Portfolio by Maria Insa Iglesias

Overview: Members from GCU's Data Science Research Group, led by Professor Gordon Morison, took part in the Corona Hack. This is a week-long competition, organised by artificial-intelligence consultancy Mindstream-AI, where multi-disciplinary teams from all over the UK use their data skills to devise innovative techniques to combat COVID-19 using publicly available data. The entire event took place online using Slack and Microsoft Teams.

Challenge: The GCU team, which Maria was part, developed a solution to aid first diagnosis of COVID-19 in hospitals based on chest X-rays and clinical annotations. During the course of the week, the team members used their data science and software-development skills to create a prototype visualisation tool, which uses X-ray images and other patient data to show doctors the level of COVID-19 severity in a patient.

Scope: Five Days. From research to conception, prototyping.

Tools: Streamlit, Python, AI

Achievement: 2nd place Hackathon Competition.

Overview: Many open-source tools like JavaScript library D3, Tableau and R exist to create interactive visualisation platform. Furthermore, there are other tools that allow rendering and interacting 3D graphics like Potree.

Challenge: Exploration of open-source for 2D and 3D interactive visualisation. Potree allowed discovering its potential tools to measure, annotate and extract the elevation profile from 3D reconstructed model. R and D3 allowed exploring common visualisation techniques such as parallel coordinate and boxplot graphs.

Tools: D3.js, Potree, ggplot2, RStudio

Overview

Overview: CREW (Scotland's Centre of Expertise for Waters) aims to raise awareness of the water environment and pharmaceutical concentrations in populated areas through effective visual communication.

Challenge: Ideate data-visualisation solutions that communicate pharmaceutical risk to both domain experts and non-expert audiences. This work delivered recommended visualisation approaches as part of the CREW-Reduction project.

Scope: Ideation, research, visualisation.

Tools: Sketching, visual techniques, GIS

Overview

Overview: Large volumes of complex data are collected which require visualisation and interaction techniques to enable domain experts to extract useful information. AI technologies enable the development of algorithms to automatically process and analyse this data, but outputs are often complex and require interpretation by domain experts.

Challenge: Develop a 2D/3D visualisation tool to support structural examiners during condition assessments. The tool allows allocation of structural defects, identification of defect type, and evaluation of severity in a photorealistic 3D environment. A tunnel case study demonstrates applicability.

Scope: Concept → research → design → prototype → user testing.

Tools: C++, Unreal Engine, Blender

Overview

Overview: Traditional railway tunnel inspections are time-consuming and can produce inconsistent data. This project designs an optical-thermal camera rig to improve inspection quality and repeatability.

Challenge: Design and manufacture an imaging rig to supplement visual/manual inspections and provide reliable data for condition monitoring and maintenance planning.

Scope: 12-week honours thesis: research → conception → design → prototype → user testing.

Tools: AutoCAD, SolidWorks, Keyshot

Achievement: Part of a distinction dissertation and published work: Imaging system for railway tunnel inspection.

Overview

Problem: Manually checking crop heights is time-consuming and inconsistent, making comparisons and harvest prediction difficult. Lack of standardised height data complicates analysis and decision-making.

Scope & Tools: Design → prototype → testing → launch (Feb–Aug 2022). Azure, APIs, TypeScript & Angular, Plotly.js.

Outcome: Customer-facing app that tracks crop growth in a Growth Tower and flags plants growing too close to lights. Supports trend analysis and operational alerts. Find more here: project details.

Overview

Problem: Users need comprehensive documentation to effectively use the IGS Crop Height Tracker.

Scope & Tools: User guide covering installation, setup, and usage instructions.

Outcome: A complete user guide that helps users understand and utilize the Crop Height Tracker effectively.

Overview

Overview: A set of visualisation standards and a catalogue to make plots feel native to their context — consistent grammar, typography and graph elements (title, subtitle, axis labels, legend, data source, logo).

Challenge: Define and document a practical visual grammar and provide code templates so teams can apply consistent styles across matplotlib, plotly and holoviews.

Scope & Tools: Documentation, example templates and a python package (matplotlib, plotly, holoviews). Includes "Backstage" developer docs and Quick Style Reference templates.

Outcome: Visual catalogue, code templates and a library of styles to reduce design debt and speed up consistent reporting. Includes examples (scatter, time-series, boxplot, heatmap) and guidance on common mistakes and limitations.

Overview: A cooperative Minecraft experience where friendly NPCs guide players through shared tasks. The goal was to create a welcoming space that helps neurodivergent people connect, collaborate, and feel included within religious communities.

Challenge: Many tech interventions focus on education or therapy, not real social connection. We needed an experience that felt safe, supportive, and genuinely social, while fitting the rhythms and values of a faith community.

Scope: From research to conception, prototyping, testing and launch. 4 months (June-Sep 2021).

Tools: Java, AWS, Minecraft plugin & other APIs.

Outcome: Designed and developed a Minecraft mod with in-game cooperative tasks supported by NPCs to encourage social interaction and inclusion.

Overview: As a freelance UX Designer for Lupovis, I designed a cybersecurity visualisation system that helps operators make sense of complex attack data and turn it into actionable decisions during incident response.

Challenge: The product was early-stage, so the interface had to be convincing enough to secure funding while still grounded in real operator workflows. The designs needed to show clarity, scalability, and a strong user story.

Scope: UX research, concepting, prototyping and validation. Oct 2020 – Feb 2021.

Tools: Figma.

Outcome: Supported cross-functional MVP delivery and helped secure £650k in funding to continue development.