Search

Citation recommendation systems mainly help researchers find the lists of references that related to their interests effectively and automatically. The existing approaches face the issues of data sparsity and high-dimensional in large-scale bibliographic network representation, which hinder the citation recommendation performance. To address these problems, we proposed a Content-Sensitive citation representation approach for Citation Recommendation, named CSCR. Firstly, the Doc2vec model is used to generate a paper embedding according to paper content. Then, utilizing the similarity between the paper content embeddings to select the assumed neighbours of the target paper, append the auxiliary links between target paper and its new neighbours in the bibliographic network. Thirdly, distributed network representation method is implemented on appended bibliographic network to obtain the paper node embedding, which can learn interpretable lower dimension embedding for paper nodes. Finally, the embedding vectors of these papers can be used to conduct citation recommendation. Experimental results show that the proposed approach significantly outperforms other benchmark methods in Normalized Discounted Cumulative Gain (NDCG) and the positive rate (Recall).

With advanced development of Internet communication and ubiquitous computing, Social Networks are providing an important information channel for smart city construction. Therefore, analyzing Location-based Social Network is a very valuable work in achieving reasonable urban zoning. In Social Networks, a main purpose of prestige assessment is to extract influential users who are regarded as the key nodes for community detection from Onine Social Networks (OSNs). However, social relationships of users are rarely used to evaluate the popularity of physical locations and zone physical locations. In order to achieve urban area function zoning by evaluating the prestige of geographic regions based on user relationships in Location based Social Networks (LBSNs), this paper proposes a Prestige Density-Based Spatial Clustering of Applications with Noise algorithm (P-DBSCAN) by improving the existing DBSCAN algorithm. Specifically, the algorithm first calculates the centrality of users in the social network, and then converts the centrality of users into the location-centrality through the users’ check-in data. After the centrality of each location is obtained, the discrete locations are clustered according to four constraints of the given radius. After clustering, the result of urban area function zoning can be achieved. Extensive experiments are conducted for demonstrating the effectiveness of our proposed algorithm in this paper. In addition, the visualization results reveal the correctness of our proposed approach.

With the number of smart contracts growing rapidly, retrieving the relevant smart contracts quickly and accurately has become an important issue. A key step for recognizing the related smart contracts is able to classify them accurately. Different from traditional text, the smart contract is composed of several parts: source code, code comments and other useful information like account information. How to make good use of those different kinds of features for effective classification is a problem need to be solved. Inspired by this, we proposed a smart contract classification approach based on Bi-LSTM model and Gaussian LDA, which can use a variety of information as inputs of the model, including source code, comments, tags, account and other content information. Bi-LSTM is utilized to capture grammar rules and context information in source code, while Gaussian LDA model is employed to generate comments feature where the semantics of the comments are enriched by embeddings. We also use attention mechanism to focus on the more relevant features in smart contracts for tags and fuse account information to provide additional information for classification. The experimental results show that the classification performance of the proposed model is superior to other baseline models.

Quality of Service (QoS) value is usually unknown in service recommendation practice. There are some matrix factorization approaches for predicting the unknown value with a user-service model, which uses a single collaboration with the user’s neighbor when looking for different services. However, the QoS value is highly related to the service provider and participants. The services are considered in various collaboration based on different users. By considering the context of services, this paper proposes a QoS prediction model using tensor decomposition based on service collaboration called Service-oriented Tensor (SOT). The prediction approach analyzes service collaboration from other similar services and relevant users by using a three-order tensor. Compared with the traditional model, the experiment results show that the proposed model achieves better prediction accuracy.

