You are here: / Allgemein

Book published– Integrating Artificial Intelligence and Visualization for Visual Knowledge Discovery

/in , , , , /by

Professor Kawa Nazemi edited together with colleagues from the London South Bank University, Instituto Superior de Engenharia de Lisboa, and the Central Washington University enhanced contributions of selected papers of the International Conference on Information Visualisation particularly on the intersection of artificial intelligence and visualization. The book will appear in the series Studies in Computational Intelligence by Springer Nature.

The book “Integrating Artificial Intelligence and Visualization for Visual Knowledge Discovery” is devoted to the emerging field of integrated visual knowledge discovery that combines advances in artificial intelligence/machine learning and visualization/visual analytics. A long-standing challenge of artificial intelligence (AI) and machine learning (ML) is explaining models to humans, especially for live-critical applications like health care. A model explanation is a fundamentally human activity, not only an algorithmic one. As current deep learning studies demonstrate, it makes the paradigm based on the visual methods critically important to address this challenge. In general, visual approaches are critical for discovering explainable high-dimensional patterns in all types in high-dimensional data offering “n-D glasses,” where preserving high-dimensional data properties and relations in visualizations is a major challenge. The current progress opens a fantastic opportunity in this domain.

This book is a collection of 25 extended works of over 70 scholars presented at AI and visual analytics-related symposia at the recent International Information Visualization Conferences with the goal of moving this integration to the next level.  The sections of this book cover integrated systems, supervised learning, unsupervised learning, optimization, and evaluation of visualizations.

The intended audience for this collection includes those developing and using emerging AI/machine learning and visualization methods. Scientists, practitioners, and students can find multiple examples of the current integration of AI/machine learning and visualization for visual knowledge discovery. The book provides a vision of future directions in this domain. New researchers will find here an inspiration to join the profession and to be involved for further development. Instructors in AI/ML and visualization classes can use it as a supplementary source in their undergraduate and graduate classes.

Shahrukh Badar defended his Master Thesis on Process Mining for Workflow-Driven Assistance in Visual Trend Analytics

/in , , , /by

In his thesis, Shahrukh Badar created process-driven assistance that is applied to the visual trend analytics domain. The goal was, based on previous users interactions and solved tasks, to assist further users in their work. Therefore, a universal visual assistance model was defined and acts also as the main contribution, based on defined interaction event taxonomy. This concept was applied to the Visual Trend Analytics domain on the SciTics reference system. This “SciTics – Science Analytics” is connected with different data sources and provides analysis of scientific documents. The interaction model provides assistance in terms of recommendations, where the user has an option either to apply a recommendation or ignore it. The solution provided in this thesis is model-based and utilizes the potential of Process Mining and Discovery techniques. It is started by creating an event taxonomy by identifying all possible ways of user interactions on the “SciTic – Visual Trend Analytics” web application. Next, enable the “SciTic – Visual Trend Analytics” web application to start logging events chronologically based on predefined taxonomy. Later, these events log is converted into Process Mining log format. Next, it applies the Process Discovery algorithm “Heuristics Miner” on these log data to generate a process model, which shows the overall flow of user interaction along with the frequencies. Later, this process model is used to provide users with recommendations.

More Information:

26 April 2022

Thesis Presentation: Process Mining for Workflow-Driven Assistance in Visual Trend Analytics

Where: TU Darmstadt / GRIS, Zoom: https://tu-darmstadt.zoom.us/j/86845586436?pwd=RUJiWm1QdWJ4VDg3MU93WUNOWWFTQT09 Who: Shahrukh Badar (Author), Prof. Dr. Arjan Kuijper (Supervisor), Dipl.-Inf. Dirk Burkhardt (Advisor/Co-Supervisor) What: Master Thesis – “Process Mining for Workflow-Driven Assistance in […]

Find out more »
TU Darmstadt / GRIS, Fraunhoferstraße 5
Darmstadt, Hessian 64283 Germany
+ Google Map

