For more information please contact Prof. dr. ir. Katrien Verbert, tel.: +32 16 32 82 86, mail: email@example.com or Prof. dr. ir. Bart Vanrumste, tel.: +32 16 32 64 07, mail: firstname.lastname@example.org.
You can apply for this job no later than August 31, 2019 via the online application tool.
KU Leuven seeks to foster an environment where all talents can flourish, regardless of gender, age, cultural background, nationality or impairments. If you have any questions relating to accessibility or support, please contact us at diversiteit.HR@kuleuven.be.
In this project, you will research a mixed-initiative recommender approach and investigate the utility of different visualization techniques to steer the recommendation process.
The research will be conducted at the HCI research group of the department of Computer Science of KU Leuven in Belgium, under close supervision of Prof. Dr. Katrien Verbert, Prof. Dr. Bart Vanrumste and Prof. Dr. Vero Vanden Abeele.
The application of recommendation techniques in the context of Healthcare has only recently gained increased attention, recommending for instance actions for patients in the context of therapy or disease management. Recommendation techniques in this critical context have to consider the heterogeneous and vulnerable population, and the inherent complexity in health care processes; we are not simply recommending the next movie or song, but actions that directly impact a patient’s health status. Unfortunately, recommender systems often appear as a “black box”. They do not offer insight into the system logic or provide a justification for recommendations. This black box nature prevents users from comprehending recommended results and can lead to trust issues when recommendations fail. In addition, the approach does not enable user feedback, which is unfortunate as this could contribute to the recommendation process.
Therefore, there is a recent interest to develop mixed-initiative approaches that enable users to understand and steer recommendation processes. Moreover, by combining interactive visualisation techniques with recommendation techniques we can support transparency and controllability of the recommendation process. To date, little research has been done to compare the utility of different visualization techniques and the level of control that should be supported. In this project, you will research a mixed-initiative recommender approach and investigate the utility of different visualization techniques to steer the recommendation process. The work will be carried out in close collaboration with care homes and with companies providing hardware and software to these care homes. The main focus is to investigate recommender systems for incontinence management.
• PhD degree in Computer Science, Electrical Engineering, Industrial Engineering
• Strong and demonstrated computer programming skills
• Research, work, or significant course experience in human-computer interaction
• Experience and/or keen interest in visualization and machine learning
• A creative mind and a talent to create engaging and aesthetic experiences
• An interest to engage in a participatory, user-centred design process
• Ability to work as an independent and flexible researcher in interdisciplinary teams
• Strong English writing and speaking skills
• Dedicated to improving the quality of life of frail older adults