Big Data Archives - Human-Computer Interaction & Visual Analyitics Reasearch Group (vis) at Darmstadt University of Applied Sciences (h

Posts

Book Chapter published in Student Handbook “Praxishandbuch Forschungsdatenmanagement”

21/01/2021/in Allgemein, Lecture, Publication, Research, Teaching /by Dirk Burkhardt

We are glad to announce that our chapter to the student handbook “Praxishandbuch Forschungsdatenmanagement” (Engl.: practice handbook research data management) was accepted and got printed at De Gruyter. Our chapter addresses the foundations of Data Visualization, which is explained on behalf of selected examples.

The book covers nowadays societal research challenges in pespective of data management and how current approaches in research can helo to handle it. Therewith, events such as the entry into force of the code “Guidelines for Safeguarding Good Scientific Practice” of the German Research Foundation (DFG) or the establishment of the National Research Data Infrastructure (NFDI) and the European Open Science Cloud (EOSC) put providers, producers and users of research data in front of specialist, technical, legal and organizational challenges. The practical handbook for research data management comprehensively covers all relevant aspects of research data management and the current framework conditions in the data ecosystem.

In particular, the practical implications of data policy and law, the respective data market, data culture, personal qualification, data management and “FAIR” data transfer and reuse are examined. The practical handbook also provides an overview of projects, developments and challenges in Research data management.

Guest Editing of Special Issue in Big Data Research Journal

12/11/2020/in Action, Allgemein, Journal, News, Publication, Research /by Kawa Nazemi

Prof. Dr. Kawa Nazemi acts as guest editor together with Vincenzo Deufemia and Giuseppe Polese the special issue on “Visualization in Big Data and Data Science” of the Big Data Research Journal.

Call for Papers:

Visualization in Big Data and Data Science

Introduction

As witnessed by Covid19 outbreak, big data and data science are becoming vital disciplines in several application domains, mainly due to the great availability of big data collections from which it is possible to mine precious patterns of knowledge. The Internet of Things (IoT) industrial revolution has furtherly contributed to boost this trend, yielding an increased interest for data analytics techniques capable of working on streams of data and time series. This has led to the development of powerful predictive models, including deep neural networks, also thanks to the availability of powerful hardware and distributed computing paradigms. Nevertheless, one of the aspects that is hindering the contamination of Big Data and Data Science in many sectors is to be ascribed to the difficulty in explaining the rationale underlying complex data analytics processes to stakeholders. While it is well-known that the data pre-processing and analytics phases account for about 70% and 20% of the whole data analytics process, respectively, there is a remaining 10% of the effort that should be devoted to the visualization and explanation of the results, also known as data journalism. Although this is a small percentage, and for this reason overlooked by many data scientists, it is one of the most critical ones in order to draw the attention of stakeholders and motivate them to trust and invest on the adoption of Big Data and Data Science technologies. This is true also in artificial intelligence where explainable AI is also becoming crucial. One way to tackle this problem is to rely on efficient visualization metaphors and intelligent visual interaction paradigms.

In this respect, we expect interdisciplinary contributions from several research communities, such as, data mining, big data, machine learning, and human-computer interaction, to provide new scalable ways for visualizing the results of complex data analytics processes, including efficient interaction techniques to explore them. In particular, they should stimulate the active involvement of stakeholders in the data analytics process by enhancing their understanding capabilities.

Paper Submission Format and Guidelines

All submitted papers must be clearly written in English and must contain only original work, which has not been published by, or is currently under review for, any other journal, conference, symposium, or workshop. Submissions are expected to not exceed 30 pages (including figures, tables, and references) in the journal’s single-column format using 11-point font. Detailed submission guidelines are available under “Guide for Authors” at:

http://www.journals.elsevier.com/big-data-research/

All manuscripts and any supplementary material should be submitted through the Elsevier Editorial System (EES). The authors must select “VSI: Big Data Science Vis” as Article Type when they reach the Article Type step in the submission process. The EES website is located at:

http://ees.elsevier.com/bdr

All papers will be peer-reviewed by at least three independent reviewers. Requests for additional information should be addressed to the guest editors.

Topics for the Special Issue

Topics of interest include, but are not limited to:

· User interfaces for data science

· Visualization of time-dependent data, geo-localized data, and maps

· Data to visualization mappings

· Interactive knowledge discovery

· Visual operators on data and knowledge

· Big data visualization in various domains (health, education, politics, …)

· Visual exploration of datasets

· Visualization of data correlations

· Visual data mining and visual knowledge discovery

· Visualization of learning models

· Visualization techniques for data profiles

· Visualization for IoT data analytics

· Visual analytics for explainable AI

· Collaborative visual analytics and data science

· Adaptive visual analytics

· Visual trend analytics

· User evaluations and case studies, reports on real cases and experiments

Important Dates

Submission Deadline: February 15, 2021

Author Notification: May 15, 2021

Revised Manuscript Due: July 1, 2021

Notification of Acceptance: October 1, 2021

Final Manuscript Due: October 15, 2021

Tentative Publication Date: December, 2021

Guest Editors

Vincenzo Deufemia, University of Salerno

Kawa Nazemi, Darmstadt University of Applied Sciences

Giuseppe Polese, University of Salerno

Website of the Special Issue

Events

Thesis Presentation: Named-Entity Recognition on Publications and Raw-Text for Meticulous Insight at Visual Trend Analytics

17/03/2020/in Scitics, Thesis /by Dirk Burkhardt

Where: TU Darmstadt / GRIS, Fraunhoferstr. 5 (Darmstadt), Room tba

!!!!! Due to the Corona crisis and the accompanying restrictions at the TU Darmstadt, the exam will be non-public! !!!!!

Who: Ubaid Rana (Author), Prof. Dr. Arjan Kuijper (Supervisor), Dipl.-Inf. Dirk Burkhardt (Advisor/Co-Supervisor)
What: Master Thesis – “Named-Entity Recognition on Publications and Raw-Text for Meticulous Insight at Visual Trend Analytics”

Abstract:

In the modern data-driven era, a massive amount of research documents are available from publicly accessible digital libraries in the form of academic papers, journals and publications. This plethora of data does not lead to new insights or knowledge. Therefore, suitable analysis techniques and graphical tools are needed to derive knowledge in order to get insight of this big data. To address this issue, researchers have developed visual analytical systems along with machine learning methods, e.g text mining with interactive data visualization, which leads to gain new insights of current and upcoming technology trends. These trends are significant for researchers, business analysts, and decision-makers for innovation, technology management and to make strategic decisions.
Nearly every existing search portal uses the traditional meta-information e.g only about the author and title to find the documents that match a search request and overlook the opportunity of extracting content-related information. It limits the possibility of discovering most relevant publications, moreover it lacks the knowledge required for trend analysis. To collect this very concrete information, named entity recognition must be used to be able to better identify the results and trends. The state-of-the-art systems use static approach for named entity recognition which means that upcoming technologies remain undetected. Modern techniques like distant supervision methods leverage big existing community-maintained data sources, such as Wikipedia, to extract entities dynamically. Nonetheless, these methods are still unstable and have never been tried on complex scenarios such as trend analysis before.
The aim of this thesis is to enable entity recognition on both static tables and dynamic community updated data sources like Wikipedia & DBpedia for trend analysis. To accomplish this goal, a model is suggested which enabled entity extraction on DBpedia and translated the extracted entities into interactive visualizations. The analysts can use these visualizations to gain trend insights, evaluate research trends or to analyze prevailing market moods and industry trends.