izvor podataka: poirot

Programski sustav za paralelnu analizu više heterogenih nizova vremenskih podataka s primjenom u biomedicini

A software system for parallel analysis of multiple heterogeneous time series with application in biomedicine

The task of time series analysis is to discover and classify significant patterns in data that contain a temporal component. This project deals with development of an integrated software system that includes general and domain specific time series features, with application in biomedicine. The goal of the project is to develop an efficient and upgradeable system for automatic classification of human body disorders based on the analysis of multiple heterogeneous biomedical signals (heart rhythm, ECG, EEG, etc.). In addition to classification, the project will also pursue visualization of disorders using computer graphics. Calculation speed will be increased using multicore parallelization. The system will contain subsystems for: 1) selection, display, and pre-processing of multiple signals from input records, 2) parallel analysis and extraction of multiple domain specific and general signal features, 3) visualization of signals and disorders using computer graphics, and 4) automatic construction and evaluation of the models. For evaluation purposes, the project will use referential biomedical signal databases from the PhysioNet portal and, if possible, anonymous records from local hospitals. One of the contributions of the system will be development of an expert subsystem for automatic recommendation of the set of features that should be extracted. The implemented general signal features will include relevant nonlinear dynamics measures. Specialized, domain specific features will be implemented for each type of biomedical signal individually. When constructing disorder models, feature space dimensionality reduction will be pursued. Disorders will be modeled based on clear description machine learning algorithms such as classification rules as well as maximum accuracy algorithms such as decision tree ensembles. Within the scope of this interdisciplinary project, several contributions in the areas of computer science, biomedical engineering, and medicine are expected.

nije evidentirano

Znanstveno-istraživački projekti





nije evidentirano

HRK 405.350,00