The IMPROVE data library is a collection of continuous and intermittent physiological observations of 59 patients in the Intensive Care Unit (ICU), recorded for one complete day at the Kuopio University Hospital. These data consisted of patient data stored as annotation and record files. The IMPROVE data library also provided the information regarding four disorders (Hypovolaemia, Cardiac Failure, Hypervolaemia and Oxygen-Content related problems) in terms of the patient data. An available model designed in Stateflow generated the risk levels for the patients. The goal of this thesis is to analyze the risk levels generated from the simulation and compare them with the physician's diagnosis. The main objective of this work is to evaluate the performance of the Stateflow model that interprets the risk level of the four disorders, for a particular patient at any instant of time and later implement it on an Infineon C 166 microcontroller board. The various limitations encountered during the implementation on the microcontroller board are discussed in the thesis. To demonstrate the rapid prototyping capabilities of using the microcontroller board a speed-comparison analysis of implementing the Stateflow model on various computers was performed.
Thesis (M.S.) University of Alaska Fairbanks, 2005
Table of Contents
Introduction -- Disease description -- State machine -- Introduction -- Description of a finite state machine -- Simulink model -- Stateflow model -- Data analysis -- Timing issues -- Model analysis with a microcontroller board -- Hardware in the loop -- Matlab/Simulink environment -- Target- infineon C166 microcontroller -- Bootstrap mode -- Method 1 : using the C166 microcontroller toolbox of Matlab -- Method 2 : using RTC167-target toolbox and tasking compiler -- Code generation using tasking compiler -- Method 3 : using RTC167-target toolbox and keil compiler -- Results and discussion -- Introduction -- Extracting and analyzing patient data -- Stateflow model analysis -- Analysis of the different implementation methods -- Speed comparison -- Conclusions and future work.
The export option will allow you to export the current search results of the entered query to a file. Different
formats are available for download. To export the items, click on the button corresponding with the preferred download format.
By default, clicking on the export buttons will result in a download of the allowed maximum amount of items.
To select a subset of the search results, click "Selective Export" button and make a selection of the items you want to export.
The amount of items that can be exported at once is similarly restricted as the full export.
After making a selection, click one of the export format buttons. The amount of items that will be exported is indicated in the bubble next to export format.