The Project

Methodology

The project is structured into seven Work Packages (WPs), each addressing a key phase of research, development, and validation. The work plan follows an iterative approach, integrating user feedback and continuous refinement to maximize impact.

WP1

Coordination and Management

This work package oversees the overall project execution, ensuring alignment with objectives, resource management, and coordination across teams. Regular progress reviews, milestone tracking, and Data Management Plan (DMP) updates will be conducted to maintain efficiency and transparency.

WP2

User Needs Analysis

To develop AI tools that truly address the challenges faced by individuals with cognitive impairments, WP2 focuses on user research through HCI methods. This WP will define user requirements based on cognitive accessibility needs, considering aspects such as simplified language, multimodal interaction, and customization options. Ethical considerations will be integrated into the study.

WP3

Accessible UX/UI Design

Building upon WP2, this WP will design and validate accessible user interfaces for AI-driven tools, emphasizing clear prompts, intuitive navigation, and multimodal interactions (e.g., text, voice, and pictograms). A User-Centered Design (UCD) approach will be applied to ensure accessibility and usability for individuals with diverse cognitive abilities.

WP4

AI Model Adaptation

This WP focuses on the selection and fine-tuning of Large Language Models (LLMs) in Spanish to ensure accessibility. The methodology includes instruction-based tuning, prompt engineering, and retrieval-augmented generation (RAG) approaches to improve the quality of AI-generated responses. Special emphasis will be placed on reducing bias, improving interpretability, and optimizing ecological efficiency in model training.

WP5

Prototype Implementation

This WP translates research findings into real-world AI applications, developing two proof-of-concept prototypes:

Use Case 1 (Education): AI-driven tools to support individuals with cognitive impairments in preparing for non-routine events, such as excursions and cultural visits, through simplified explanations, pictograms, and structured information.
Use Case 2 (Health): AI-assisted tools for simplifying medical reports, discharge summaries, and health-related content, improving accessibility through clear language, voice synthesis, and interactive dialogues.

WP6

Empirical Validation

To ensure that the developed AI solutions effectively meet user needs, WP6 will conduct holistic assessments, including:

Usability and accessibility testing with real users, ensuring the tools are intuitive and beneficial.
AI performance evaluation, verifying the effectiveness of simplified language models.
Findings from this WP will inform refinements in WP3, WP4, and WP5, ensuring iterative improvements based on empirical evidence.

WP7

Dissemination and Impact

This WP is dedicated to maximizing project visibility and scientific impact through the following:

Academic publications and conference presentations in AI, accessibility, and HCI fields.
Collaboration with European research initiatives to extend project outcomes.
Public engagement and industry outreach to encourage adoption of accessibility-driven AI solutions.

A long-term sustainability strategy, exploring opportunities for follow-up funding and large-scale implementation.

Project PID2023-148577OB Funded by:

Accessibility

Este sitio web se ha diseñado para cumplir con el Real Decreto 1112/2018, de 7 de septiembre, sobre accesibilidad de los sitios web y aplicaciones para dispositivos móviles del sector público, en el que se indica que hay que ser conforme con la norma UNE-EN 301 549, que en lo que se refiere al contenido web, es cumplir con las Web Content Accessibility Guidelines (WCAG) 2.1.

Social networks