eHealth

We research and develop technologies that focus on supporting the healthcare practice, through advanced multisensorial networks signal processing, computer vision algorithms and inference engines for user monitoring and behavioural modeling, as well as through VR-based intervention and reinforcement tools. In this context, our research includes:

- In-house automatic recognition of daily activities based on depth image processing and ambient multisensorial platforms, within an MCI/Alzheimer monitoring and support context – focus on in-vitro system training, prior to system installation. Reference: EnNOISIS project

eHealth

 

- Physical exercise interventions support and monitoring for MCI/Alzheimer – physical exercises guided through VR-trainer, monitored through markerless motion tracking, compared to optimal or past executions of the patient. Reference: EnNOISIS project

eHealth

- Cognitive reinforcement and monitoring tools, targeting MCI and Alzheimer’s disease. We have developed cognitive screening tests and VR-based tools engaging users in close-to-real-life scenarios, such as shopping in supermarket or gardening. Reference: EnNOISIS project

eHealth

eHealth

 

- Biosignals monitoring. Research and development of processing algorithms for biosignals including ECG, GSR, EMG, EEG, toward detecting human affective states.
Indicative publications:
1. D. Giakoumis, D. Tzovaras, K. Moustakas, G. Hassapis, "Automatic Recognition of Boredom in Video Games using novel Biosignal Moment-based Features", IEEE Transactions on Affective Computing, vol. 2, no. 3, pp. 119-133, September 2011
2. D. Giakoumis, D. Tzovaras, G. Hassapis, "Subject-dependent biosignal features for increased accuracy in psychological stress detection", International Journal of Human-Computer Studies, 71 (4). 425-439, April 2013


- Monitoring activity-related behavioural correlates of stress. Enhancing automatic psychological stress detection through novel activity-related behavioural features, extracted through computer vision and accelerometer signal processing. Reference: INTERSTRESS project
Indicative publication: D. Giakoumis, A. Drosou, P. Cipresso, D. Tzovaras, G. Hassapis, A. Gaggioli, G. Riva, "Using Activity-Related Behavioural Features towards more Effective Automatic Stress Detection", PLoS ONE 7(9): e43571., 26 July 2012, doi:10.1371/journal.pone.0043571

eHealth


View Related Demos