Denne tekst er automatisk oversat og kan derfor afvige fra originalen. Der kan ikke drages rettigheder på baggrund af denne oversættelse.
At blockchain, IoT, and data science are interesting technologies, and we know it. Last Monday, 19 students proved that they are also applicable in healthcare and mobility during the presentations of the results of Q1-2 2018 from the ICT Lab Utrecht.
Vaccination registration with Blockchain
The vaccination booklet, where traveler vaccinations are recorded, is in desperate need of innovation. There is no control over the data currently being recorded. This leads to a fragmented approach, incorrect registration, and fraud. Moreover, losing your booklet can be a big problem (and it happens quite often…).
If the vaccination booklet were to be digitized, the composition of the recorded data could be controlled. 
Digitization also offers opportunities to register and authorize users of the booklet. Blockchain's added value is that there is no need to trust a central party to guard (and modify) the data.
Ana, Joris, Karim, Lex, and Timo explored possibilities for digitizing the vaccination booklet using blockchain. The results of their live demo presented on Monday were so promising that they will dedicate themselves to building a working and tested application from September for six months.
Big Data in healthcare
There are tons of open data available on healthcare costs, but can you really do something with it? 
You'd think the more data, the better, but the usability of data depends heavily on their interconnectivity.
Bram, Christiaan, Koshin, Steven, and Thijs researched how healthcare data can be used to identify so-called hotspots. They reduced a lot of data to a dataset where data was linked together. Then, they reduced this 'Swiss cheese' of data to a nicely filled Excel sheet where a large number of indicators per municipality are compared. They used this data to test the usability of models by applying various machine learning approaches.
Smart monitoring zone
There are few countries in the world where, just like in the Netherlands, most bicycle locks are worth more than the bike itself. Despite these sturdy chain locks, the Netherlands faces a bicycle theft problem. An estimated 450,000 bicycles are stolen each year. The municipality of Utrecht is now exploring whether IoT combined with RFID tags can be used to reduce bicycle theft. The concept works as follows: 2 RFID tags are mounted on the bike and 1 RFID tag on the keychain. At a bicycle parking facility, a UHF-RFID reader is placed, similar to the gates at train stations but with higher power. 
When a person parks their bike, the reader registers the three RFID tags. After parking the bike, two transmitters (on the bike) remain, and one transmitter (on the keychain) exits the zone. The system then registers this as a person locking their bike and walking away. This data is then sent to the cloud via the LoRa network. If the two transmitters leave the zone without the third one, it indicates that the bike is being stolen. However, there are still many questions about this concept. What is the range of the UHF-RFID reader? Is LoRa a suitable technology to send the data? How should the RFID tags be best attached to the bike? What are possible interference factors for reading the RFID tags?
To answer these questions, Anton, Armand, Leon, and Wessel set up a test installation at the Hooghiemstraplein in Utrecht.
VRIs and bicycle data
Bike loops on the road are laid to communicate with traffic lights: when a cyclist rides over them, the traffic light 'knows' it's time to turn green. A nice additional feature is that these loops can be used to count the number of cyclists riding over them. 
This is not always very accurate; some cyclists are missed. How can these loops be calibrated to measure accurately?
Daan, Jawad, Rami, Steven, and Younes investigated patterns in VRI data of cyclists in the Utrecht city center. They discovered that certain differences between loop counts are a good predictor of 'crowdedness' (bike traffic jams and congestion). In this way, calibrating the loops for measuring the effects of certain infrastructure changes is not immediately necessary.