Accurately predicting sea surface temperature (SST) plays an important role in the study of marine ecosystems and global climate. The SST prediction problem is usually formulated as a time-series regression problem; i.e., the future SST is predicted based on the historical SST. However, the existing methods are typically devoted to modeling the highly nonlinear temporal correlations in SST data. They often ignore the dynamic spatial correlations that exist. This can limit the performance of these models, making accurately predicting SST challenging. To address this challenge, by combining graph neural networks (GNNs) that have a clear advantage in modeling spatial correlations, we propose a global spatiotemporal graph attention network (GSTGAT). Specifically, we capture the global dynamic spatial correlations of nodes through a global graph attention network (GGAT) module that fuses the static adjacency matrix learned adaptively by the graph learning (GL) module with the dynamic attention coefficients. A gated temporal convolutional network (GTCN) module is used to capture the nonlinear temporal correlations. Then, the above modules are integrated into a unified neural network to predict SST. We conduct experiments on multiple time-scale datasets in the Bohai Sea and the South China Sea. The experimental results show that GSTGAT achieves the best performance and consistently outperforms other methods for different prediction horizons in the two sea areas.

Sea surface temperature (SST) prediction plays an important role in ocean-related fields. It is challenging due to the nonlinear temporal dynamics with changing complex factors and the inherent difficulties in long-scale predictions. Conventional models often lack efficient information extraction and cannot meet the requirements of long-scale predictions. Therefore, the gate recurrent unit (GRU) encoder-decoder with SST codes and dynamic influence link (DIL), GRU encoder-decoder (GED), which considered both the static and dynamic influence, is proposed in this letter. Each SST code, capturing the static information more effectively, was computed by all hidden states of the encoder and was individually associated with each predicted SST. The DIL, capturing the dynamic influence, connected the SST code with the early predicted future SST for solving the long-scale dependence problem. GED was tested on the Bohai Sea SST data sets and South China Sea SST data sets and compared with full-connected long-short term memory (FC-LSTM) and support vector regression. The results demonstrated that GED outperformed others on different prediction scales and different prediction terms (daily, weekly, and monthly), especially in terms of long-scale and long-term predictions. In addition, attention relationships between historical and future SSTs were further explored, and there was a meaningful finding that each future daily mean SST of Bohai Sea most strongly correlated with the past 27th to 29th historical values.

With the rapid development of computer and communication, data mining and related fields are facing huge challenges. In the research of data mining and text analysis, how to extract concepts more objectively and reasonably is a key issue. Existing approaches seem to lack the intensive analysis of structural nature of structured text, which will affect the effectiveness and accuracy of text analysis. This paper proposes a novel approach of structured text analysis and concept extraction using entropy weight method. It quantitatively assesses the contribution of each module in evaluating the weight of concept. Based on the position of the concept in the text, concepts can be mined more effectively. Furthermore, the method is applied to the field of academic text analysis to verify its effectiveness and advantages over traditional methods. And the experimental results also prove that the method can provide solid theoretical and technical support for personalized academic information services

Due to the development of web technology, the research on Internet big data become more and more popular.However, information presents polymorphism and complexity under the status of the rapid development of Internet big data.Most of the traditional methods of event influence calculation use observable data to evaluate and ignore the decay influence of event.In fact, event influence growths from the moment of event happening to the end, meanwhile, it accompanis with a certain decay.What's more, event influence presents observable influence and decay influence on different network media.This paper proposes a new method to calculate event influence on different network media and find the relationships between observable influence and decay influence on different stages of event.Experiments show that better influence calculation will be achieved by decay algorithm based on Ebbinghaus forgetting curve and information fusion by considering interaction between observable influence and decay influence.

Summary With the development and popularization of Internet big data, the cyber world nearly parallels to the real world to reflect social hot event. However, the multi‐source and heterogeneity features of reality data lead to incompleteness and unreality based on Internet data. To solve the above issues, we propose Event Space Model (ESM) for event analysis by multi‐viewer. In the model, each event is mapped into Network Public Opinion Data Space (OS) and Actual Behavior Data Space (BS). In addition, we propose an Event Starting Point Discovery Algorithm (ESPDA) to effectively detect starting point of event and to identify the representation of event trajectory in OS and BS. The experimental results prove that the ESM represent event from multi‐viewer, while the ESPDA intensively identify events and improve recall and precision of starting point of event. Copyright © 2016 John Wiley & Sons, Ltd.

The knowledge on the internet is uncertain, quickly updated and from multi-sources. The information we extract from a field in webpages is usually one-sided and contains incorrect data. This paper proposed an algorithm to extract data from internet web pages or text documents by using the association strength. The algorithm combines knowledge extraction method of the text mining with the technology of the intelligence analysis to the data. It uses ontology theory to describe the knowledge, and automatically extract the knowledge from the web pages or text documents which is returned by the search engine.

Network resources are fully rich, but the source of information is uneven. Huge amount of information, complex diversity of the network information and vastly different perspectives has brought great distress for people to identify information [1]. Due to the complexity of objective things, uncertainty and ambiguity of human thinking and other factors, the actual decision-making information is often difficult to quantify. General choice is to express the decision-making information in the form of qualitative language, but this multi-language form depends on human mind. What's more, different decision-makers will be based on their existing personal experience or cognition degree on the same issue to make good and bad, individualized decision-making, thereby it increases the uncertainty in decision making and labor costs in decision-making process. In this paper, considering the entirety of information on the whole and the drawback of the information on the local, we combine the human knowledge with machine algorithm. The method proposed in this paper is based on the similarity degree of the research object's attributes and categories, which uses the ideas of information fusion [2], make good use of a variety of information together and in view of multidimensional multi-granularity information to confirm each other to find a more effective method to distinguish the similarity measure of information object.

