Search results

As well known, in the finite element method, the calculation and the location of the elements of the matrix C of the coefficients requires a lot of calculation times and memory employment especially for 3D problems. Besides, once the matrix C is properly filled, the solution of the system of linear equations is computationally expensive.

The paper consists of two parts. In the first part, to quickly calculate and store only the non‐null terms of the matrix of the system, a geometrical analysis on three‐dimensional domains has been carried out. The second part of the paper deals with the solution of the system of linear equations and proposes a procedure for increasing the solution speed: the traditional method of the conjugate gradient is hybridized with an adequate genetic algorithm (Genetic Conjugate Gradient).

The proposed geometrical procedure allows us to calculate the non‐null terms and their location within the matrix C by simple recursive formulas. The results concerning the genetic conjugate gradient show that the convergence to the solution of the linear system is obtained in a much smaller number iterations and the calculation time is also significantly decreased.

The approach proposed to analyze the geometrical space has been turned out to be very useful in terms of memory saving and computational cost. The genetic conjugate gradient is an original hybrid method to solve large scale problems quicker than the traditional conjugate gradient. An application of the method has been shown for current fields generated by grounding electrodes.

Measuring the similarity between two resources is considered difficult due to a lack of reliable information and a wide variety of available information regarding the resources. Many approaches have been devised to tackle such difficulty. Although content-based approaches, which adopted resource-related data in comparing resources, played a major role in similarity measurement methodology, the lack of semantic insight on the data may leave these approaches imperfect. The purpose of this paper is to incorporate data semantics into the measuring process.

The emerged linked open data (LOD) provide a practical solution to tackle such difficulty. Common methodologies consuming LOD mainly focused on using link attributes that provide some sort of semantic relations between data. In this work, methods for measuring semantic distances between resources using information gathered from LOD were proposed. Such distances were then applied to music recommendation, focusing on the effect of various weight and level settings.

This work conducted experiments using the MusicBrainz dataset and evaluated the proposed schemes for the plausibility of LOD on music recommendation. The experimental result shows that the proposed methods electively improved classic approaches for both linked data semantic distance (LDSD) and PathSim methods by 47 and 9.7%, respectively.

The main contribution of this work is to develop novel schemes for incorporating knowledge from LOD. Two types of knowledge, namely attribute and path, were derived and incorporated into similarity measurements. Such knowledge may reflect the relationships between resources in a semantic manner since the links in LOD carry much semantic information regarding connecting resources.

To communicate their sustainability and responsible management practices to the public, firms can leverage digital technologies both at the organisational and managerial levels. This study explores how firms' communications of responsible management contribute to sustainability in supply chains, as well as the role of blockchain in promoting responsible management.

Employing a qualitative methodology, the authors perform social media analytics (content analysis and sentiment analysis) on a dataset obtained from the social media posts of managers.

The study identifies eight key responsible management practices and shed new light on the role of blockchain in responsible management. The study results contribute to theory by linking responsible management practices with existing sustainability practices in the supply chain. The authors also demonstrate that blockchain enhances responsible management.

Reliance on publicly available data from social media, comprising corporate statements emanating from managers is a major limitation in this study.

The eight responsible management practices identified in this study are recommended for managers of different supply chain echelons to promote sustainable supply chain management (SSCM). The study findings also offer new rationale for blockchain adoption in supply chains.

To the best of our knowledge, this is the first study to link the concepts of responsible management and SSCM. Moreover, the authors obtain empirical evidence from managers in the luxury fashion supply chain.

Online news websites provide diverse article topics, such as fashion news, entertainment and movie information, to attract more users and create more benefits. Recommending movie information to users reading news online can enhance the impression of diverse information and may consequently improve benefits. Accordingly, providing online movie recommendations can improve users’ satisfactions with the website, and thus is an important trend for online news websites. This study aims to propose a novel online recommendation method for recommending movie information to users when they are browsing news articles.

Association rule mining is applied to users’ news and movie browsing to find latent associations between news and movies. A novel online recommendation approach is proposed based on latent Dirichlet allocation (LDA), enhanced collaborative topic modeling (ECTM) and the diversity of recommendations. The performance of proposed approach is evaluated via an online evaluation on a real news website.

The online evaluation results show that the click-through rate can be improved by the proposed hybrid method integrating recommendation diversity, LDA, ECTM and users’ online interests, which are adapted to the current browsing news. The experiment results also show that considering recommendation diversity can achieve better performance.

Existing studies had not investigated the problem of recommending movie information to users while they are reading news online. To address this problem, a novel hybrid recommendation method is proposed for dealing with cross-type recommendation tasks and the cold-start issue. Moreover, the proposed method is implemented and evaluated online in a real world news website, while such online evaluation is rarely conducted in related research. This work contributes to deriving user’s online preferences for cross-type recommendations by integrating recommendation diversity, LDA, ECTM and adaptive online interests. The research findings also contribute to increasing the commercial value of the online news websites.

Patent trade recommendations necessitate recommendation interpretability in addition to recommendation accuracy because of patent transaction risks and the technological complexity of patents. This study designs an interpretable knowledge-aware patent recommendation model (IKPRM) for patent trading. IKPRM first creates a patent knowledge graph (PKG) for patent trade recommendations and then leverages paths in the PKG to achieve recommendation interpretability.