Nowadays, a growing number of web services are offered in API marketplaces browsed by service developers or third-party registries. Under this situation, API marketplaces' users greatly rely on a search engine to find suitable web services. However, due to the fact that functional attributes of web services are usually described in short texts, the search engine-based discovery approach suffers from the semantic sparsity problem, which hinders the effect of service discovery. To address this issue, we propose a novel web service discovery approach using word embedding and Gaussian latent Dirichlet allocation (Gaussian LDA). Unlike most existing service discovery approaches, our approach first uses context information generated by word embedding to enrich the semantics of service descriptions and users' queries. Then, the enriched service description is loaded into the Gaussian LDA model to acquire service description representation. Finally, the services are ranked by considering the relevance between the extended user's query and service description representation. The experiments conducted on a real-world web service dataset and the results demonstrate that the proposed approach achieves superior effectiveness on web service discovery.

With an increasing number of scholarly publications, accessing and retrieving appropriate papers is becoming an essential task for researchers. Citation recommendation, which can automatically provide a reference list based on a text segment, can overcome this problem. In this paper, we first construct a heterogeneous bibliographic network and deem citation recommendation as edge prediction problem, and then we develop a network representation-based edge prediction (NREP) model, which can simultaneously learn the edge prediction knowledge and the predictive representation for efficient citation recommendation. For personalized recommendation, we incorporate author information. We conduct extensive experiments on two datasets; the experimental results show that the NREP-based approach outperforms the other four state-of-the-art baseline approaches in terms of recall, mean average precision, and normalized discounted cumulative gain.

With the increasing number of scientific papers, researchers find it more and more difficult to obtain relevant and appropriate papers to cite. Citation recommendation aims to overcome this problem by providing a reference paper list for a given manuscript. In this paper, we propose a bibliographic network representation (BNR) model, which simultaneously incorporates bibliographic network structure and content of different kinds of objects (authors, papers, and venues) for efficient recommendation. The proposed model also makes personalized citation recommendation possible, which is a new issue that a few papers addressed in the past. When conducting experiments on the ACL Anthology Network and DBLP datasets, the results demonstrate that the proposed BNR-based citation recommendation approach is able to achieve considerable improvement over other network representation-based citation recommendation approaches. The performance of the personalized recommendation approach is also competitive with the non-personalized recommendation approach.

Formal Concept Analysis (FCA) methodology, as an efficient knowledge representation and knowledge discovery tool and has been widely used in various fields, such as data mining, expert systems, and others. Knowledge reduction is an essential issue for knowledge discovery. This paper focuses on attribute reduction in FCA and explores the internal relation between concept stability and attribute reduction. By observing the concept stability of concepts in original concept lattice and reduced concept lattice, a theorem about the invariance of concept stability for attribute reduction in concept lattice is presented and proved mathematically. It is believed that the proposed theorem provides a novel solution for quick attribute reduction and benefit for other social system applications.

This paper focuses on the master and doctoral dissertations on "data-driven control", "model-free adaptive control" and "iterative learning control" collected by Chinese National Knowledge Infrastructure (CNKI) database before October 31, 2019. Exploiting big data technology, three topics mentioned above are studied in the form of mapping knowledge graph by Python, ROSTCM and Ucinet social network analysis software. Our research mainly explores and analyzes the temporal evolution as well as development status of the subject words, the cultivation organizations, the fund support, the co-occurrence of key words, the co-occurrence of dissertations topics and the characteristics of supervisor -student relationship, etc., which can provide references for relevant research fields.

Information retrieval-based Web service discovery approach suffers from the semantic sparsity problem caused by lacking of statistical information when the Web services are described in short texts. To handle this problem, external information is often utilized to improve the discovery performance. Inspired by this, we propose a novel Web service discovery approach based on a neural topic model and leveraging Web service labels. More specifically, words in Web services are mapped into continuous embeddings, and labels are integrated by a neural topic model simultaneously for embodying external semantics of the Web service description. Based on the topic model, the services are interpreted into hierarchical models for building a service querying and ranking model. Extensive experiments on several datasets demonstrated that the proposed approach achieves improved performance in terms of F-measure. The results also suggest that leveraging external information is useful for semantic sparse Web service discovery.

