F
Franc Jager
Researcher at University of Ljubljana
Publications - 48
Citations - 1190
Franc Jager is an academic researcher from University of Ljubljana. The author has contributed to research in topics: ST segment & Electrocardiography. The author has an hindex of 15, co-authored 47 publications receiving 1042 citations. Previous affiliations of Franc Jager include Massachusetts Institute of Technology & Ljubljana University Medical Centre.
Papers
More filters
Journal ArticleDOI
A comparison of various linear and non-linear signal processing techniques to separate uterine EMG records of term and pre-term delivery groups
TL;DR: Various linear and non-linear signal-processing techniques were applied to three-channel uterine EMG records to separate term and pre-term deliveries, showing noticeable differences between term delivery records recorded before and after the 26th week.
Journal ArticleDOI
Long-term ST database: a reference for the development and evaluation of automated ischaemia detectors and for the study of the dynamics of myocardial ischaemia.
Franc Jager,Franc Jager,Alessandro Taddei,George B. Moody,George B. Moody,Michele Emdin,G. Antolic,R. Dorn,A. Smrdel,C Marchesi,C Marchesi,Roger G. Mark,Roger G. Mark +12 more
TL;DR: The long-term ST database provides a comprehensive representation of ‘real-world’ data, with numerous examples of transient ischaemic and non-ischaemic ST segment changes, arrhythmias, conduction abnormalities, axis shifts, noise and artifacts.
Journal ArticleDOI
Detection of transient ST segment episodes during ambulatory ECG monitoring
TL;DR: Using the European Society of Cardiology ST-T Database, a Karhunen-Loève transform-based algorithm is developed for robust automated detection of transient ST segment episodes during ambulatory ECG monitoring and its performance is compared to other recently developed algorithms.
Proceedings ArticleDOI
Analysis of transient ST segment changes during ambulatory monitoring using the Karhunen-Loeave transform
TL;DR: An algorithm based on the Karhunen-Loeave transform (KLT) is presented for robust automated detection of ischemic ST segment episodes and measurement of the duration of ischemia in two-channel ambulatory electrocardiographic data.
Journal ArticleDOI
Dynamic neural network architecture inspired by the immune algorithm to predict preterm deliveries in pregnant women
TL;DR: A new dynamic self-organized network immune algorithm that classifies term and preterm records, using an open dataset containing 300 records, shows an improvement on existing studies with 89% sensitivity, 91% specificity, 90% positive predicted value, and an overall accuracy of 90%.