China
Africa
Explore chapters and articles related to this topic
Mobile Augmented Reality to Enable Intelligent Mall Shopping by Network Data
Published in Yulei Wu, Fei Hu, Geyong Min, Albert Y. Zomaya, Big Data and Computational Intelligence in Networking, 2017
To construct the types for enumerating templates, we resorted to three options. First, we constructed a dictionary to map a keyword or phrase to a type based on Freebase9 and Microsoft Academic Search (MAS),10 such as mapping “data mining” to topic. Freebase is an open and general database containing a huge number of types across many different domains. Thus, we can rely on it to devise templates for many real-world applications. In addition, we used MAS to supplement types for the researcher domain. Second, we relied on Stanford CoreNLP [26] to recognize the named entities as types, such as organization, person and location. Third, we devised regular expressions to tag well-formed texts, such as phonenum, url and email.
Domain-Specific Journal Recommendation Using a Feed Forward Neural Network
Published in Himansu Das, Jitendra Kumar Rout, Suresh Chandra Moharana, Nilanjan Dey, Applied Intelligent Decision Making in Machine Learning, 2020
For the notion that motivated this work, we use Google Scholar, Semantic Scholar, Scopus, Web of Science, and Microsoft Academic data to provide customizable recommendations for individuals. The aim is to support the research community by recommending the most suitable article from a curated list of publications for their domain of interest. For this drive, we developed a method to assess the publication attainment from a set of researchers who are involved in the identical research domain. The method comprises a scraper to acquire the required data. Figure 5.1 provides an overview of the tool.
Unifying Functional User Interface Design Principles
Published in International Journal of Human–Computer Interaction, 2021
Jenny Ruiz, Estefanía Serral, Monique Snoeck
Once we had the list of authors as sources for UI design principles, we compiled the principles proposed by each author. To that end, we performed two additional steps: 1) identification of the author’s works where principles are proposed (note that some works are not immediately obtained from the SLR because they are, e.g., not digitalized) and 2) compilation of the principles proposed in those works. After having tried multiple strategies and based on the problems we experienced (see Section 5.1), the final strategy was as follows: We selected the list of the most important authors as sources for principles from the SLR, descriptions of courses, books, etc. (see the previous section).We used Harzing´s Publish or Perish software as tool to retrieve and analyze academic citations using Google Scholar as data source. Publish or Perish is a software program that retrieves and analyzes academic citations. It uses Google Scholar and Microsoft Academic Search to obtain the raw citations, then analyzes these and presents impact metrics. We look for the three most cited works of each author that mention the principles (the original or rephrased principles).Count the citation per author for those three works (note that if several authors proposed a principle together in a joint work the citation of that work is counted only once when counting citations for the principles).