Abstract Queries to Web search engines are usually short and ambiguous, which provides insufficient information needs of users for effectively retrieving relevant Web pages. To address this problem, query suggestion is implemented by most search engines. However, existing methods do not leverage the contradiction between accuracy and computation complexity appropriately (e.g. Google's ‘Search related to’ and Yahoo's ‘Also Try’). In this paper, the recommended words are extracted from the search results of the query, which guarantees the real time of query suggestion properly. A scheme for ranking words based on semantic similarity presents a list of words as the query suggestion results, which ensures the accuracy of query suggestion. Moreover, the experimental results show that the proposed method significantly improves the quality of query suggestion over some popular Web search engines (e.g. Google and Yahoo). Finally, an offline experiment that compares the accuracy of snippets in capturing the number of words in a document is performed, which increases the confidence of the method proposed by the paper. Copyright © 2010 John Wiley & Sons, Ltd.

SUMMARY Semantic similarity measures play important roles in many Web‐related tasks such as Web browsing and query suggestion. Because taxonomy‐based methods can not deal with continually emerging words, recently Web‐based methods have been proposed to solve this problem. Because of the noise and redundancy hidden in the Web data, robustness and accuracy are still challenges. In this paper, we propose a method integrating page counts and snippets returned by Web search engines. Then, the semantic snippets and the number of search results are used to remove noise and redundancy in the Web snippets (‘Web‐snippet’ includes the title, summary, and URL of a Web page returned by a search engine). After that, a method integrating page counts, semantics snippets, and the number of already displayed search results are proposed. The proposed method does not need any human annotated knowledge (e.g., ontologies), and can be applied Web‐related tasks (e.g., query suggestion) easily. A correlation coefficient of 0.851 against Rubenstein–Goodenough benchmark dataset shows that the proposed method outperforms the existing Web‐based methods by a wide margin. Moreover, the proposed semantic similarity measure significantly improves the quality of query suggestion against some page counts based methods. Copyright © 2011 John Wiley & Sons, Ltd.

Association Link Network (ALN) aims to establish associated relations among various resources. By extending the hyperlink network World Wide Web to an association-rich network, ALN is able to effectively support Web intelligence activities such as Web browsing, Web knowledge discovery, and publishing, etc. Since existing methods for building semantic link on Web resources cannot effectively and automatically organize loose Web resources, effective Web intelligence activities are still challenging. In this paper, a discovery algorithm of associated resources is first proposed to build original ALN for organizing loose Web resources. Second, three schemas for constructing kernel ALN and connection-rich ALN (C-ALN) are developed gradually to optimize the organizing of Web resources. After that, properties of different types of ALN are discussed, which show that C-ALN has good performances to support Web intelligence activities. Moreover, an evaluation method is presented to verify the correctness of C-ALN for semantic link on documents. Finally, an application using C-ALN to organize Web services is presented, which shows that C-ALN is an effective and efficient tool for building semantic link on the resources of Web services.

Web service has already been an important paradigm for web applications. Growing number of services need efficiently locating the desired web services. The similarity metric of web services plays important role in service search and classification. The very small text fragments in WSDL of web services are unsuitable for applying the traditional IR techniques. We describe our approach which supports the similarity search and classification of service operations. The approach firstly employs the external knowledge to compute the semantic distance of terms from two compared services. The similarity of services is measured upon these distances. Previous researches treat terms within the same WSDL documents as the isolated words and neglect the semantic association among them, hence lower down the accuracy of the similarity metric. We provide our method which tries to reflect the underlying semantics of web services by utilizing the terms within WSDL fully. The experiments show that our method works well on both service classification and query.

Personalized services provide specific services to satisfy userpsilas real-time requirements. How to effectively discover and organize proper Web resources is a key issue. Based on Web knowledge flow which is used to semantically organize and represent Web resources that are recommended to user, this paper presents a 3-way strategy of finding proper resources for a user in multi-user environment. With this strategy, generation of Web Knowledge flow can be accomplished based on collaborative user and semantics link network. First, according to the similarity degree between active user and collaborative user, collaborative user is refined to strict kind and loose kind. Secondly, userpsilas browsing sequence of Web resources is presented to find collaborative users and implemented in a 3-D coordinate space. Thirdly, average information entropy of semantic relationship between Web resources is presented to evaluate the similarity of userspsila browsing feature. The experimental results demonstrate the validity of the method. It can be seen that the proposed method has a brilliant perspective in the applications of Web personalized services.

Abstract Similarity Knowledge Flow (SKF) is a kind of scientific workflow, providing an effective technique and theoretical support for intelligent browsing in the Web and e‐Science environment. In this paper, a Semantic Link Networks (SLN) based SKF generation method is proposed. First, the topics are represented by Element Fuzzy Cognitive Maps then the semantic values of concepts/keywords and relations are calculated. Third, semantic similarity degrees between topics are calculated to build SLN‐based semantic values of concepts and their relations in Element Fuzzy Cognitive Maps. In this way, similar relations at the keyword level are extended to the topic level. With the help of SLN and based on user's demand, SKF is generated as the browsing path of topics to guide user browsing behaviors. Finally, the semantic value of SKF is defined as a criterion to evaluate the browsing path of topics. Experimental results show that the browsing path of topics is easy to be activated by SKF which is generated by SLN. The proposed method has been proved to have a very good prospect in the fields of Web services and e‐Science applications. Copyright © 2009 John Wiley & Sons, Ltd.