Machine Learning
VACLab research in machine learning typicaxlly explores applied ML topics such as clustering, prediction, classification, anomaly detection. These projects most often have a visualization-based component, either with visualizations designed to improve ML performance or ML designed to improve the user experience with visualization.
Publications
Knowledge Compass: A Question Answering System Guiding Students with Follow-Up Question Recommendations
Pedagogical question-answering (QA) systems have been utilized for providing individual support in online learning courses. However, …
October 2023
Demo Proceedings of ACM UIST
Human-Computer Collaboration for Visual Analytics: an Agent-based Framework
The visual analytics community has long been aiming to better understand users and assist them in their analytic endeavours. As a …
June 2023
Computer Graphics Forum (Proceedings of EuroVis 2023)
GRAFS: Graphical Faceted Search System to Support Conceptual Understanding in Exploratory Search
When people search for information about a new topic within large document collections, they implicitly construct a mental model of the …
Interpretable Anomaly Detection in Event Sequences via Sequence Matching and Visual Comparison
Anomaly detection is a common analytical task that aims to identify rare cases that differ from the typical cases that make up the …
July 2021
IEEE TVCG (Early Access)
AutoClips: An Automatic Approach to Video Generation from Data Facts
Data videos, a storytelling genre that visualizes data facts with motion graphics, are gaining increasing popularity among data …
June 2021
Computer Graphics Forum (Volume 40, Number 3, Proceedings of EuroVis 2021)
An Evaluation of Clinical Natural Language Processing Systems to Extract Symptomatic Adverse Events from Patient-Authored Free-Text Narratives
Symptomatic adverse events (AEs) such as nausea are common among patients enrolled in cancer clinical trials. Historically, this …
March 2021
American Medical Informatics Association (AMIA) Informatics Summit Podium Abstract
Visual Causality Analysis of Event Sequence Data
Causality is crucial to understanding the mechanisms behind complex systems and making decisions that lead to intended outcomes. Event …
January 2021
IEEE TVCG (Volume 27, Issue 2)
CarePre: An Intelligent Clinical Decision Assistance System
Clinical decision support systems are widely used to assist with medical decision making. However, clinical decision support systems …
February 2020
ACM Transactions on Computing for Healthcare (Volume 1, Issue 1)
Visual Anomaly Detection in Event Sequence Data
Anomaly detection is a common analytical task that aims to identify rare cases that differ from the typical cases that make up the …
Precision VISSTA: Bring-Your-Own-Device (BYOD) mHealth Data for Precision Health
A Bring-Your-Own-Device (BYOD) model for contributing mobile health (mHealth) data enables real-world data collection as patients go …
November 2019
American Medical Informatics Association (AMIA) Annual Symposium Podium Abstract
Precision VISSTA: Machine Learning Prediction and Inference for Bring-Your-Own-Device (BYOD) mHealth Data
Precision VISSTA is a bring-your-own-device (BYOD) mobile health (mHealth) patient-powered research study focused on Inflammatory Bowel …
November 2019
American Medical Informatics Association (AMIA) Annual Symposium Podium Abstract
Bootstrapping estimates of stability for clusters, observations and model selection
Clustering is a challenging problem in unsupervised learning. In lieu of a gold standard, stability has become a valuable surrogate to …
Han Yu, Brian Chapman, Arianna Di Florio, Ellen Eischen, David Gotz, Mathews Jacob, Rachael Hageman Blair
March 2019
Computational Statistics (Volume 34, Issue 1)
Visual Progression Analysis of Event Sequence Data
Event sequence data is common to a broad range of application domains, from security to health care to scholarly communication. This …
January 2019
IEEE TVCG (Volume 25, Issue 1)
RCLens: Interactive Rare Category Exploration and Identification
Rare category identification is an important task in many application domains, ranging from network security, to financial fraud …
July 2018
IEEE TVCG (Volume 24, Issue 7)
ECGLens: Interactive Visual Exploration of Large Scale ECG Data for Arrhythmia Detection
The Electrocardiogram (ECG) is commonly used to detect arrhythmias. Traditionally, a single ECG observation is used for diagnosis, …
April 2018
ACM CHI Conference on Human Factors in Computing Systems
EventThread: Visual Summarization and Stage Analysis of Event Sequence Data
Event sequence data such as electronic health records, a person’s academic records, or car service records, are ordered series of …
January 2018
IEEE TVCG (Volume 24, Issue 1)
Interactive Temporal Feature Construction: A User-Driven Approach to Predictive Model Development
As organizations gather ever larger and more detailed datasets, predictive modeling is becoming a widely used technology in support of …
Comparative Visualization of the RNA Suboptimal Conformational Ensemble In Vivo
When a ribonucleic acid (RNA) molecule folds, it often does not adopt a single, well-defined conformation. The folding energy landscape …
June 2017
Biophysical Journal (Volume 113, Issue 2)
Flexible bootstrapping and analytic approaches towards the clustering of complex medical data
Identifying subgroups from a severely heterogeneous population is major challenge for Big Data. Different clustering methods optimize …
Rachael Hageman Blair, Brian Chapman, Arianna Di Florio, Ellen Eischen, David Gotz, Mathews Jacob, Han Yu
November 2016
NIH Big Data to Knowledge (BD2K) All Hands Meeting Posters
UnTangle Map: Visual Analysis of Probabilistic Multi-Label Data
Data with multiple probabilistic labels are common in many situations. For example, a movie may be associated with multiple genres with …
Interactive Ensemble clustering for mixed data with application to mood disorders
Mental disorders are among the most elusive conditions in medicine and defy simple models, be they biological, psychological, social, …
November 2015
NIH Big Data to Knowledge (BD2K) All Hands Meeting Posters
Iterative Cohort Analysis and Exploration
Cohort analysis is a widely used technique for the investigation of risk factors for groups of people. It is commonly employed to gain …
UnTangle: Visual Mining for Data with Uncertain Multi-Labels Via Triangle Map
Data with multiple uncertain labels are common in many situations. For examples, a movie may be associated with multiple genres with …
Progressive Visual Analytics
As datasets grow and analytic algorithms become more complex, the typical workflow of analysts launching an analytic, waiting for it to …
Visualizing Accuracy to Improve Predictive Model Performance
Visualization methods have traditionally focused on visualizing retrospective data, often with the goal of helping users identify data …
ICDA: A Platform for Intelligent Care Delivery Analytics
The identification of high-risk patients is a critical component in improving patient outcomes and managing costs. This paper …
Interactive Visual Patient Cohort Analysis
Retrospective patient cohort analysis is a widely used technique in many healthcare studies. Due to its data intensive nature, the …
SolarMap: Multifaceted Visual Analytics for Topic Exploration
Documents in rich text corpora often contain multiple facets of information. For example, an article from a medical document collection …
December 2011
IEEE International Converence on Data Mining (ICDM)
ChronAtlas: A Visualization for Dynamic Topic Exploration
Documents in rich text corpora such as digital libraries and social media often contain complex information. These data resources are …
Predicting Patient's Trajectory of Physiological Data using Temporal Trends in Similar Patients: A System for Near-Term Prognostics
Providing near-term prognostic insight to clinicians helps them to better assess the near-term impact of their decisions and potential …
October 2010
American Medical Informatics Association (AMIA) Annual Symposium