Sibgha Nazir defended her Master Thesis on Visual Analytics on Enterprise Reports for Investment and Strategical Analysis

/in , , , /by

In her thesis, Sibgha Nazir created a visual analytical approach to analyze annual financial reports in the perspective of investors’ interests. The goal of the thesis is to make use of visual analytics for the fundamental analysis of a business to support investors and business decision-makers. The idea is to collect the financial reports, extract the data and feed them to the visual analytics system. Financial reports are PDF documents published by public companies annually and quarterly which are readily available on companies’ websites containing the values of all financial indicators which fully and vividly paint the picture of a companies’ business. The financial indicators in those reports make the basis of fundamental analysis. The thesis focuses on those manually collected reports from the companies’ websites and conceptualizes and implements a pipeline that gathers text and facts from the reports, processes them, and feeds them to a visual analytics dashboard. Furthermore, the thesis uses state-of-the-art visualization tools and techniques to implement a visual analytics dashboard as the proof of concept and extends the visualization interface with interaction capability by giving them options to choose the parameter of their choice allowing the analyst to filter and view the available data. The dashboard fully integrates with the data transformation pipeline to consume the data that has been collected, structured, and processed and aims to display the financial indicators as well as allow the user to display them graphically. It also implements a user interface for manual data correction ensuring continuous data cleansing.

The presented application makes use of state-of-the-art financial analytics and information visualization techniques to enable visual trend analysis. The application is a great tool for investors and business analysts for gaining insights into the business and analyzing historical trends of its earnings and expenses and several other use-cases where financial reports of the business are a primary source of valuable information.

More Information:

28 March 2022

Thesis Presentation: Visual Analytics on Enterprise Reports for Investment and Strategical Analysis

Where: TU Darmstadt / GRIS, Zoom: https://tu-darmstadt.zoom.us/j/83620126004?pwd=a1hyUkprRWpMVXd3eEpNRTBVYk9tUT09 Who: Sibgha Nazir (Author), Prof. Dr. Arjan Kuijper (Supervisor), Dipl.-Inf. Dirk Burkhardt (Advisor/Co-Supervisor) What: Master Thesis – “Visual Analytics on Enterprise Reports for […]

Find out more »
TU Darmstadt / GRIS, Fraunhoferstraße 5
Darmstadt, Hessian 64283 Germany
+ Google Map

Advisory Board of the EUt+ Academic Press

/in , , , , , , , /by

Professor Kawa Nazemi was assigned as an advisory board member of the academic press of the European University of Technology (EUt+).

The EUt+ is an alliance of eight universities that make up the European University of Technology. The partners are Technical University of Sofia, Cyprus University of Technology, University of Technology Troyes, Hochschule Darmstadt, University of Applied Sciences, Technological University Dublin, Riga Technical University, Technical University of Cluj-Napoca, Technical University of Cartagena.

The EUT+ is part of the European initiative to build a European Education Area. The EUT+ Academic Press is an open access academic press. All material is free to read online. The academic press is committed to the principle that scholarship should be available to all without barriers or paywalls. It offers authors a global readership and thus contributes to the dissemination of knowledge. The academic press welcomes quality works of scholarship regardless of the subject area. The material is licensed under Creative Commons Attribution-Non-commercial-No Derivatives 4.0 International (CC BY-NC-ND 4.0) license We are committed to Gold Open Access which is the free, immediate and permanent online access to a publication’s version of record. Currently, there are no fees for authors.

Please find more information here.

Establishment of an Afghanistan Online University

/in , , , , , /by

The Human-Computer Interaction and Visual Analytics group of the Darmstadt University of Applied Sciences led the technical sessions on the first conference on establishing the Afghanistan Online University. Prof. Dr. Kawa Nazemi was assigned to the steering committee and the coordination team of the envisaged university.

The Afghanistan Online University aims to provide young persons of Afghan origin living outside Afghanistan – notably those living in refugee camps and other precarious settings – the opportunity to acquire general professional competencies and expertise in Afghan culture and society. A comprehensive system of online teaching, learning, and examination concurrently ensure the accessibility of the study provisions for young persons living in Afghanistan.

