Quantified Self staat voor de zelfmetende mens. Het aantal mensen dat met zelf gegeneerde gezondheidsgegevens het zorgproces binnenwandelt gaat de komende jaren groeien. Verschillende soorten activity trackers en gezondheidsapplicaties voor de smartphone maken het relatief eenvoudig om persoonlijke gegevens te verzamelen over beweging, voeding, slaap, hartslag, menstruatiecyclus, etc. Steeds vaker zullen patiënten dit soort data meenemen naar de huisarts. Het is daarom raadzaam kennis te nemen van wat er zoal aan zelfmeettechnologie beschikbaar is en hoe het is gesteld met de kwaliteit, toepasbaarheid of zelfs generaliseerbaarheid van de data. In dit artikel lichten we de achtergrond van Quantified Self toe, zetten we dit in een breder perspectief van technologische ontwikkelingen en zullen we iets zeggen over de zin en onzin van zelfmetingen, waarbij de focus zal liggen op Quantified Self met betrekking tot gezondheid en levensstijl.
DOCUMENT
Learning is all about feedback. Runners, for example, use apps like the RunKeeper. Research shows that apps like that enhance engagement and results. And people think it is fun. The essence being that the behavior of the runner is tracked and communicated back to the runner in a dashboard. We wondered if you can reach the same positive effect if you had a dashboard for Study-behaviour. For students. And what should you measure, track and communicate? We wondered if we could translate the Quantified Self Movement into a Quantified Student. So, together with students, professors and companies we started designing & building Quantified Student Apps. Apps that were measuring all kinds of study-behaviour related data. Things like Time On Campus, Time Online, Sleep, Exercise, Galvanic Skin Response, Study Results and so on. We developed tools to create study – information and prototyped the Apps with groups of student. At the same time we created a Big Data Lake and did a lot of Privacy research. The Big Difference between the Quantified Student Program and Learning Analytics is that we only present the data to the student. It is his/her data! It is his/her decision to act on it or not. The Quantified Student Apps are designed as a Big Mother never a Big Brother. The project has just started. But we already designed, created and learned a lot. 1. We designed and build for groups of prototypes for Study behavior Apps: a. Apps that measure sleep & exercise and compare it to study results, like MyRhytm; b. Apps that measure study hours and compare it to study results, like Nomi; c. Apps that measure group behavior and signal problems, like Groupmotion; d. Apps that measure on campus time and compare it with peers, like workhorse; 2. We researched student fysics to see if we could find his personal Cup-A-Soup-Moment (meaning, can we find by looking at his/her biometrics when the concentration levels dip?); 3. We created a Big Data lake with student data and Open Data and are looking for correlation and causality there. We already found some interesting patterns. In doing so we learned a lot. We learned it is often hard to acquire the right data. It is hard to create and App or a solution that is presenting the data in the right way and presents it in a form of actionable information. We learned that health trackers are still very inprecise. We learned about (and solved some) challenges surrounding privacy. Next year (2017) we will scale the most promising prototype, measure the effects, start a new researchproject and continu working on our data lake. Things will be interesting, and we will blog about it on www.quantifiedstudent.nl.
LINK
Er ontstaan in Nederland veel blessures als gevolg van overbelasting in alle lagen van de sport. Hoe kunnen deze blessures worden voorkomen? Insteek van dit project is het gebruik van (sensor)technologie en big data analyse voor het vroegtijdig detecteren van signalen van overbelasting en daarmee het voorkomen van blessures. Een grote hoeveelheid technologie wordt momenteel al gebruikt voor het meten aan sporters (quantified self). Professionele sportclubs investeren in dure systemen. Diepte-interviews tonen echter aan dat er twee grote problemen zijn: ten eerste de grote hoeveelheid data en ten tweede de kennis voor een juiste interpretatie van de data benodigd voor een omzetting naar een trainingsadvies. Computermodellen opgebouwd uit systematische data-analyse van de enorme hoeveelheden trainingsdata en aangevuld met domeinkennis kunnen deze problemen oplossen. Er is behoefte aan een systeem waarin informatie uit verschillende bronnen in één systeem wordt opgeslagen en toegankelijk gemaakt om vervolgens geïntegreerd geanalyseerd te kunnen worden. Individuele profielen moeten gebouwd worden uit de data voor een snelle, automatische interpretatie. Hiermee kan grensbewaking voor overbelasting plaatsvinden en kunnen trainingsaanpassingen gedaan worden waar nodig. Vanuit deze behoefte richt het project zich op de praktijkvraag “Hoe kunnen we een praktisch toepasbaar gereedschap ontwikkelen dat valide de externe en interne trainingsbelasting kan meten, de (para)medische staf en/of fysiek trainer helpt bij het detecteren van (potentiële) overbelasting en daarmee helpt bij het plegen van de juiste interventies voor het voorkomen van blessures?”. Het principe van een dergelijke ‘belastingmonitor’ is al aangetoond. Voor een volwaardig prototype zal echter zowel het computermodel als de gebruikersapplicatie technisch gezien moeten worden doorontwikkeld, geoptimaliseerd, uitgebreid en vooral getest. Daar richten de onderzoeksvragen van dit project zich op. De focus ligt in eerste instantie op het (betaalde) voetbal, maar kan ook naar andere teamsporten en de breedtesport vertaald worden.
