented speed. This paper presents an empirical study carried out to assess and analyze the development pattern of 35 smart cities in China using the principal component analysis (PCA) and back propagation (BP) neural network techniques. The proposed PCA-BP neural network assessment processing model is applied with six dimensional factors and twenty-two operating indices. With the feature extraction and performance score calculated via PCA, BP neural network is adopted for city classification to recognize the development differences in smart cities. The results indicate that the factor-driven impetus evolves into innovation-driven impetus, narrowing the gap from the holistic perspective between the first and middle-ranking groups, while two middle-ranking groups show a similar upward trend in terms of developing a smart economy through sustainable productivity in innovative enterprises and high-tech industry. To some extent, in response to a similar improving trend in the application of smart services, a distinct advantage of an individual index can be a complementary offset to unapparent holistic highlighting the reception of the lowest average points. Unbalanced development exists in two subaverage groups that are deficient in the initial inventory of smart infrastructure and demands. A relatively large difference exists in the smart mobility index among cities, whereas the opposite case is found concerning the smart environment index. Finally, corresponding optimized development pattern are recommended for building a sustainable smart city. (C) 2019 Elsevier Ltd. All rights reserved.
摘要:
As an interdisciplinary topic, human travel-choice behavior has attracted the interests of transportation managers, theoretical computer science researchers and economists. Recent studies on tacit coordination in iterated route choice games (i.e., a large number of subjects could achieve the transportation network equilibrium in limited rounds) have been driven by two questions. (1) Will learning behavior promote tacit coordination in route choice games? (2) Which learning model can best account for these choices/behaviors? To answer the first question, we choose a set of learning models and conduct extensive simulations to determine their success in accounting for major behavioral patterns. To answer the second question, we compare these models to one another by competitively testing their predictions on four different datasets. Although all the selected models account reasonably well for the slow convergence of the mean route choice to equilibrium, they account only moderately well for the mean frequencies of the round-to-round switches from one route to another and fail to appropriately account for substantial individual differences. The implications of these findings for model construction and testing are briefly discussed.
作者机构:
[Zuo, Zhiping; Li, Yanhui] Wuhan Coll, Sch Management, Wuhan 430212, Hubei, Peoples R China;[Fu, Jing] Wuhan Business Univ, Sch Business Adm, Wuhan 430056, Hubei, Peoples R China;[Li, Yanhui; Wu, Jianlin] Cent China Normal Univ, Sch Informat Management, Wuhan 430079, Hubei, Peoples R China;[Fu, Jing] Hubei Acad Agr Sci, Inst Agr Econ & Technol, Wuhan 430064, Hubei, Peoples R China
通讯机构:
[Fu, Jing] W;[Fu, Jing] H;Wuhan Business Univ, Sch Business Adm, Wuhan 430056, Hubei, Peoples R China. Hubei Acad Agr Sci, Inst Agr Econ & Technol, Wuhan 430064, Hubei, Peoples R China.
关键词:
scheduling problem;human resource;multi-skill;hybrid meta heuristic
摘要:
In situations where an organization has limited human resources and a lack of multi-skilled employees, organizations pay more and more attention to cost control and personnel arrangements. Based on the consideration of the service personnel scheduling as well as the routing arrangement, service personnel of different skills were divided into different types according to their multiple skills. A mathematical programming model was developed to reduce the actual cost of organization. Then, a hybrid meta heuristic that combines a tabu search algorithm with a simulated annealing was designed to solve the problem. This meta heuristic employs several neighborhood search operators and integrates the advantages of both the tabu search algorithm and the simulated annealing algorithm. Finally, the stability and validity of the algorithm were validated by the tests of several kinds of examples.
期刊:
Frontiers in Genetics,2019年10:491009 ISSN:1664-8021
通讯作者:
Jiang, Xingpeng
作者机构:
[Zhu, Qiang] Cent China Normal Univ, Sch Informat Management, Wuhan, Hubei, Peoples R China.;[Jiang, Xingpeng; He, Tingting; Pan, Min; Zhu, Qiang; Zhu, Qing] Cent China Normal Univ, Sch Comp, Wuhan, Hubei, Peoples R China.;[Jiang, Xingpeng; He, Tingting; Pan, Min; Zhu, Qing] Cent China Normal Univ, Hubei Prov Key Lab Artificial Intelligence & Smar, Wuhan, Hubei, Peoples R China.
通讯机构:
[Jiang, Xingpeng] C;Cent China Normal Univ, Sch Comp, Wuhan, Hubei, Peoples R China.;Cent China Normal Univ, Hubei Prov Key Lab Artificial Intelligence & Smar, Wuhan, Hubei, Peoples R China.
摘要:
The microbiome-wide association studies are to figure out the relationship between microorganisms and humans, with the goal of discovering relevant biomarkers to guide disease diagnosis. However, the microbiome data is complex, with high noise and dimensions. Traditional machine learning methods are limited by the models' representation ability and cannot learn complex patterns from the data. Recently, deep learning has been widely applied to fields ranging from text processing to image recognition due to its efficient flexibility and high capacity. But the deep learning models must be trained with enough data in order to achieve good performance, which is impractical in reality. In addition, deep learning is considered as black box and hard to interpret. These factors make deep learning not widely used in microbiome-wide association studies. In this work, we construct a sparse microbial interaction network and embed this graph into deep model to alleviate the risk of overfitting and improve the performance. Further, we explore a Graph Embedding Deep Feedforward Network (GEDFN) to conduct feature selection and guide meaningful microbial markers' identification. Based on the experimental results, we verify the feasibility of combining the microbial graph model with the deep learning model, and demonstrate the feasibility of applying deep learning and feature selection on microbial data. Our main contributions are: firstly, we utilize different methods to construct a variety of microbial interaction networks and combine the network via graph embedding deep learning. Secondly, we introduce a feature selection method based on graph embedding and validate the biological meaning of microbial markers. The code is available at https://github.com/MicroAVA/GEDFN.git.
摘要:
Educational inequality is an important factor in the development of human capital, and limits the output of regional economic activities. The unequal distribution of educational resources has become a hot topic noticed by the public, and has restricted sustainable economic growth. This paper provides a better understanding of educational inequality, and explores the impacts of information and communication technology (ICT) and transportation infrastructure on the distribution of educational resources. The panel data models are constructed to discuss the relationship among ICT, transportation infrastructure, and educational inequality, using the data of 31 provinces in China from 2006 to 2016. The empirical results show that there is a positive relationship between ICT and educational inequality, while transportation infrastructure can restrain the unequal distribution of educational resources. Moreover, there is a significant inverted U-shaped relationship between transportation infrastructure and educational inequality. Since China's education reform in 2010, the relationship among ICT, transportation infrastructure, and educational inequality has been significantly changed, as well as the influence mechanism of ICT. In addition, transportation infrastructure in China western regions can effectively alleviate the problem of educational inequality, and its impact will increase with the growth of transportation investments. It is necessary to consider the rational allocation of educational resources, and this is essential to relieve the problem of educational inequality. Therefore, our results demonstrate the key roles of information technology and transportation network in the field of education, and provide some new ideas for the solution of educational inequality.