Wessel Kraaij

Functie:
Professor Applied Data Analytics

Wessel Kraaij is principal scientist at the dept of Data Science, specialized in machine learning for decision support and coaching.

Research area

My main research areas include machine learning from unstructured data in diverse applications such as information retrieval, text mining, multimedia search, context sensitive AI, health data, personalized health and data driven policy making.

As a recognized expert in the area of Information Retrieval, I have been active in the application domains (social) media analysis, bioinformatics and health. I am mostly known for my contribution to TRECVid – the global benchmark forum on the evaluation of content-based analysis of digital video.

More recently, I have changed focus to the analysis of unstructured health data for the purpose of developing more effective personalized health advice and interventions as well as supporting sustainable society transitions on a community level. An important sub-problem is the challenge to learn from sensitive data without disclosing the data in a federated setting.

Other relevant challenges include the development of standardized analytics of lifestyle and health across decades of time span to allow analogical reasoning across large cohorts of health data. My ambition is to link TNO’s operational excellence with the longer term research horizons of academic research to achieve impact in the domain of AI and health.

Recent results

My recent work at TNO has focused on learning predictive models from distributed health data [COMMIT/ Prana Data, H2020 RECAP-PRETERM, H2020 BIGMEDILYTICS]. Federated secure machine learning from distributed data has been demonstrated as a Proof-of-Concept at the mid-term review of BigMedilytics. As scientific lead of the Early Research Programme on Big Data, I guided the development of novel methods for modeling and reasoning with uncertainty in big data processing pipelines.

In February 2018, I was appointed director of the Leiden University Data Science programme covering data intensive research in natural, social and health sciences as well as humanities. In 2017, I was recognized as distinguished member of the ACM for outstanding contributions to computing. In 2018, I was awarded the IEEE PAMI Mark Everingham award for co-leading the ‘TRECVid Video Retrieval Evaluation 2003-2018’.

PhD supervision

  • Anne Dirkson [SIDN fonds]
  • Annelieke van den Berg [Leiden University Data Science Programme]
  • Elsbeth de Korte [COMMIT/ SWELL] (graduated April 2021)
  • Dirk Hoevenaars [NWO , met VU]
  • Ahnjili Zhuparris [CHDR]
  • Arian Askari [H2020]

Top publications

  • Privacy-preserving dataset combination and Lasso regression for healthcare predictions
  • MB van Egmond, G Spini, O van der Galien, A IJpma, T Veugen, W Kraaij, ...
  • BMC medical informatics and decision making 21 (1), 1-16
  • Mike Keesman, Veronica Janssen, Hareld Kemps, Monika Hollander, Wilma Scholte op Reimer, Lisette van Gemert-Pijnen, Arno Hoes, Wessel Kraaij, Niels Chavannes, Douwe Atsma, Roderik Kraaijenhagen, Andrea Evers, and on behalf of the BENEFIT consortium. “BENEFIT for all: An ecosystem to facilitate sustained healthy living and reduce the burden of cardiovascular disease”. European Journal of Preventive Cardiology, 2018. Note: PMID: 30486650
  • Kraaij, W., Verberne, S., Koldijk, S. et al. , “Personalized support for well-being at work: an overview of the SWELL project”, User Modeling & User-Adapted Interaction (2019).
  • Anne Dirkson, Suzan Verberne, and Wessel Kraaij. Conversation-aware fil- tering of online patient forum messages. In Proceedings of the Fifth Social Media Mining for Health Applications Workshop & Shared Task, pages 11–18, Barcelona, Spain (Online), December 2020. Association for Computational Linguistics.
  • George Awad, Asad Butt, Keith Curtis, Jonathan Fiscus, Afzad Godil, Yooy- oung Lee, Andrew Delgado, Jesse Zhang, Eliot Godard, B. Chocot, Lukas Diduch, J.Liu, Alan Smeaton, Yvette Graham, Gareth Jones, Wessel Kraaij, and Georges Qu´ enot. Trecvid 2020: A comprehensive campaign for evaluating video retrieval tasks across multiple application domains. In Proceedings of TRECVID 2020. NIST, 2020.
  • AC van den Berg, SN Giest, SM Groeneveld, and W Kraaij. Inclusivity in online platforms: Recruitment strategies for improving participation of diverse sociodemographic groups. Public Administration Review, 2020.

Den Haag - New Babylon

Anna van Buerenplein 1
NL-2595 DA The Hague

Postal address

P.O. Box 96800
NL-2509 JE The Hague