First, we construct a PKG to integrate online company behaviors and patent information using natural language processing techniques. Second, a bidirectional long short-term memory network (BiLSTM) is utilized with an attention mechanism to establish the connecting paths of a company — patent pair in PKG. Finally, the prediction score of a company — patent pair is calculated by assigning different weights to their connecting paths. The semantic relationships in connecting paths help explain why a candidate patent is recommended.

Experiments on a real dataset from a patent trading platform verify that IKPRM significantly outperforms baseline methods in terms of hit ratio and normalized discounted cumulative gain (nDCG). The analysis of an online user study verified the interpretability of our recommendations.

A meta-path-based recommendation can achieve certain explainability but suffers from low flexibility when reasoning on heterogeneous information. To bridge this gap, we propose the IKPRM to explain the full paths in the knowledge graph. IKPRM demonstrates good performance and transparency and is a solid foundation for integrating interpretable artificial intelligence into complex tasks such as intelligent recommendations.

The purpose of this paper is to discuss the emerging geographic features of current concepts of relevance, and to improve, modify, and extend the framework proposed by Mizzaro (1998). The objective is to define a new framework able to account, more completely and precisely, for the notions of relevance involved in mobile information seeking scenarios.

The authors formalise two new dimensions of relevance. The first dimension emphasises the spatio-temporal nature of the information seeking process. The second dimension allows us to describe how different concepts of relevance rely on different abstractions of reality.

The new framework allows: to conceptualise the point in space and time at which a given notion of relevance refers to; to conceptualise the level of abstraction taken into account by a given notion of relevance; and to include widely adopted facets (e.g. users mobility, preferences, and social context) in the classification of notions of relevance.

The conceptual discussion presented in this paper contributes to the future development of relevance in the scope of mobile information seeking scenarios. The authors provide a more comprehensive framework for conceptualization, development, and classification of notions of relevance in the field of information retrieval and location-based services.

The purpose of this paper is to present a prototype ontology‐based application that has been developed for competency management and learning paths.

The paper provides an overview of competency management and related work in this area, a description of the competency ontology, and a functional and architectural analysis.

The paper provides information on work related to ontology‐based competency management systems, indicating an enhanced approach with a detailed analysis of system architecture and functional analysis.

The proposed application will be implemented through a .NET deployment, in Microsoft Hellas, the Greek subsidiary of the multinational IT company.

Ontologies have already been created in different scientific areas, including knowledge and competency management. However, only a few ontology‐based applications are available today within the domain of competency management. In this paper an ontology‐based application is presented has been developed for competency management and learning paths. Specifically, the paper provides an overview of competency management and related work in this area, a description of the competency ontology, and a functional and architectural analysis.

There is still little support for the consumer decision‐making process on the web, especially when prices are not the primary property of a product. Reasons for that are complex product specifications as well as often volitional weak interoperability between e‐commerce sites. This paper aims to address this issue.

The semantic web is supposed to make product information more interoperable between different sites. Additionally, some products with limited time frames of availability, like real estates or second‐hand cars, require periodical searches over several days, weeks, or even months. For those kinds of products existing systems cannot be applied. Instant information about new offers on the market is therefore crucial. Wireless access to the web enables services to become instantaneous and to provide up‐to‐date information to users.

This paper presents a framework which is based on multivariate product comparison allowing users to delegate search requests to an agent. The success of the agent depends heavily on the matching algorithm. Fuzzy utility functions and the analytical hierarchy process are a very feasible combination for the scoring of offers.

The proposed system supports users finding products on the web matching specific user preferences and instantly informs them when new items become available on the virtual market. As a specific use case the framework is being applied to the real estate sector, because especially for this sector several shortcomings of the current support have been identified.

Aims to review the key concepts of competency management (CM) and to propose method for developing competency method.

Examines the CM features of 22 CM systems and 18 learning management systems.

Finds that the areas of open standard (XML, web services, RDF), semantic technologies (ontologies and the semantic web) and portals with self‐service technologies are going to play a significant part in the evolution of CM systems.

Emphasizes the beneficial attributes of CM for private and public organizations.

The purpose of this paper is to present a generic pipeline for Resource Description Framework (RDF) graph mining to provide a comprehensive review of each step in the knowledge discovery from data process. The authors also investigate different approaches and combinations to extract feature vectors from RDF graphs to apply the clustering and theme identification tasks.

The proposed methodology comprises four steps. First, the authors generate several graph substructures (Walks, Set of Walks, Walks with backward and Set of Walks with backward). Second, the authors build neural language models to extract numerical vectors of the generated sequences by using word embedding techniques (Word2Vec and Doc2Vec) combined with term frequency-inverse document frequency (TF-IDF). Third, the authors use the well-known K-means algorithm to cluster the RDF graph. Finally, the authors extract the most relevant rdf:type from the grouped vertices to describe the semantics of each theme by generating the labels.

The experimental evaluation on the state of the art data sets (AIFB, BGS and Conference) shows that the combination of Set of Walks-with-backward with TF-IDF and Doc2vec techniques give excellent results. In fact, the clustering results reach more than 97% and 90% in terms of purity and F-measure, respectively. Concerning the theme identification, the results show that by using the same combination, the purity and F-measure criteria reach more than 90% for all the considered data sets.

The originality of this paper lies in two aspects: first, a new machine learning pipeline for RDF data is presented; second, an efficient process to identify and extract relevant graph substructures from an RDF graph is proposed. The proposed techniques were combined with different neural language models to improve the accuracy and relevance of the obtained feature vectors that will be fed to the clustering mechanism.