Bilge Celik

Bilge Celik

Auto-generated profile, based on publicly available information

Bilge Celik

Department of Computer Science & Mathematics Eindhoven University of Technology Groene Loper 5 5600MB Eindhoven The Netherlands

Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
2 March 2021 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
BCBilge Celik
Bilge Celik
JVJoaquin Vanschoren
Joaquin Vanschoren
Automated Machine Learning (AutoML) systems have been shown to efficiently build good models for new datasets. However, it is often not clear how well they can adapt when the data evolves over time. The main goal of this study is to understand the effect of concept drift on the performance of AutoML methods, and which adaptation strategies can be employed to make them more robust to changes in the underlying data. To that end, we propose 6 concept drift adaptation strategies and evaluate their effectiveness on a variety of AutoML approaches for building machine learning pipelines, including Bayesian optimization, genetic programming, and random search with automated stacking. These are evaluated empirically on real-world and synthetic data streams with different types of concept drift. Based on this analysis, we propose ways to develop more sophisticated and robust AutoML techniques.

6 December 2022 in Machine Learning
Verified
Journal Article
Closed access
PDF file
BCBilge Celik
Bilge Celik
PSPrabhant Singh
Prabhant Singh
JVJoaquin Vanschoren
Joaquin Vanschoren

29 December 2014 in Expert Systems with Applications
Verified
Journal Article
Closed access
BÇB. Çelik
B. Çelik
EKEsra Karasakal
Esra Karasakal
CICem Iyigün
Cem Iyigün

7 December 2022 in arXiv
Verified
Preprint
Open access
PDF file
BCBilge Celik
Bilge Celik
PSPrabhant Singh
Prabhant Singh
JVJoaquin Vanschoren
Joaquin Vanschoren
Automated Machine Learning (AutoML) has been used successfully in settings where the learning task is assumed to be static. In many real-world scenarios, however, the data distribution will evolve over time, and it is yet to be shown whether AutoML techniques can effectively design online pipelines in dynamic environments. This study aims to automate pipeline design for online learning while continuously adapting to data drift. For this purpose, we design an adaptive Online Automated Machine Learning (OAML) system, searching the complete pipeline configuration space of online learners, including preprocessing algorithms and ensembling techniques. This system combines the inherent adaptation capabilities of online learners with the fast automated pipeline (re)optimization capabilities of AutoML. Focusing on optimization techniques that can adapt to evolving objectives, we evaluate asynchronous genetic programming and asynchronous successive halving to optimize these pipelines continually. We experiment on real and artificial data streams with varying types of concept drift to test the performance and adaptation capabilities of the proposed system. The results confirm the utility of OAML over popular online learning algorithms and underscore the benefits of continuous pipeline redesign in the presence of data drift.

17 October 2026 in npj Digital Medicine
Verified
Journal Article
Open access
PDF file
JKJosephine W. van Koevorden
Josephine W. van Koevorden
RMRachael Mertooetomo
Rachael Mertooetomo
DNDavid Neal
David Neal
BÇBilge Çelik
Bilge Çelik
VSVeerle Struben
Veerle Struben
RDRichard Dirven
Richard Dirven
Large Language Models (LLMs) may support clinicians by facilitating information management, but their usability in real-world oncology practice remains understudied. This study evaluated the workflow performance of Artificial Intelligence-based First Consultation Preparation (AI-FCP), generating structured summaries from unstructured clinical documentation, co-created with end users. In a prospective single‑group pre‑post design, nine clinicians completed a person-level baseline, followed by 33 consultations with AI-FCP. Case numbers varied by clinic scheduling and enrollment timing, potentially introducing survivorship bias. Usability was evaluated using validated questionnaires and study-specific instruments. Post AI-FCP, overall perceived workload (NASA-TLX) was 28.9% lower than baseline (Hodges-Lehmann estimate difference −12.3; 95% CI –21.7 to –3.3), with self-reported average time savings of 3.26 min (SD = 2.65) per case. Preparation succeeded in 84.9% of consultations; 63.6% of summaries were complete. These exploratory findings suggest clinicians perceived lower workload and reported improved workflow efficiency with AI-FCP. Further research is needed to determine generalizability.

10 May 2022 in arXiv
Verified
Preprint
Open access
PDF file
BCBilge Celik
Bilge Celik
JVJoaquin Vanschoren
Joaquin Vanschoren
Automated Machine Learning (AutoML) systems have been shown to efficiently build good models for new datasets. However, it is often not clear how well they can adapt when the data evolves over time. The main goal of this study is to understand the effect of data stream challenges such as concept drift on the performance of AutoML methods, and which adaptation strategies can be employed to make them more robust. To that end, we propose 6 concept drift adaptation strategies and evaluate their effectiveness on different AutoML approaches. We do this for a variety of AutoML approaches for building machine learning pipelines, including those that leverage Bayesian optimization, genetic programming, and random search with automated stacking. These are evaluated empirically on real-world and synthetic data streams with different types of concept drift. Based on this analysis, we propose ways to develop more sophisticated and robust AutoML techniques.