{{ 'SLOGAN_PART_1' | translate }} {{ 'SLOGAN_PART_2' | translate }}
{{ 'WHAT IS THE CYBERPSG?' | translate }}
Cyber PSG introduces a new, fast and objective approach to support evaluation of extensive recordings (Big Data) of sleep data. It provides simple and efficient way of data analysis for clinical practice and research. Modern software architecture allows for stand-alone implementation of the CyberPSG as well as integration of it’s computing algorithms
-
{{ 'Biosignal' | translate }}
{{ 'Application provides fast visualisation of the wide range of the biosignals. ' | translate }}
-
{{ 'Cluster Visualisation' | translate }}
{{ 'System performs Ward’s clustering algorithm with the Cluster visualisation.' | translate }}
-
{{ 'Hypnogram' | translate }}
{{ 'Clusters can be used for fast classification into sleep categories.' | translate }}
{{ 'THE NEED FOR FAST SLEEP DATA PROCESSING' | translate }}
{{ 'USAGE_DESC' | translate }}
{{'CYBER PSG FEATURES' | translate }}
{{'FEATURES_DESC' | translate }}
-
{{'FEATURE_1_HEADING' | translate }}
{{'FEATURE_1_HEADING_DESC' | translate }}
-
{{'FEATURE_2_HEADING' | translate }}
{{'FEATURE_2_HEADING_DESC' | translate }}
-
{{'FEATURE_3_HEADING' | translate }}
{{'FEATURE_3_HEADING_DESC' | translate }}
-
{{'FEATURE_4_HEADING' | translate }}
{{'FEATURE_4_HEADING_DESC' | translate }}
-
{{'FEATURE_5_HEADING' | translate }}
{{'FEATURE_5_HEADING_DESC' | translate }}
-
{{'FEATURE_6_HEADING' | translate }}
{{'FEATURE_6_HEADING_DESC' | translate }}
{{'USED METHODS' | translate }}
{{ 'Advantages of hierarchical clustering' | translate }}
-
{{ 'Dendrogram' | translate }}
{{ 'Expert has an option to browse and classify assembled hierarchical tree at any cut level. Both endleaves and higher tree nodes and their sub-trees could be classified.' | translate }}
-
{{ 'Cluster Map' | translate }}
{{ 'Members of the selected clusters are shown on the timeline as well as highlighted in the given signal montage.' | translate }}
-
{{ 'Cluster Classification' | translate }}
{{ 'The expert has full control in choice of the level of classification (i.e. selection of the cutting depth in a hierarchical tree) and the quantity and selection of samples for evaluation of individual clusters.' | translate }}
{{ 'Screenshot of the application' | translate }}
{{'ABOUT_COMPANY_PROFILE' | translate }}
{{'WANT_TO_KNOW_MORE_DESC' | translate }}