Interactive Visual Analytics and Explainable AI for Big Data
A special issue of Big Data and Cognitive Computing (ISSN 2504-2289).
Deadline for manuscript submissions: closed (15 April 2022) | Viewed by 686
Special Issue Editors
Interests: investigating the use of unsupervised learning, especially dimensionality reduction techniques; in the interactive visual analysis of complex and high-dimensional data; interpretable machine learning, text and topic analysis, and learning analytics; increase the level of interactivity in the process; improve the interpretability of complex learning algorithms, and to effectively incorporate these analysis methods into high-impact domain-specific workflows
Special Issues, Collections and Topics in MDPI journals
Interests: information visualisation (InfoVis); human–computer interaction (HCI); machine learning (ML) and artificial intelligence (AI); investigate the potential of integrating ML/AI techniques with interactive visual analysis methods, supporting users while carrying out data analysis tasks; explainable AI (XAI)
Special Issue Information
Dear Colleagues,
The benefits obtained from efficient and effective analysis methods for Big Data are not a prospect of the future anymore, but a reality. Smart organizations which intend to improve their processes with data-driven insights experience such benefits in their everyday routine. Research activities with high-throughput experimental processes, the optimization of large-scale industrial manufacturing, and investigation of human activities based on the monitoring of content generation are just some of the areas where Big Data analysis is well on the way of becoming not only a competitive advantage, but an absolute necessity.
Many different (but intersecting) research areas have been responsible for paving the way to this reality in recent years. One of them is machine learning, whose techniques have provided technical advances that allow computers to learn complex patterns in large amounts of data. However, with great power also comes great complexity; such complexity could hinder decision-making when analysts must understand the patterns—and their origins—before applying them. The debate on the need for explainability and interpretability in machine learning, and in artificial intelligence (AI) in general, is currently of great interest to the international research community, and has the potential to spark important changes across all its application areas.
In this Special Issue, we focus on the role of information visualization, human-computer interaction, and interactive visual analytics in solving the challenge of exploring Big Data with the use of complex machine learning techniques—supervised or unsupervised—while balancing potentially-contrasting requirements, such as complexity and efficiency vs. explainability and/or interpretability. Recent advances in these research areas have shown that well-designed interactive visualization-based solutions can be key for including the human in the loop of Big Data analysis. The investigation of datasets, algorithms, and models in coherent workflows, supported by visual analytics, can lead to the ultimate goals of obtaining impactful insights from large-scale data in a trustworthy and assessable way.
The following is a non-exhaustive list of suggested topics for submissions, but we will also gladly consider related submissions that explore the subject from unexpected and novel perspectives.
- New visual abstractions, interaction paradigms and visual analytics workflows for exploring Big Data
- Design and evaluation of explainable AI solutions in combination with interactive visual analytics
- Effective use of unsupervised learning (e.g. dimensionality reduction, clustering) in exploratory visual analysis
- Design studies in high-impact and domain-specific challenges related to Big Data solved with interactive visual analytics
- Systematic reviews and state-of-the-art summaries focusing on relevant topics within interactive visual analytics and explainable AI
- Quantitative and qualitative experimental evidence on the effectiveness of interactive visual analytics and explainable AI methods applied to Big Data
Dr. Rafael M. Martins
Dr. Maria Riveiro
Guest Editors
Manuscript Submission Information
Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.
Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Big Data and Cognitive Computing is an international peer-reviewed open access monthly journal published by MDPI.
Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1800 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.
Keywords
- visual analytics
- interaction
- human–computer interaction
- explainable AI
- big data
- exploratory visual analysis
