Data visualization Lab
Data visualization Lab
Overview
The Data Visualization Lab aims to provide state-of-the-art computational and visual analytics facilities for data visualization–oriented courses and research activities. The lab focuses on transforming complex datasets into meaningful visual representations to support data-driven decision-making. It enables students and researchers to design and develop interactive dashboards, visual analytics systems, and storytelling solutions using charts, graphs, geospatial maps, and real-time visualizations. The lab supports experimentation with large-scale datasets from domains such as healthcare, finance, smart cities, social media, and IoT. By promoting hands-on learning, interdisciplinary collaboration, and innovation, the Data Visualization Lab empowers students, researchers, and professionals to gain insights from data using modern visualization tools, libraries, and frameworks, while also providing strong support for web-based and analytics-driven application development.
Objectives
- To provide hands-on training in data visualization techniques for structured, semi-structured, and unstructured datasets.
- To support teaching and laboratory components of courses related to data visualization, data analytics, business intelligence, and visual analytics.
- To facilitate experimentation with large-scale and real-time datasets from domains such as healthcare, finance, smart cities, IoT, and social media.
- To promote data-driven decision-making by integrating visualization with data preprocessing, analytics, and machine learning models.
- To support project development, research publications, and industry-oriented solutions in the area of visual analytics.
Key Focus Areas
- Core domains the lab works on
- Data Visualization and Visual Analytics Design and development of static, interactive, and real-time visualizations for effective interpretation of complex and large-scale datasets.
- Data Science and Analytics Visual exploration, pattern discovery, and insight generation from structured and unstructured data to support data-driven decision-making.
- Artificial Intelligence and Machine Learning Visualization Visualization of model behavior, training processes, feature importance, and performance evaluation to improve model interpretability and validation.
- Domain-Specific Visualization Applications Visualization-driven analysis for applications in healthcare, IoT, smart cities, transportation, environmental monitoring, and social data.
- Ongoing research themes
- Interactive and Visual Analytics for Large-Scale Data Development of interactive visualization techniques for efficient exploration and interpretation of high-volume and high-dimensional datasets.
- Explainable AI and Model Interpretability through Visualization Visualization-driven approaches to understand, interpret, and validate machine learning and deep learning models.
- Visualization for Healthcare and Biomedical Data Visual analytics of physiological, clinical, and sensor data to support diagnosis, monitoring, and decision-making.
- Visualization of IoT, Edge, and Streaming Data Real-time visualization of data generated from IoT devices, edge intelligence systems, and cyber-physical applications.
- Visual Analytics for Smart Systems and Sustainable Applications Data-driven visualization solutions for smart cities, transportation systems, energy management, and environmental monitoring
Research Publications:
- Rakshan, N., Ragav, B., Rishikesh, G., Kumaran, K. and Saranya, G., 2025, March. Geospatial modelling of groundwater potential zones: A data-driven optimization. In 2025 International Conference on Data Science, Agents & Artificial Intelligence (ICDSAAI)(pp. 1-6). IEEE.
