You are here: / Visual Trend Analysis

Tag Archive for: Visual Trend Analysis

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

Book appeared – Integrating Artificial Intelligence and Visualization

/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.
Read more

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.

 

 

Best Paper Award at the iV 2021

/in , , /by

We are proud to announce that our paper on “Visual Analytics and Similarity Search – Interest-based Similarity Search in Scientific Data” at the iV2021 conference was honored with “The Best Paper Award” for its innovative contribution in terms of originality of concepts and application in Visual Analytics and Data Science. The “Best Paper Awards” is given to contributions that will be selected by the committee among the papers presented in iV2021 and applied for the award. The study’s relevance to the symposium’s scope, its scientific contribution, writing/presentation style will be considered in the evaluation process as well.

The Information Visualisation Conference (iV) is an international conference that aims to provide a foundation for integrating the human-centered, technological and strategic aspects of information visualization to promote international exchange, cooperation, and development. The conference was held virtually at the University of Technology, Sydney.

Three Papers Accepted at IEEE Information Technology and Management Science Conference (ITMS 2020)

/in , , , , /by

Three of our submitted collaboration papers got accepted at the this year’s IEEE Information Technology and Management Science Conference 2020. The conference aims at bringing together young scientists and researchers from information technologies and management sciences in an effort to promote and encourage cross-fertilization of ideas and tools related to the general topics of the conference, such as Information Technology, Information Systems, Computer Technologies, Data Processing, System Security and Control, Modelling and Simulation, Automatic Control, E-Commerce and E-Governance, Cloud Computing, Human Computer Interaction, Cyber-Physical Systems, Intelligent Systems, Internet of Everything.

Paper #1: Visual Analytics Indicators for Mobility and Transportation

Abstract:
Visual Analytics enables a deep analysis of complex and multivariate data by applying machine learning methods and interactive visualization. These complex analyses lead to gain insights and knowledge for a variety of analytics tasks to enable the decision-making process. The enablement of decision-making processes is essential for managing and planning mobility and transportation. These are influenced by a variety of indicators such as new technological developments, ecological and economic changes, political decisions and in particular humans’ mobility behavior. New technologies will lead to a different mobility behavior with new constraints. These changes in mobility behavior and logistics require analytical systems to forecast the required information and probably appearing changes. These systems have to consider different perspectives and employ multiple indicators. Visual Analytics enable such analytical tasks. We introduce in this paper the main indicators for Visual Analytics for mobility and transportation that are e exemplary explained through two case studies to illustrate the advantages of such systems. The examples are aimed to demonstrate the benefits of Visual Analytics in mobility.

Link to paper/fulltext: DOI: 10.1109/ITMS51158.2020.9259321

More information about the technology and topic: Scitics for Visual Trend Analytics, Business Analytics,  Trend Analytics and Technology Foresights

Paper #2: Innovations in Mobility and Logistics: Assistance of Complex Analytical Processes in Visual Trend Analytics

Abstract:
A variety of new technologies and business ideas are arising in the domain of mobility and logistics. It can be differentiated between fundamental new approaches, e.g. central packaging stations or deliveries via drones and minor technological advancements that aim on more ecologically and economic transportation. The need for analytical systems that enable identifying new technologies, innovations, business models etc. and give also the opportunity to rate those in perspective of business relevance is growing. The users’ behavior is commonly investigated in adaptive systems, which is considering the induvial preferences of users, but neglecting often the tasks and goals of the analysis. A process-related supports could assist to solve an analytical task in a more efficient and effective way. We introduce in this paper an approach that enables non-professionals to perform visual trend analysis through an advanced process assistance based on process mining and visual adaptation. This allows to calculate a process model based on events, which is the baseline for process support feature calculation. These features in form of visual adaptations and the process model enable assisting non-experts in complex analytical tasks.

Link to paper/fulltext: DOI: 10.1109/ITMS51158.2020.9259309

More information about the technology and topic: Scitics for Visual Trend Analytics, Business Analytics,  Trend Analytics and Technology Foresights

Paper #3: On Microservice Architecture Based Communication Environment for Cycling Map Developing and Maintenance Simulator

Abstract:
Urban transport infrastructure nowadays involves environmentally friendly modes of transport, the most democratic of which is cycling. Citizens will use bicycles if a reasonably designed cycle path scheme will be provided. Cyclists also need to know the characteristics and load of the planned route before the trip. Prediction can be provided by simulation, but it is often necessary to use heterogeneous and distributed models that require a specific communication environment to ensure interaction. The article describes an easy communication environment that is used to implement interaction and interoperability in a multi-agent-based cycle path design and exploitation simulator, where each domain simulation is performed as a microservice.

