Eindhoven University of Technology (TU/e) is an internationally renowned technical university located in the vibrant technological heart of the Netherlands with high tech companies such as Philips, ASML, NXP and DAF Trucks. The TU/e has an excellent reputation in collaboration with industry proven among other things by the fact that it is the number one university in the world with respect to joint scientific publications with industrial partners.

The Data Science Center Eindhoven is the response of the TU/e to the growing volume and importance of data. Through the DSC/e, the TU/e unites its strong research groups in areas related to data science: computer science, mathematics, electrical engineering, industrial engineering, innovation sciences, and industrial design. Research at the DSC/e is multidisciplinary, reflecting the fact that data science research requires a broad range of expertise and skills.

The TU/e has recently started a long-term strategic cooperation with Philips Research Eindhoven on three topics: data science, health and lighting. As a first concrete action, 70 PhD students are being hired for these three topics using joint funding from the TU/e and Philips, of which 18 PhD students will work on the data science topic. These students will together with researchers from the TU/e and Philips form a strong research community working together on scientific and industrial challenges.

Project Themes

The entire project is divided into 5 themes. Within each theme there is a specific application focus that will be addressed through intensive collaboration from several disciplines. For each individual PhD project we briefly mention the TU/e supervisors and their departments (M&CS = Mathematics and Computer Science, EE = Electrical Engineering, IE&IS = Industrial Engineering and Innovation Sciences). PhD students will have their home base at the department of the first mentioned professor.

Data Driven Value Proposition Digital components are being added to Philips lifestyle products. The data from these products as well as from Philips touch points must be combined to optimize user experience and maintain customer satisfaction. This will be delivered through personalized e-coaching and guidance apps. We are looking for students with expertise in one or more of the following fields: data mining, machine learning, process analytics, predictive analytics, and psychology. This theme has openings for 4 PhD students:

- User-centric Consumer Data Analytics: User Behaviour Modelling (supervisors: Professors De Bra (M&CS) and Petkovic (M&CS))
- User-centric Consumer Data Analytics: User Guidance Principles Modelling (supervisors: Professors IJsselsteijn (IE&IS) and De Bra (M&CS))
- Product-centric Consumer Data Analytics: Product Usage Lifecycle Analysis (supervisors: Professors Van der Aalst (M&CS) and Snijders (IE&IS))
- Product-centric Consumer Data Analytics: Text Mining for Consumer Insight Analytics (supervisors: Professors Snijders (IE&IS) and De Bra (IE&IS))

Healthcare Smart Maintenance Philips has strong leadership positions in healthcare imaging and patient monitoring systems. In the healthcare domain, reducing equipment downtime and cost of ownership for hospitals is of vital importance. Smart maintenance exploits that professional equipment is connected to the internet and aims to use event and sensor data for overall cost reduction. We are looking for students with expertise in one or more of the following fields: operations research, maintenance, process mining, data mining, machine learning, process analytics and predictive analytics. This theme has openings for 3 PhD students:



- Transforming Event Data into Predictive Models (Professors Van der Aalst (M&CS) and Van Houtum (IE&IS))
- Turning Outcomes of Predictive Models into Better Maintenance Decisions (Professors Boxma (M&CS) and Van Houtum (IE&IS))
- Maintenance Concepts for Healthcare Systems (Professors Van Houtum (IE&IS) and Van Leeuwaarden (M&CS))

Optimizing Healthcare Workflows The delivery of patient care in hospital is a complex workflow based on fixed protocols. Optimization of patient care at reduced cost requires the orchestration of multiple clinical workflows. Timely getting the imaging/lab tests done and getting the results back to physicians can help quickly diagnose/treat the patient, and save lives. The rapid digitization of diagnostics in radiology and pathology calls for a data-driven optimization of the workflows. We are looking for students with expertise in one or more of the following fields: visualisation, data mining, machine learning, process analytics and predictive analytics. This theme has openings for 4 PhD students:

- Predictive Analytics for Healthcare Workflows (Professors Van der Aalst (M&CS) and Van Wijk (M&CS))
- Visual Analytics for Healthcare Workflows (Professors Van Wijk (M&CS) and Van der Aalst (M&CS))
- Radiology Workflow Optimization and Orchestration (Professors Van der Aalst (M&CS) and Van Wijk (M&CS))
- Modelling and Optimization of Pathology Workflows and Flexible Semantic Orchestration (Professors Van Wijk (M&CS) and Van der Aalst (M&CS))

Continuous Personal Health Philips wishes to develop a cost-effective system for empowering people to self-manage their health. An important enabler is the wearable sensor technology developed by Philips because that provides unobtrusive monitoring of behaviour and habits. We are looking for students with expertise in one or more of the following fields: signal processing, statistics, data mining, machine learning, and psychology. This theme has openings for 5 PhD students:

- Effective Self-Management by E-Coaching (Professors IJsselsteijn (IE&IS) and De Bra (M&CS))
- Unobtrusive Health and Behaviour Monitoring (Professors Van der Hofstad (M&CS) and Aarts (EE))
- Cardiac Arrhythmia and Self-Management (Professors Aarts (EE) & Van der Hofstad (M&CS))
- Blood Pressure Monitoring and Lifestyle Interventions (Professors Korsten (EE) and IJsselsteijn (IE&IS))
- Early Stratification of Cardio-vascular Health Risks (Professors Korsten (EE) & Kaymak (IE&IS))

Data Analytics for Lighting Data gathered from large hardware systems offers new exciting service propositions. Philips has a unique position with the ability to extend the hardware to collect data or to respond to the outcome of predictive filters. In the field of building management and connected lighting infrastructures, this includes the ability to launch service businesses, to optimally predict cost-benefits in service offerings, to provide adaptive configuration, and to support network maintenance. We are looking for students with a background in one or more of the following fields: distributed systems, real-time systems, resource management data mining, and machine learning. This theme has openings for 2 PhD students:
- Data Analytics for Infrastructures of Connected Lighting (Professors Lukkien (M&CS) and Linnartz (EE))
- Data Analytics for Building Management Services (Professors Linnartz (EE) and Lukkien (M&CS))