In biosignal-related projects, manual annotation of events is commonly used to create accurate reference labels. This is helpful for evaluating the performance of feature extraction methods. However, manual labeling can be repetitive and time-consuming.
To address this, a BioSPPy-powered UI has been developed in Python using the Tkinter library. The platform allows generating "pre-annotations" using the default BioSPPy's advanced algorithms and then allows users to navigate through the signal to check for missing annotations or make adjustments, saving time.
The platform supports 10 biosignal modalities and 15 feature extractors through its integration with BioSPPy.
In biosignal-related projects, manual annotation of events is commonly used to create accurate reference labels. This is helpful for evaluating the performance of feature extraction methods. However, manual labeling can be repetitive and time-consuming.
To address this, a BioSPPy-powered UI has been developed in Python using the Tkinter library. The platform allows generating "pre-annotations" using the default BioSPPy's advanced algorithms and then allows users to navigate through the signal to check for missing annotations or make adjustments, saving time.
The platform supports 10 biosignal modalities and 15 feature extractors through its integration with BioSPPy.
Preview of the platform (GIF) https://lh3.googleusercontent.com/7ozXm5XaT25dKh9VKUTUdwy_5POJM78pVFZVmSvPmsLDCu9CiNw58Nw8sj5cvXaJbjwhJsW_rzETuFQxiPBepzaxfpueQF3GFr5_CUH6u2PYBDxCFtHgnzGEU0Y_ziKBQA=w1280