Part of the
TU DelftTU EindhovenUniversity of TwenteWageningen University


+31(0)6 48 27 55 61


Empathic Lighting

In this project, we aim to develop an affect-adaptive lighting system to be deployed in independent living for seniors. Seniors often experience negative affective states, such as gloominess due to the distance from their families or anxiety when disoriented (e.g. due to dementia). For updates check out site

Building on existing evidence of the power of (colored) lighting to relieve elderly from negative affective states, we aim to develop a system, that, when set in a room, (1) detects negative affective states of users, based on the analysis of audio and video signals as well as on a model of the user personality; (2) upon detection of a negative state, deploys an appropriate lighting configuration to relieve it and (3) allows a certain degree of personalization of the lighting configuration in order to maximize its beneficial effect. The project is expected to advance the knowledge in (1) affect detection, by including user personality models into existing affect detection paradigms, and (2) ambient assisted living, by exploring opportunities that personalization provides to the effectiveness of affect-adaptive care.

This project is embedded into the broader context of “Empathic Computing” research, which aims at utilizing ICT to design systems that unobtrusively detect negative affective states and act upon them in order to relieve the user in a way comparable to fellow humans. Our goal is to collect under the umbrella of Empathic Computing all 4TU researchers interested in generating new knowledge in the fields of affective computing, computer vision, user modelling, sensors, wearables, internet of things, human-computer/robot/media interaction and ambient intelligence, towards the creation of empathic, caring systems. To stimulate this, we propose to employ the NIRICT funding into not only research-related activities, but also networking events and workshops on the theme of Empathic Computing.