The rapid growth of scientific papers makes it difficult to find relevant and appropriate citations. Context-aware citation recommendation aims to overcome this problem by providing a list of scientific papers given a short passage of text. In this paper, we propose a long–short-term memory (LSTM)-based model for context-aware citation recommendation, which first learns the distributed representations of the citation contexts and the scientific papers separately based on LSTM, and then measures the relevance based on the learned distributed representation of citation contexts and the scientific papers. Finally, the scientific papers with high relevance scores are selected as the recommendation list. In particular, we try to incorporate author information, venue information, and content information in scientific paper distributed vector representation. Furthermore, we integrate author information of the given context in citation context distributed vector representation. Thus, the proposed model makes personalized context-aware citation recommendation possible, which is a new issue that few papers addressed in the past. When conducting experiments on the ACL Anthology Network and DBLP data sets, the results demonstrate the proposed LSTM-based model for context-aware citation recommendation is able to achieve considerable improvement over previous context-aware citation recommendation approaches. The personalized recommendation approach is also competitive with the non-personalized recommendation approach.

Many state-of-the-art citation recommendation methods have been proposed for finding a list of reference papers for a given manuscript, among which the graph-based method has gained particular attention, due to its flexibility for incorporating various information that embodies user’s preferences. To achieve a more synthetic, accurate, and personalized recommendation result than the previous graph-based methods, this paper proposes a new graph-based recommendation framework that exploiting diversified link information in a bibliographic network and the concise query information that embodies the specific requirement of user comprehensively. The proposed framework not only performs mutual reinforcement rules on all available multiple types of relations in a multi-layered graph but also incorporates the query information into the multi-layered mutual reinforcement schema to construct a multi-layered mutually reinforced query-focused (MMRQ) citation recommendation approach. Extensive experiments have been conducted on a subset of anthology network data set. Experimental results of Recall measures, normalized discounted cumulative gain measures, and case study all demonstrate that our MMRQ method obtains a superior citation recommendation.

Although there has been a lot of research in multi-label learning task, little attention has been paid on the weak label problem, in which only a subset of labels has been assigned to each instance in the training set. The extreme form of weak label learning is to predict all the labels from just one label set in the training phase. In this paper, we focus on dealing with this kind of weak label learning task, which is commonly met in old legacy information system, and it is also called “Hercules Learning.”We propose a label-group-optimization-based Hercules learning algorithm, which divides the entire label set into multiple groups according to the classifier's capability to distinguish them, so for each group, we can train a classifier which can predict instance's label within the group with high accuracy. The experimental results show that our algorithm is obviously superior to the existing weak label learning algorithm.

In order to explore and evaluate the effects of velocity variation trend of multiple preceding cars used in the Cooperative Adaptive Cruise Control (CACC) strategy on the dynamic characteristic, fuel economy and emission of the corresponding traffic flow, we conduct a study as follows: firstly, with the real-time car-following (CF) data, the close relationship between multiple preceding cars’ velocity fluctuation feedback and the host car’s behaviors is explored, the evaluation results clearly show that multiple preceding cars’ velocity fluctuation with different time window-width are highly correlated to the host car’s acceleration/deceleration. Then, a microscopic traffic flow model is proposed to evaluate the effects of multiple preceding cars’ velocity fluctuation feedback in the CACC strategy on the traffic flow evolution process. Finally, numerical simulations on fuel economy and exhaust emission of the traffic flow are also implemented by utilizing VT-micro model. Simulation results prove that considering multiple preceding cars’ velocity fluctuation feedback in the control strategy of the CACC system can improve roadway traffic mobility, fuel economy and exhaust emission performance.

Systems for recommending scientific papers mainly help researchers to find a list of references that related to the researcher's interest effectively and automatically. Many state-of-the-art technique have been used for recommendation system, however, the traditional approaches has the issues of data scarcities and cold start, and existing recommended approaches with network representation only focus on one aspect of node information and cannot leverage content information. In this paper, we proposed a Citation Recommendation method with a Content-Aware bibliographic network representation, called CR-CA, whose recommended process contains two levels: (1) At the node content level, the proposed approach calculates similarities between the target and candidate papers, selecting an initial seed set of papers; (2) At the citation network structure level, this approach exploits citation relationship between papers to study latent representation of the scientific papers based on a deep natural language method–DeepWalk. The proposed approach was tested on the AAN dataset demonstrate that this approach outperforms baseline algorithms, in the true positive rate (Recall) and normalized discounted cumulative gain (NDCG).