Link to paper/fulltext: DOI: 10.1109/ITMS51158.2020.9259299

More information about the the topic: eGovernance and Policy Modeling

Midhad Blazevic defended his Master Thesis on Visual Search and Exploration for Scientific Publications through Similarity

/in , , , /by

In his thesis, Midhad Blazevic alyzes exploratory search systems which use sophisticated features, visualizations and similarity-based algorithms to enhance exploratory searches. Examining how similarity algorithms are currently used in combination with elements from information retrieval, natural language processing and visualizations, but also examine what exploratory search is, what the requirements are and what makes it so special in modern times. Furthermore, the user himself or herself will be analyzed as user behavior during exploratory searches is a key factor that has to be taken into consideration when looking to optimize the exploratory search process overall. Based on these aspects, means of improvement will be developed and showcased, which will be used to determine if there is an improvement in comparison to other well-known systems. The outcome of this thesis will present a prototype of an exploratory search system along with a practical use case.

Two Papers Accepted at 6th Collaborative European Research Conference (CERC 2020)

/in , , , , /by

At the this year’s Collaborative European Research Conference (CERC 2020) two of our students papers titled “Visual Dashboards in Trend Analytics to Observe Competitors and Leading Domain Experts” and “A Future Prospect for European Collaboration on Advanced Analytics in Economy and Society” were accepted for presentation. Due to Corona epidemic the conference is hold virtually. The multidisciplinary CERC is an annual event that takes place since 2011 when it was initiated by University partners across Europe. It brings together researchers from a wide range of disciplines in order to foster knowledge transfer, inter-disciplinary exchange and collaboration.

Paper #1: Visual Dashboards in Trend Analytics to Observe Competitors and Leading Domain Experts

Abstract:
The rapid changes due to digitalization challenges a variety of market players and forces them to find strategies to be aware of changes in these markets, particularly those that impacts their business. The main challenge is how a practical solution could look like and how technology can support market players in these trend ob-servation tasks. The paper outlines therefore a technological solution to observe specific authors e.g. researchers who influence a certain market or engineers of competitor. In many branches both are well-known groups to market players and there is almost the need of a technology that support the topical observation. The main contributions of this paper are next to the concept of how a visual dash-board could enable a market observation and how data has to be processed for it, the prototypical implementation which enables an evaluation later on. Further-more, the definition of a principal technological analysis for innovation and tech-nology management is created and is also an important contribution to the scien-tific community that specifically considers the technology perspective and it cor-responding requirements.

Link to paper/fulltext: http://ceur-ws.org/Vol-2815/CERC2020_paper14.pdf

More information about the technology: Scitics for Visual Trend Analytics

Paper #2: A Future Prospect for European Collaboration on Advanced Analytics in Economy and Society

Abstract:
Analytical Reasoning by applying machine learning approaches, artificial intelli-gence, NLP and visualizations allow to get deep insights into the different do-mains of various stakeholders and enable to solve complex tasks. Thereby the tasks are very heterogenous and subject of investigation in the different areas of application. These tasks or challenges should be defined by the stakeholders themselves and lead through a deep investigation to advanced analytical ap-proaches. We therefore set up a strategic alliance of research, enterprises and so-cietal organization with the goal of a strong collaboration to identify in a first step these challenges and workout technological solutions for each application scenar-io. We give in this paper a first draft of current challenges and technological ad-vancements. The main contribution of this paper is next to an accurate description of the current challenges in the analytics domain, also the description of an agen-da how these challenges can be solved. Furthermore, a process is explained, how the strategic alliance should act and organize their work to realize beneficial and useful analytical solutions.

Link to paper/fulltext: http://ceur-ws.org/Vol-2815/CERC2020_paper27.pdf

More information about the project and the expected collaboration project: EuroStraNet-project, VisCOST-project, partner network for COST

 

The whole proceedings of the CERC 2020 are available under: http://ceur-ws.org/Vol-2815/.

