Interactive Visual Analytics for AI, Knowledge Integration, and Decision Intelligence

Permanent URI for this collectionhttps://hdl.handle.net/10125/112434

Browse

Recent Submissions

Now showing 1 - 4 of 4
  • Thumbnail Image
    Item type: Item ,
    A Visual Analytics Framework for Imputing Incomplete Time-Series Data
    (2026-01-06) Yeon, Hanbyul; Jang, Yun
    Missing or corrupted data during collection or transmission can distort the original characteristics of time-series datasets, leading to biased and unreliable analyses. Although numerous statistical and machine learning techniques have been developed to address data incompleteness, the absence of ground truth makes it challenging to determine the optimal imputation strategy. The effectiveness of imputation largely depends on the nature of the dataset, the mechanism and extent of missingness, and the specific missing patterns—all of which can vary significantly. Consequently, the quality and reliability of imputation results are often influenced by the analyst’s expertise and intuition. In this paper, we propose a visual analytics approach designed to support decision-making in imputing missing values within incomplete time-series data. Our system enables analysts to investigate potential causes of missingness, understand data characteristics, and compare various imputation models interactively. Through a series of use cases, we demonstrate how our approach facilitates informed and transparent model selection, ultimately enhancing the trustworthiness of downstream analysis.
  • Thumbnail Image
    Item type: Item ,
    StyleScript: A Structured Data Augmentation Framework for Transformer-Based OCR in Engineering Documents
    (2026-01-06) Javadnejad, Farshid; Li, Jiang; Kovacic, Samual; Sousa-Poza, Andres; Khallouli, Wael
    Engineering documents often contain a combination of printed and handwritten text, intricate layouts, and visual degradation, posing significant challenges to Optical Character Recognition (OCR) systems. Transformer-based models like TrOCR provide strong baseline performance but require domain-specific data augmentation to generalize effectively. This paper introduces StyleScript, a structured data augmentation framework that generates realistic synthetic word images by extracting stroke-based style features such as slant angle and thickness. We fine-tune both TrOCR (small) and TrOCR (large) models using real and StyleScript-augmented data derived from a Military Sealift Command (MSC) dataset. Additionally, we develop a systematic OCR pipeline combining preprocessing, CRAFT-based text detection, and fine-tuned TrOCR recognition to digitize full-page engineering documents with spatial fidelity. Experimental results show that StyleScript-enhanced training improves OCR performance across diverse document conditions, making it a practical solution for engineering and other technical domains with limited annotated data.
  • Thumbnail Image
    Item type: Item ,
    VisPile: A Visual Analytics System for Analyzing Multiple Text Documents With Large Language Models and Knowledge Graphs
    (2026-01-06) Coscia, Adam; Endert, Alex
    Intelligence analysts perform sensemaking over collections of documents using various visual and analytic techniques to gain insights from large amounts of text. As data scales grow, our work explores how to leverage two AI technologies, large language models (LLMs) and knowledge graphs (KGs), in a visual text analysis tool, enhancing sensemaking and helping analysts keep pace. Collaborating with intelligence community experts, we developed a visual analytics system called VisPile. VisPile integrates an LLM and a KG into various UI functions that assist analysts in grouping documents into piles, performing sensemaking tasks like summarization and relationship mapping on piles, and validating LLM- and KG-generated evidence. Our paper describes the tool, as well as feedback received from six professional intelligence analysts that used VisPile to analyze a text document corpus.
  • Thumbnail Image
    Item type: Item ,