Text

Programmeringsspråk

Programvarutestlaboratorium

Resurseffektivisering

Statsvetenskap

Säkerhetskritisk teknik

Teknisk matematik

Digitalisering av framtidens energi

Formell modellering och analys av inbyggda system

Förnybar energi

Heterogena system

Industriella AI-system

Industriell programvaruteknik

Komplexa inbyggda system i realtid

Lärande och optimering

Modellbaserad konstruktion av inbäddade system

Medicinsk teknik

Artificiell intelligens och intelligenta system

Automatiserade mjukvaruspråkutveckling och mjukvaruteknik

Certifierbara bevis och justifieringsteknik

Cyber-fysisk systemanalys

IEMI: Intelligent extraction of mental imagery during stroke rehabilitation

IEMI syftar till att utveckla intelligenta algoritmer för att extrahera ett kontinuerligt mått, från hjärnaktiviteten, relaterat till mental imagery (MI) av en fysisk rörelse. Projektet är särskilt inriktat på strokeöverlevare i deras rehabiliteringsprocess mot fysisk återhämtning.

Avslutat

Start

2017-07-01

Avslut

2019-06-30

Huvudfinansiering

Samarbetspartners

Forskningsområde

Forskningsinriktning

Projektansvarig vid MDU

No partial template found

Projektbeskrivning

Stroke is affecting around 30 000 people in Sweden every year. Despite intensive rehabilitation, a large group continues to live with persistent disabilities. Physical rehabilitation consists of regular training with a physiotherapist to increase mobility and strength of the affected limb. During training, patients are encouraged to simultaneously imagine the trained movements. Despite a lot of research showing the importance of MI for physical recovery, a means to measure MI in real time does not yet exist.

This is where IEMI comes in. The extracted measure of mental imagery will serve as crucial decision support for: 1) physiotherapists, who will receive real-time information on the mental engagement of patients during rehabilitation, 2) stroke patients, who will receive real-time feedback to strengthen their MI and directly enhance related brain activations. In addition, collected brain activity data will serve as a basis for developing functional diagnostics tools that can serve as a support for assessing the severity of stroke and deciding appropriate strategy for rehabilitation.

The outcomes of IEMI are expected to yield a prototype system of clinical decision support for enhanced stroke rehabilitation. Expert competences in artificial intelligence and in specialized stroke rehabilitation are merged in IEMI to present a highly innovative technology with the potential to substantially increase the quality of stroke rehabilitation.