Two Paper Accepted at 24rd Internation Conference Information Visualization (iV 2020)

/in , , , , /by
We are very glad to be accepted for presenting our papers titled “Comparison of Full-text Articles and Abstracts for Visual Trend Analytics through Natural Language Processing” and “An Industry 4.0-Ready […]
Read more

Tag Archive for: Visual Trend Analysis

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

/in , /by

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 Visual Trend Analytics”

Abstract:

In today’s data-driven world, a large amount of data is being generated daily. This data is generated by different sources, such as social networking platforms, industrial machinery, daily transactions, etc. The companies or businesses are not only generating data but also utilizing them to improve their processes, business decisions, etc. There are several applications and tools that help users to analyze this big data in-depth, by providing numerous ways to explore it, including different types of visualization, pivoting, filtering, grouping data, etc. The challenge with such applications is that it creates long and heavy learning curves for users, who need to work with such applications. Many systems are often designed for a specific purpose, and therewith to know how a single system works is not enough. To enable a better work entrance with such an analytical system, a kind of adaptive assistance would be helpful. So, the system would hint the users regarding his previous work and interaction, what next action might be useful. The thesis aims to face this challenge with process-driven assistance that is applied to the visual trend analytics domain. The goal is, based on previous users interactions and solved tasks, to assist further users in their work. Therefore, a universal visual assistance model is defined and acts also as the main contribution, based on defined interaction event taxonomy. This concept is applied on the Visual Trend Analytics domain on the SciTic reference system, This “SciTic – Visual Trend 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.

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

/in , /by

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 Investment and Strategical Analysis”

Abstract:

Given the availability of enormous data in today’s time, suitable analysis techniques and graphical tools are required to derive knowledge in order to make this data useful. Scientists and developers have come up with visual analytical systems that combine machine learning technologies, such as text mining with interactive data visualization, to provide fresh insights into the present and future trends. Data visualization has progressed to become a cutting-edge method for displaying and interacting with graphics on a single screen. Using visualizations, decision-makers may unearth insights in minutes, and teams can spot trends and significant outliers in minutes [1]. A vast variety of automatic data analysis methods have been developed during the previous few decades. For investors, researchers, analysts, and decision-makers, these developments are significant in terms of innovation, technology management, and strategic decision-making.

The financial business is only one of many that will be influenced by the habits of the next generation, and it must be on the lookout for new ideas. Using cutting-edge financial analytics tools will, of course, have a significant commercial impact. Visual analytics, when added to the capabilities, can deliver relevant and helpful insights. By collecting financial internal information from different organizations, putting them in one place, and incorporating visual analytics tools, financial analytics software will address crucial business challenges with unprecedented speed, precision, and ease.

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 this 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 a 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.

26th International Conference Information Visualization (iV 2022)

/in /by

We are co-organizing the International Symposium Visual Analytics and Data Science at the next International Information Visualisation Conference (iV 2022), which is held online. The Information Visualisation Conference (iV) is an international conference that aims to provide a foundation for integrating the human-centered, technological and strategic aspects of information visualization to promote international exchange, cooperation and development. The proceedings will be published as usual in IEEE Xplore.

Visual Analytics is the science of analytical reasoning empowered by interactive visualizations. The research on Visual Analytics is closely related to that of Data Science. Both areas seek to enhance the knowledge discovery process using machine learning, data mining, and artificial intelligence methods. In contrast, Visual Analytics allows direct manipulation of the underlying models through graphical representations commonly. By leveraging human perception of the visual space, patterns that might not otherwise be discovered emerge. Visual Analytics utilizes concepts from various disciplines, including computer graphics, information visualization, machine learning, artificial intelligence, knowledge discovery, cognition, and visual perception.

Papers on all aspects of Visual Analytics and Data Science are solicited. Papers will be refereed and appear in the main conference proceedings published by Conference Publishing Services CPS – Conference Publishing Services, – Library of Congress/ISSN, ISBN, and other bibliographical registration details; Arrange for indexing through INSPEC, EI (Compendex), Thomson ISI, and other indexing services. A selection of the best papers will be recommended for publication in special issues of scientific journals, or as an edited book.