Structural colour (SC) is created by light interacting with regular nanostructures in angle-dependent ways resulting in vivid hues. This form of intense colouration offers commercial and industrial benefits over dyes and other pigments. Advantages include durability, efficient use of light, anti-fade properties and the potential to be created from low cost materials (e.g. cellulose fibres). SC is widely found in nature, examples include butterflies, squid, beetles, plants and even bacteria. Flavobacterium IR1 is a Gram-negative, gliding bacterium isolated from Rotterdam harbour. IR1 is able to rapidly self-assemble into a 2D photonic crystal (a form of SC) on hydrated surfaces. Colonies of IR1 are able to display intense, angle-dependent colours when illuminated with white light. The process of assembly from a disordered structure to intense hues, that reflect the ordering of the cells, is possible within 10-20 minutes. This bacterium can be stored long-term by freeze drying and then rapidly activated by hydration. We see these properties as suiting a cellular reporter system quite distinct from those on the market, SC is intended to be “the new Green Fluorescent Protein”. The ability to understand the genomics and genetics of SC is the unique selling point to be exploited in product development. We propose exploiting SC in IR1 to create microbial biosensors to detect, in the first instance, volatile compounds that are damaging to health and the environment over the long term. Examples include petroleum or plastic derivatives that cause cancer, birth defects and allergies, indicate explosives or other insidious hazards. Hoekmine, working with staff and students within the Hogeschool Utrecht and iLab, has developed the tools to do these tasks. We intend to create a freeze-dried disposable product (disposables) that, when rehydrated, allow IR1 strains to sense and report multiple hazardous vapours alerting industries and individuals to threats. The data, visible as brightly coloured patches of bacteria, will be captured and quantified by mobile phone creating a system that can be used in any location by any user without prior training. Access to advice, assay results and other information will be via a custom designed APP. This work will be performed in parallel with the creation of a business plan and market/IP investigation to prepare the ground for seed investment. The vision is to make a widely usable series of tests to allow robust environmental monitoring for all to improve the quality of life. In the future, this technology will be applied to other areas of diagnostics.
Automated driving nowadays has become reality with the help of in-vehicle (ADAS) systems. More and more of such systems are being developed by OEMs and service providers. These (partly) automated systems are intended to enhance road and traffic safety (among other benefits) by addressing human limitations such as fatigue, low vigilance/distraction, reaction time, low behavioral adaptation, etc. In other words, (partly) automated driving should relieve the driver from his/her one or more preliminary driving tasks, making the ride enjoyable, safer and more relaxing. The present in-vehicle systems, on the contrary, requires continuous vigilance/alertness and behavioral adaptation from human drivers, and may also subject them to frequent in-and-out-of-the-loop situations and warnings. The tip of the iceberg is the robotic behavior of these in-vehicle systems, contrary to human driving behavior, viz. adaptive according to road, traffic, users, laws, weather, etc. Furthermore, no two human drivers are the same, and thus, do not possess the same driving styles and preferences. So how can one design of robotic behavior of an in-vehicle system be suitable for all human drivers? To emphasize the need for HUBRIS, this project proposes quantifying the behavioral difference between human driver and two in-vehicle systems through naturalistic driving in highway conditions, and subsequently, formulating preliminary design guidelines using the quantified behavioral difference matrix. Partners are V-tron, a service provider and potential developer of in-vehicle systems, Smits Opleidingen, a driving school keen on providing state-of-the-art education and training, Dutch Autonomous Mobility (DAM) B.V., a company active in operations, testing and assessment of self-driving vehicles in the Groningen province, Goudappel Coffeng, consultants in mobility and experts in traffic psychology, and Siemens Industry Software and Services B.V. (Siemens), developers of traffic simulation environments for testing in-vehicle systems.