INDUSTRY:

INDUSTRY:

AI & SMART SYSTEMS

AI & SMART SYSTEMS

CLIENT:

CLIENT:

UNIVERSITY OF AMSTERDAM

UNIVERSITY OF AMSTERDAM

EXPERIENCE:

EXPERIENCE:

HUMAN-CENTERED SYSTEMS DESIGN, AI, SENSORS

HUMAN-CENTERED SYSTEMS DESIGN, AI, SENSORS

LOCATION:

LOCATION:

AMSTERDAM

AMSTERDAM

Smart Information System

Smart Information System

Smart Information System

about.
about.
Smart Information System for Learning Space Selection

Developed for the University of Amsterdam, this project delivers a Smart and Inclusive Information System designed to help university students find learning spaces that best fit their environmental needs and personal preferences. Built as a web-based platform featuring an interactive dashboard, the system guides students in selecting suitable study areas on campus based on real-time and predicted conditions such as lighting, temperature, noise level, room capacity, and openness. By placing student agency at the core of the system’s functionality, the tool supports more effective and inclusive learning experiences.

Smart Information System for Learning Space Selection

Developed for the University of Amsterdam, this project delivers a Smart and Inclusive Information System designed to help university students find learning spaces that best fit their environmental needs and personal preferences. Built as a web-based platform featuring an interactive dashboard, the system guides students in selecting suitable study areas on campus based on real-time and predicted conditions such as lighting, temperature, noise level, room capacity, and openness. By placing student agency at the core of the system’s functionality, the tool supports more effective and inclusive learning experiences.

The system architecture (Figure 2) includes four main components: back-end data processing, a front-end website and dashboard, integrated data sources, and the student as the primary user. Environmental data—such as temperature (sensor-collected), natural lighting and noise level (manually evaluated), and real-time weather data—feeds into an adjustment algorithm that predicts future conditions based on user-selected dates and times. Students can filter learning spaces by selecting preferences for factors like noise level, lighting, and room size. These preferences are matched to categorized learning spaces across LAB42, presented via a Tableau-powered dashboard embedded into a custom-built HTML/CSS website.

The system doesn't alter physical environments but enhances how students interact with them. Each study space is classified into user-friendly categories—such as Relaxed, Deep Work, or Energy Hub—based on environmental factors. This makes the interface both intuitive and actionable. A linear regression model was trained to predict future indoor temperatures using real-time weather forecasts. The system architecture is modular and scalable, meaning it can be expanded to other buildings or universities. By combining data-driven modeling, thoughtful UI design, and human-centered values, the system provides an adaptive and empowering experience for students navigating complex learning environments.

The system doesn't alter physical environments but enhances how students interact with them. Each study space is classified into user-friendly categories—such as Relaxed, Deep Work, or Energy Hub—based on environmental factors. This makes the interface both intuitive and actionable. A linear regression model was trained to predict future indoor temperatures using real-time weather forecasts. The system architecture is modular and scalable, meaning it can be expanded to other buildings or universities. By combining data-driven modeling, thoughtful UI design, and human-centered values, the system provides an adaptive and empowering experience for students navigating complex learning environments.

Curious about what we can create together?

Available For Work

All rights reserved,

hzalle ©2025

Curious about what we can create together?

Available For Work

All rights reserved,

hzalle ©2025