Thesis supervisor: Zoltán Juhász
Location of studies (in Hungarian): University of Pannonia, H-8200 Veszprém, Egyetem u. 10. Hungary Abbreviation of location of studies: PE
Description of the research topic:
State-of-the art medical data processing (e.g. EEG, fMRI) is a complex and time-consuming task requiring powerful computers with large memory and computing capacity. The amount of data produced by today’s imaging systems and measurement devices lead to large processing times and require such an infrastructure that not every research group or institute can afford. Stream processing offers an alternative, resource-efficient processing strategy that can be supported by GPUs and cloud environments, but this requires the re-design of traditional algorithms. The goal of this research is to study stream-based algorithms and their application for real-time execution of medical signal processing algorithms. The primary focus of the research is on EEG measurements, with a possibility later to extend into ECG and other medical data processing problems.
Papers related to the topic:
1. Z Juhasz, G Kozmann, “A GPU-based Soft Real-Time System for Simultaneous EEG Processing and Visualization”, Scalable Computing: Practice and Experience 17 (2), 61-78 (2016). https://doi.org/10.12694/scpe.v17i2.1156
Required language skills: english Further requirements: Applicants should have a very good command of English, and strong interest in complex software systems, their architectural and programming problems. Knowledge of parallel and distributed programming techniques is essential, just as good algorithmic
Number of students who can be accepted: 1
Deadline for application: 2021-02-28
2024. IV. 17. ODT ülés Az ODT következő ülésére 2024. június 14-én, pénteken 10.00 órakor kerül sor a Semmelweis Egyetem Szenátusi termében (Bp. Üllői út 26. I. emelet).