With the increase of design scale and complexity, security vulnerabilities residing in hardware designs become hard to detect. Existing functional testing and verification methods cannot guarantee test and verification coverage in design phase. Fortunately, gate level information flow tracking (GLIFT) has been proposed to enforce bit-tight information flow security from the gate level to detect security vulnerabilities and prevent information leakage effectively. However, there is a significant limitation that the inherent high complexity of GLIFT logic causes significant overheads in static verification and physical implementation. In order to address the limitation, we propose a simplified GLIFT method that incorporates more detailed optimization logic routes to reduce its complexity and allow don’t care to simplify original GLIFT logic. Experimental results have demonstrated that the simplified GLIFT method can reduce the design overhand in several gates by sacrificing a fraction of GLIFT precision.

As the scale of integrated circuits continuously increasing, guaranteeing intensity of testing and coverage rate of verification in the design phase absolutely is becoming severe challenges. As a solution, Gate Level Information Flow Tracking (GLIFT) method is able to precisely measure all the logical information flows in the underlying hardware to prevent information leakage resulting from these harmful flows of information. However, preliminary research work for GLIFT mainly focused on the basic theories as well as the generation algorithms, which only can track logic formalization under the Boolean logic system. These approaches ignored that digital circuits are typically described by multi-valued logic during hardware design and verification. To address that issue, we present to expand the GLIFT method for multi-valued logic system. In this paper, the label propagation rule set is respectively derived for four-valued and nine-valued logic systems by extending the label propagation set for Boolean logic. Moreover, in order to support the characteristics of multi-valued logic in label propagation, the formal descriptions of GLIFT logic for primitive gates are improved in computing hardware as well. The experimental results demonstrate that the extended method is consistent with the label propagation rule of the multi-valued logic system.

Cloud service resource allocation is an essential task in cloud computing. The cloud service resource allocation problem is modeled as an optimization problem, and is solved via different particle swarm optimization (PSO) variants in this paper. The aim of our method is to minimize the delay and the price at the same time. Based on the experimental results, it could be conducted that the good performance could be achieved via PSO algorithms. The future research is to utilize PSO algorithms on solving more real-world problems, especially with other quality of service problems.

Reasonable house price prediction is a meaningful task, and the house clustering is an important process in the prediction. In this paper, we propose the method of Multi-Scale Affinity Propagation(MSAP) aggregating the house appropriately by the landmark and the facility. Then in each cluster, using Linear Regression model with Normal Noise(LRNN) predicts the reasonable price, which is verified by the increasing number of the renting reviews. Experiments show that the precision of the reasonable price prediction improved greatly via the method of MSAP.

Sentiment analysis still is a problem in text data analysis. In this paper, the proposed model which fuses the convolution neural network with the tree bank information has been introduced. This model not only takes into consideration of the syntax information, but also the structure information which is better than other single factor model. By a sequence of experiments, we can prove the goodness of this model in sentiment analysis.

Service topic detection is one of the most important techniques in service information extraction, clustering and recommendation. Comparing with short text corpus in social network, service description corpus possesses higher dimensionality and more diversity. It is difficult to detect topics from a large number of service descriptions. To address these challenges, we proposed a new LDA (Latent Dirichlet Allocation) model based topic detection method, referred to as CV-LDA (Context sensitive word Vector based LDA). It utilizes a word embedding based method that generate context sensitive vector to cluster the words for decreasing dimensionality. Through topic perplexity analysis in the real-world dataset, it is obvious that topics detected by our method has a lower perplexity, comparing with word frequency weighing based vectors.