J
Jasmina Bogojeska
Researcher at IBM
Publications - 36
Citations - 725
Jasmina Bogojeska is an academic researcher from IBM. The author has contributed to research in topics: Computer science & Server. The author has an hindex of 12, co-authored 31 publications receiving 595 citations. Previous affiliations of Jasmina Bogojeska include Max Planck Society.
Papers
More filters
Proceedings ArticleDOI
Multi-task learning for HIV therapy screening
TL;DR: This work derives a solution that produces resampling weights which match the pool of all examples to the target distribution of any given task, and substantially improves the overall prediction accuracy.
Proceedings ArticleDOI
Predicting Disk Replacement towards Reliable Data Centers
TL;DR: A highly accurate SMART-based analysis pipeline that can correctly predict the necessity of a disk replacement even 10-15 days in advance and uses statistical techniques to automatically detect which SMART parameters correlate with disk replacement.
Journal ArticleDOI
Determinants of HIV-1 reservoir size and long-term dynamics during suppressive ART.
Nadine Bachmann,Chantal von Siebenthal,Valentina Vongrad,Teja Turk,Kathrin Neumann,Niko Beerenwinkel,Niko Beerenwinkel,Jasmina Bogojeska,Jaques Fellay,Jaques Fellay,Volker Roth,Yik Lim Kok,Christian W. Thorball,Alessandro Borghesi,Sonali Parbhoo,Mario Wieser,Jürg Böni,Matthieu Perreau,Thomas Klimkait,Sabine Yerly,Manuel Battegay,Andri Rauch,Matthias Hoffmann,Enos Bernasconi,Matthias Cavassini,Roger D. Kouyos,Huldrych F. Günthard,Karin J. Metzner +27 more
TL;DR: Evaluating viral and host characteristics associated with reservoir size and long-term dynamics in 1,057 individuals on suppressive antiretroviral therapy shows that in 26.6% of individuals the reservoir increases, and viral blips and low-level viremia are significantly associated with slower reservoir decay.
Combining Kernel and Model Based Learning for HIV Therapy Selection.
TL;DR: A mixture-of-experts model is proposed that automatically selects between the methods in order to assign the most appropriate therapy choice to an individual and it is verified that therapy combinations proposed using this approach significantly outperform previous methods.
Proceedings ArticleDOI
Classifying server behavior and predicting impact of modernization actions
TL;DR: This paper identifies and rank servers with problematic behavior as candidates for modernization using a random forest classifier and chooses a predictive model that yields high quality predictions and outperforms traditional linear regression models on a large set of real data.