Students will be prepared to be professionally active in tune with their competencies all over the world and contribute to a desirable future of Afghanistan. A mix of professors and junior academics both from various countries of the world and of Afghan origin – among them those having lost the opportunity to serve universities in Afghanistan – can contribute to academic quality in all disciplines represented and the enhancement of knowledge on Afghan culture and society. Cooperation in teaching and research will be encouraged between scholars employed at this online university, those at a partner institution to be found for each discipline, and persons from many countries and institutions to be involved on a part-time basis.

Study programs on bachelor and master level, similar in length to the dominant „Bologna“ practices, as well as doctoral training will be provided – as customary at most open universities in the world – in the humanities, social sciences, and economic sciences, actually in 10 fields: Language and literature, education, psychology, social work, sociology, political science, journalism/communication science, economics, business studies, and additionally in IT/computer science. Master programs might specialize in certain topics (e.g. natural resources management) or interdisciplinary (e.g., gender studies). These fields are likely to be enriched by a creative dialogue between the theories, methods, and findings and the specifics of culture and society of Afghan culture and society. No study programs are envisaged in fields requiring substantial laboratory work or internships, of a clear universalistic knowledge base, and a sole national or regional thrust. Further education and continuing professional education programs might be added in the future.

Altogether, 60 professors and the same number of junior academic staff (FTE), supported by a substantial number of administrative staff, have to be employed for the ten disciplines to cover half of the teaching assignments and to be the backbone of research. A quarter of teaching each will be taken care of by scholars of the partner institutions and scholars from all over the world being involved part-time. Altogether, about 5,000 students can be accommodated, and a further increase can be realized with limited additional resources.

The online university will strive for high academic quality, a convincing link between academic quality and professional relevance, a guarantee of academic freedom, as well as support of the academic areas and of those persons suffering most under current adverse political conditions in Afghanistan, i.e., ethnic and religious minorities as well as women.

 

Kick-off Meeting of the Project “Digitallabor Groß-Gerau – Dozenturio”

/in , , , /by

Digitization and digital education are playing an increasingly important role in career guidance, career preparation, and vocational education. Various open technologies and didactic approaches are available that can be used for digital teaching in vocational education.

However, basic digital education and knowledge about the possibilities of digital teaching are often lacking. The VIS-Group is cooperating with the Groß-Gerau district and the Center for Applied Computer Science at the Darmstadt University of Applied Sciences to provide a single-source of learning materials and learning technologies in the “Dozenturio” learning system.

The intermediate results of the project were introduced in December 15th 2021 by the VIS-Group. The event started with a welcome by the District Administrator Thomas Will followed by the main goals and conceptual structure by Nicole Möhlenkamp from the Department of Education and Schools – Youth Vocational Assistance, Qualification, and Employment. Among others, representatives of the adult education centers of the district and the city of Rüsselsheim am Main, the municipal job center of the district of Groß-Gerau, the state education authority and the IT center of the district were present. District Administrator Thomas Will and First District Deputy Walter Astheimer also took part in the panel discussion.

The project website already includes various video training courses on communication systems, various selected OER learning platforms (OER: Open Educational Resources), and a variety of technologies to enable both the digital transformation and the didactical transformation of digital content. The platform is accessible to anyone who wants to learn about digital teaching and communication through www.dozenturio.de.

The goal of the project is to develop qualification modules for digital teaching, learning, advising, and communicating. In addition, demand-oriented training offers for employees of the district as well as for regional educational institutions are planned. As part of the training and qualification budget of the state of Hesse. The district of Groß-Gerau has been provided with funds for the implementation of digital learning offerings for the period from September 1, 2020 to August 31, 2022, which will be used for the project described. With this funding program, the district of Groß-Gerau is taking advantage of the opportunities offered by digitization and opening up access opportunities for multipliers, teachers, and advisors.

