The submission contains: (1) realtime - C++ code for performing Factoral Switching Linear Dynamical System (FSLDS) inference in real time on CSV input files; (2) matlab - Matlab code used for offline parameter estimation and inference on historical data;(3) preprocessor - C++ code, documentation and executables for the conversion of high frequency waveform data to 1Hz data; (4) licensing information; and (5) a report describing the development of this code and results of its use on a set of patients from the Neuro ICU in the Southern General Hospital, Glasgow.
Williams, Chris; Lal, Partha; Shaw, Martin. (2015). Code for Factorial Switching Linear Dynamical System (FSLDS) Monitoring of Intensive Care Unit Data, [software]. University of Edinburgh, School of Informatics, Institute for Adaptive and Neural Computation. http://dx.doi.org/10.7488/ds/300.
|Date made available||22 Sep 2015|