 

The topics of interest include but are not limited to:

  • Combining visual and computational methods of Data Analysis, Machine Learning, and Artificial Intelligence
  • Visual Analytics models and approaches
  • Novel Visual Analytics applications
  • Visual Trend Analytics
  • Visual Analytics, geo-visualization and geographical visualization of spatial, temporal, and Spatio-temporal data
  • Visualization support for multi-criteria decision analysis related to multivariate and spatial data
  • Knowledge construction and management in Visual Analytics
  • Guidance in Visual Analytics
  • Intelligent approaches of Visual Analytics and Data Science
  • Adaptive Visual Analytics
  • HCI issues of geographical and Spatio-temporal visual analytics
  • Cognitive approaches and explanations for Visual Analytics
  • Visual Analytics for explaining AI
  • Visualization of Data Mining algorithms
  • Empirical performance studies
  • Evaluation of Visual Data Mining methods
  • Collaborative Visual Analytics and Data Science
  • Computational steering for long-running Data Mining applications
  • Reviews and surveys of related literature


Related news for further information:

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

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

/in , /by

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 Visual Trend Analytics”

Abstract:

In today’s data-driven world, a large amount of data is being generated daily. This data is generated by different sources, such as social networking platforms, industrial machinery, daily transactions, etc. The companies or businesses are not only generating data but also utilizing them to improve their processes, business decisions, etc. There are several applications and tools that help users to analyze this big data in-depth, by providing numerous ways to explore it, including different types of visualization, pivoting, filtering, grouping data, etc. The challenge with such applications is that it creates long and heavy learning curves for users, who need to work with such applications. Many systems are often designed for a specific purpose, and therewith to know how a single system works is not enough. To enable a better work entrance with such an analytical system, a kind of adaptive assistance would be helpful. So, the system would hint the users regarding his previous work and interaction, what next action might be useful. The thesis aims to face this challenge with process-driven assistance that is applied to the visual trend analytics domain. The goal is, based on previous users interactions and solved tasks, to assist further users in their work. Therefore, a universal visual assistance model is defined and acts also as the main contribution, based on defined interaction event taxonomy. This concept is applied on the Visual Trend Analytics domain on the SciTic reference system, This “SciTic – Visual Trend 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.

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

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

/in , /by

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 Investment and Strategical Analysis”

Abstract:

Given the availability of enormous data in today’s time, suitable analysis techniques and graphical tools are required to derive knowledge in order to make this data useful. Scientists and developers have come up with visual analytical systems that combine machine learning technologies, such as text mining with interactive data visualization, to provide fresh insights into the present and future trends. Data visualization has progressed to become a cutting-edge method for displaying and interacting with graphics on a single screen. Using visualizations, decision-makers may unearth insights in minutes, and teams can spot trends and significant outliers in minutes [1]. A vast variety of automatic data analysis methods have been developed during the previous few decades. For investors, researchers, analysts, and decision-makers, these developments are significant in terms of innovation, technology management, and strategic decision-making.

The financial business is only one of many that will be influenced by the habits of the next generation, and it must be on the lookout for new ideas. Using cutting-edge financial analytics tools will, of course, have a significant commercial impact. Visual analytics, when added to the capabilities, can deliver relevant and helpful insights. By collecting financial internal information from different organizations, putting them in one place, and incorporating visual analytics tools, financial analytics software will address crucial business challenges with unprecedented speed, precision, and ease.

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 this 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 a 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.

Book appeared – Integrating Artificial Intelligence and Visualization

/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.
Read more

26th International Conference Information Visualization (iV 2022)

/in /by

We are co-organizing the International Symposium Visual Analytics and Data Science at the next International Information Visualisation Conference (iV 2022), which is held online. The Information Visualisation Conference (iV) is an international conference that aims to provide a foundation for integrating the human-centered, technological and strategic aspects of information visualization to promote international exchange, cooperation and development. The proceedings will be published as usual in IEEE Xplore.

Visual Analytics is the science of analytical reasoning empowered by interactive visualizations. The research on Visual Analytics is closely related to that of Data Science. Both areas seek to enhance the knowledge discovery process using machine learning, data mining, and artificial intelligence methods. In contrast, Visual Analytics allows direct manipulation of the underlying models through graphical representations commonly. By leveraging human perception of the visual space, patterns that might not otherwise be discovered emerge. Visual Analytics utilizes concepts from various disciplines, including computer graphics, information visualization, machine learning, artificial intelligence, knowledge discovery, cognition, and visual perception.