Further information

Lennart Sina defended his Master Thesis on Visual Analytics for Unstructured Data and Scalable Data Models

/in , , , /by

In the thesis, Lennart Sina conceptualized and implemented a visual analytics system that scales data through middleware to enable more efficient analysis. For this purpose, diverse approaches and systems were investigated, which led to a coherent concept. The concept was implemented and connected to an existing database, enabling real-world use of the system and real-world conditions. The scientific contribution of the present work is three-fold: (1) the concept of a visual analytics system to scale data, (2) a novel data model, and (3) a novel and a fully implemented visual dashboard that also enables reporting.

 

 

Article Published to Visual Data Analytics in impact Magazine for Applied Research and Art

/in , , , , , , /by

The impact Magazine for Applied Research and Art of the Darmstadt University of Applied Sciences published an article, based on an interview with Prof. Dr. Kawa Nazemi, to the research field Visual Data Analytics.

The article is about how tangible patterns can be discerned from huge data sets with the help of visual analysis and representation, and how applicable predictions can be made using a combination of artificial and human intelligence: That is the specialty of Kawa Nazemi, professor for computer science at the h_da’s Department of Media. The head of the Human-Computer Interaction and Visual Analytics research group is a sought-after expert in this still-young field and is also successfully making his mark on the international stage.

Further information

Call for Papers to the Collaborative European Research Conference 2021

/in , , , /by

This year’s Collaborative European Research Conference (CERC) will take place with the support of scientists and members of our team. The 7th edition of the conference aims at young academics and is primarily organized and held by colleagues from Munster Technological University (Cork, Ireland). The conference will take place from 9-10 September 2021 as blended event in presence and online/virtual.

The CERC was held for the first time in 2010 by the Darmstadt University of Applied Sciences (h_da) and the Munster Technological University (Cork, Ireland) – previously named Cork Institute of Technology (CIT) – and was originally organized by lecturers from the IT department of these two institutions. The event, which takes place alternately every year at one of the partner universities, is deliberately interdisciplinary and the presented researches cover a wide range of topics – from bioinformatics to social history. This promotes the exchange of ideas between the specialist areas and thus the opportunity for new collaborations.

CERC 2021 has the goal of a broad research program. Relevant topics for the conference include, but are not limited to, the following areas:

  • eHealth
  • Natural Language Processing and its applications
  • Internet of Things, Networks and Robotics
  • Sensors and wireless temperature measurements
  • Data Computing and Artificial Intelligence
  • Business and Society
  • Visual Computing and Data Analytics
  • Cybersecurity and cybercrime
  • BioInformatics and BioMedicine

Accepted contributions will be published in digital proceedings with an ISSN number – it is intended that publications shall be submitted to CEUR-WS for online publication, indexed among other at DBLP, Scopus, Semantic Scholar and Google Scholar. Extended versions of the best papers may be published into an upcoming special issues of “Sensors” (ISSN 1424-8220, Impact Factor: 3.275) and “Methods and Protocols” (ISSN 2409-9279; CODEN: MPERC6) Journals.

If you have interesting research results, you are invited to submit your paper by June 3oth. Interested parties can also attend the conference without a submission. Please note the information on the website: http://www.cerc-conf.eu.

Irtaza Rasheed defended his Master Thesis on Name Disambiguation on Digital Library Data for an Enhanced Profile Analysis in Visual Trend Analytics

/in , , , /by

In his thesis, Irtaza Rasheed implementated a universal name disambiguation approach that considers almost any existing property to identify authors. After an author of a paper is identied, the normalized name writing form on the paper is used to refine the author model and even give an overview about the different writing forms of the author’s name. This can be achieved by first examine the research on Human-Computer Interaction specifically with focus on (Visual) Trend Analysis. Furthermore, a research on different name disambiguation techniques. After that, building a concept and implementing a generalized method to identify author name and affiliation disambiguation while evaluating different properties.

About | Imprint | Data Privacy

© 2022 Research Group on Human-Computer Interaction & Visual Analytics (vis) – Darmstadt University of Applied Sciences (h_da)