General introduction

The department of Industrial Design is one of the nine departments of the Eindhoven University of Technology (TU/e). Research at the department is focused on two areas or thematic clusters: Systemic Change and Future Everyday.

The Systemic Change cluster focuses on designing innovations that have impact on systemic structures and groups of people, ultimately aiming to address large-scale issues such as urban health, future mobility and sustainability. Field data is used in novel iterative and circular research-through-design processes involving strategic alliances of stakeholders.

'Systemic Change uses Design and Technology to study socio-technical systems at the level of a community, by designing interventions addressing societal challenges and analyzing their effect on the eco-system'. Systemic change is the extension to standard Human-Computer Interaction Processes and Methods to address societal change.

The Systemic Change cluster focuses on the co-creation of socio-technical systems operating in semi-open real-life ecosystems or field labs, with the aim to address clearly defined societal challenges and study the nature, drivers and opportunities for sustainable change induced by these systems on an ecosystem level. Main focus is the usage of emerging technology (e.g. sensors and actuators, visualization of data, application of AI methods or datamining crowd platforms) to envision, design and evaluate these systems and their longitudinal effects. To enable these long-term studies, we develop the necessary methods, tools, platforms, spaces and field labs to support the co-creation and analyses of these socio-technological systems in cross-disciplinary stakeholder teams.

This project is carried out in close collaboration with the department of Mathematics and Computer Science. In the department Computer Science the section Information Systems studies subjects related to the design, realization, analysis and optimization of information systems. In this section the Data Mining (DM) chair studies techniques and knowledge discovery approaches that are at the core of data science. The group is known for its contributions to the areas of predictive analytics, automation of machine learning and networked science, subgroup discovery and exceptional model mining, and similarity computations on complex data. In this group one research line, lead by dr. Joaquin Vanschoren, concentrates on the progressive automation of machine learning. Dr. Vanschoren founded and leads OpenML.org, an open science platform allowing scientists to share datasets and train many machine learning models from many software tools in a frictionless yet principled way. It also organizes all results online, providing detailed insight into the performance of machine learning techniques, and allowing a more scientific, data-driven approach to building new machine learning systems. Subsequently, he uses this knowledge to create automatic machine learning (AutoML) techniques that learn from these experiments to help people build better models, faster, or automate the process entirely.  Machine learning is the science of making computers act without being explicitly programmed. Instead, algorithms are used to find patterns in data.

The ITEA Inno4Health project

In our aging population, the number of surgeries performed is increasing rapidly. At the same time, there is a growing risk of complications, as patients are becoming frailer and have more comorbidities. In top sports, tracking the condition of athletes is essential to guide physical preparation. However, maladaptation to training, risks of injuries and adverse health events like sudden cardiac arrest are often reported in the news, affecting both elite as well as recreational athletes.

These problematic challenges deriving from the healthcare and sports domains may require solutions that have a lot more in common than it could intuitively be thought.

In the clinical community, preparing patients to be fit for surgery and rehabilitation generates a win-win situation for: i) payers in terms of healthcare cost savings, ii) patients in terms of health outcome and iii) clinicians in terms of workload; due to optimized speed of recovery and minimized chance of complications. In the sports practice, preparing athletes to achieve top performance during competitions is a routine practice, which requires insight into the fitness, recovery and psychological status of the individual.

INNO4HEALTH aims to stimulate innovation in continuous health and fitness monitoring and address challenges within both healthcare and sports domains. In healthcare, continuous monitoring of health and fitness will provide information to patients and their treating physicians regarding the readiness associated with surgery and the ability to recover rapidly from invasive treatment. In top sports, the same technology will be used to continuously assess fitness and health to provide information to athletes and their coaches and to help them optimize performance during competitions.

INNO4HEALTH will create innovate design for wearable sensors (insoles, shirts, plasters) that address usability needs of both patients and athletes. Wearable products (commercially available or investigational research prototypes) will be included in a device ecosystem to enable data collection in healthcare and sports use cases. AI technology will be used for the first time to develop algorithms for performance and fitness assessment with validity in both patients and athletes. Ultimately, domain-dependent professional dashboards and applications will be created to generate actionable insights for health and fitness improvement programs.

In the context of this project TU/e will develop:

• AI (deep learning) techniques that are able to accurately model detailed biophysical and other health data, and that are additionally able to efficiently adapt to new, personalized data, gathered locally by individual users, to optimize personalized healthcare or training.
• Localized AI systems that will involve the development of AI algorithms which, after a learning phase, have the ability to semi-autonomously, deal with low-level biophysical signals of individual patients in order to detect both long-term trends affecting fitness/medical condition of people involved. Only high-level signals and trends are communicated to a more central level thus preserving patient's privacy as well as the risk on misuse of the information. 
• Feedback-coaching systems that will communicate the above information on an individualized manner to the users (and coaches/medical specialists) involved.

A full description of the ITEA project is available at request.

2 PhD positions on the ITEA project Inno4Health

These positions are part of collaboration between the departments of Industrial Design and Computer Science as part of the larger Inno4Health consortium. This consortium is led by Philips Research

The two successful PhD Candidates will be embedded in the Systemic Change Group under the supervision of Prof. Dr. Ir. Aarnout Brombacher and the Data Mining group of the Department of Computer Science led by Dr. Joaquin Vanschoren. The PhD candidates will also actively participate in the Inno4Health consortium.

We are looking for candidates that meet the following requirements:

• a solid background in Computer Science and/or Industrial Design (or an adjacent field in the engineering sciences) with a strong affinity towards technology and programming, shown by a master's degree in Industrial Design, Computer Science or related disciplines,
• a strong interest in methods and their development
• a good basis is data analytics and statistics
• good communication skills in English, both in speaking and in writing;
• capability and willingness to work both independently and in a team of researchers and interact with domain experts; being highly motivated, rigorous, and disciplined;
• being enthusiastic about working on the changing use cases;
• experience in research and a publication record will be considered additional advantages.

We offer:

• a challenging job in a dynamic and ambitious university;
• A full time temporary appointment for a period of 4 years, with an intermediate evaluation after 9 months;
• A gross salary of €2.395 per month in the first year increasing up to €3.061 in the fourth year;
• a yearly holiday allowance of 8% of the yearly salary;
• a yearly end year allowance of 8.3% of the yearly salary;
• a broad package of fringe benefits (including an excellent technical infrastructure, moving expenses, savings schemes and excellent sports facilities).
• The PhD candidates will be working partly at the TU/e Industrial Design and at Philips Experience Design both in Eindhoven.