Papers on all aspects of Visual Analytics and Data Science are solicited. Papers will be refereed and appear in the main conference proceedings published by Conference Publishing Services CPS – Conference Publishing Services, – Library of Congress/ISSN, ISBN, and other bibliographical registration details; Arrange for indexing through INSPEC, EI (Compendex), Thomson ISI, and other indexing services. A selection of the best papers will be recommended for publication in special issues of scientific journals, or as an edited book.

 

The topics of interest include but are not limited to:

  • Combining visual and computational methods of Data Analysis, Machine Learning, and Artificial Intelligence
  • Visual Analytics models and approaches
  • Novel Visual Analytics applications
  • Visual Trend Analytics
  • Visual Analytics, geo-visualization and geographical visualization of spatial, temporal, and Spatio-temporal data
  • Visualization support for multi-criteria decision analysis related to multivariate and spatial data
  • Knowledge construction and management in Visual Analytics
  • Guidance in Visual Analytics
  • Intelligent approaches of Visual Analytics and Data Science
  • Adaptive Visual Analytics
  • HCI issues of geographical and Spatio-temporal visual analytics
  • Cognitive approaches and explanations for Visual Analytics
  • Visual Analytics for explaining AI
  • Visualization of Data Mining algorithms
  • Empirical performance studies
  • Evaluation of Visual Data Mining methods
  • Collaborative Visual Analytics and Data Science
  • Computational steering for long-running Data Mining applications
  • Reviews and surveys of related literature


Related news for 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.

 

 

Best Paper Award at the iV 2021

/in , , /by

We are proud to announce that our paper on “Visual Analytics and Similarity Search – Interest-based Similarity Search in Scientific Data” at the iV2021 conference was honored with “The Best Paper Award” for its innovative contribution in terms of originality of concepts and application in Visual Analytics and Data Science. The “Best Paper Awards” is given to contributions that will be selected by the committee among the papers presented in iV2021 and applied for the award. The study’s relevance to the symposium’s scope, its scientific contribution, writing/presentation style will be considered in the evaluation process as well.

The Information Visualisation Conference (iV) is an international conference that aims to provide a foundation for integrating the human-centered, technological and strategic aspects of information visualization to promote international exchange, cooperation, and development. The conference was held virtually at the University of Technology, Sydney.

Online @ 25th International Conference Information Visualization (iV 2021)

/in /by

We are co-organizing the International Symposium Visual Analytics and Data Science at the next International Information Visualisation Conference (iV 2021), which is held online. The Information Visualisation Conference (iV) is an international conference that aims to provide a foundation for integrating the human-centered, technological and strategic aspects of information visualization to promote international exchange, cooperation and development. The proceedings will be published as usual in IEEE Xplore.

Visual Analytics is viewed as the science of analytical reasoning empowered by interactive visualizations. It combines interactive visualizations with models and approaches of machine learning and artificial intelligence, enabling solving complex analytical tasks by uncovering hidden patterns in data.
The research on Visual Analytics is closely related to that of Data Science. Both areas seek to enhance the knowledge discovery process using machine learning, data mining, and artificial intelligence methods, whereas Visual Analytics allows commonly a direct manipulation of the underlying models through graphical representations. By leveraging human perception of the visual space, patterns that might not otherwise be discovered. Visual Analytics utilizes concepts from a wide variety of disciplines, including Computer Graphics, Information Visualization, Machine Learning, Artificial Intelligence, Knowledge Discovery, Cognition, and Visual Perception.
Papers on all aspects of Visual Analytics and Data Science are solicited. Papers will be refereed and appear in the main conference proceedings published by Conference Publishing Services CPS – Conference Publishing Services, – Library of Congress/ISSN, ISBN, and other bibliographical registration details; Arrange for indexing through INSPEC, EI (Compendex), Thomson ISI, and other indexing services.

A selection of the best papers will be recommended for publication in special issues of scientific journals, or as an edited book.

Topics of interest:

  • Combining visual and computational methods of data analysis
  • Visual querying
  • Visual analytics of spatial, temporal, and spatiotemporal data
  • Knowledge construction and management in visual analytics
  • Privacy issues in visual analytics
  • Cognitive approaches and explanations for visual data mining
  • Visualization of the data mining algorithm
  • Scalability issues
  • Empirical studies of performance
  • Evaluation of visual data mining methods
  • Collaborative visualization and mining
  • Applications of visual data mining and analytics
  • Case studies
  • Computational steering for long-running data mining applications
  • Reviews and surveys of related literature


Related news for further information:

About | Services | Imprint | Data Privacy

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